diff --git a/ultralytics-main/.github/ISSUE_TEMPLATE/config.yml b/ultralytics-main/.github/ISSUE_TEMPLATE/config.yml deleted file mode 100644 index 9018a62..0000000 --- a/ultralytics-main/.github/ISSUE_TEMPLATE/config.yml +++ /dev/null @@ -1,11 +0,0 @@ -blank_issues_enabled: true -contact_links: - - name: 📄 Docs - url: https://docs.ultralytics.com/ - about: Full Ultralytics YOLOv8 Documentation - - name: 💬 Forum - url: https://community.ultralytics.com/ - about: Ask on Ultralytics Community Forum - - name: 🎧 Discord - url: https://ultralytics.com/discord - about: Ask on Ultralytics Discord diff --git a/ultralytics-main/.github/workflows/ci.yaml b/ultralytics-main/.github/workflows/ci.yaml deleted file mode 100644 index 4eadc3b..0000000 --- a/ultralytics-main/.github/workflows/ci.yaml +++ /dev/null @@ -1,288 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLO Continuous Integration (CI) GitHub Actions tests - -name: Ultralytics CI - -on: - push: - branches: [main] - paths-ignore: - - "docs/**" - - "mkdocs.yml" - pull_request: - branches: [main] - paths-ignore: - - "docs/**" - schedule: - - cron: "0 0 * * *" # runs at 00:00 UTC every day - workflow_dispatch: - inputs: - hub: - description: "Run HUB" - default: false - type: boolean - benchmarks: - description: "Run Benchmarks" - default: false - type: boolean - tests: - description: "Run Tests" - default: false - type: boolean - gpu: - description: "Run GPU" - default: false - type: boolean - conda: - description: "Run Conda" - default: false - type: boolean - -jobs: - HUB: - if: github.repository == 'ultralytics/ultralytics' && (github.event_name == 'schedule' || github.event_name == 'push' || (github.event_name == 'workflow_dispatch' && github.event.inputs.hub == 'true')) - runs-on: ${{ matrix.os }} - strategy: - fail-fast: false - matrix: - os: [ubuntu-latest] - python-version: ["3.11"] - steps: - - uses: actions/checkout@v4 - - uses: actions/setup-python@v5 - with: - python-version: ${{ matrix.python-version }} - cache: "pip" # caching pip dependencies - - name: Install requirements - shell: bash # for Windows compatibility - run: | - python -m pip install --upgrade pip wheel - pip install -e . --extra-index-url https://download.pytorch.org/whl/cpu - - name: Check environment - run: | - yolo checks - pip list - - name: Test HUB training - shell: python - env: - API_KEY: ${{ secrets.ULTRALYTICS_HUB_API_KEY }} - MODEL_ID: ${{ secrets.ULTRALYTICS_HUB_MODEL_ID }} - run: | - import os - from ultralytics import YOLO, hub - api_key, model_id = os.environ['API_KEY'], os.environ['MODEL_ID'] - hub.login(api_key) - hub.reset_model(model_id) - model = YOLO('https://hub.ultralytics.com/models/' + model_id) - model.train() - - name: Test HUB inference API - shell: python - env: - API_KEY: ${{ secrets.ULTRALYTICS_HUB_API_KEY }} - MODEL_ID: ${{ secrets.ULTRALYTICS_HUB_MODEL_ID }} - run: | - import os - import requests - import json - api_key, model_id = os.environ['API_KEY'], os.environ['MODEL_ID'] - url = f"https://api.ultralytics.com/v1/predict/{model_id}" - headers = {"x-api-key": api_key} - data = {"size": 320, "confidence": 0.25, "iou": 0.45} - with open("ultralytics/assets/zidane.jpg", "rb") as f: - response = requests.post(url, headers=headers, data=data, files={"image": f}) - assert response.status_code == 200, f'Status code {response.status_code}, Reason {response.reason}' - print(json.dumps(response.json(), indent=2)) - - Benchmarks: - if: github.event_name != 'workflow_dispatch' || github.event.inputs.benchmarks == 'true' - runs-on: ${{ matrix.os }} - strategy: - fail-fast: false - matrix: - os: [ubuntu-latest, macos-14] - python-version: ["3.11"] - model: [yolov8n] - steps: - - uses: actions/checkout@v4 - - uses: actions/setup-python@v5 - with: - python-version: ${{ matrix.python-version }} - cache: "pip" # caching pip dependencies - - name: Install requirements - shell: bash # for Windows compatibility - run: | - python -m pip install --upgrade pip wheel - pip install -e ".[export]" "coverage[toml]" --extra-index-url https://download.pytorch.org/whl/cpu - # yolo export format=tflite imgsz=32 || true - - name: Check environment - run: | - yolo checks - pip list - - name: Benchmark YOLOWorld DetectionModel - shell: bash - run: coverage run -a --source=ultralytics -m ultralytics.cfg.__init__ benchmark model='path with spaces/yolov8s-worldv2.pt' imgsz=160 verbose=0.318 - - name: Benchmark SegmentationModel - shell: bash - run: coverage run -a --source=ultralytics -m ultralytics.cfg.__init__ benchmark model='path with spaces/${{ matrix.model }}-seg.pt' imgsz=160 verbose=0.281 - - name: Benchmark ClassificationModel - shell: bash - run: coverage run -a --source=ultralytics -m ultralytics.cfg.__init__ benchmark model='path with spaces/${{ matrix.model }}-cls.pt' imgsz=160 verbose=0.166 - - name: Benchmark PoseModel - shell: bash - run: coverage run -a --source=ultralytics -m ultralytics.cfg.__init__ benchmark model='path with spaces/${{ matrix.model }}-pose.pt' imgsz=160 verbose=0.183 - - name: Benchmark OBBModel - shell: bash - run: coverage run -a --source=ultralytics -m ultralytics.cfg.__init__ benchmark model='path with spaces/${{ matrix.model }}-obb.pt' imgsz=160 verbose=0.472 - - name: Merge Coverage Reports - run: | - coverage xml -o coverage-benchmarks.xml - - name: Upload Coverage Reports to CodeCov - if: github.repository == 'ultralytics/ultralytics' - uses: codecov/codecov-action@v4 - with: - flags: Benchmarks - env: - CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }} - - name: Benchmark Summary - run: | - cat benchmarks.log - echo "$(cat benchmarks.log)" >> $GITHUB_STEP_SUMMARY - - Tests: - if: github.event_name != 'workflow_dispatch' || github.event.inputs.tests == 'true' - timeout-minutes: 60 - runs-on: ${{ matrix.os }} - strategy: - fail-fast: false - matrix: - os: [ubuntu-latest, macos-14] - python-version: ["3.11"] - torch: [latest] - include: - - os: ubuntu-latest - python-version: "3.8" # torch 1.8.0 requires python >=3.6, <=3.8 - torch: "1.8.0" # min torch version CI https://pypi.org/project/torchvision/ - steps: - - uses: actions/checkout@v4 - - uses: actions/setup-python@v5 - with: - python-version: ${{ matrix.python-version }} - cache: "pip" # caching pip dependencies - - name: Install requirements - shell: bash # for Windows compatibility - run: | - # CoreML must be installed before export due to protobuf error from AutoInstall - python -m pip install --upgrade pip wheel - torch="" - if [ "${{ matrix.torch }}" == "1.8.0" ]; then - torch="torch==1.8.0 torchvision==0.9.0" - fi - pip install -e . $torch pytest-cov "coremltools>=7.0; platform_system != 'Windows' and python_version <= '3.11'" --extra-index-url https://download.pytorch.org/whl/cpu - - name: Check environment - run: | - yolo checks - pip list - - name: Pytest tests - shell: bash # for Windows compatibility - run: | - slow="" - if [[ "${{ github.event_name }}" == "schedule" ]] || [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then - pip install mlflow pycocotools 'ray[tune]' - slow="--slow" - fi - pytest $slow --cov=ultralytics/ --cov-report xml tests/ - - name: Upload Coverage Reports to CodeCov - if: github.repository == 'ultralytics/ultralytics' # && matrix.os == 'ubuntu-latest' && matrix.python-version == '3.11' - uses: codecov/codecov-action@v4 - with: - flags: Tests - env: - CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }} - - GPU: - if: github.repository == 'ultralytics/ultralytics' && (github.event_name != 'workflow_dispatch' || github.event.inputs.gpu == 'true') - timeout-minutes: 60 - runs-on: gpu-latest - steps: - - uses: actions/checkout@v4 - - name: Install requirements - run: pip install -e . - - name: Check environment - run: | - yolo checks - pip list - - name: Pytest tests - run: pytest --cov=ultralytics/ --cov-report xml tests/test_cuda.py - - name: Upload Coverage Reports to CodeCov - uses: codecov/codecov-action@v4 - with: - flags: GPU - env: - CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }} - - Conda: - if: github.repository == 'ultralytics/ultralytics' && (github.event_name == 'schedule_disabled' || github.event.inputs.conda == 'true') - runs-on: ${{ matrix.os }} - strategy: - fail-fast: false - matrix: - os: [ubuntu-latest] - python-version: ["3.11"] - defaults: - run: - shell: bash -el {0} - steps: - - uses: conda-incubator/setup-miniconda@v3 - with: - python-version: ${{ matrix.python-version }} - mamba-version: "*" - channels: conda-forge,defaults - channel-priority: true - activate-environment: anaconda-client-env - - name: Install Libmamba - run: | - conda config --set solver libmamba - - name: Install Ultralytics package from conda-forge - run: | - conda install -c pytorch -c conda-forge pytorch torchvision ultralytics openvino - - name: Install pip packages - run: | - # CoreML must be installed before export due to protobuf error from AutoInstall - pip install pytest "coremltools>=7.0; platform_system != 'Windows' and python_version <= '3.11'" - - name: Check environment - run: | - conda list - - name: Test CLI - run: | - yolo predict model=yolov8n.pt imgsz=320 - yolo train model=yolov8n.pt data=coco8.yaml epochs=1 imgsz=32 - yolo val model=yolov8n.pt data=coco8.yaml imgsz=32 - yolo export model=yolov8n.pt format=torchscript imgsz=160 - - name: Test Python - run: | - python -c " - from ultralytics import YOLO - model = YOLO('yolov8n.pt') - results = model.train(data='coco8.yaml', epochs=3, imgsz=160) - results = model.val(imgsz=160) - results = model.predict(imgsz=160) - results = model.export(format='onnx', imgsz=160) - " - - name: PyTest - run: | - git clone https://github.com/ultralytics/ultralytics - pytest ultralytics/tests - - Summary: - runs-on: ubuntu-latest - needs: [HUB, Benchmarks, Tests, GPU, Conda] # Add job names that you want to check for failure - if: always() # This ensures the job runs even if previous jobs fail - steps: - - name: Check for failure and notify - if: (needs.HUB.result == 'failure' || needs.Benchmarks.result == 'failure' || needs.Tests.result == 'failure' || needs.GPU.result == 'failure' || needs.Conda.result == 'failure') && github.repository == 'ultralytics/ultralytics' && (github.event_name == 'schedule' || github.event_name == 'push') - uses: slackapi/slack-github-action@v1.25.0 - with: - payload: | - {"text": " GitHub Actions error for ${{ github.workflow }} ❌\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* ${{ github.event_name }}\n"} - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_YOLO }} diff --git a/ultralytics-main/.github/workflows/cla.yml b/ultralytics-main/.github/workflows/cla.yml deleted file mode 100644 index a11ee19..0000000 --- a/ultralytics-main/.github/workflows/cla.yml +++ /dev/null @@ -1,37 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -name: CLA Assistant -on: - issue_comment: - types: - - created - pull_request_target: - types: - - reopened - - opened - - synchronize - -jobs: - CLA: - if: github.repository == 'ultralytics/ultralytics' - runs-on: ubuntu-latest - steps: - - name: CLA Assistant - if: (github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I sign the CLA') || github.event_name == 'pull_request_target' - uses: contributor-assistant/github-action@v2.3.1 - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - # must be repository secret token - PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }} - with: - path-to-signatures: "signatures/version1/cla.json" - path-to-document: "https://docs.ultralytics.com/help/CLA" # CLA document - # branch should not be protected - branch: "main" - allowlist: dependabot[bot],github-actions,[pre-commit*,pre-commit*,bot* - - remote-organization-name: ultralytics - remote-repository-name: cla - custom-pr-sign-comment: "I have read the CLA Document and I sign the CLA" - custom-allsigned-prcomment: All Contributors have signed the CLA. ✅ - #custom-notsigned-prcomment: 'pull request comment with Introductory message to ask new contributors to sign' diff --git a/ultralytics-main/.github/workflows/codeql.yaml b/ultralytics-main/.github/workflows/codeql.yaml deleted file mode 100644 index e6e3e85..0000000 --- a/ultralytics-main/.github/workflows/codeql.yaml +++ /dev/null @@ -1,42 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -name: "CodeQL" - -on: - schedule: - - cron: "0 0 1 * *" - workflow_dispatch: - -jobs: - analyze: - name: Analyze - runs-on: ${{ 'ubuntu-latest' }} - permissions: - actions: read - contents: read - security-events: write - - strategy: - fail-fast: false - matrix: - language: ["python"] - # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ] - - steps: - - name: Checkout repository - uses: actions/checkout@v4 - - # Initializes the CodeQL tools for scanning. - - name: Initialize CodeQL - uses: github/codeql-action/init@v3 - with: - languages: ${{ matrix.language }} - # If you wish to specify custom queries, you can do so here or in a config file. - # By default, queries listed here will override any specified in a config file. - # Prefix the list here with "+" to use these queries and those in the config file. - # queries: security-extended,security-and-quality - - - name: Perform CodeQL Analysis - uses: github/codeql-action/analyze@v3 - with: - category: "/language:${{matrix.language}}" diff --git a/ultralytics-main/.github/workflows/docker.yaml b/ultralytics-main/.github/workflows/docker.yaml deleted file mode 100644 index afd2a66..0000000 --- a/ultralytics-main/.github/workflows/docker.yaml +++ /dev/null @@ -1,159 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest images on DockerHub https://hub.docker.com/r/ultralytics - -name: Publish Docker Images - -on: - push: - branches: [main] - paths-ignore: - - "docs/**" - - "mkdocs.yml" - workflow_dispatch: - inputs: - Dockerfile: - type: boolean - description: Use Dockerfile - default: true - Dockerfile-cpu: - type: boolean - description: Use Dockerfile-cpu - Dockerfile-arm64: - type: boolean - description: Use Dockerfile-arm64 - Dockerfile-jetson: - type: boolean - description: Use Dockerfile-jetson - Dockerfile-python: - type: boolean - description: Use Dockerfile-python - Dockerfile-conda: - type: boolean - description: Use Dockerfile-conda - push: - type: boolean - description: Push images to Docker Hub - default: true - -jobs: - docker: - if: github.repository == 'ultralytics/ultralytics' - name: Push - runs-on: ubuntu-latest - strategy: - fail-fast: false - max-parallel: 6 - matrix: - include: - - dockerfile: "Dockerfile" - tags: "latest" - platforms: "linux/amd64" - - dockerfile: "Dockerfile-cpu" - tags: "latest-cpu" - platforms: "linux/amd64" - - dockerfile: "Dockerfile-arm64" - tags: "latest-arm64" - platforms: "linux/arm64" - - dockerfile: "Dockerfile-jetson" - tags: "latest-jetson" - platforms: "linux/arm64" - - dockerfile: "Dockerfile-python" - tags: "latest-python" - platforms: "linux/amd64" - # - dockerfile: "Dockerfile-conda" - # tags: "latest-conda" - # platforms: "linux/amd64" - steps: - - name: Checkout repo - uses: actions/checkout@v4 - with: - fetch-depth: 0 # copy full .git directory to access full git history in Docker images - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Set up Docker Buildx - uses: docker/setup-buildx-action@v3 - - - name: Login to Docker Hub - uses: docker/login-action@v3 - with: - username: ${{ secrets.DOCKERHUB_USERNAME }} - password: ${{ secrets.DOCKERHUB_TOKEN }} - - - name: Retrieve Ultralytics version - id: get_version - run: | - VERSION=$(grep "^__version__ =" ultralytics/__init__.py | awk -F'"' '{print $2}') - echo "Retrieved Ultralytics version: $VERSION" - echo "version=$VERSION" >> $GITHUB_OUTPUT - - VERSION_TAG=$(echo "${{ matrix.tags }}" | sed "s/latest/${VERSION}/") - echo "Intended version tag: $VERSION_TAG" - echo "version_tag=$VERSION_TAG" >> $GITHUB_OUTPUT - - - name: Check if version tag exists on DockerHub - id: check_tag - run: | - RESPONSE=$(curl -s https://hub.docker.com/v2/repositories/ultralytics/ultralytics/tags/$VERSION_TAG) - MESSAGE=$(echo $RESPONSE | jq -r '.message') - if [[ "$MESSAGE" == "null" ]]; then - echo "Tag $VERSION_TAG already exists on DockerHub." - echo "exists=true" >> $GITHUB_OUTPUT - elif [[ "$MESSAGE" == *"404"* ]]; then - echo "Tag $VERSION_TAG does not exist on DockerHub." - echo "exists=false" >> $GITHUB_OUTPUT - else - echo "Unexpected response from DockerHub. Please check manually." - echo "exists=false" >> $GITHUB_OUTPUT - fi - env: - VERSION_TAG: ${{ steps.get_version.outputs.version_tag }} - - - name: Build Image - if: github.event_name == 'push' || github.event.inputs[matrix.dockerfile] == 'true' - uses: nick-invision/retry@v3 - with: - timeout_minutes: 60 - retry_wait_seconds: 30 - max_attempts: 2 # retry once - command: | - docker build \ - --platform ${{ matrix.platforms }} \ - -f docker/${{ matrix.dockerfile }} \ - -t ultralytics/ultralytics:${{ matrix.tags }} \ - -t ultralytics/ultralytics:${{ steps.get_version.outputs.version_tag }} \ - . - - - name: Run Tests - if: (github.event_name == 'push' || github.event.inputs[matrix.dockerfile] == 'true') && matrix.platforms == 'linux/amd64' && matrix.dockerfile != 'Dockerfile-conda' # arm64 images not supported on GitHub CI runners - run: docker run ultralytics/ultralytics:${{ matrix.tags }} /bin/bash -c "pip install pytest && pytest tests" - - - name: Run Benchmarks - # WARNING: Dockerfile (GPU) error on TF.js export 'module 'numpy' has no attribute 'object'. - if: (github.event_name == 'push' || github.event.inputs[matrix.dockerfile] == 'true') && matrix.platforms == 'linux/amd64' && matrix.dockerfile != 'Dockerfile' && matrix.dockerfile != 'Dockerfile-conda' # arm64 images not supported on GitHub CI runners - run: docker run ultralytics/ultralytics:${{ matrix.tags }} yolo benchmark model=yolov8n.pt imgsz=160 verbose=0.318 - - - name: Push Docker Image with Ultralytics version tag - if: (github.event_name == 'push' || (github.event.inputs[matrix.dockerfile] == 'true' && github.event.inputs.push == 'true')) && steps.check_tag.outputs.exists == 'false' && matrix.dockerfile != 'Dockerfile-conda' - run: | - docker push ultralytics/ultralytics:${{ steps.get_version.outputs.version_tag }} - - - name: Push Docker Image with latest tag - if: github.event_name == 'push' || (github.event.inputs[matrix.dockerfile] == 'true' && github.event.inputs.push == 'true') - run: | - docker push ultralytics/ultralytics:${{ matrix.tags }} - if [[ "${{ matrix.tags }}" == "latest" ]]; then - t=ultralytics/ultralytics:latest-runner - docker build -f docker/Dockerfile-runner -t $t . - docker push $t - fi - - - name: Notify on failure - if: github.event_name == 'push' && failure() # do not notify on cancelled() as cancelling is performed by hand - uses: slackapi/slack-github-action@v1.25.0 - with: - payload: | - {"text": " GitHub Actions error for ${{ github.workflow }} ❌\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* ${{ github.event_name }}\n"} - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_YOLO }} diff --git a/ultralytics-main/.github/workflows/format.yml b/ultralytics-main/.github/workflows/format.yml deleted file mode 100644 index 470d4f3..0000000 --- a/ultralytics-main/.github/workflows/format.yml +++ /dev/null @@ -1,28 +0,0 @@ -# Ultralytics 🚀 - AGPL-3.0 license -# Ultralytics Actions https://github.com/ultralytics/actions -# This workflow automatically formats code and documentation in PRs to official Ultralytics standards - -name: Ultralytics Actions - -on: - push: - branches: [main] - pull_request_target: - branches: [main] - types: [opened, closed, synchronize] - -jobs: - format: - runs-on: ubuntu-latest - steps: - - name: Run Ultralytics Formatting - uses: ultralytics/actions@main - with: - token: ${{ secrets.GITHUB_TOKEN }} # automatically generated, do not modify - python: true # format Python code and docstrings - markdown: true # format Markdown and YAML - spelling: true # check spelling - links: false # check broken links - summary: true # print PR summary with GPT4 (requires 'openai_api_key' or 'openai_azure_api_key' and 'openai_azure_endpoint') - openai_azure_api_key: ${{ secrets.OPENAI_AZURE_API_KEY }} - openai_azure_endpoint: ${{ secrets.OPENAI_AZURE_ENDPOINT }} diff --git a/ultralytics-main/.github/workflows/greetings.yml b/ultralytics-main/.github/workflows/greetings.yml deleted file mode 100644 index 00e0f9d..0000000 --- a/ultralytics-main/.github/workflows/greetings.yml +++ /dev/null @@ -1,58 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -name: Greetings - -on: - pull_request_target: - types: [opened] - issues: - types: [opened] - -jobs: - greeting: - runs-on: ubuntu-latest - steps: - - uses: actions/first-interaction@v1 - with: - repo-token: ${{ secrets.GITHUB_TOKEN }} - pr-message: | - 👋 Hello @${{ github.actor }}, thank you for submitting an Ultralytics YOLOv8 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to: - - - ✅ Verify your PR is **up-to-date** with `ultralytics/ultralytics` `main` branch. If your PR is behind you can update your code by clicking the 'Update branch' button or by running `git pull` and `git merge main` locally. - - ✅ Verify all YOLOv8 Continuous Integration (CI) **checks are passing**. - - ✅ Update YOLOv8 [Docs](https://docs.ultralytics.com) for any new or updated features. - - ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ — Bruce Lee - - See our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for details and let us know if you have any questions! - - issue-message: | - 👋 Hello @${{ github.actor }}, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the [Docs](https://docs.ultralytics.com) for new users where you can find many [Python](https://docs.ultralytics.com/usage/python/) and [CLI](https://docs.ultralytics.com/usage/cli/) usage examples and where many of the most common questions may already be answered. - - If this is a 🐛 Bug Report, please provide a [minimum reproducible example](https://docs.ultralytics.com/help/minimum_reproducible_example/) to help us debug it. - - If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our [Tips for Best Training Results](https://docs.ultralytics.com/yolov5/tutorials/tips_for_best_training_results/). - - Join the vibrant [Ultralytics Discord](https://ultralytics.com/discord) 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users. - - ## Install - - Pip install the `ultralytics` package including all [requirements](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) in a [**Python>=3.8**](https://www.python.org/) environment with [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). - - ```bash - pip install ultralytics - ``` - - ## Environments - - YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): - - - **Notebooks** with free GPU: Run on Gradient Open In Colab Open In Kaggle - - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial/) - - **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial/) - - **Docker Image**. See [Docker Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/docker_image_quickstart_tutorial/) Docker Pulls - - ## Status - - Ultralytics CI - - If this badge is green, all [Ultralytics CI](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml?query=event%3Aschedule) tests are currently passing. CI tests verify correct operation of all YOLOv8 [Modes](https://docs.ultralytics.com/modes/) and [Tasks](https://docs.ultralytics.com/tasks/) on macOS, Windows, and Ubuntu every 24 hours and on every commit. diff --git a/ultralytics-main/.github/workflows/links.yml b/ultralytics-main/.github/workflows/links.yml deleted file mode 100644 index 73542b3..0000000 --- a/ultralytics-main/.github/workflows/links.yml +++ /dev/null @@ -1,90 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Continuous Integration (CI) GitHub Actions tests broken link checker using https://github.com/lycheeverse/lychee -# Ignores the following status codes to reduce false positives: -# - 403(OpenVINO, 'forbidden') -# - 429(Instagram, 'too many requests') -# - 500(Zenodo, 'cached') -# - 502(Zenodo, 'bad gateway') -# - 999(LinkedIn, 'unknown status code') - -name: Check Broken links - -on: - workflow_dispatch: - schedule: - - cron: "0 0 * * *" # runs at 00:00 UTC every day - -jobs: - Links: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v4 - - - name: Download and install lychee - run: | - LYCHEE_URL=$(curl -s https://api.github.com/repos/lycheeverse/lychee/releases/latest | grep "browser_download_url" | grep "x86_64-unknown-linux-gnu.tar.gz" | cut -d '"' -f 4) - curl -L $LYCHEE_URL -o lychee.tar.gz - tar xzf lychee.tar.gz - sudo mv lychee /usr/local/bin - - - name: Test Markdown and HTML links with retry - uses: nick-invision/retry@v3 - with: - timeout_minutes: 5 - retry_wait_seconds: 60 - max_attempts: 3 - command: | - lychee \ - --scheme https \ - --timeout 60 \ - --insecure \ - --accept 403,429,500,502,999 \ - --exclude-all-private \ - --exclude 'https?://(www\.)?(linkedin\.com|twitter\.com|instagram\.com|kaggle\.com|fonts\.gstatic\.com|url\.com)' \ - --exclude-path docs/zh \ - --exclude-path docs/es \ - --exclude-path docs/ru \ - --exclude-path docs/pt \ - --exclude-path docs/fr \ - --exclude-path docs/de \ - --exclude-path docs/ja \ - --exclude-path docs/ko \ - --exclude-path docs/hi \ - --exclude-path docs/ar \ - --github-token ${{ secrets.GITHUB_TOKEN }} \ - './**/*.md' \ - './**/*.html' - - - name: Test Markdown, HTML, YAML, Python and Notebook links with retry - if: github.event_name == 'workflow_dispatch' - uses: nick-invision/retry@v3 - with: - timeout_minutes: 5 - retry_wait_seconds: 60 - max_attempts: 3 - command: | - lychee \ - --scheme https \ - --timeout 60 \ - --insecure \ - --accept 429,999 \ - --exclude-all-private \ - --exclude 'https?://(www\.)?(linkedin\.com|twitter\.com|instagram\.com|kaggle\.com|fonts\.gstatic\.com|url\.com)' \ - --exclude-path '**/ci.yaml' \ - --exclude-path docs/zh \ - --exclude-path docs/es \ - --exclude-path docs/ru \ - --exclude-path docs/pt \ - --exclude-path docs/fr \ - --exclude-path docs/de \ - --exclude-path docs/ja \ - --exclude-path docs/ko \ - --exclude-path docs/hi \ - --exclude-path docs/ar \ - --github-token ${{ secrets.GITHUB_TOKEN }} \ - './**/*.md' \ - './**/*.html' \ - './**/*.yml' \ - './**/*.yaml' \ - './**/*.py' \ - './**/*.ipynb' diff --git a/ultralytics-main/.github/workflows/publish.yml b/ultralytics-main/.github/workflows/publish.yml deleted file mode 100644 index ca2980f..0000000 --- a/ultralytics-main/.github/workflows/publish.yml +++ /dev/null @@ -1,113 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Publish pip package to PyPI https://pypi.org/project/ultralytics/ and Docs to https://docs.ultralytics.com - -name: Publish to PyPI and Deploy Docs - -on: - push: - branches: [main] - workflow_dispatch: - inputs: - pypi: - type: boolean - description: Publish to PyPI - docs: - type: boolean - description: Deploy Docs - -jobs: - publish: - if: github.repository == 'ultralytics/ultralytics' && github.actor == 'glenn-jocher' - name: Publish - runs-on: ubuntu-latest - steps: - - name: Checkout code - uses: actions/checkout@v4 - with: - fetch-depth: "0" # pulls all commits (needed correct last updated dates in Docs) - - name: Set up Python environment - uses: actions/setup-python@v5 - with: - python-version: "3.11" - cache: "pip" # caching pip dependencies - - name: Install dependencies - run: | - python -m pip install --upgrade pip wheel build twine - pip install -e ".[dev]" --extra-index-url https://download.pytorch.org/whl/cpu - - name: Check PyPI version - shell: python - run: | - import os - import ultralytics - from ultralytics.utils.checks import check_latest_pypi_version - - v_local = tuple(map(int, ultralytics.__version__.split('.'))) - v_pypi = tuple(map(int, check_latest_pypi_version().split('.'))) - print(f'Local version is {v_local}') - print(f'PyPI version is {v_pypi}') - d = [a - b for a, b in zip(v_local, v_pypi)] # diff - increment = (d[0] == d[1] == 0) and (0 < d[2] < 3) # only publish if patch version increments by 1 or 2 - os.system(f'echo "increment={increment}" >> $GITHUB_OUTPUT') - os.system(f'echo "version={ultralytics.__version__}" >> $GITHUB_OUTPUT') - if increment: - print('Local version is higher than PyPI version. Publishing new version to PyPI ✅.') - id: check_pypi - - name: Publish to PyPI - continue-on-error: true - if: (github.event_name == 'push' || github.event.inputs.pypi == 'true') && steps.check_pypi.outputs.increment == 'True' - env: - PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }} - run: | - python -m build - python -m twine upload dist/* -u __token__ -p $PYPI_TOKEN - - name: Deploy Docs - continue-on-error: true - if: (github.event_name == 'push' || github.event.inputs.docs == 'true') && github.repository == 'ultralytics/ultralytics' && github.actor == 'glenn-jocher' - env: - PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }} - INDEXNOW_KEY: ${{ secrets.INDEXNOW_KEY_DOCS }} - run: | - export JUPYTER_PLATFORM_DIRS=1 - python docs/build_docs.py - git config --global user.name "Glenn Jocher" - git config --global user.email "glenn.jocher@ultralytics.com" - git clone https://github.com/ultralytics/docs.git docs-repo - cd docs-repo - git checkout gh-pages || git checkout -b gh-pages - rm -rf * - cp -R ../site/* . - echo "$INDEXNOW_KEY" > "$INDEXNOW_KEY.txt" - git add . - LATEST_HASH=$(git rev-parse --short=7 HEAD) - git commit -m "Update Docs for 'ultralytics ${{ steps.check_pypi.outputs.version }} - $LATEST_HASH'" - git push https://$PERSONAL_ACCESS_TOKEN@github.com/ultralytics/docs.git gh-pages - - name: Extract PR Details - run: | - if [ "${{ github.event_name }}" = "pull_request" ]; then - PR_JSON=$(curl -s -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" https://api.github.com/repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}) - PR_NUMBER=${{ github.event.pull_request.number }} - PR_TITLE=$(echo $PR_JSON | jq -r '.title') - else - COMMIT_SHA=${{ github.event.after }} - PR_JSON=$(curl -s -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" "https://api.github.com/search/issues?q=repo:${{ github.repository }}+is:pr+is:merged+sha:$COMMIT_SHA") - PR_NUMBER=$(echo $PR_JSON | jq -r '.items[0].number') - PR_TITLE=$(echo $PR_JSON | jq -r '.items[0].title') - fi - echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV - echo "PR_TITLE=$PR_TITLE" >> $GITHUB_ENV - - name: Notify on Slack (Success) - if: success() && github.event_name == 'push' && steps.check_pypi.outputs.increment == 'True' - uses: slackapi/slack-github-action@v1.25.0 - with: - payload: | - {"text": " GitHub Actions success for ${{ github.workflow }} ✅\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* NEW 'ultralytics ${{ steps.check_pypi.outputs.version }}' pip package published 😃\n*Job Status:* ${{ job.status }}\n*Pull Request:* ${{ env.PR_TITLE }}\n"} - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_YOLO }} - - name: Notify on Slack (Failure) - if: failure() - uses: slackapi/slack-github-action@v1.25.0 - with: - payload: | - {"text": " GitHub Actions error for ${{ github.workflow }} ❌\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* ${{ github.event_name }}\n*Job Status:* ${{ job.status }}\n*Pull Request:* ${{ env.PR_TITLE }}\n"} - env: - SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_YOLO }} diff --git a/ultralytics-main/.github/workflows/stale.yml b/ultralytics-main/.github/workflows/stale.yml deleted file mode 100644 index dd85035..0000000 --- a/ultralytics-main/.github/workflows/stale.yml +++ /dev/null @@ -1,47 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -name: Close stale issues -on: - schedule: - - cron: "0 0 * * *" # Runs at 00:00 UTC every day - -jobs: - stale: - runs-on: ubuntu-latest - steps: - - uses: actions/stale@v9 - with: - repo-token: ${{ secrets.GITHUB_TOKEN }} - - stale-issue-message: | - 👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help. - - For additional resources and information, please see the links below: - - - **Docs**: https://docs.ultralytics.com - - **HUB**: https://hub.ultralytics.com - - **Community**: https://community.ultralytics.com - - Feel free to inform us of any other **issues** you discover or **feature requests** that come to mind in the future. Pull Requests (PRs) are also always welcomed! - - Thank you for your contributions to YOLO 🚀 and Vision AI ⭐ - - stale-pr-message: | - 👋 Hello there! We wanted to let you know that we've decided to close this pull request due to inactivity. We appreciate the effort you put into contributing to our project, but unfortunately, not all contributions are suitable or aligned with our product roadmap. - - We hope you understand our decision, and please don't let it discourage you from contributing to open source projects in the future. We value all of our community members and their contributions, and we encourage you to keep exploring new projects and ways to get involved. - - For additional resources and information, please see the links below: - - - **Docs**: https://docs.ultralytics.com - - **HUB**: https://hub.ultralytics.com - - **Community**: https://community.ultralytics.com - - Thank you for your contributions to YOLO 🚀 and Vision AI ⭐ - - days-before-issue-stale: 30 - days-before-issue-close: 10 - days-before-pr-stale: 90 - days-before-pr-close: 30 - exempt-issue-labels: "documentation,tutorial,TODO" - operations-per-run: 300 # The maximum number of operations per run, used to control rate limiting. diff --git a/ultralytics-main/.gitignore b/ultralytics-main/.gitignore deleted file mode 100644 index 0854267..0000000 --- a/ultralytics-main/.gitignore +++ /dev/null @@ -1,166 +0,0 @@ -# Byte-compiled / optimized / DLL files -__pycache__/ -*.py[cod] -*$py.class - -# C extensions -*.so - -# Distribution / packaging -.Python -build/ -develop-eggs/ -dist/ -downloads/ -eggs/ -.eggs/ -lib/ -lib64/ -parts/ -sdist/ -var/ -wheels/ -pip-wheel-metadata/ -share/python-wheels/ -*.egg-info/ -.installed.cfg -*.egg -MANIFEST - -# PyInstaller -# Usually these files are written by a python script from a template -# before PyInstaller builds the exe, so as to inject date/other info into it. -*.manifest -*.spec - -# Installer logs -pip-log.txt -pip-delete-this-directory.txt - -# Unit test / coverage reports -htmlcov/ -.tox/ -.nox/ -.coverage -.coverage.* -.cache -nosetests.xml -coverage.xml -*.cover -*.py,cover -.hypothesis/ -.pytest_cache/ -mlruns/ - -# Translations -*.mo -*.pot - -# Django stuff: -*.log -local_settings.py -db.sqlite3 -db.sqlite3-journal - -# Flask stuff: -instance/ -.webassets-cache - -# Scrapy stuff: -.scrapy - -# Sphinx documentation -docs/_build/ - -# PyBuilder -target/ - -# Jupyter Notebook -.ipynb_checkpoints - -# IPython -profile_default/ -ipython_config.py - -# Profiling -*.pclprof - -# pyenv -.python-version - -# pipenv -# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. -# However, in case of collaboration, if having platform-specific dependencies or dependencies -# having no cross-platform support, pipenv may install dependencies that don't work, or not -# install all needed dependencies. -#Pipfile.lock - -# PEP 582; used by e.g. github.com/David-OConnor/pyflow -__pypackages__/ - -# Celery stuff -celerybeat-schedule -celerybeat.pid - -# SageMath parsed files -*.sage.py - -# Environments -.env -.venv -.idea -env/ -venv/ -ENV/ -env.bak/ -venv.bak/ - -# Spyder project settings -.spyderproject -.spyproject - -# VSCode project settings -.vscode/ - -# Rope project settings -.ropeproject - -# mkdocs documentation -/site -mkdocs_github_authors.yaml - -# mypy -.mypy_cache/ -.dmypy.json -dmypy.json - -# Pyre type checker -.pyre/ - -# datasets and projects -datasets/ -runs/ -wandb/ -tests/ -.DS_Store - -# Neural Network weights ----------------------------------------------------------------------------------------------- -weights/ -*.weights -*.pt -*.pb -*.onnx -*.engine -*.mlmodel -*.mlpackage -*.torchscript -*.tflite -*.h5 -*_saved_model/ -*_web_model/ -*_openvino_model/ -*_paddle_model/ -pnnx* - -# Autogenerated files for tests -/ultralytics/assets/ diff --git a/ultralytics-main/.pre-commit-config.yaml b/ultralytics-main/.pre-commit-config.yaml deleted file mode 100644 index 03461f1..0000000 --- a/ultralytics-main/.pre-commit-config.yaml +++ /dev/null @@ -1,86 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Pre-commit hooks. For more information see https://github.com/pre-commit/pre-commit-hooks/blob/main/README.md -# Optionally remove from local hooks with 'rm .git/hooks/pre-commit' - -# Define bot property if installed via https://github.com/marketplace/pre-commit-ci -ci: - autofix_prs: true - autoupdate_commit_msg: "[pre-commit.ci] pre-commit suggestions" - autoupdate_schedule: monthly - submodules: true - -# Exclude directories (optional) -# exclude: 'docs/' - -# Define repos to run -repos: - - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.5.0 - hooks: - - id: end-of-file-fixer - - id: trailing-whitespace - - id: check-case-conflict - # - id: check-yaml - - id: check-docstring-first - - id: detect-private-key - - - repo: https://github.com/asottile/pyupgrade - rev: v3.15.0 - hooks: - - id: pyupgrade - name: Upgrade code - - - repo: https://github.com/astral-sh/ruff-pre-commit - rev: v0.1.11 - hooks: - - id: ruff - args: [--fix] - - - repo: https://github.com/executablebooks/mdformat - rev: 0.7.17 - hooks: - - id: mdformat - name: MD formatting - additional_dependencies: - - mdformat-gfm - - mdformat-frontmatter - - mdformat-mkdocs - args: - - --wrap=no - - --number - exclude: 'docs/.*\.md' - # exclude: "README.md|README.zh-CN.md|CONTRIBUTING.md" - - - repo: https://github.com/codespell-project/codespell - rev: v2.2.6 - hooks: - - id: codespell - exclude: "docs/de|docs/fr|docs/pt|docs/es|docs/mkdocs_de.yml" - args: - - --ignore-words-list=crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall - - - repo: https://github.com/hadialqattan/pycln - rev: v2.4.0 - hooks: - - id: pycln - args: [--all] -# -# - repo: https://github.com/PyCQA/docformatter -# rev: v1.7.5 -# hooks: -# - id: docformatter - -# - repo: https://github.com/asottile/yesqa -# rev: v1.4.0 -# hooks: -# - id: yesqa - -# - repo: https://github.com/asottile/dead -# rev: v1.5.0 -# hooks: -# - id: dead - -# - repo: https://github.com/ultralytics/pre-commit -# rev: bd60a414f80a53fb8f593d3bfed4701fc47e4b23 -# hooks: -# - id: capitalize-comments diff --git a/ultralytics-main/Author_advice.txt b/ultralytics-main/Author_advice.txt deleted file mode 100644 index 22b6129..0000000 --- a/ultralytics-main/Author_advice.txt +++ /dev/null @@ -1,7 +0,0 @@ - -# 双目测距运行yolov8-stereo.py文件即可 - -# 测量速度运行stereo-speed.py文件 - - -具体操作步骤见播客主页：https://blog.csdn.net/qq_45077760 \ No newline at end of file diff --git a/ultralytics-main/CITATION.cff b/ultralytics-main/CITATION.cff deleted file mode 100644 index bee0abe..0000000 --- a/ultralytics-main/CITATION.cff +++ /dev/null @@ -1,26 +0,0 @@ -# This CITATION.cff file was generated with https://bit.ly/cffinit - -cff-version: 1.2.0 -title: Ultralytics YOLO -message: >- - If you use this software, please cite it using the - metadata from this file. -type: software -authors: - - given-names: Glenn - family-names: Jocher - affiliation: Ultralytics - orcid: 'https://orcid.org/0000-0001-5950-6979' - - given-names: Ayush - family-names: Chaurasia - affiliation: Ultralytics - orcid: 'https://orcid.org/0000-0002-7603-6750' - - family-names: Qiu - given-names: Jing - affiliation: Ultralytics - orcid: 'https://orcid.org/0000-0003-3783-7069' -repository-code: 'https://github.com/ultralytics/ultralytics' -url: 'https://ultralytics.com' -license: AGPL-3.0 -version: 8.0.0 -date-released: '2023-01-10' diff --git a/ultralytics-main/Instance Segmentation-camera.py b/ultralytics-main/Instance Segmentation-camera.py deleted file mode 100644 index 5cc4e88..0000000 --- a/ultralytics-main/Instance Segmentation-camera.py +++ /dev/null @@ -1,37 +0,0 @@ -import cv2 -from ultralytics import YOLO -from ultralytics.utils.plotting import Annotator, colors - -model = YOLO("yolov8n-seg.pt") # segmentation model -names = model.model.names -cap = cv2.VideoCapture(0) -w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - -out = cv2.VideoWriter('instance-segmentation.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - -while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - results = model.predict(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].masks is not None: - clss = results[0].boxes.cls.cpu().tolist() - masks = results[0].masks.xy - for mask, cls in zip(masks, clss): - annotator.seg_bbox(mask=mask, - mask_color=colors(int(cls), True), - det_label=names[int(cls)]) - - out.write(im0) - cv2.imshow("instance-segmentation", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - -out.release() -cap.release() -cv2.destroyAllWindows() \ No newline at end of file diff --git a/ultralytics-main/Instance Segmentation-pic-video.py b/ultralytics-main/Instance Segmentation-pic-video.py deleted file mode 100644 index 8aa8b1e..0000000 --- a/ultralytics-main/Instance Segmentation-pic-video.py +++ /dev/null @@ -1,66 +0,0 @@ -from ultralytics import YOLO -import cv2 -import os -from ultralytics.utils.plotting import Annotator, colors -if __name__ == '__main__': -# 实例分割检测文件夹里所有图片视频（实例分割和掩码分割不同）： - model = YOLO('yolov8n-seg.pt') - names = model.model.names - input_folder = 'ultralytics/assets' # 输入文件夹 - output_folder = 'runs/detect/test' # 输出文件夹 - - if not os.path.exists(output_folder): - os.makedirs(output_folder) - - # 获取输入文件夹中所有文件的文件名 - all_files = [f for f in os.listdir(input_folder)] - - for file_name in all_files: - file_path = os.path.join(input_folder, file_name) - if file_name.endswith('.jpg') or file_name.endswith('.png'): - # 处理图片 - im0 = cv2.imread(file_path) - results = model.predict(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].masks is not None: - clss = results[0].boxes.cls.cpu().tolist() - masks = results[0].masks.xy - for mask, cls in zip(masks, clss): - annotator.seg_bbox(mask=mask, - mask_color=colors(int(cls), True), - det_label=names[int(cls)]) - - output_path = os.path.join(output_folder, file_name) - cv2.imwrite(output_path, im0) - - elif file_name.endswith('.mp4') or file_name.endswith('.avi'): - # 处理视频 - cap = cv2.VideoCapture(file_path) - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter(os.path.join(output_folder, file_name + '_segmented.avi'), cv2.VideoWriter_fourcc(*'MJPG'), - fps, (w, h)) - - while True: - ret, im0 = cap.read() - if not ret: - print(f"视频 {file_name} 处理完成") - break - - results = model.predict(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].masks is not None: - clss = results[0].boxes.cls.cpu().tolist() - masks = results[0].masks.xy - for mask, cls in zip(masks, clss): - annotator.seg_bbox(mask=mask, - mask_color=colors(int(cls), True), - det_label=names[int(cls)]) - - out.write(im0) - cv2.imshow("instance-segmentation", im0) - - out.release() - cap.release() diff --git a/ultralytics-main/Instance Segmentation-track-camera.py b/ultralytics-main/Instance Segmentation-track-camera.py deleted file mode 100644 index 61b18ac..0000000 --- a/ultralytics-main/Instance Segmentation-track-camera.py +++ /dev/null @@ -1,42 +0,0 @@ -import cv2 -from ultralytics import YOLO -from ultralytics.utils.plotting import Annotator, colors - -from collections import defaultdict - -track_history = defaultdict(lambda: []) - -model = YOLO("yolov8n-seg.pt") # segmentation model -cap = cv2.VideoCapture(0) -w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - -out = cv2.VideoWriter('instance-segmentation-object-tracking.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - -while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - annotator = Annotator(im0, line_width=2) - - results = model.track(im0, persist=True) - - if results[0].boxes.id is not None and results[0].masks is not None: - masks = results[0].masks.xy - track_ids = results[0].boxes.id.int().cpu().tolist() - - for mask, track_id in zip(masks, track_ids): - annotator.seg_bbox(mask=mask, - mask_color=colors(track_id, True), - track_label=str(track_id)) - - out.write(im0) - cv2.imshow("instance-segmentation-object-tracking", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - -out.release() -cap.release() -cv2.destroyAllWindows() \ No newline at end of file diff --git a/ultralytics-main/Instance Segmentation-track-pic-video.py b/ultralytics-main/Instance Segmentation-track-pic-video.py deleted file mode 100644 index ceaef95..0000000 --- a/ultralytics-main/Instance Segmentation-track-pic-video.py +++ /dev/null @@ -1,67 +0,0 @@ -from ultralytics import YOLO -import cv2 -import os -from ultralytics.utils.plotting import Annotator, colors -from collections import defaultdict -if __name__ == '__main__': -# 实例分割检测文件夹里所有图片视频（实例分割和掩码分割不同）： - model = YOLO('yolov8n-seg.pt') - names = model.model.names - input_folder = 'ultralytics/assets' # 输入文件夹 - output_folder = 'runs/detect/test1' # 输出文件夹 - - if not os.path.exists(output_folder): - os.makedirs(output_folder) - - # 获取输入文件夹中所有文件的文件名 - all_files = [f for f in os.listdir(input_folder)] - - for file_name in all_files: - file_path = os.path.join(input_folder, file_name) - if file_name.endswith('.jpg') or file_name.endswith('.png'): - # 处理图片 - im0 = cv2.imread(file_path) - results = model.track(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].boxes.id is not None and results[0].masks is not None: - masks = results[0].masks.xy - track_ids = results[0].boxes.id.int().cpu().tolist() - for mask, track_id in zip(masks, track_ids): - annotator.seg_bbox(mask=mask, - mask_color=colors(track_id, True), - track_label=str(track_id)) - - output_path = os.path.join(output_folder, file_name) - cv2.imwrite(output_path, im0) - - elif file_name.endswith('.mp4') or file_name.endswith('.avi'): - # 处理视频 - cap = cv2.VideoCapture(file_path) - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter(os.path.join(output_folder, file_name + '_segmented.avi'), cv2.VideoWriter_fourcc(*'MJPG'), - fps, (w, h)) - - while True: - ret, im0 = cap.read() - if not ret: - print(f"视频 {file_name} 处理完成") - break - - results = model.track(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].boxes.id is not None and results[0].masks is not None: - masks = results[0].masks.xy - track_ids = results[0].boxes.id.int().cpu().tolist() - for mask, track_id in zip(masks, track_ids): - annotator.seg_bbox(mask=mask, - mask_color=colors(track_id, True), - track_label=str(track_id)) - - out.write(im0) - cv2.imshow("instance-segmentation", im0) - - out.release() - cap.release() diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_456_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_456_00_42_15.jpg deleted file mode 100644 index bef0dcb..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_456_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_457_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_457_00_42_15.jpg deleted file mode 100644 index 3de1ae9..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_457_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_458_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_458_00_42_15.jpg deleted file mode 100644 index ff53e53..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_458_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_459_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_459_00_42_15.jpg deleted file mode 100644 index 92c7011..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_459_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_460_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_460_00_42_15.jpg deleted file mode 100644 index 952aa4a..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_460_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_461_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_461_00_42_15.jpg deleted file mode 100644 index 25c523e..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_461_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_462_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_462_00_42_15.jpg deleted file mode 100644 index 7e47ffe..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_462_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_463_00_42_15.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_463_00_42_15.jpg deleted file mode 100644 index 463d928..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_463_00_42_15.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_464_00_42_16.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_464_00_42_16.jpg deleted file mode 100644 index b68f63e..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_464_00_42_16.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_465_00_42_16.jpg b/ultralytics-main/dataset/coco128/images/train2017/image_BS1_465_00_42_16.jpg deleted file mode 100644 index bea513a..0000000 Binary files a/ultralytics-main/dataset/coco128/images/train2017/image_BS1_465_00_42_16.jpg and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/labels/train2017.cache b/ultralytics-main/dataset/coco128/labels/train2017.cache deleted file mode 100644 index 5d453a7..0000000 Binary files a/ultralytics-main/dataset/coco128/labels/train2017.cache and /dev/null differ diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_456_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_456_00_42_15.txt deleted file mode 100644 index f5f15ec..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_456_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.016146 0.229630 0.030208 0.085185 -1 0.584896 0.175926 0.015625 0.062963 -1 0.555208 0.171296 0.014583 0.068519 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_457_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_457_00_42_15.txt deleted file mode 100644 index 35b3439..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_457_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.020833 0.233333 0.039583 0.088889 -1 0.584375 0.175926 0.014583 0.059259 -1 0.556250 0.174074 0.012500 0.059259 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_458_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_458_00_42_15.txt deleted file mode 100644 index 1167b31..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_458_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.026042 0.231481 0.050000 0.096296 -1 0.584896 0.179630 0.015625 0.062963 -1 0.555208 0.172222 0.012500 0.059259 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_459_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_459_00_42_15.txt deleted file mode 100644 index 95620ab..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_459_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.032292 0.227778 0.062500 0.103704 -1 0.586458 0.175000 0.012500 0.061111 -1 0.552604 0.176852 0.015625 0.068519 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_460_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_460_00_42_15.txt deleted file mode 100644 index 46a76a2..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_460_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.035417 0.227778 0.068750 0.103704 -1 0.587500 0.175000 0.018750 0.053704 -1 0.553125 0.172222 0.012500 0.062963 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_461_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_461_00_42_15.txt deleted file mode 100644 index 073adce..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_461_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.041146 0.228704 0.080208 0.101852 -1 0.587500 0.177778 0.014583 0.066667 -1 0.553125 0.174074 0.012500 0.062963 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_462_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_462_00_42_15.txt deleted file mode 100644 index 9662efd..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_462_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.045312 0.228704 0.088542 0.101852 -1 0.586979 0.177778 0.013542 0.055556 -1 0.554688 0.174074 0.013542 0.062963 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_463_00_42_15.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_463_00_42_15.txt deleted file mode 100644 index 0bfafab..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_463_00_42_15.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.053646 0.230556 0.105208 0.101852 -1 0.586458 0.175926 0.014583 0.055556 -1 0.552604 0.169444 0.015625 0.064815 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_464_00_42_16.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_464_00_42_16.txt deleted file mode 100644 index d869c72..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_464_00_42_16.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.058333 0.231481 0.114583 0.096296 -1 0.588021 0.180556 0.013542 0.075926 -1 0.552083 0.176852 0.010417 0.061111 diff --git a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_465_00_42_16.txt b/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_465_00_42_16.txt deleted file mode 100644 index 7f15e7d..0000000 --- a/ultralytics-main/dataset/coco128/labels/train2017/image_BS1_465_00_42_16.txt +++ /dev/null @@ -1,3 +0,0 @@ -0 0.061458 0.231481 0.120833 0.100000 -1 0.588542 0.180556 0.012500 0.053704 -1 0.552083 0.175000 0.010417 0.061111 diff --git a/ultralytics-main/docker/Dockerfile b/ultralytics-main/docker/Dockerfile deleted file mode 100644 index b96173e..0000000 --- a/ultralytics-main/docker/Dockerfile +++ /dev/null @@ -1,85 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is CUDA-optimized for YOLOv8 single/multi-GPU training and inference - -# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch or nvcr.io/nvidia/pytorch:23.03-py3 -FROM pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime -RUN pip install --no-cache nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package -RUN apt update \ - && apt install --no-install-recommends -y gcc git zip curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 - -# Security updates -# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796 -RUN apt upgrade --no-install-recommends -y openssl tar - -# Create working directory -WORKDIR /usr/src/ultralytics - -# Copy contents -# COPY . /usr/src/ultralytics # git permission issues inside container -RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/ - -# Install pip packages -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -e ".[export]" albumentations comet pycocotools - -# Run exports to AutoInstall packages -# Edge TPU export fails the first time so is run twice here -RUN yolo export model=tmp/yolov8n.pt format=edgetpu imgsz=32 || yolo export model=tmp/yolov8n.pt format=edgetpu imgsz=32 -RUN yolo export model=tmp/yolov8n.pt format=ncnn imgsz=32 -# Requires <= Python 3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991 -RUN pip install --no-cache paddlepaddle>=2.6.0 x2paddle -# Fix error: `np.bool` was a deprecated alias for the builtin `bool` segmentation error in Tests -RUN pip install --no-cache numpy==1.23.5 -# Remove exported models -RUN rm -rf tmp - -# Set environment variables -ENV OMP_NUM_THREADS=1 -# Avoid DDP error "MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library" https://github.com/pytorch/pytorch/issues/37377 -ENV MKL_THREADING_LAYER=GNU - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest && sudo docker build -f docker/Dockerfile -t $t . && sudo docker push $t - -# Pull and Run with access to all GPUs -# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t - -# Pull and Run with access to GPUs 2 and 3 (inside container CUDA devices will appear as 0 and 1) -# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus '"device=2,3"' $t - -# Pull and Run with local directory access -# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t - -# Kill all -# sudo docker kill $(sudo docker ps -q) - -# Kill all image-based -# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/ultralytics:latest) - -# DockerHub tag update -# t=ultralytics/ultralytics:latest tnew=ultralytics/ultralytics:v6.2 && sudo docker pull $t && sudo docker tag $t $tnew && sudo docker push $tnew - -# Clean up -# sudo docker system prune -a --volumes - -# Update Ubuntu drivers -# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/ - -# DDP test -# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3 - -# GCP VM from Image -# docker.io/ultralytics/ultralytics:latest diff --git a/ultralytics-main/docker/Dockerfile-arm64 b/ultralytics-main/docker/Dockerfile-arm64 deleted file mode 100644 index e9ab84c..0000000 --- a/ultralytics-main/docker/Dockerfile-arm64 +++ /dev/null @@ -1,51 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest-arm64 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is aarch64-compatible for Apple M1, M2, M3, Raspberry Pi and other ARM architectures - -# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu with "FROM arm64v8/ubuntu:22.04" (deprecated) -# Start FROM Debian image for arm64v8 https://hub.docker.com/r/arm64v8/debian (new) -FROM arm64v8/debian:bookworm-slim - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package -# cmake and build-essential is needed to build onnxsim when exporting to tflite -RUN apt update \ - && apt install --no-install-recommends -y python3-pip git zip curl htop gcc libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 build-essential - -# Create working directory -WORKDIR /usr/src/ultralytics - -# Copy contents -# COPY . /usr/src/ultralytics # git permission issues inside container -RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/ - -# Remove python3.11/EXTERNALLY-MANAGED to avoid 'externally-managed-environment' issue, Debian 12 Bookworm error -RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED - -# Install pip packages -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -e ".[export]" - -# Creates a symbolic link to make 'python' point to 'python3' -RUN ln -sf /usr/bin/python3 /usr/bin/python - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-arm64 && sudo docker build --platform linux/arm64 -f docker/Dockerfile-arm64 -t $t . && sudo docker push $t - -# Run -# t=ultralytics/ultralytics:latest-arm64 && sudo docker run -it --ipc=host $t - -# Pull and Run -# t=ultralytics/ultralytics:latest-arm64 && sudo docker pull $t && sudo docker run -it --ipc=host $t - -# Pull and Run with local volume mounted -# t=ultralytics/ultralytics:latest-arm64 && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/ultralytics-main/docker/Dockerfile-conda b/ultralytics-main/docker/Dockerfile-conda deleted file mode 100644 index 30d4ce1..0000000 --- a/ultralytics-main/docker/Dockerfile-conda +++ /dev/null @@ -1,40 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest-conda image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is optimized for Ultralytics Anaconda (https://anaconda.org/conda-forge/ultralytics) installation and usage - -# Start FROM miniconda3 image https://hub.docker.com/r/continuumio/miniconda3 -FROM continuumio/miniconda3:latest - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -RUN apt update \ - && apt install --no-install-recommends -y libgl1 - -# Copy contents -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt . - -# Install conda packages -# mkl required to fix 'OSError: libmkl_intel_lp64.so.2: cannot open shared object file: No such file or directory' -RUN conda config --set solver libmamba && \ - conda install pytorch torchvision pytorch-cuda=11.8 -c pytorch -c nvidia && \ - conda install -c conda-forge ultralytics mkl - # conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics mkl - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-conda && sudo docker build -f docker/Dockerfile-cpu -t $t . && sudo docker push $t - -# Run -# t=ultralytics/ultralytics:latest-conda && sudo docker run -it --ipc=host $t - -# Pull and Run -# t=ultralytics/ultralytics:latest-conda && sudo docker pull $t && sudo docker run -it --ipc=host $t - -# Pull and Run with local volume mounted -# t=ultralytics/ultralytics:latest-conda && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/ultralytics-main/docker/Dockerfile-cpu b/ultralytics-main/docker/Dockerfile-cpu deleted file mode 100644 index f829ebf..0000000 --- a/ultralytics-main/docker/Dockerfile-cpu +++ /dev/null @@ -1,57 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest-cpu image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLOv8 deployments - -# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu -FROM ubuntu:23.10 - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package -RUN apt update \ - && apt install --no-install-recommends -y python3-pip git zip curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 - -# Create working directory -WORKDIR /usr/src/ultralytics - -# Copy contents -# COPY . /usr/src/ultralytics # git permission issues inside container -RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/ - -# Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error -RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED - -# Install pip packages -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -e ".[export]" --extra-index-url https://download.pytorch.org/whl/cpu - -# Run exports to AutoInstall packages -RUN yolo export model=tmp/yolov8n.pt format=edgetpu imgsz=32 -RUN yolo export model=tmp/yolov8n.pt format=ncnn imgsz=32 -# Requires <= Python 3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991 -# RUN pip install --no-cache paddlepaddle>=2.6.0 x2paddle -# Remove exported models -RUN rm -rf tmp - -# Creates a symbolic link to make 'python' point to 'python3' -RUN ln -sf /usr/bin/python3 /usr/bin/python - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-cpu && sudo docker build -f docker/Dockerfile-cpu -t $t . && sudo docker push $t - -# Run -# t=ultralytics/ultralytics:latest-cpu && sudo docker run -it --ipc=host --name NAME $t - -# Pull and Run -# t=ultralytics/ultralytics:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host --name NAME $t - -# Pull and Run with local volume mounted -# t=ultralytics/ultralytics:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/ultralytics-main/docker/Dockerfile-jetson b/ultralytics-main/docker/Dockerfile-jetson deleted file mode 100644 index 6528628..0000000 --- a/ultralytics-main/docker/Dockerfile-jetson +++ /dev/null @@ -1,50 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:jetson image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Supports JetPack for YOLOv8 on Jetson Nano, TX1/TX2, Xavier NX, AGX Xavier, AGX Orin, and Orin NX - -# Start FROM https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-pytorch -FROM nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3 - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package -RUN apt update \ - && apt install --no-install-recommends -y gcc git zip curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 - -# Create working directory -WORKDIR /usr/src/ultralytics - -# Copy contents -# COPY . /usr/src/ultralytics # git permission issues inside container -RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/ - -# Remove opencv-python from Ultralytics dependencies as it conflicts with opencv-python installed in base image -RUN grep -v "opencv-python" pyproject.toml > temp.toml && mv temp.toml pyproject.toml - -# Install pip packages manually for TensorRT compatibility https://github.com/NVIDIA/TensorRT/issues/2567 -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache tqdm matplotlib pyyaml psutil pandas onnx "numpy==1.23" -RUN pip install --no-cache -e . - -# Set environment variables -ENV OMP_NUM_THREADS=1 - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-jetson && sudo docker build --platform linux/arm64 -f docker/Dockerfile-jetson -t $t . && sudo docker push $t - -# Run -# t=ultralytics/ultralytics:latest-jetson && sudo docker run -it --ipc=host $t - -# Pull and Run -# t=ultralytics/ultralytics:latest-jetson && sudo docker pull $t && sudo docker run -it --ipc=host $t - -# Pull and Run with NVIDIA runtime -# t=ultralytics/ultralytics:latest-jetson && sudo docker pull $t && sudo docker run -it --ipc=host --runtime=nvidia $t diff --git a/ultralytics-main/docker/Dockerfile-python b/ultralytics-main/docker/Dockerfile-python deleted file mode 100644 index 8423dbb..0000000 --- a/ultralytics-main/docker/Dockerfile-python +++ /dev/null @@ -1,54 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds ultralytics/ultralytics:latest-cpu image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLOv8 deployments - -# Use the official Python 3.10 slim-bookworm as base image -FROM python:3.10-slim-bookworm - -# Downloads to user config dir -ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \ - https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \ - /root/.config/Ultralytics/ - -# Install linux packages -# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package -RUN apt update \ - && apt install --no-install-recommends -y python3-pip git zip curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 - -# Create working directory -WORKDIR /usr/src/ultralytics - -# Copy contents -# COPY . /usr/src/ultralytics # git permission issues inside container -RUN git clone https://github.com/ultralytics/ultralytics -b main /usr/src/ultralytics -ADD https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt /usr/src/ultralytics/ - -# Remove python3.11/EXTERNALLY-MANAGED or use 'pip install --break-system-packages' avoid 'externally-managed-environment' Ubuntu nightly error -# RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED - -# Install pip packages -RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -e ".[export]" --extra-index-url https://download.pytorch.org/whl/cpu - -# Run exports to AutoInstall packages -RUN yolo export model=tmp/yolov8n.pt format=edgetpu imgsz=32 -RUN yolo export model=tmp/yolov8n.pt format=ncnn imgsz=32 -# Requires <= Python 3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991 -RUN pip install --no-cache paddlepaddle>=2.6.0 x2paddle -# Remove exported models -RUN rm -rf tmp - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-python && sudo docker build -f docker/Dockerfile-python -t $t . && sudo docker push $t - -# Run -# t=ultralytics/ultralytics:latest-python && sudo docker run -it --ipc=host $t - -# Pull and Run -# t=ultralytics/ultralytics:latest-python && sudo docker pull $t && sudo docker run -it --ipc=host $t - -# Pull and Run with local volume mounted -# t=ultralytics/ultralytics:latest-python && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t diff --git a/ultralytics-main/docker/Dockerfile-runner b/ultralytics-main/docker/Dockerfile-runner deleted file mode 100644 index c0f8659..0000000 --- a/ultralytics-main/docker/Dockerfile-runner +++ /dev/null @@ -1,38 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Builds GitHub actions CI runner image for deployment to DockerHub https://hub.docker.com/r/ultralytics/ultralytics -# Image is CUDA-optimized for YOLOv8 single/multi-GPU training and inference tests - -# Start FROM Ultralytics GPU image -FROM ultralytics/ultralytics:latest - -# Set the working directory -WORKDIR /actions-runner - -# Download and unpack the latest runner from https://github.com/actions/runner -RUN FILENAME=actions-runner-linux-x64-2.309.0.tar.gz && \ - curl -o $FILENAME -L https://github.com/actions/runner/releases/download/v2.309.0/$FILENAME && \ - tar xzf $FILENAME && \ - rm $FILENAME - -# Install runner dependencies -ENV RUNNER_ALLOW_RUNASROOT=1 -ENV DEBIAN_FRONTEND=noninteractive -RUN ./bin/installdependencies.sh && \ - apt-get -y install libicu-dev - -# Inline ENTRYPOINT command to configure and start runner with default TOKEN and NAME -ENTRYPOINT sh -c './config.sh --url https://github.com/ultralytics/ultralytics \ - --token ${GITHUB_RUNNER_TOKEN:-TOKEN} \ - --name ${GITHUB_RUNNER_NAME:-NAME} \ - --labels gpu-latest \ - --replace && \ - ./run.sh' - - -# Usage Examples ------------------------------------------------------------------------------------------------------- - -# Build and Push -# t=ultralytics/ultralytics:latest-runner && sudo docker build -f docker/Dockerfile-runner -t $t . && sudo docker push $t - -# Pull and Run in detached mode with access to GPUs 0 and 1 -# t=ultralytics/ultralytics:latest-runner && sudo docker run -d -e GITHUB_RUNNER_TOKEN=TOKEN -e GITHUB_RUNNER_NAME=NAME --ipc=host --gpus '"device=0,1"' $t diff --git a/ultralytics-main/docs/README.md b/ultralytics-main/docs/README.md deleted file mode 100644 index 954e130..0000000 --- a/ultralytics-main/docs/README.md +++ /dev/null @@ -1,140 +0,0 @@ -
- - -# 📚 Ultralytics Docs - -Ultralytics Docs are the gateway to understanding and utilizing our cutting-edge machine learning tools. These documents are deployed to [https://docs.ultralytics.com](https://docs.ultralytics.com) for your convenience. - -[![pages-build-deployment](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment) [![Check Broken links](https://github.com/ultralytics/docs/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/links.yml) [![Check Domains](https://github.com/ultralytics/docs/actions/workflows/check_domains.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/check_domains.yml) [![Ultralytics Actions](https://github.com/ultralytics/docs/actions/workflows/format.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/format.yml) Discord - -## 🛠️ Installation - -[![PyPI version](https://badge.fury.io/py/ultralytics.svg)](https://badge.fury.io/py/ultralytics) [![Downloads](https://static.pepy.tech/badge/ultralytics)](https://pepy.tech/project/ultralytics) - -To install the ultralytics package in developer mode, ensure you have Git and Python 3 installed on your system. Then, follow these steps: - -1. Clone the ultralytics repository to your local machine using Git: - - ```bash - git clone https://github.com/ultralytics/ultralytics.git - ``` - -2. Navigate to the cloned repository's root directory: - - ```bash - cd ultralytics - ``` - -3. Install the package in developer mode using pip (or pip3 for Python 3): - - ```bash - pip install -e '.[dev]' - ``` - -- This command installs the ultralytics package along with all development dependencies, allowing you to modify the package code and have the changes immediately reflected in your Python environment. - -## 🚀 Building and Serving Locally - -The `mkdocs serve` command builds and serves a local version of your MkDocs documentation, ideal for development and testing: - -```bash -mkdocs serve -``` - -- #### Command Breakdown: - - - `mkdocs` is the main MkDocs command-line interface. - - `serve` is the subcommand to build and locally serve your documentation. - -- 🧐 Note: - - - Grasp changes to the docs in real-time as `mkdocs serve` supports live reloading. - - To stop the local server, press `CTRL+C`. - -## 🌍 Building and Serving Multi-Language - -Supporting multi-language documentation? Follow these steps: - -1. Stage all new language \*.md files with Git: - - ```bash - git add docs/**/*.md -f - ``` - -2. Build all languages to the `/site` folder, ensuring relevant root-level files are present: - - ```bash - # Clear existing /site directory - rm -rf site - - # Loop through each language config file and build - mkdocs build -f docs/mkdocs.yml - for file in docs/mkdocs_*.yml; do - echo "Building MkDocs site with $file" - mkdocs build -f "$file" - done - ``` - -3. To preview your site, initiate a simple HTTP server: - - ```bash - cd site - python -m http.server - # Open in your preferred browser - ``` - -- 🖥️ Access the live site at `http://localhost:8000`. - -## 📤 Deploying Your Documentation Site - -Choose a hosting provider and deployment method for your MkDocs documentation: - -- Configure `mkdocs.yml` with deployment settings. -- Use `mkdocs deploy` to build and deploy your site. - -* ### GitHub Pages Deployment Example: - ```bash - mkdocs gh-deploy - ``` - -- Update the "Custom domain" in your repository's settings for a personalized URL. - -![196814117-fc16e711-d2be-4722-9536-b7c6d78fd167](https://user-images.githubusercontent.com/26833433/210150206-9e86dcd7-10af-43e4-9eb2-9518b3799eac.png) - -- For detailed deployment guidance, consult the [MkDocs documentation](https://www.mkdocs.org/user-guide/deploying-your-docs/). - -## 💡 Contribute - -We cherish the community's input as it drives Ultralytics open-source initiatives. Dive into the [Contributing Guide](https://docs.ultralytics.com/help/contributing) and share your thoughts via our [Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey). A heartfelt thank you 🙏 to each contributor! - - - -![Ultralytics open-source contributors](https://github.com/ultralytics/assets/raw/main/im/image-contributors.png) - -## 📜 License - -Ultralytics presents two licensing options: - -- **AGPL-3.0 License**: Perfect for academia and open collaboration. Details are in the [LICENSE](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) file. -- **Enterprise License**: Tailored for commercial usage, offering a seamless blend of Ultralytics technology in your products. Learn more at [Ultralytics Licensing](https://ultralytics.com/license). - -## ✉️ Contact - -For bug reports and feature requests, navigate to [GitHub Issues](https://github.com/ultralytics/docs/issues). Engage with peers and the Ultralytics team on [Discord](https://ultralytics.com/discord) for enriching conversations! - -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
diff --git a/ultralytics-main/docs/build_docs.py b/ultralytics-main/docs/build_docs.py deleted file mode 100644 index 825df80..0000000 --- a/ultralytics-main/docs/build_docs.py +++ /dev/null @@ -1,141 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -This Python script is designed to automate the building and post-processing of MkDocs documentation, particularly for -projects with multilingual content. It streamlines the workflow for generating localized versions of the documentation -and updating HTML links to ensure they are correctly formatted. - -Key Features: -- Automated building of MkDocs documentation: The script compiles both the main documentation and - any localized versions specified in separate MkDocs configuration files. -- Post-processing of generated HTML files: After the documentation is built, the script updates all - HTML files to remove the '.md' extension from internal links. This ensures that links in the built - HTML documentation correctly point to other HTML pages rather than Markdown files, which is crucial - for proper navigation within the web-based documentation. - -Usage: -- Run the script from the root directory of your MkDocs project. -- Ensure that MkDocs is installed and that all MkDocs configuration files (main and localized versions) - are present in the project directory. -- The script first builds the documentation using MkDocs, then scans the generated HTML files in the 'site' - directory to update the internal links. -- It's ideal for projects where the documentation is written in Markdown and needs to be served as a static website. - -Note: -- This script is built to be run in an environment where Python and MkDocs are installed and properly configured. -""" - -import os -import re -import shutil -import subprocess -from pathlib import Path - -from tqdm import tqdm - -DOCS = Path(__file__).parent.resolve() -SITE = DOCS.parent / "site" - - -def build_docs(clone_repos=True): - """Build docs using mkdocs.""" - if SITE.exists(): - print(f"Removing existing {SITE}") - shutil.rmtree(SITE) - - # Get hub-sdk repo - if clone_repos: - repo = "https://github.com/ultralytics/hub-sdk" - local_dir = DOCS.parent / Path(repo).name - if not local_dir.exists(): - os.system(f"git clone {repo} {local_dir}") - os.system(f"git -C {local_dir} pull") # update repo - shutil.rmtree(DOCS / "en/hub/sdk", ignore_errors=True) # delete if exists - shutil.copytree(local_dir / "docs", DOCS / "en/hub/sdk") # for docs - shutil.rmtree(DOCS.parent / "hub_sdk", ignore_errors=True) # delete if exists - shutil.copytree(local_dir / "hub_sdk", DOCS.parent / "hub_sdk") # for mkdocstrings - print(f"Cloned/Updated {repo} in {local_dir}") - - # Build the main documentation - print(f"Building docs from {DOCS}") - subprocess.run(f"mkdocs build -f {DOCS.parent}/mkdocs.yml", check=True, shell=True) - print(f"Site built at {SITE}") - - -def update_page_title(file_path: Path, new_title: str): - """Update the title of an HTML file.""" - - # Read the content of the file - with open(file_path, encoding="utf-8") as file: - content = file.read() - - # Replace the existing title with the new title - updated_content = re.sub(r".*?", f"{new_title}", content) - - # Write the updated content back to the file - with open(file_path, "w", encoding="utf-8") as file: - file.write(updated_content) - - -def update_html_head(script=""): - """Update the HTML head section of each file.""" - html_files = Path(SITE).rglob("*.html") - for html_file in tqdm(html_files, desc="Processing HTML files"): - with html_file.open("r", encoding="utf-8") as file: - html_content = file.read() - - if script in html_content: # script already in HTML file - return - - head_end_index = html_content.lower().rfind("") - if head_end_index != -1: - # Add the specified JavaScript to the HTML file just before the end of the head tag. - new_html_content = html_content[:head_end_index] + script + html_content[head_end_index:] - with html_file.open("w", encoding="utf-8") as file: - file.write(new_html_content) - - -def update_subdir_edit_links(subdir="", docs_url=""): - """Update the HTML head section of each file.""" - from bs4 import BeautifulSoup - - if str(subdir[0]) == "/": - subdir = str(subdir[0])[1:] - html_files = (SITE / subdir).rglob("*.html") - for html_file in tqdm(html_files, desc="Processing subdir files"): - with html_file.open("r", encoding="utf-8") as file: - soup = BeautifulSoup(file, "html.parser") - - # Find the anchor tag and update its href attribute - a_tag = soup.find("a", {"class": "md-content__button md-icon"}) - if a_tag and a_tag["title"] == "Edit this page": - a_tag["href"] = f"{docs_url}{a_tag['href'].split(subdir)[-1]}" - - # Write the updated HTML back to the file - with open(html_file, "w", encoding="utf-8") as file: - file.write(str(soup)) - - -def main(): - """Builds docs, updates titles and edit links, and prints local server command.""" - build_docs() - - # Update titles - update_page_title(SITE / "404.html", new_title="Ultralytics Docs - Not Found") - - # Update edit links - update_subdir_edit_links( - subdir="hub/sdk/", # do not use leading slash - docs_url="https://github.com/ultralytics/hub-sdk/tree/develop/docs/", - ) - - # Update HTML file head section - script = "" - if any(script): - update_html_head(script) - - # Show command to serve built website - print('Serve site at http://localhost:8000 with "python -m http.server --directory site"') - - -if __name__ == "__main__": - main() diff --git a/ultralytics-main/docs/build_reference.py b/ultralytics-main/docs/build_reference.py deleted file mode 100644 index a9ddd07..0000000 --- a/ultralytics-main/docs/build_reference.py +++ /dev/null @@ -1,130 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Helper file to build Ultralytics Docs reference section. Recursively walks through ultralytics dir and builds an MkDocs -reference section of *.md files composed of classes and functions, and also creates a nav menu for use in mkdocs.yaml. - -Note: Must be run from repository root directory. Do not run from docs directory. -""" - -import re -from collections import defaultdict -from pathlib import Path - -# Get package root i.e. /Users/glennjocher/PycharmProjects/ultralytics/ultralytics -from ultralytics.utils import ROOT as PACKAGE_DIR - -# Constants -REFERENCE_DIR = PACKAGE_DIR.parent / "docs/en/reference" -GITHUB_REPO = "ultralytics/ultralytics" - - -def extract_classes_and_functions(filepath: Path) -> tuple: - """Extracts class and function names from a given Python file.""" - content = filepath.read_text() - class_pattern = r"(?:^|\n)class\s(\w+)(?:\(|:)" - func_pattern = r"(?:^|\n)def\s(\w+)\(" - - classes = re.findall(class_pattern, content) - functions = re.findall(func_pattern, content) - - return classes, functions - - -def create_markdown(py_filepath: Path, module_path: str, classes: list, functions: list): - """Creates a Markdown file containing the API reference for the given Python module.""" - md_filepath = py_filepath.with_suffix(".md") - - # Read existing content and keep header content between first two --- - header_content = "" - if md_filepath.exists(): - existing_content = md_filepath.read_text() - header_parts = existing_content.split("---") - for part in header_parts: - if "description:" in part or "comments:" in part: - header_content += f"---{part}---\n\n" - - module_name = module_path.replace(".__init__", "") - module_path = module_path.replace(".", "/") - url = f"https://github.com/{GITHUB_REPO}/blob/main/{module_path}.py" - edit = f"https://github.com/{GITHUB_REPO}/edit/main/{module_path}.py" - title_content = ( - f"# Reference for `{module_path}.py`\n\n" - f"!!! Note\n\n" - f" This file is available at [{url}]({url}). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request]({edit}) 🛠️. Thank you 🙏!\n\n" - ) - md_content = ["

\n"] + [f"## ::: {module_name}.{class_name}\n\n

\n" for class_name in classes] - md_content.extend(f"## ::: {module_name}.{func_name}\n\n

\n" for func_name in functions) - md_content = header_content + title_content + "\n".join(md_content) - if not md_content.endswith("\n"): - md_content += "\n" - - md_filepath.parent.mkdir(parents=True, exist_ok=True) - md_filepath.write_text(md_content) - - return md_filepath.relative_to(PACKAGE_DIR.parent) - - -def nested_dict() -> defaultdict: - """Creates and returns a nested defaultdict.""" - return defaultdict(nested_dict) - - -def sort_nested_dict(d: dict) -> dict: - """Sorts a nested dictionary recursively.""" - return {key: sort_nested_dict(value) if isinstance(value, dict) else value for key, value in sorted(d.items())} - - -def create_nav_menu_yaml(nav_items: list, save: bool = False): - """Creates a YAML file for the navigation menu based on the provided list of items.""" - nav_tree = nested_dict() - - for item_str in nav_items: - item = Path(item_str) - parts = item.parts - current_level = nav_tree["reference"] - for part in parts[2:-1]: # skip the first two parts (docs and reference) and the last part (filename) - current_level = current_level[part] - - md_file_name = parts[-1].replace(".md", "") - current_level[md_file_name] = item - - nav_tree_sorted = sort_nested_dict(nav_tree) - - def _dict_to_yaml(d, level=0): - """Converts a nested dictionary to a YAML-formatted string with indentation.""" - yaml_str = "" - indent = " " * level - for k, v in d.items(): - if isinstance(v, dict): - yaml_str += f"{indent}- {k}:\n{_dict_to_yaml(v, level + 1)}" - else: - yaml_str += f"{indent}- {k}: {str(v).replace('docs/en/', '')}\n" - return yaml_str - - # Print updated YAML reference section - print("Scan complete, new mkdocs.yaml reference section is:\n\n", _dict_to_yaml(nav_tree_sorted)) - - # Save new YAML reference section - if save: - (PACKAGE_DIR.parent / "nav_menu_updated.yml").write_text(_dict_to_yaml(nav_tree_sorted)) - - -def main(): - """Main function to extract class and function names, create Markdown files, and generate a YAML navigation menu.""" - nav_items = [] - - for py_filepath in PACKAGE_DIR.rglob("*.py"): - classes, functions = extract_classes_and_functions(py_filepath) - - if classes or functions: - py_filepath_rel = py_filepath.relative_to(PACKAGE_DIR) - md_filepath = REFERENCE_DIR / py_filepath_rel - module_path = f"{PACKAGE_DIR.name}.{py_filepath_rel.with_suffix('').as_posix().replace('/', '.')}" - md_rel_filepath = create_markdown(md_filepath, module_path, classes, functions) - nav_items.append(str(md_rel_filepath)) - - create_nav_menu_yaml(nav_items) - - -if __name__ == "__main__": - main() diff --git a/ultralytics-main/docs/coming_soon_template.md b/ultralytics-main/docs/coming_soon_template.md deleted file mode 100644 index f8d7802..0000000 --- a/ultralytics-main/docs/coming_soon_template.md +++ /dev/null @@ -1,34 +0,0 @@ ---- -description: Discover what's next for Ultralytics with our under-construction page, previewing new, groundbreaking AI and ML features coming soon. -keywords: Ultralytics, coming soon, under construction, new features, AI updates, ML advancements, YOLO, technology preview ---- - -# Under Construction 🏗️🌟 - -Welcome to the Ultralytics "Under Construction" page! Here, we're hard at work developing the next generation of AI and ML innovations. This page serves as a teaser for the exciting updates and new features we're eager to share with you! - -## Exciting New Features on the Way 🎉 - -- **Innovative Breakthroughs:** Get ready for advanced features and services that will transform your AI and ML experience. -- **New Horizons:** Anticipate novel products that redefine AI and ML capabilities. -- **Enhanced Services:** We're upgrading our services for greater efficiency and user-friendliness. - -## Stay Updated 🚧 - -This placeholder page is your first stop for upcoming developments. Keep an eye out for: - -- **Newsletter:** Subscribe [here](https://ultralytics.com/#newsletter) for the latest news. -- **Social Media:** Follow us [here](https://www.linkedin.com/company/ultralytics) for updates and teasers. -- **Blog:** Visit our [blog](https://ultralytics.com/blog) for detailed insights. - -## We Value Your Input 🗣️ - -Your feedback shapes our future releases. Share your thoughts and suggestions [here](https://ultralytics.com/contact). - -## Thank You, Community! 🌍 - -Your [contributions](https://docs.ultralytics.com/help/contributing) inspire our continuous [innovation](https://github.com/ultralytics/ultralytics). Stay tuned for the big reveal of what's next in AI and ML at Ultralytics! - ---- - -Excited for what's coming? Bookmark this page and get ready for a transformative AI and ML journey with Ultralytics! 🛠️🤖 diff --git a/ultralytics-main/docs/en/CNAME b/ultralytics-main/docs/en/CNAME deleted file mode 100644 index 339382a..0000000 --- a/ultralytics-main/docs/en/CNAME +++ /dev/null @@ -1 +0,0 @@ -docs.ultralytics.com diff --git a/ultralytics-main/docs/en/guides/azureml-quickstart.md b/ultralytics-main/docs/en/guides/azureml-quickstart.md deleted file mode 100644 index 56b1cea..0000000 --- a/ultralytics-main/docs/en/guides/azureml-quickstart.md +++ /dev/null @@ -1,152 +0,0 @@ ---- -comments: true -description: Step-by-step Quickstart Guide to Running YOLOv8 Object Detection Models on AzureML for Fast Prototyping and Testing -keywords: Ultralytics, YOLOv8, Object Detection, Azure Machine Learning, Quickstart Guide, Prototype, Compute Instance, Terminal, Notebook, IPython Kernel, CLI, Python SDK ---- - -# YOLOv8 🚀 on AzureML - -## What is Azure? - -[Azure](https://azure.microsoft.com/) is Microsoft's cloud computing platform, designed to help organizations move their workloads to the cloud from on-premises data centers. With the full spectrum of cloud services including those for computing, databases, analytics, machine learning, and networking, users can pick and choose from these services to develop and scale new applications, or run existing applications, in the public cloud. - -## What is Azure Machine Learning (AzureML)? - -Azure Machine Learning, commonly referred to as AzureML, is a fully managed cloud service that enables data scientists and developers to efficiently embed predictive analytics into their applications, helping organizations use massive data sets and bring all the benefits of the cloud to machine learning. AzureML offers a variety of services and capabilities aimed at making machine learning accessible, easy to use, and scalable. It provides capabilities like automated machine learning, drag-and-drop model training, as well as a robust Python SDK so that developers can make the most out of their machine learning models. - -## How Does AzureML Benefit YOLO Users? - -For users of YOLO (You Only Look Once), AzureML provides a robust, scalable, and efficient platform to both train and deploy machine learning models. Whether you are looking to run quick prototypes or scale up to handle more extensive data, AzureML's flexible and user-friendly environment offers various tools and services to fit your needs. You can leverage AzureML to: - -- Easily manage large datasets and computational resources for training. -- Utilize built-in tools for data preprocessing, feature selection, and model training. -- Collaborate more efficiently with capabilities for MLOps (Machine Learning Operations), including but not limited to monitoring, auditing, and versioning of models and data. - -In the subsequent sections, you will find a quickstart guide detailing how to run YOLOv8 object detection models using AzureML, either from a compute terminal or a notebook. - -## Prerequisites - -Before you can get started, make sure you have access to an AzureML workspace. If you don't have one, you can create a new [AzureML workspace](https://learn.microsoft.com/azure/machine-learning/concept-workspace?view=azureml-api-2) by following Azure's official documentation. This workspace acts as a centralized place to manage all AzureML resources. - -## Create a compute instance - -From your AzureML workspace, select Compute > Compute instances > New, select the instance with the resources you need. - -

- Create Azure Compute Instance -

- -## Quickstart from Terminal - -Start your compute and open a Terminal: - -

- Open Terminal -

- -### Create virtualenv - -Create your conda virtualenv and install pip in it: - -```bash -conda create --name yolov8env -y -conda activate yolov8env -conda install pip -y -``` - -Install the required dependencies: - -```bash -cd ultralytics -pip install -r requirements.txt -pip install ultralytics -pip install onnx>=1.12.0 -``` - -### Perform YOLOv8 tasks - -Predict: - -```bash -yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' -``` - -Train a detection model for 10 epochs with an initial learning_rate of 0.01: - -```bash -yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 -``` - -You can find more [instructions to use the Ultralytics CLI here](../quickstart.md#use-ultralytics-with-cli). - -## Quickstart from a Notebook - -### Create a new IPython kernel - -Open the compute Terminal. - -

- Open Terminal -

- -From your compute terminal, you need to create a new ipykernel that will be used by your notebook to manage your dependencies: - -```bash -conda create --name yolov8env -y -conda activate yolov8env -conda install pip -y -conda install ipykernel -y -python -m ipykernel install --user --name yolov8env --display-name "yolov8env" -``` - -Close your terminal and create a new notebook. From your Notebook, you can select the new kernel. - -Then you can open a Notebook cell and install the required dependencies: - -```bash -%%bash -source activate yolov8env -cd ultralytics -pip install -r requirements.txt -pip install ultralytics -pip install onnx>=1.12.0 -``` - -Note that we need to use the `source activate yolov8env` for all the %%bash cells, to make sure that the %%bash cell uses environment we want. - -Run some predictions using the [Ultralytics CLI](../quickstart.md#use-ultralytics-with-cli): - -```bash -%%bash -source activate yolov8env -yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' -``` - -Or with the [Ultralytics Python interface](../quickstart.md#use-ultralytics-with-python), for example to train the model: - -```python -from ultralytics import YOLO - -# Load a model -model = YOLO("yolov8n.pt") # load an official YOLOv8n model - -# Use the model -model.train(data="coco128.yaml", epochs=3) # train the model -metrics = model.val() # evaluate model performance on the validation set -results = model("https://ultralytics.com/images/bus.jpg") # predict on an image -path = model.export(format="onnx") # export the model to ONNX format -``` - -You can use either the Ultralytics CLI or Python interface for running YOLOv8 tasks, as described in the terminal section above. - -By following these steps, you should be able to get YOLOv8 running quickly on AzureML for quick trials. For more advanced uses, you may refer to the full AzureML documentation linked at the beginning of this guide. - -## Explore More with AzureML - -This guide serves as an introduction to get you up and running with YOLOv8 on AzureML. However, it only scratches the surface of what AzureML can offer. To delve deeper and unlock the full potential of AzureML for your machine learning projects, consider exploring the following resources: - -- [Create a Data Asset](https://learn.microsoft.com/azure/machine-learning/how-to-create-data-assets): Learn how to set up and manage your data assets effectively within the AzureML environment. -- [Initiate an AzureML Job](https://learn.microsoft.com/azure/machine-learning/how-to-train-model): Get a comprehensive understanding of how to kickstart your machine learning training jobs on AzureML. -- [Register a Model](https://learn.microsoft.com/azure/machine-learning/how-to-manage-models): Familiarize yourself with model management practices including registration, versioning, and deployment. -- [Train YOLOv8 with AzureML Python SDK](https://medium.com/@ouphi/how-to-train-the-yolov8-model-with-azure-machine-learning-python-sdk-8268696be8ba): Explore a step-by-step guide on using the AzureML Python SDK to train your YOLOv8 models. -- [Train YOLOv8 with AzureML CLI](https://medium.com/@ouphi/how-to-train-the-yolov8-model-with-azureml-and-the-az-cli-73d3c870ba8e): Discover how to utilize the command-line interface for streamlined training and management of YOLOv8 models on AzureML. diff --git a/ultralytics-main/docs/en/guides/conda-quickstart.md b/ultralytics-main/docs/en/guides/conda-quickstart.md deleted file mode 100644 index 5163220..0000000 --- a/ultralytics-main/docs/en/guides/conda-quickstart.md +++ /dev/null @@ -1,132 +0,0 @@ ---- -comments: true -description: Comprehensive guide to setting up and using Ultralytics YOLO models in a Conda environment. Learn how to install the package, manage dependencies, and get started with object detection projects. -keywords: Ultralytics, YOLO, Conda, environment setup, object detection, package installation, deep learning, machine learning, guide ---- - -# Conda Quickstart Guide for Ultralytics - -

- Ultralytics Conda Package Visual -

- -This guide provides a comprehensive introduction to setting up a Conda environment for your Ultralytics projects. Conda is an open-source package and environment management system that offers an excellent alternative to pip for installing packages and dependencies. Its isolated environments make it particularly well-suited for data science and machine learning endeavors. For more details, visit the Ultralytics Conda package on [Anaconda](https://anaconda.org/conda-forge/ultralytics) and check out the Ultralytics feedstock repository for package updates on [GitHub](https://github.com/conda-forge/ultralytics-feedstock/). - -[![Conda Recipe](https://img.shields.io/badge/recipe-ultralytics-green.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Version](https://img.shields.io/conda/vn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Platforms](https://img.shields.io/conda/pn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) - -## What You Will Learn - -- Setting up a Conda environment -- Installing Ultralytics via Conda -- Initializing Ultralytics in your environment -- Using Ultralytics Docker images with Conda - ---- - -## Prerequisites - -- You should have Anaconda or Miniconda installed on your system. If not, download and install it from [Anaconda](https://www.anaconda.com/) or [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/). - ---- - -## Setting up a Conda Environment - -First, let's create a new Conda environment. Open your terminal and run the following command: - -```bash -conda create --name ultralytics-env python=3.8 -y -``` - -Activate the new environment: - -```bash -conda activate ultralytics-env -``` - ---- - -## Installing Ultralytics - -You can install the Ultralytics package from the conda-forge channel. Execute the following command: - -```bash -conda install -c conda-forge ultralytics -``` - -### Note on CUDA Environment - -If you're working in a CUDA-enabled environment, it's a good practice to install `ultralytics`, `pytorch`, and `pytorch-cuda` together to resolve any conflicts: - -```bash -conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics -``` - ---- - -## Using Ultralytics - -With Ultralytics installed, you can now start using its robust features for object detection, instance segmentation, and more. For example, to predict an image, you can run: - -```python -from ultralytics import YOLO - -model = YOLO('yolov8n.pt') # initialize model -results = model('path/to/image.jpg') # perform inference -results[0].show() # display results for the first image -``` - ---- - -## Ultralytics Conda Docker Image - -If you prefer using Docker, Ultralytics offers Docker images with a Conda environment included. You can pull these images from [DockerHub](https://hub.docker.com/r/ultralytics/ultralytics). - -Pull the latest Ultralytics image: - -```bash -# Set image name as a variable -t=ultralytics/ultralytics:latest-conda - -# Pull the latest Ultralytics image from Docker Hub -sudo docker pull $t -``` - -Run the image: - -```bash -# Run the Ultralytics image in a container with GPU support -sudo docker run -it --ipc=host --gpus all $t # all GPUs -sudo docker run -it --ipc=host --gpus '"device=2,3"' $t # specify GPUs -``` - ---- - -Certainly, you can include the following section in your Conda guide to inform users about speeding up installation using `libmamba`: - ---- - -## Speeding Up Installation with Libmamba - -If you're looking to [speed up the package installation](https://www.anaconda.com/blog/a-faster-conda-for-a-growing-community) process in Conda, you can opt to use `libmamba`, a fast, cross-platform, and dependency-aware package manager that serves as an alternative solver to Conda's default. - -### How to Enable Libmamba - -To enable `libmamba` as the solver for Conda, you can perform the following steps: - -1. First, install the `conda-libmamba-solver` package. This can be skipped if your Conda version is 4.11 or above, as `libmamba` is included by default. - - ```bash - conda install conda-libmamba-solver - ``` - -2. Next, configure Conda to use `libmamba` as the solver: - - ```bash - conda config --set solver libmamba - ``` - -And that's it! Your Conda installation will now use `libmamba` as the solver, which should result in a faster package installation process. - ---- - -Congratulations! You have successfully set up a Conda environment, installed the Ultralytics package, and are now ready to explore its rich functionalities. Feel free to dive deeper into the [Ultralytics documentation](../index.md) for more advanced tutorials and examples. diff --git a/ultralytics-main/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md b/ultralytics-main/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md deleted file mode 100644 index 90f9145..0000000 --- a/ultralytics-main/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md +++ /dev/null @@ -1,140 +0,0 @@ ---- -comments: true -description: Guide on how to use Ultralytics with a Coral Edge TPU on a Raspberry Pi for increased inference performance. -keywords: Ultralytics, YOLOv8, Object Detection, Coral, Edge TPU, Raspberry Pi, embedded, edge compute, sbc, accelerator, mobile ---- - -# Coral Edge TPU on a Raspberry Pi with Ultralytics YOLOv8 🚀 - -

- Raspberry Pi single board computer with USB Edge TPU accelerator -

- -## What is a Coral Edge TPU? - -The Coral Edge TPU is a compact device that adds an Edge TPU coprocessor to your system. It enables low-power, high-performance ML inference for TensorFlow Lite models. Read more at the [Coral Edge TPU home page](https://coral.ai/products/accelerator). - -## Boost Raspberry Pi Model Performance with Coral Edge TPU - -Many people want to run their models on an embedded or mobile device such as a Raspberry Pi, since they are very power efficient and can be used in many different applications. However, the inference performance on these devices is usually poor even when using formats like [onnx](../integrations/onnx.md) or [openvino](../integrations/openvino.md). The Coral Edge TPU is a great solution to this problem, since it can be used with a Raspberry Pi and accelerate inference performance greatly. - -## Edge TPU on Raspberry Pi with TensorFlow Lite (New)⭐ - -The [existing guide](https://coral.ai/docs/accelerator/get-started/) by Coral on how to use the Edge TPU with a Raspberry Pi is outdated, and the current Coral Edge TPU runtime builds do not work with the current TensorFlow Lite runtime versions anymore. In addition to that, Google seems to have completely abandoned the Coral project, and there have not been any updates between 2021 and 2024. This guide will show you how to get the Edge TPU working with the latest versions of the TensorFlow Lite runtime and an updated Coral Edge TPU runtime on a Raspberry Pi single board computer (SBC). - -## Prerequisites - -- [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/) (2GB or more recommended) or [Raspberry Pi 5](https://www.raspberrypi.com/products/raspberry-pi-5/) (Recommended) -- [Raspberry Pi OS](https://www.raspberrypi.com/software/) Bullseye/Bookworm (64-bit) with desktop (Recommended) -- [Coral USB Accelerator](https://coral.ai/products/accelerator/) -- A non-ARM based platform for exporting an Ultralytics PyTorch model - -## Installation Walkthrough - -This guide assumes that you already have a working Raspberry Pi OS install and have installed `ultralytics` and all dependencies. To get `ultralytics` installed, visit the [quickstart guide](../quickstart.md) to get setup before continuing here. - -### Installing the Edge TPU runtime - -First, we need to install the Edge TPU runtime. There are many different versions available, so you need to choose the right version for your operating system. - -| Raspberry Pi OS | High frequency mode | Version to download | -|-----------------|:-------------------:|--------------------------------------------| -| Bullseye 32bit | No | `libedgetpu1-std_ ... .bullseye_armhf.deb` | -| Bullseye 64bit | No | `libedgetpu1-std_ ... .bullseye_arm64.deb` | -| Bullseye 32bit | Yes | `libedgetpu1-max_ ... .bullseye_armhf.deb` | -| Bullseye 64bit | Yes | `libedgetpu1-max_ ... .bullseye_arm64.deb` | -| Bookworm 32bit | No | `libedgetpu1-std_ ... .bookworm_armhf.deb` | -| Bookworm 64bit | No | `libedgetpu1-std_ ... .bookworm_arm64.deb` | -| Bookworm 32bit | Yes | `libedgetpu1-max_ ... .bookworm_armhf.deb` | -| Bookworm 64bit | Yes | `libedgetpu1-max_ ... .bookworm_arm64.deb` | - -[Download the latest version from here](https://github.com/feranick/libedgetpu/releases). - -After downloading the file, you can install it with the following command: - -```bash -sudo dpkg -i path/to/package.deb -``` - -After installing the runtime, you need to plug in your Coral Edge TPU into a USB 3.0 port on your Raspberry Pi. This is because, according to the official guide, a new `udev` rule needs to take effect after installation. - -???+ warning "Important" - - If you already have the Coral Edge TPU runtime installed, uninstall it using the following command. - - ```bash - # If you installed the standard version - sudo apt remove libedgetpu1-std - - # If you installed the high frequency version - sudo apt remove libedgetpu1-max - ``` - -## Export your model to a Edge TPU compatible model - -To use the Edge TPU, you need to convert your model into a compatible format. It is recommended that you run export on Google Colab, x86_64 Linux machine, using the official [Ultralytics Docker container](docker-quickstart.md), or using [Ultralytics HUB](../hub/quickstart.md), since the Edge TPU compiler is not available on ARM. See the [Export Mode](../modes/export.md) for the available arguments. - -!!! Exporting the model - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('path/to/model.pt') # Load a official model or custom model - - # Export the model - model.export(format='edgetpu') - ``` - - === "CLI" - - ```bash - yolo export model=path/to/model.pt format=edgetpu # Export a official model or custom model - ``` - -The exported model will be saved in the `_saved_model/` folder with the name `_full_integer_quant_edgetpu.tflite`. - -## Running the model - -After exporting your model, you can run inference with it using the following code: - -!!! Running the model - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('path/to/edgetpu_model.tflite') # Load a official model or custom model - - # Run Prediction - model.predict("path/to/source.png") - ``` - - === "CLI" - - ```bash - yolo predict model=path/to/edgetpu_model.tflite source=path/to/source.png # Load a official model or custom model - ``` - -Find comprehensive information on the [Predict](../modes/predict.md) page for full prediction mode details. - -???+ warning "Important" - - You should run the model using `tflite-runtime` and not `tensorflow`. - If `tensorflow` is installed, uninstall tensorflow with the following command: - - ```bash - pip uninstall tensorflow tensorflow-aarch64 - ``` - - Then install/update `tflite-runtime`: - - ``` - pip install -U tflite-runtime - ``` - - If you want a `tflite-runtime` wheel for `tensorflow` 2.15.0 download it from [here](https://github.com/feranick/TFlite-builds/releases) and install it using `pip` or your package manager of choice. diff --git a/ultralytics-main/docs/en/guides/distance-calculation.md b/ultralytics-main/docs/en/guides/distance-calculation.md deleted file mode 100644 index c479d5f..0000000 --- a/ultralytics-main/docs/en/guides/distance-calculation.md +++ /dev/null @@ -1,107 +0,0 @@ ---- -comments: true -description: Distance Calculation Using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Distance Calculation, Object Tracking, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Distance Calculation using Ultralytics YOLOv8 🚀 - -## What is Distance Calculation? - -Measuring the gap between two objects is known as distance calculation within a specified space. In the case of [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics), the bounding box centroid is employed to calculate the distance for bounding boxes highlighted by the user. - -

-
- -
- Watch: Distance Calculation using Ultralytics YOLOv8 -

- -## Visuals - -| Distance Calculation using Ultralytics YOLOv8 | -|:-----------------------------------------------------------------------------------------------------------------------------------------------:| -| ![Ultralytics YOLOv8 Distance Calculation](https://github.com/RizwanMunawar/RizwanMunawar/assets/62513924/6b6b735d-3c49-4b84-a022-2bf6e3c72f8b) | - -## Advantages of Distance Calculation? - -- **Localization Precision:** Enhances accurate spatial positioning in computer vision tasks. -- **Size Estimation:** Allows estimation of physical sizes for better contextual understanding. -- **Scene Understanding:** Contributes to a 3D understanding of the environment for improved decision-making. - -???+ tip "Distance Calculation" - - - Click on any two bounding boxes with Left Mouse click for distance calculation - -!!! Example "Distance Calculation using YOLOv8 Example" - - === "Video Stream" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import distance_calculation - import cv2 - - model = YOLO("yolov8n.pt") - names = model.model.names - - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("distance_calculation.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init distance-calculation obj - dist_obj = distance_calculation.DistanceCalculation() - dist_obj.set_args(names=names, view_img=True) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - - tracks = model.track(im0, persist=True, show=False) - im0 = dist_obj.start_process(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - - ``` - -???+ tip "Note" - - - Mouse Right Click will delete all drawn points - - Mouse Left Click can be used to draw points - -### Optional Arguments `set_args` - -| Name | Type | Default | Description | -|------------------|--------|-----------------|--------------------------------------------------------| -| `names` | `dict` | `None` | Classes names | -| `view_img` | `bool` | `False` | Display frames with counts | -| `line_thickness` | `int` | `2` | Increase bounding boxes thickness | -| `line_color` | `RGB` | `(255, 255, 0)` | Line Color for centroids mapping on two bounding boxes | -| `centroid_color` | `RGB` | `(255, 0, 255)` | Centroid color for each bounding box | - -### Arguments `model.track` - -| Name | Type | Default | Description | -|-----------|---------|----------------|-------------------------------------------------------------| -| `source` | `im0` | `None` | source directory for images or videos | -| `persist` | `bool` | `False` | persisting tracks between frames | -| `tracker` | `str` | `botsort.yaml` | Tracking method 'bytetrack' or 'botsort' | -| `conf` | `float` | `0.3` | Confidence Threshold | -| `iou` | `float` | `0.5` | IOU Threshold | -| `classes` | `list` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `verbose` | `bool` | `True` | Display the object tracking results | diff --git a/ultralytics-main/docs/en/guides/docker-quickstart.md b/ultralytics-main/docs/en/guides/docker-quickstart.md deleted file mode 100644 index 6c45268..0000000 --- a/ultralytics-main/docs/en/guides/docker-quickstart.md +++ /dev/null @@ -1,119 +0,0 @@ ---- -comments: true -description: Complete guide to setting up and using Ultralytics YOLO models with Docker. Learn how to install Docker, manage GPU support, and run YOLO models in isolated containers. -keywords: Ultralytics, YOLO, Docker, GPU, containerization, object detection, package installation, deep learning, machine learning, guide ---- - -# Docker Quickstart Guide for Ultralytics - -

- Ultralytics Docker Package Visual -

- -This guide serves as a comprehensive introduction to setting up a Docker environment for your Ultralytics projects. [Docker](https://docker.com/) is a platform for developing, shipping, and running applications in containers. It is particularly beneficial for ensuring that the software will always run the same, regardless of where it's deployed. For more details, visit the Ultralytics Docker repository on [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics). - -[![Docker Pulls](https://img.shields.io/docker/pulls/ultralytics/ultralytics?logo=docker)](https://hub.docker.com/r/ultralytics/ultralytics) - -## What You Will Learn - -- Setting up Docker with NVIDIA support -- Installing Ultralytics Docker images -- Running Ultralytics in a Docker container -- Mounting local directories into the container - ---- - -## Prerequisites - -- Make sure Docker is installed on your system. If not, you can download and install it from [Docker's website](https://www.docker.com/products/docker-desktop). -- Ensure that your system has an NVIDIA GPU and NVIDIA drivers are installed. - ---- - -## Setting up Docker with NVIDIA Support - -First, verify that the NVIDIA drivers are properly installed by running: - -```bash -nvidia-smi -``` - -### Installing NVIDIA Docker Runtime - -Now, let's install the NVIDIA Docker runtime to enable GPU support in Docker containers: - -```bash -# Add NVIDIA package repositories -curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - -distribution=$(lsb_release -cs) -curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list - -# Install NVIDIA Docker runtime -sudo apt-get update -sudo apt-get install -y nvidia-docker2 - -# Restart Docker service to apply changes -sudo systemctl restart docker -``` - -### Verify NVIDIA Runtime with Docker - -Run `docker info | grep -i runtime` to ensure that `nvidia` appears in the list of runtimes: - -```bash -docker info | grep -i runtime -``` - ---- - -## Installing Ultralytics Docker Images - -Ultralytics offers several Docker images optimized for various platforms and use-cases: - -- **Dockerfile:** GPU image, ideal for training. -- **Dockerfile-arm64:** For ARM64 architecture, suitable for devices like [Raspberry Pi](raspberry-pi.md). -- **Dockerfile-cpu:** CPU-only version for inference and non-GPU environments. -- **Dockerfile-jetson:** Optimized for NVIDIA Jetson devices. -- **Dockerfile-python:** Minimal Python environment for lightweight applications. -- **Dockerfile-conda:** Includes [Miniconda3](https://docs.conda.io/projects/miniconda/en/latest/) and Ultralytics package installed via Conda. - -To pull the latest image: - -```bash -# Set image name as a variable -t=ultralytics/ultralytics:latest - -# Pull the latest Ultralytics image from Docker Hub -sudo docker pull $t -``` - ---- - -## Running Ultralytics in Docker Container - -Here's how to execute the Ultralytics Docker container: - -```bash -# Run with all GPUs -sudo docker run -it --ipc=host --gpus all $t - -# Run specifying which GPUs to use -sudo docker run -it --ipc=host --gpus '"device=2,3"' $t -``` - -The `-it` flag assigns a pseudo-TTY and keeps stdin open, allowing you to interact with the container. The `--ipc=host` flag enables sharing of host's IPC namespace, essential for sharing memory between processes. The `--gpus` flag allows the container to access the host's GPUs. - -### Note on File Accessibility - -To work with files on your local machine within the container, you can use Docker volumes: - -```bash -# Mount a local directory into the container -sudo docker run -it --ipc=host --gpus all -v /path/on/host:/path/in/container $t -``` - -Replace `/path/on/host` with the directory path on your local machine and `/path/in/container` with the desired path inside the Docker container. - ---- - -Congratulations! You're now set up to use Ultralytics with Docker and ready to take advantage of its powerful capabilities. For alternate installation methods, feel free to explore the [Ultralytics quickstart documentation](../quickstart.md). diff --git a/ultralytics-main/docs/en/guides/heatmaps.md b/ultralytics-main/docs/en/guides/heatmaps.md deleted file mode 100644 index 3b8b911..0000000 --- a/ultralytics-main/docs/en/guides/heatmaps.md +++ /dev/null @@ -1,301 +0,0 @@ ---- -comments: true -description: Advanced Data Visualization with Ultralytics YOLOv8 Heatmaps -keywords: Ultralytics, YOLOv8, Advanced Data Visualization, Heatmap Technology, Object Detection and Tracking, Jupyter Notebook, Python SDK, Command Line Interface ---- - -# Advanced Data Visualization: Heatmaps using Ultralytics YOLOv8 🚀 - -## Introduction to Heatmaps - -A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) transforms complex data into a vibrant, color-coded matrix. This visual tool employs a spectrum of colors to represent varying data values, where warmer hues indicate higher intensities and cooler tones signify lower values. Heatmaps excel in visualizing intricate data patterns, correlations, and anomalies, offering an accessible and engaging approach to data interpretation across diverse domains. - -

-
- -
- Watch: Heatmaps using Ultralytics YOLOv8 -

- -## Why Choose Heatmaps for Data Analysis? - -- **Intuitive Data Distribution Visualization:** Heatmaps simplify the comprehension of data concentration and distribution, converting complex datasets into easy-to-understand visual formats. -- **Efficient Pattern Detection:** By visualizing data in heatmap format, it becomes easier to spot trends, clusters, and outliers, facilitating quicker analysis and insights. -- **Enhanced Spatial Analysis and Decision-Making:** Heatmaps are instrumental in illustrating spatial relationships, aiding in decision-making processes in sectors such as business intelligence, environmental studies, and urban planning. - -## Real World Applications - -| Transportation | Retail | -|:-----------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------:| -| ![Ultralytics YOLOv8 Transportation Heatmap](https://github.com/RizwanMunawar/ultralytics/assets/62513924/288d7053-622b-4452-b4e4-1f41aeb764aa) | ![Ultralytics YOLOv8 Retail Heatmap](https://github.com/RizwanMunawar/ultralytics/assets/62513924/edef75ad-50a7-4c0a-be4a-a66cdfc12802) | -| Ultralytics YOLOv8 Transportation Heatmap | Ultralytics YOLOv8 Retail Heatmap | - -!!! tip "Heatmap Configuration" - - - `heatmap_alpha`: Ensure this value is within the range (0.0 - 1.0). - - `decay_factor`: Used for removing heatmap after an object is no longer in the frame, its value should also be in the range (0.0 - 1.0). - -!!! Example "Heatmaps using Ultralytics YOLOv8 Example" - - === "Heatmap" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import heatmap - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("heatmap_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init heatmap - heatmap_obj = heatmap.Heatmap() - heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA, - imw=w, - imh=h, - view_img=True, - shape="circle") - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = heatmap_obj.generate_heatmap(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - - ``` - - === "Line Counting" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import heatmap - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("heatmap_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - line_points = [(20, 400), (1080, 404)] # line for object counting - - # Init heatmap - heatmap_obj = heatmap.Heatmap() - heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA, - imw=w, - imh=h, - view_img=True, - shape="circle", - count_reg_pts=line_points) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = heatmap_obj.generate_heatmap(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - - === "Region Counting" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import heatmap - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("heatmap_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Define region points - region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)] - - # Init heatmap - heatmap_obj = heatmap.Heatmap() - heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA, - imw=w, - imh=h, - view_img=True, - shape="circle", - count_reg_pts=region_points) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = heatmap_obj.generate_heatmap(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - - === "Im0" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import heatmap - import cv2 - - model = YOLO("yolov8s.pt") # YOLOv8 custom/pretrained model - - im0 = cv2.imread("path/to/image.png") # path to image file - h, w = im0.shape[:2] # image height and width - - # Heatmap Init - heatmap_obj = heatmap.Heatmap() - heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA, - imw=w, - imh=h, - view_img=True, - shape="circle") - - results = model.track(im0, persist=True) - im0 = heatmap_obj.generate_heatmap(im0, tracks=results) - cv2.imwrite("ultralytics_output.png", im0) - ``` - - === "Specific Classes" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import heatmap - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("heatmap_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - classes_for_heatmap = [0, 2] # classes for heatmap - - # Init heatmap - heatmap_obj = heatmap.Heatmap() - heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA, - imw=w, - imh=h, - view_img=True, - shape="circle") - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False, - classes=classes_for_heatmap) - - im0 = heatmap_obj.generate_heatmap(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - -### Arguments `set_args` - -| Name | Type | Default | Description | -|-----------------------|----------------|-------------------|-----------------------------------------------------------| -| `view_img` | `bool` | `False` | Display the frame with heatmap | -| `colormap` | `cv2.COLORMAP` | `None` | cv2.COLORMAP for heatmap | -| `imw` | `int` | `None` | Width of Heatmap | -| `imh` | `int` | `None` | Height of Heatmap | -| `heatmap_alpha` | `float` | `0.5` | Heatmap alpha value | -| `count_reg_pts` | `list` | `None` | Object counting region points | -| `count_txt_thickness` | `int` | `2` | Count values text size | -| `count_txt_color` | `RGB Color` | `(0, 0, 0)` | Foreground color for Object counts text | -| `count_color` | `RGB Color` | `(255, 255, 255)` | Background color for Object counts text | -| `count_reg_color` | `RGB Color` | `(255, 0, 255)` | Counting region color | -| `region_thickness` | `int` | `5` | Counting region thickness value | -| `decay_factor` | `float` | `0.99` | Decay factor for heatmap area removal after specific time | -| `shape` | `str` | `circle` | Heatmap shape for display "rect" or "circle" supported | -| `line_dist_thresh` | `int` | `15` | Euclidean Distance threshold for line counter | - -### Arguments `model.track` - -| Name | Type | Default | Description | -|-----------|---------|----------------|-------------------------------------------------------------| -| `source` | `im0` | `None` | source directory for images or videos | -| `persist` | `bool` | `False` | persisting tracks between frames | -| `tracker` | `str` | `botsort.yaml` | Tracking method 'bytetrack' or 'botsort' | -| `conf` | `float` | `0.3` | Confidence Threshold | -| `iou` | `float` | `0.5` | IOU Threshold | -| `classes` | `list` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | - -### Heatmap COLORMAPs - -| Colormap Name | Description | -|---------------------------------|----------------------------------------| -| `cv::COLORMAP_AUTUMN` | Autumn color map | -| `cv::COLORMAP_BONE` | Bone color map | -| `cv::COLORMAP_JET` | Jet color map | -| `cv::COLORMAP_WINTER` | Winter color map | -| `cv::COLORMAP_RAINBOW` | Rainbow color map | -| `cv::COLORMAP_OCEAN` | Ocean color map | -| `cv::COLORMAP_SUMMER` | Summer color map | -| `cv::COLORMAP_SPRING` | Spring color map | -| `cv::COLORMAP_COOL` | Cool color map | -| `cv::COLORMAP_HSV` | HSV (Hue, Saturation, Value) color map | -| `cv::COLORMAP_PINK` | Pink color map | -| `cv::COLORMAP_HOT` | Hot color map | -| `cv::COLORMAP_PARULA` | Parula color map | -| `cv::COLORMAP_MAGMA` | Magma color map | -| `cv::COLORMAP_INFERNO` | Inferno color map | -| `cv::COLORMAP_PLASMA` | Plasma color map | -| `cv::COLORMAP_VIRIDIS` | Viridis color map | -| `cv::COLORMAP_CIVIDIS` | Cividis color map | -| `cv::COLORMAP_TWILIGHT` | Twilight color map | -| `cv::COLORMAP_TWILIGHT_SHIFTED` | Shifted Twilight color map | -| `cv::COLORMAP_TURBO` | Turbo color map | -| `cv::COLORMAP_DEEPGREEN` | Deep Green color map | - -These colormaps are commonly used for visualizing data with different color representations. diff --git a/ultralytics-main/docs/en/guides/hyperparameter-tuning.md b/ultralytics-main/docs/en/guides/hyperparameter-tuning.md deleted file mode 100644 index 4888c34..0000000 --- a/ultralytics-main/docs/en/guides/hyperparameter-tuning.md +++ /dev/null @@ -1,206 +0,0 @@ ---- -comments: true -description: Dive into hyperparameter tuning in Ultralytics YOLO models. Learn how to optimize performance using the Tuner class and genetic evolution. -keywords: Ultralytics, YOLO, Hyperparameter Tuning, Tuner Class, Genetic Evolution, Optimization ---- - -# Ultralytics YOLO Hyperparameter Tuning Guide - -## Introduction - -Hyperparameter tuning is not just a one-time set-up but an iterative process aimed at optimizing the machine learning model's performance metrics, such as accuracy, precision, and recall. In the context of Ultralytics YOLO, these hyperparameters could range from learning rate to architectural details, such as the number of layers or types of activation functions used. - -### What are Hyperparameters? - -Hyperparameters are high-level, structural settings for the algorithm. They are set prior to the training phase and remain constant during it. Here are some commonly tuned hyperparameters in Ultralytics YOLO: - -- **Learning Rate** `lr0`: Determines the step size at each iteration while moving towards a minimum in the loss function. -- **Batch Size** `batch`: Number of images processed simultaneously in a forward pass. -- **Number of Epochs** `epochs`: An epoch is one complete forward and backward pass of all the training examples. -- **Architecture Specifics**: Such as channel counts, number of layers, types of activation functions, etc. - -

- Hyperparameter Tuning Visual -

- -For a full list of augmentation hyperparameters used in YOLOv8 please refer to the [configurations page](../usage/cfg.md#augmentation-settings). - -### Genetic Evolution and Mutation - -Ultralytics YOLO uses genetic algorithms to optimize hyperparameters. Genetic algorithms are inspired by the mechanism of natural selection and genetics. - -- **Mutation**: In the context of Ultralytics YOLO, mutation helps in locally searching the hyperparameter space by applying small, random changes to existing hyperparameters, producing new candidates for evaluation. -- **Crossover**: Although crossover is a popular genetic algorithm technique, it is not currently used in Ultralytics YOLO for hyperparameter tuning. The focus is mainly on mutation for generating new hyperparameter sets. - -## Preparing for Hyperparameter Tuning - -Before you begin the tuning process, it's important to: - -1. **Identify the Metrics**: Determine the metrics you will use to evaluate the model's performance. This could be AP50, F1-score, or others. -2. **Set the Tuning Budget**: Define how much computational resources you're willing to allocate. Hyperparameter tuning can be computationally intensive. - -## Steps Involved - -### Initialize Hyperparameters - -Start with a reasonable set of initial hyperparameters. This could either be the default hyperparameters set by Ultralytics YOLO or something based on your domain knowledge or previous experiments. - -### Mutate Hyperparameters - -Use the `_mutate` method to produce a new set of hyperparameters based on the existing set. - -### Train Model - -Training is performed using the mutated set of hyperparameters. The training performance is then assessed. - -### Evaluate Model - -Use metrics like AP50, F1-score, or custom metrics to evaluate the model's performance. - -### Log Results - -It's crucial to log both the performance metrics and the corresponding hyperparameters for future reference. - -### Repeat - -The process is repeated until either the set number of iterations is reached or the performance metric is satisfactory. - -## Usage Example - -Here's how to use the `model.tune()` method to utilize the `Tuner` class for hyperparameter tuning of YOLOv8n on COCO8 for 30 epochs with an AdamW optimizer and skipping plotting, checkpointing and validation other than on final epoch for faster Tuning. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Initialize the YOLO model - model = YOLO('yolov8n.pt') - - # Tune hyperparameters on COCO8 for 30 epochs - model.tune(data='coco8.yaml', epochs=30, iterations=300, optimizer='AdamW', plots=False, save=False, val=False) - ``` - -## Results - -After you've successfully completed the hyperparameter tuning process, you will obtain several files and directories that encapsulate the results of the tuning. The following describes each: - -### File Structure - -Here's what the directory structure of the results will look like. Training directories like `train1/` contain individual tuning iterations, i.e. one model trained with one set of hyperparameters. The `tune/` directory contains tuning results from all the individual model trainings: - -```plaintext -runs/ -└── detect/ - ├── train1/ - ├── train2/ - ├── ... - └── tune/ - ├── best_hyperparameters.yaml - ├── best_fitness.png - ├── tune_results.csv - ├── tune_scatter_plots.png - └── weights/ - ├── last.pt - └── best.pt -``` - -### File Descriptions - -#### best_hyperparameters.yaml - -This YAML file contains the best-performing hyperparameters found during the tuning process. You can use this file to initialize future trainings with these optimized settings. - -- **Format**: YAML -- **Usage**: Hyperparameter results -- **Example**: - ```yaml - # 558/900 iterations complete ✅ (45536.81s) - # Results saved to /usr/src/ultralytics/runs/detect/tune - # Best fitness=0.64297 observed at iteration 498 - # Best fitness metrics are {'metrics/precision(B)': 0.87247, 'metrics/recall(B)': 0.71387, 'metrics/mAP50(B)': 0.79106, 'metrics/mAP50-95(B)': 0.62651, 'val/box_loss': 2.79884, 'val/cls_loss': 2.72386, 'val/dfl_loss': 0.68503, 'fitness': 0.64297} - # Best fitness model is /usr/src/ultralytics/runs/detect/train498 - # Best fitness hyperparameters are printed below. - - lr0: 0.00269 - lrf: 0.00288 - momentum: 0.73375 - weight_decay: 0.00015 - warmup_epochs: 1.22935 - warmup_momentum: 0.1525 - box: 18.27875 - cls: 1.32899 - dfl: 0.56016 - hsv_h: 0.01148 - hsv_s: 0.53554 - hsv_v: 0.13636 - degrees: 0.0 - translate: 0.12431 - scale: 0.07643 - shear: 0.0 - perspective: 0.0 - flipud: 0.0 - fliplr: 0.08631 - mosaic: 0.42551 - mixup: 0.0 - copy_paste: 0.0 - ``` - -#### best_fitness.png - -This is a plot displaying fitness (typically a performance metric like AP50) against the number of iterations. It helps you visualize how well the genetic algorithm performed over time. - -- **Format**: PNG -- **Usage**: Performance visualization - -

- Hyperparameter Tuning Fitness vs Iteration -

- -#### tune_results.csv - -A CSV file containing detailed results of each iteration during the tuning. Each row in the file represents one iteration, and it includes metrics like fitness score, precision, recall, as well as the hyperparameters used. - -- **Format**: CSV -- **Usage**: Per-iteration results tracking. -- **Example**: - ```csv - fitness,lr0,lrf,momentum,weight_decay,warmup_epochs,warmup_momentum,box,cls,dfl,hsv_h,hsv_s,hsv_v,degrees,translate,scale,shear,perspective,flipud,fliplr,mosaic,mixup,copy_paste - 0.05021,0.01,0.01,0.937,0.0005,3.0,0.8,7.5,0.5,1.5,0.015,0.7,0.4,0.0,0.1,0.5,0.0,0.0,0.0,0.5,1.0,0.0,0.0 - 0.07217,0.01003,0.00967,0.93897,0.00049,2.79757,0.81075,7.5,0.50746,1.44826,0.01503,0.72948,0.40658,0.0,0.0987,0.4922,0.0,0.0,0.0,0.49729,1.0,0.0,0.0 - 0.06584,0.01003,0.00855,0.91009,0.00073,3.42176,0.95,8.64301,0.54594,1.72261,0.01503,0.59179,0.40658,0.0,0.0987,0.46955,0.0,0.0,0.0,0.49729,0.80187,0.0,0.0 - ``` - -#### tune_scatter_plots.png - -This file contains scatter plots generated from `tune_results.csv`, helping you visualize relationships between different hyperparameters and performance metrics. Note that hyperparameters initialized to 0 will not be tuned, such as `degrees` and `shear` below. - -- **Format**: PNG -- **Usage**: Exploratory data analysis - -

- Hyperparameter Tuning Scatter Plots -

- -#### weights/ - -This directory contains the saved PyTorch models for the last and the best iterations during the hyperparameter tuning process. - -- **`last.pt`**: The last.pt are the weights from the last epoch of training. -- **`best.pt`**: The best.pt weights for the iteration that achieved the best fitness score. - -Using these results, you can make more informed decisions for your future model trainings and analyses. Feel free to consult these artifacts to understand how well your model performed and how you might improve it further. - -## Conclusion - -The hyperparameter tuning process in Ultralytics YOLO is simplified yet powerful, thanks to its genetic algorithm-based approach focused on mutation. Following the steps outlined in this guide will assist you in systematically tuning your model to achieve better performance. - -### Further Reading - -1. [Hyperparameter Optimization in Wikipedia](https://en.wikipedia.org/wiki/Hyperparameter_optimization) -2. [YOLOv5 Hyperparameter Evolution Guide](../yolov5/tutorials/hyperparameter_evolution.md) -3. [Efficient Hyperparameter Tuning with Ray Tune and YOLOv8](../integrations/ray-tune.md) - -For deeper insights, you can explore the `Tuner` class source code and accompanying documentation. Should you have any questions, feature requests, or need further assistance, feel free to reach out to us on [GitHub](https://github.com/ultralytics/ultralytics/issues/new/choose) or [Discord](https://ultralytics.com/discord). diff --git a/ultralytics-main/docs/en/guides/index.md b/ultralytics-main/docs/en/guides/index.md deleted file mode 100644 index 62c2ccb..0000000 --- a/ultralytics-main/docs/en/guides/index.md +++ /dev/null @@ -1,65 +0,0 @@ ---- -comments: true -description: In-depth exploration of Ultralytics' YOLO. Learn about the YOLO object detection model, how to train it on custom data, multi-GPU training, exporting, predicting, deploying, and more. -keywords: Ultralytics, YOLO, Deep Learning, Object detection, PyTorch, Tutorial, Multi-GPU training, Custom data training, SAHI, Tiled Inference ---- - -# Comprehensive Tutorials to Ultralytics YOLO - -Welcome to the Ultralytics' YOLO 🚀 Guides! Our comprehensive tutorials cover various aspects of the YOLO object detection model, ranging from training and prediction to deployment. Built on PyTorch, YOLO stands out for its exceptional speed and accuracy in real-time object detection tasks. - -Whether you're a beginner or an expert in deep learning, our tutorials offer valuable insights into the implementation and optimization of YOLO for your computer vision projects. Let's dive in! - -

-
- -
- Watch: Ultralytics YOLOv8 Guides Overview -

- -## Guides - -Here's a compilation of in-depth guides to help you master different aspects of Ultralytics YOLO. - -- [YOLO Common Issues](yolo-common-issues.md) ⭐ RECOMMENDED: Practical solutions and troubleshooting tips to the most frequently encountered issues when working with Ultralytics YOLO models. -- [YOLO Performance Metrics](yolo-performance-metrics.md) ⭐ ESSENTIAL: Understand the key metrics like mAP, IoU, and F1 score used to evaluate the performance of your YOLO models. Includes practical examples and tips on how to improve detection accuracy and speed. -- [Model Deployment Options](model-deployment-options.md): Overview of YOLO model deployment formats like ONNX, OpenVINO, and TensorRT, with pros and cons for each to inform your deployment strategy. -- [K-Fold Cross Validation](kfold-cross-validation.md) 🚀 NEW: Learn how to improve model generalization using K-Fold cross-validation technique. -- [Hyperparameter Tuning](hyperparameter-tuning.md) 🚀 NEW: Discover how to optimize your YOLO models by fine-tuning hyperparameters using the Tuner class and genetic evolution algorithms. -- [SAHI Tiled Inference](sahi-tiled-inference.md) 🚀 NEW: Comprehensive guide on leveraging SAHI's sliced inference capabilities with YOLOv8 for object detection in high-resolution images. -- [AzureML Quickstart](azureml-quickstart.md) 🚀 NEW: Get up and running with Ultralytics YOLO models on Microsoft's Azure Machine Learning platform. Learn how to train, deploy, and scale your object detection projects in the cloud. -- [Conda Quickstart](conda-quickstart.md) 🚀 NEW: Step-by-step guide to setting up a [Conda](https://anaconda.org/conda-forge/ultralytics) environment for Ultralytics. Learn how to install and start using the Ultralytics package efficiently with Conda. -- [Docker Quickstart](docker-quickstart.md) 🚀 NEW: Complete guide to setting up and using Ultralytics YOLO models with [Docker](https://hub.docker.com/r/ultralytics/ultralytics). Learn how to install Docker, manage GPU support, and run YOLO models in isolated containers for consistent development and deployment. -- [Raspberry Pi](raspberry-pi.md) 🚀 NEW: Quickstart tutorial to run YOLO models to the latest Raspberry Pi hardware. -- [Triton Inference Server Integration](triton-inference-server.md) 🚀 NEW: Dive into the integration of Ultralytics YOLOv8 with NVIDIA's Triton Inference Server for scalable and efficient deep learning inference deployments. -- [YOLO Thread-Safe Inference](yolo-thread-safe-inference.md) 🚀 NEW: Guidelines for performing inference with YOLO models in a thread-safe manner. Learn the importance of thread safety and best practices to prevent race conditions and ensure consistent predictions. -- [Isolating Segmentation Objects](isolating-segmentation-objects.md) 🚀 NEW: Step-by-step recipe and explanation on how to extract and/or isolate objects from images using Ultralytics Segmentation. -- [Edge TPU on Raspberry Pi](coral-edge-tpu-on-raspberry-pi.md): [Google Edge TPU](https://coral.ai/products/accelerator) accelerates YOLO inference on [Raspberry Pi](https://www.raspberrypi.com/). -- [View Inference Images in a Terminal](view-results-in-terminal.md): Use VSCode's integrated terminal to view inference results when using Remote Tunnel or SSH sessions. -- [OpenVINO Latency vs Throughput Modes](optimizing-openvino-latency-vs-throughput-modes.md) - Learn latency and throughput optimization techniques for peak YOLO inference performance. - -## Real-World Projects - -- [Object Counting](object-counting.md) 🚀 NEW: Explore the process of real-time object counting with Ultralytics YOLOv8 and acquire the knowledge to effectively count objects in a live video stream. -- [Object Cropping](object-cropping.md) 🚀 NEW: Explore object cropping using YOLOv8 for precise extraction of objects from images and videos. -- [Object Blurring](object-blurring.md) 🚀 NEW: Apply object blurring with YOLOv8 for privacy protection in image and video processing. -- [Workouts Monitoring](workouts-monitoring.md) 🚀 NEW: Discover the comprehensive approach to monitoring workouts with Ultralytics YOLOv8. Acquire the skills and insights necessary to effectively use YOLOv8 for tracking and analyzing various aspects of fitness routines in real time. -- [Objects Counting in Regions](region-counting.md) 🚀 NEW: Explore counting objects in specific regions with Ultralytics YOLOv8 for precise and efficient object detection in varied areas. -- [Security Alarm System](security-alarm-system.md) 🚀 NEW: Discover the process of creating a security alarm system with Ultralytics YOLOv8. This system triggers alerts upon detecting new objects in the frame. Subsequently, you can customize the code to align with your specific use case. -- [Heatmaps](heatmaps.md) 🚀 NEW: Elevate your understanding of data with our Detection Heatmaps! These intuitive visual tools use vibrant color gradients to vividly illustrate the intensity of data values across a matrix. Essential in computer vision, heatmaps are skillfully designed to highlight areas of interest, providing an immediate, impactful way to interpret spatial information. -- [Instance Segmentation with Object Tracking](instance-segmentation-and-tracking.md) 🚀 NEW: Explore our feature on [Object Segmentation](https://docs.ultralytics.com/tasks/segment/) in Bounding Boxes Shape, providing a visual representation of precise object boundaries for enhanced understanding and analysis. -- [VisionEye View Objects Mapping](vision-eye.md) 🚀 NEW: This feature aim computers to discern and focus on specific objects, much like the way the human eye observes details from a particular viewpoint. -- [Speed Estimation](speed-estimation.md) 🚀 NEW: Speed estimation in computer vision relies on analyzing object motion through techniques like [object tracking](https://docs.ultralytics.com/modes/track/), crucial for applications like autonomous vehicles and traffic monitoring. -- [Distance Calculation](distance-calculation.md) 🚀 NEW: Distance calculation, which involves measuring the separation between two objects within a defined space, is a crucial aspect. In the context of Ultralytics YOLOv8, the method employed for this involves using the bounding box centroid to determine the distance associated with user-highlighted bounding boxes. - -## Contribute to Our Guides - -We welcome contributions from the community! If you've mastered a particular aspect of Ultralytics YOLO that's not yet covered in our guides, we encourage you to share your expertise. Writing a guide is a great way to give back to the community and help us make our documentation more comprehensive and user-friendly. - -To get started, please read our [Contributing Guide](../help/contributing.md) for guidelines on how to open up a Pull Request (PR) 🛠️. We look forward to your contributions! - -Let's work together to make the Ultralytics YOLO ecosystem more robust and versatile 🙏! diff --git a/ultralytics-main/docs/en/guides/instance-segmentation-and-tracking.md b/ultralytics-main/docs/en/guides/instance-segmentation-and-tracking.md deleted file mode 100644 index 558ab57..0000000 --- a/ultralytics-main/docs/en/guides/instance-segmentation-and-tracking.md +++ /dev/null @@ -1,140 +0,0 @@ ---- -comments: true -description: Instance Segmentation with Object Tracking using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Instance Segmentation, Object Detection, Object Tracking, Bounding Box, Computer Vision, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Instance Segmentation and Tracking using Ultralytics YOLOv8 🚀 - -## What is Instance Segmentation? - -[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) instance segmentation involves identifying and outlining individual objects in an image, providing a detailed understanding of spatial distribution. Unlike semantic segmentation, it uniquely labels and precisely delineates each object, crucial for tasks like object detection and medical imaging. - -There are two types of instance segmentation tracking available in the Ultralytics package: - -- **Instance Segmentation with Class Objects:** Each class object is assigned a unique color for clear visual separation. - -- **Instance Segmentation with Object Tracks:** Every track is represented by a distinct color, facilitating easy identification and tracking. - -

-
- -
- Watch: Instance Segmentation with Object Tracking using Ultralytics YOLOv8 -

- -## Samples - -| Instance Segmentation | Instance Segmentation + Object Tracking | -|:---------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![Ultralytics Instance Segmentation](https://github.com/RizwanMunawar/ultralytics/assets/62513924/d4ad3499-1f33-4871-8fbc-1be0b2643aa2) | ![Ultralytics Instance Segmentation with Object Tracking](https://github.com/RizwanMunawar/ultralytics/assets/62513924/2e5c38cc-fd5c-4145-9682-fa94ae2010a0) | -| Ultralytics Instance Segmentation 😍 | Ultralytics Instance Segmentation with Object Tracking 🔥 | - -!!! Example "Instance Segmentation and Tracking" - - === "Instance Segmentation" - - ```python - import cv2 - from ultralytics import YOLO - from ultralytics.utils.plotting import Annotator, colors - - model = YOLO("yolov8n-seg.pt") # segmentation model - names = model.model.names - cap = cv2.VideoCapture("path/to/video/file.mp4") - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter('instance-segmentation.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - results = model.predict(im0) - annotator = Annotator(im0, line_width=2) - - if results[0].masks is not None: - clss = results[0].boxes.cls.cpu().tolist() - masks = results[0].masks.xy - for mask, cls in zip(masks, clss): - annotator.seg_bbox(mask=mask, - mask_color=colors(int(cls), True), - det_label=names[int(cls)]) - - out.write(im0) - cv2.imshow("instance-segmentation", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - out.release() - cap.release() - cv2.destroyAllWindows() - - ``` - - === "Instance Segmentation with Object Tracking" - - ```python - import cv2 - from ultralytics import YOLO - from ultralytics.utils.plotting import Annotator, colors - - from collections import defaultdict - - track_history = defaultdict(lambda: []) - - model = YOLO("yolov8n-seg.pt") # segmentation model - cap = cv2.VideoCapture("path/to/video/file.mp4") - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter('instance-segmentation-object-tracking.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - annotator = Annotator(im0, line_width=2) - - results = model.track(im0, persist=True) - - if results[0].boxes.id is not None and results[0].masks is not None: - masks = results[0].masks.xy - track_ids = results[0].boxes.id.int().cpu().tolist() - - for mask, track_id in zip(masks, track_ids): - annotator.seg_bbox(mask=mask, - mask_color=colors(track_id, True), - track_label=str(track_id)) - - out.write(im0) - cv2.imshow("instance-segmentation-object-tracking", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - out.release() - cap.release() - cv2.destroyAllWindows() - ``` - -### `seg_bbox` Arguments - -| Name | Type | Default | Description | -|---------------|---------|-----------------|----------------------------------------| -| `mask` | `array` | `None` | Segmentation mask coordinates | -| `mask_color` | `tuple` | `(255, 0, 255)` | Mask color for every segmented box | -| `det_label` | `str` | `None` | Label for segmented object | -| `track_label` | `str` | `None` | Label for segmented and tracked object | - -## Note - -For any inquiries, feel free to post your questions in the [Ultralytics Issue Section](https://github.com/ultralytics/ultralytics/issues/new/choose) or the discussion section mentioned below. diff --git a/ultralytics-main/docs/en/guides/isolating-segmentation-objects.md b/ultralytics-main/docs/en/guides/isolating-segmentation-objects.md deleted file mode 100644 index f8e9a7a..0000000 --- a/ultralytics-main/docs/en/guides/isolating-segmentation-objects.md +++ /dev/null @@ -1,325 +0,0 @@ ---- -comments: true -description: A concise guide on isolating segmented objects using Ultralytics. -keywords: Ultralytics, YOLO, segmentation, Python, object detection, inference, dataset, prediction, instance segmentation, contours, binary mask, object mask, image processing ---- - -# Isolating Segmentation Objects - -After performing the [Segment Task](../tasks/segment.md), it's sometimes desirable to extract the isolated objects from the inference results. This guide provides a generic recipe on how to accomplish this using the Ultralytics [Predict Mode](../modes/predict.md). - -

- Example Isolated Object Segmentation -

- -## Recipe Walk Through - -1. Begin with the necessary imports - - ```python - from pathlib import Path - - import cv2 - import numpy as np - from ultralytics import YOLO - ``` - - ???+ tip "Ultralytics Install" - - See the Ultralytics [Quickstart](../quickstart.md/#install-ultralytics) Installation section for a quick walkthrough on installing the required libraries. - - *** - -2. Load a model and run `predict()` method on a source. - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-seg.pt') - - # Run inference - results = model.predict() - ``` - - !!! question "No Prediction Arguments?" - - Without specifying a source, the example images from the library will be used: - - ``` - 'ultralytics/assets/bus.jpg' - 'ultralytics/assets/zidane.jpg' - ``` - - This is helpful for rapid testing with the `predict()` method. - - For additional information about Segmentation Models, visit the [Segment Task](../tasks/segment.md#models) page. To learn more about `predict()` method, see [Predict Mode](../modes/predict.md) section of the Documentation. - - *** - -3. Now iterate over the results and the contours. For workflows that want to save an image to file, the source image `base-name` and the detection `class-label` are retrieved for later use (optional). - - ```{ .py .annotate } - # (2) Iterate detection results (helpful for multiple images) - for r in res: - img = np.copy(r.orig_img) - img_name = Path(r.path).stem # source image base-name - - # Iterate each object contour (multiple detections) - for ci,c in enumerate(r): - # (1) Get detection class name - label = c.names[c.boxes.cls.tolist().pop()] - - ``` - - 1. To learn more about working with detection results, see [Boxes Section for Predict Mode](../modes/predict.md#boxes). - 2. To learn more about `predict()` results see [Working with Results for Predict Mode](../modes/predict.md#working-with-results) - - ??? info "For-Loop" - - A single image will only iterate the first loop once. A single image with only a single detection will iterate each loop _only_ once. - - *** - -4. Start with generating a binary mask from the source image and then draw a filled contour onto the mask. This will allow the object to be isolated from the other parts of the image. An example from `bus.jpg` for one of the detected `person` class objects is shown on the right. - - ![Binary Mask Image](https://github.com/ultralytics/ultralytics/assets/62214284/59bce684-fdda-4b17-8104-0b4b51149aca){ width="240", align="right" } - - ```{ .py .annotate } - # Create binary mask - b_mask = np.zeros(img.shape[:2], np.uint8) - - # (1) Extract contour result - contour = c.masks.xy.pop() - # (2) Changing the type - contour = contour.astype(np.int32) - # (3) Reshaping - contour = contour.reshape(-1, 1, 2) - - - # Draw contour onto mask - _ = cv2.drawContours(b_mask, - [contour], - -1, - (255, 255, 255), - cv2.FILLED) - - ``` - - 1. For more info on `c.masks.xy` see [Masks Section from Predict Mode](../modes/predict.md#masks). - - 2. Here, the values are cast into `np.int32` for compatibility with `drawContours()` function from OpenCV. - - 3. The OpenCV `drawContours()` function expects contours to have a shape of `[N, 1, 2]` expand section below for more details. - -
- Expand to understand what is happening when defining the contour variable. -

- - - `c.masks.xy` :: Provides the coordinates of the mask contour points in the format `(x, y)`. For more details, refer to the [Masks Section from Predict Mode](../modes/predict.md#masks). - - - `.pop()` :: As `masks.xy` is a list containing a single element, this element is extracted using the `pop()` method. - - - `.astype(np.int32)` :: Using `masks.xy` will return with a data type of `float32`, but this won't be compatible with the OpenCV `drawContours()` function, so this will change the data type to `int32` for compatibility. - - - `.reshape(-1, 1, 2)` :: Reformats the data into the required shape of `[N, 1, 2]` where `N` is the number of contour points, with each point represented by a single entry `1`, and the entry is composed of `2` values. The `-1` denotes that the number of values along this dimension is flexible. - -

-

-
- Expand for an explanation of the drawContours() configuration. -

- - - Encapsulating the `contour` variable within square brackets, `[contour]`, was found to effectively generate the desired contour mask during testing. - - - The value `-1` specified for the `drawContours()` parameter instructs the function to draw all contours present in the image. - - - The `tuple` `(255, 255, 255)` represents the color white, which is the desired color for drawing the contour in this binary mask. - - - The addition of `cv2.FILLED` will color all pixels enclosed by the contour boundary the same, in this case, all enclosed pixels will be white. - - - See [OpenCV Documentation on `drawContours()`](https://docs.opencv.org/4.8.0/d6/d6e/group__imgproc__draw.html#ga746c0625f1781f1ffc9056259103edbc) for more information. - -

-

- - *** - -5. Next the there are 2 options for how to move forward with the image from this point and a subsequent option for each. - - ### Object Isolation Options - - !!! example "" - - === "Black Background Pixels" - - ```py - # Create 3-channel mask - mask3ch = cv2.cvtColor(b_mask, cv2.COLOR_GRAY2BGR) - - # Isolate object with binary mask - isolated = cv2.bitwise_and(mask3ch, img) - - ``` - - ??? question "How does this work?" - - - First, the binary mask is first converted from a single-channel image to a three-channel image. This conversion is necessary for the subsequent step where the mask and the original image are combined. Both images must have the same number of channels to be compatible with the blending operation. - - - The original image and the three-channel binary mask are merged using the OpenCV function `bitwise_and()`. This operation retains only pixel values that are greater than zero `(> 0)` from both images. Since the mask pixels are greater than zero `(> 0)` only within the contour region, the pixels remaining from the original image are those that overlap with the contour. - - ### Isolate with Black Pixels: Sub-options - - ??? info "Full-size Image" - - There are no additional steps required if keeping full size image. - -
- ![Example Full size Isolated Object Image Black Background](https://github.com/ultralytics/ultralytics/assets/62214284/845c00d0-52a6-4b1e-8010-4ba73e011b99){ width=240 } -
Example full-size output
-
- - ??? info "Cropped object Image" - - Additional steps required to crop image to only include object region. - - ![Example Crop Isolated Object Image Black Background](https://github.com/ultralytics/ultralytics/assets/62214284/103dbf90-c169-4f77-b791-76cdf09c6f22){ align="right" } - ``` { .py .annotate } - # (1) Bounding box coordinates - x1, y1, x2, y2 = c.boxes.xyxy.cpu().numpy().squeeze().astype(np.int32) - # Crop image to object region - iso_crop = isolated[y1:y2, x1:x2] - - ``` - - 1. For more information on bounding box results, see [Boxes Section from Predict Mode](../modes/predict.md/#boxes) - - ??? question "What does this code do?" - - - The `c.boxes.xyxy.cpu().numpy()` call retrieves the bounding boxes as a NumPy array in the `xyxy` format, where `xmin`, `ymin`, `xmax`, and `ymax` represent the coordinates of the bounding box rectangle. See [Boxes Section from Predict Mode](../modes/predict.md/#boxes) for more details. - - - The `squeeze()` operation removes any unnecessary dimensions from the NumPy array, ensuring it has the expected shape. - - - Converting the coordinate values using `.astype(np.int32)` changes the box coordinates data type from `float32` to `int32`, making them compatible for image cropping using index slices. - - - Finally, the bounding box region is cropped from the image using index slicing. The bounds are defined by the `[ymin:ymax, xmin:xmax]` coordinates of the detection bounding box. - - === "Transparent Background Pixels" - - ```py - # Isolate object with transparent background (when saved as PNG) - isolated = np.dstack([img, b_mask]) - - ``` - - ??? question "How does this work?" - - - Using the NumPy `dstack()` function (array stacking along depth-axis) in conjunction with the binary mask generated, will create an image with four channels. This allows for all pixels outside of the object contour to be transparent when saving as a `PNG` file. - - ### Isolate with Transparent Pixels: Sub-options - - ??? info "Full-size Image" - - There are no additional steps required if keeping full size image. - -
- ![Example Full size Isolated Object Image No Background](https://github.com/ultralytics/ultralytics/assets/62214284/b1043ee0-369a-4019-941a-9447a9771042){ width=240 } -
Example full-size output + transparent background
-
- - ??? info "Cropped object Image" - - Additional steps required to crop image to only include object region. - - ![Example Crop Isolated Object Image No Background](https://github.com/ultralytics/ultralytics/assets/62214284/5910244f-d1e1-44af-af7f-6dea4c688da8){ align="right" } - ``` { .py .annotate } - # (1) Bounding box coordinates - x1, y1, x2, y2 = c.boxes.xyxy.cpu().numpy().squeeze().astype(np.int32) - # Crop image to object region - iso_crop = isolated[y1:y2, x1:x2] - - ``` - - 1. For more information on bounding box results, see [Boxes Section from Predict Mode](../modes/predict.md/#boxes) - - ??? question "What does this code do?" - - - When using `c.boxes.xyxy.cpu().numpy()`, the bounding boxes are returned as a NumPy array, using the `xyxy` box coordinates format, which correspond to the points `xmin, ymin, xmax, ymax` for the bounding box (rectangle), see [Boxes Section from Predict Mode](../modes/predict.md/#boxes) for more information. - - - Adding `squeeze()` ensures that any extraneous dimensions are removed from the NumPy array. - - - Converting the coordinate values using `.astype(np.int32)` changes the box coordinates data type from `float32` to `int32` which will be compatible when cropping the image using index slices. - - - Finally the image region for the bounding box is cropped using index slicing, where the bounds are set using the `[ymin:ymax, xmin:xmax]` coordinates of the detection bounding box. - - ??? question "What if I want the cropped object **including** the background?" - - This is a built in feature for the Ultralytics library. See the `save_crop` argument for [Predict Mode Inference Arguments](../modes/predict.md/#inference-arguments) for details. - - *** - -6. What to do next is entirely left to you as the developer. A basic example of one possible next step (saving the image to file for future use) is shown. - - - **NOTE:** this step is optional and can be skipped if not required for your specific use case. - - ??? example "Example Final Step" - - ```py - # Save isolated object to file - _ = cv2.imwrite(f'{img_name}_{label}-{ci}.png', iso_crop) - ``` - - - In this example, the `img_name` is the base-name of the source image file, `label` is the detected class-name, and `ci` is the index of the object detection (in case of multiple instances with the same class name). - -## Full Example code - -Here, all steps from the previous section are combined into a single block of code. For repeated use, it would be optimal to define a function to do some or all commands contained in the `for`-loops, but that is an exercise left to the reader. - -```{ .py .annotate } -from pathlib import Path - -import cv2 -import numpy as np -from ultralytics import YOLO - -m = YOLO('yolov8n-seg.pt')#(4)! -res = m.predict()#(3)! - -# iterate detection results (5) -for r in res: - img = np.copy(r.orig_img) - img_name = Path(r.path).stem - - # iterate each object contour (6) - for ci,c in enumerate(r): - label = c.names[c.boxes.cls.tolist().pop()] - - b_mask = np.zeros(img.shape[:2], np.uint8) - - # Create contour mask (1) - contour = c.masks.xy.pop().astype(np.int32).reshape(-1, 1, 2) - _ = cv2.drawContours(b_mask, [contour], -1, (255, 255, 255), cv2.FILLED) - - # Choose one: - - # OPTION-1: Isolate object with black background - mask3ch = cv2.cvtColor(b_mask, cv2.COLOR_GRAY2BGR) - isolated = cv2.bitwise_and(mask3ch, img) - - # OPTION-2: Isolate object with transparent background (when saved as PNG) - isolated = np.dstack([img, b_mask]) - - # OPTIONAL: detection crop (from either OPT1 or OPT2) - x1, y1, x2, y2 = c.boxes.xyxy.cpu().numpy().squeeze().astype(np.int32) - iso_crop = isolated[y1:y2, x1:x2] - - # TODO your actions go here (2) - -``` - -1. The line populating `contour` is combined into a single line here, where it was split to multiple above. -2. {==What goes here is up to you!==} -3. See [Predict Mode](../modes/predict.md) for additional information. -4. See [Segment Task](../tasks/segment.md#models) for more information. -5. Learn more about [Working with Results](../modes/predict.md#working-with-results) -6. Learn more about [Segmentation Mask Results](../modes/predict.md#masks) diff --git a/ultralytics-main/docs/en/guides/kfold-cross-validation.md b/ultralytics-main/docs/en/guides/kfold-cross-validation.md deleted file mode 100644 index 9eb53a1..0000000 --- a/ultralytics-main/docs/en/guides/kfold-cross-validation.md +++ /dev/null @@ -1,278 +0,0 @@ ---- -comments: true -description: An in-depth guide demonstrating the implementation of K-Fold Cross Validation with the Ultralytics ecosystem for object detection datasets, leveraging Python, YOLO, and sklearn. -keywords: K-Fold cross validation, Ultralytics, YOLO detection format, Python, sklearn, object detection ---- - -# K-Fold Cross Validation with Ultralytics - -## Introduction - -This comprehensive guide illustrates the implementation of K-Fold Cross Validation for object detection datasets within the Ultralytics ecosystem. We'll leverage the YOLO detection format and key Python libraries such as sklearn, pandas, and PyYaml to guide you through the necessary setup, the process of generating feature vectors, and the execution of a K-Fold dataset split. - -

- K-Fold Cross Validation Overview -

- -Whether your project involves the Fruit Detection dataset or a custom data source, this tutorial aims to help you comprehend and apply K-Fold Cross Validation to bolster the reliability and robustness of your machine learning models. While we're applying `k=5` folds for this tutorial, keep in mind that the optimal number of folds can vary depending on your dataset and the specifics of your project. - -Without further ado, let's dive in! - -## Setup - -- Your annotations should be in the [YOLO detection format](../datasets/detect/index.md). - -- This guide assumes that annotation files are locally available. - -- For our demonstration, we use the [Fruit Detection](https://www.kaggle.com/datasets/lakshaytyagi01/fruit-detection/code) dataset. - - This dataset contains a total of 8479 images. - - It includes 6 class labels, each with its total instance counts listed below. - -| Class Label | Instance Count | -|:------------|:--------------:| -| Apple | 7049 | -| Grapes | 7202 | -| Pineapple | 1613 | -| Orange | 15549 | -| Banana | 3536 | -| Watermelon | 1976 | - -- Necessary Python packages include: - - - `ultralytics` - - `sklearn` - - `pandas` - - `pyyaml` - -- This tutorial operates with `k=5` folds. However, you should determine the best number of folds for your specific dataset. - -1. Initiate a new Python virtual environment (`venv`) for your project and activate it. Use `pip` (or your preferred package manager) to install: - - - The Ultralytics library: `pip install -U ultralytics`. Alternatively, you can clone the official [repo](https://github.com/ultralytics/ultralytics). - - Scikit-learn, pandas, and PyYAML: `pip install -U scikit-learn pandas pyyaml`. - -2. Verify that your annotations are in the [YOLO detection format](../datasets/detect/index.md). - - - For this tutorial, all annotation files are found in the `Fruit-Detection/labels` directory. - -## Generating Feature Vectors for Object Detection Dataset - -1. Start by creating a new Python file and import the required libraries. - - ```python - import datetime - import shutil - from pathlib import Path - from collections import Counter - - import yaml - import numpy as np - import pandas as pd - from ultralytics import YOLO - from sklearn.model_selection import KFold - ``` - -2. Proceed to retrieve all label files for your dataset. - - ```python - dataset_path = Path('./Fruit-detection') # replace with 'path/to/dataset' for your custom data - labels = sorted(dataset_path.rglob("*labels/*.txt")) # all data in 'labels' - ``` - -3. Now, read the contents of the dataset YAML file and extract the indices of the class labels. - - ```python - yaml_file = 'path/to/data.yaml' # your data YAML with data directories and names dictionary - with open(yaml_file, 'r', encoding="utf8") as y: - classes = yaml.safe_load(y)['names'] - cls_idx = sorted(classes.keys()) - ``` - -4. Initialize an empty `pandas` DataFrame. - - ```python - indx = [l.stem for l in labels] # uses base filename as ID (no extension) - labels_df = pd.DataFrame([], columns=cls_idx, index=indx) - ``` - -5. Count the instances of each class-label present in the annotation files. - - ```python - for label in labels: - lbl_counter = Counter() - - with open(label,'r') as lf: - lines = lf.readlines() - - for l in lines: - # classes for YOLO label uses integer at first position of each line - lbl_counter[int(l.split(' ')[0])] += 1 - - labels_df.loc[label.stem] = lbl_counter - - labels_df = labels_df.fillna(0.0) # replace `nan` values with `0.0` - ``` - -6. The following is a sample view of the populated DataFrame: - - ```pandas - 0 1 2 3 4 5 - '0000a16e4b057580_jpg.rf.00ab48988370f64f5ca8ea4...' 0.0 0.0 0.0 0.0 0.0 7.0 - '0000a16e4b057580_jpg.rf.7e6dce029fb67f01eb19aa7...' 0.0 0.0 0.0 0.0 0.0 7.0 - '0000a16e4b057580_jpg.rf.bc4d31cdcbe229dd022957a...' 0.0 0.0 0.0 0.0 0.0 7.0 - '00020ebf74c4881c_jpg.rf.508192a0a97aa6c4a3b6882...' 0.0 0.0 0.0 1.0 0.0 0.0 - '00020ebf74c4881c_jpg.rf.5af192a2254c8ecc4188a25...' 0.0 0.0 0.0 1.0 0.0 0.0 - ... ... ... ... ... ... ... - 'ff4cd45896de38be_jpg.rf.c4b5e967ca10c7ced3b9e97...' 0.0 0.0 0.0 0.0 0.0 2.0 - 'ff4cd45896de38be_jpg.rf.ea4c1d37d2884b3e3cbce08...' 0.0 0.0 0.0 0.0 0.0 2.0 - 'ff5fd9c3c624b7dc_jpg.rf.bb519feaa36fc4bf630a033...' 1.0 0.0 0.0 0.0 0.0 0.0 - 'ff5fd9c3c624b7dc_jpg.rf.f0751c9c3aa4519ea3c9d6a...' 1.0 0.0 0.0 0.0 0.0 0.0 - 'fffe28b31f2a70d4_jpg.rf.7ea16bd637ba0711c53b540...' 0.0 6.0 0.0 0.0 0.0 0.0 - ``` - -The rows index the label files, each corresponding to an image in your dataset, and the columns correspond to your class-label indices. Each row represents a pseudo feature-vector, with the count of each class-label present in your dataset. This data structure enables the application of K-Fold Cross Validation to an object detection dataset. - -## K-Fold Dataset Split - -1. Now we will use the `KFold` class from `sklearn.model_selection` to generate `k` splits of the dataset. - - - Important: - - Setting `shuffle=True` ensures a randomized distribution of classes in your splits. - - By setting `random_state=M` where `M` is a chosen integer, you can obtain repeatable results. - - ```python - ksplit = 5 - kf = KFold(n_splits=ksplit, shuffle=True, random_state=20) # setting random_state for repeatable results - - kfolds = list(kf.split(labels_df)) - ``` - -2. The dataset has now been split into `k` folds, each having a list of `train` and `val` indices. We will construct a DataFrame to display these results more clearly. - - ```python - folds = [f'split_{n}' for n in range(1, ksplit + 1)] - folds_df = pd.DataFrame(index=indx, columns=folds) - - for idx, (train, val) in enumerate(kfolds, start=1): - folds_df[f'split_{idx}'].loc[labels_df.iloc[train].index] = 'train' - folds_df[f'split_{idx}'].loc[labels_df.iloc[val].index] = 'val' - ``` - -3. Now we will calculate the distribution of class labels for each fold as a ratio of the classes present in `val` to those present in `train`. - - ```python - fold_lbl_distrb = pd.DataFrame(index=folds, columns=cls_idx) - - for n, (train_indices, val_indices) in enumerate(kfolds, start=1): - train_totals = labels_df.iloc[train_indices].sum() - val_totals = labels_df.iloc[val_indices].sum() - - # To avoid division by zero, we add a small value (1E-7) to the denominator - ratio = val_totals / (train_totals + 1E-7) - fold_lbl_distrb.loc[f'split_{n}'] = ratio - ``` - - The ideal scenario is for all class ratios to be reasonably similar for each split and across classes. This, however, will be subject to the specifics of your dataset. - -4. Next, we create the directories and dataset YAML files for each split. - - ```python - supported_extensions = ['.jpg', '.jpeg', '.png'] - - # Initialize an empty list to store image file paths - images = [] - - # Loop through supported extensions and gather image files - for ext in supported_extensions: - images.extend(sorted((dataset_path / 'images').rglob(f"*{ext}"))) - - # Create the necessary directories and dataset YAML files (unchanged) - save_path = Path(dataset_path / f'{datetime.date.today().isoformat()}_{ksplit}-Fold_Cross-val') - save_path.mkdir(parents=True, exist_ok=True) - ds_yamls = [] - - for split in folds_df.columns: - # Create directories - split_dir = save_path / split - split_dir.mkdir(parents=True, exist_ok=True) - (split_dir / 'train' / 'images').mkdir(parents=True, exist_ok=True) - (split_dir / 'train' / 'labels').mkdir(parents=True, exist_ok=True) - (split_dir / 'val' / 'images').mkdir(parents=True, exist_ok=True) - (split_dir / 'val' / 'labels').mkdir(parents=True, exist_ok=True) - - # Create dataset YAML files - dataset_yaml = split_dir / f'{split}_dataset.yaml' - ds_yamls.append(dataset_yaml) - - with open(dataset_yaml, 'w') as ds_y: - yaml.safe_dump({ - 'path': split_dir.as_posix(), - 'train': 'train', - 'val': 'val', - 'names': classes - }, ds_y) - ``` - -5. Lastly, copy images and labels into the respective directory ('train' or 'val') for each split. - - - __NOTE:__ The time required for this portion of the code will vary based on the size of your dataset and your system hardware. - - ```python - for image, label in zip(images, labels): - for split, k_split in folds_df.loc[image.stem].items(): - # Destination directory - img_to_path = save_path / split / k_split / 'images' - lbl_to_path = save_path / split / k_split / 'labels' - - # Copy image and label files to new directory (SamefileError if file already exists) - shutil.copy(image, img_to_path / image.name) - shutil.copy(label, lbl_to_path / label.name) - ``` - -## Save Records (Optional) - -Optionally, you can save the records of the K-Fold split and label distribution DataFrames as CSV files for future reference. - -```python -folds_df.to_csv(save_path / "kfold_datasplit.csv") -fold_lbl_distrb.to_csv(save_path / "kfold_label_distribution.csv") -``` - -## Train YOLO using K-Fold Data Splits - -1. First, load the YOLO model. - - ```python - weights_path = 'path/to/weights.pt' - model = YOLO(weights_path, task='detect') - ``` - -2. Next, iterate over the dataset YAML files to run training. The results will be saved to a directory specified by the `project` and `name` arguments. By default, this directory is 'exp/runs#' where # is an integer index. - - ```python - results = {} - - # Define your additional arguments here - batch = 16 - project = 'kfold_demo' - epochs = 100 - - for k in range(ksplit): - dataset_yaml = ds_yamls[k] - model.train(data=dataset_yaml,epochs=epochs, batch=batch, project=project) # include any train arguments - results[k] = model.metrics # save output metrics for further analysis - ``` - -## Conclusion - -In this guide, we have explored the process of using K-Fold cross-validation for training the YOLO object detection model. We learned how to split our dataset into K partitions, ensuring a balanced class distribution across the different folds. - -We also explored the procedure for creating report DataFrames to visualize the data splits and label distributions across these splits, providing us a clear insight into the structure of our training and validation sets. - -Optionally, we saved our records for future reference, which could be particularly useful in large-scale projects or when troubleshooting model performance. - -Finally, we implemented the actual model training using each split in a loop, saving our training results for further analysis and comparison. - -This technique of K-Fold cross-validation is a robust way of making the most out of your available data, and it helps to ensure that your model performance is reliable and consistent across different data subsets. This results in a more generalizable and reliable model that is less likely to overfit to specific data patterns. - -Remember that although we used YOLO in this guide, these steps are mostly transferable to other machine learning models. Understanding these steps allows you to apply cross-validation effectively in your own machine learning projects. Happy coding! diff --git a/ultralytics-main/docs/en/guides/model-deployment-options.md b/ultralytics-main/docs/en/guides/model-deployment-options.md deleted file mode 100644 index a487ea4..0000000 --- a/ultralytics-main/docs/en/guides/model-deployment-options.md +++ /dev/null @@ -1,305 +0,0 @@ ---- -comments: true -description: A guide to help determine which deployment option to choose for your YOLOv8 model, including essential considerations. -keywords: YOLOv8, Deployment, PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, CoreML, TensorFlow, Export ---- - -# Understanding YOLOv8’s Deployment Options - -## Introduction - -You've come a long way on your journey with YOLOv8. You've diligently collected data, meticulously annotated it, and put in the hours to train and rigorously evaluate your custom YOLOv8 model. Now, it’s time to put your model to work for your specific application, use case, or project. But there's a critical decision that stands before you: how to export and deploy your model effectively. - -This guide walks you through YOLOv8’s deployment options and the essential factors to consider to choose the right option for your project. - -## How to Select the Right Deployment Option for Your YOLOv8 Model - -When it's time to deploy your YOLOv8 model, selecting a suitable export format is very important. As outlined in the [Ultralytics YOLOv8 Modes documentation](../modes/export.md#usage-examples), the model.export() function allows for converting your trained model into a variety of formats tailored to diverse environments and performance requirements. - -The ideal format depends on your model's intended operational context, balancing speed, hardware constraints, and ease of integration. In the following section, we'll take a closer look at each export option, understanding when to choose each one. - -### YOLOv8’s Deployment Options - -Let’s walk through the different YOLOv8 deployment options. For a detailed walkthrough of the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -#### PyTorch - -PyTorch is an open-source machine learning library widely used for applications in deep learning and artificial intelligence. It provides a high level of flexibility and speed, which has made it a favorite among researchers and developers. - -- **Performance Benchmarks**: PyTorch is known for its ease of use and flexibility, which may result in a slight trade-off in raw performance when compared to other frameworks that are more specialized and optimized. - -- **Compatibility and Integration**: Offers excellent compatibility with various data science and machine learning libraries in Python. - -- **Community Support and Ecosystem**: One of the most vibrant communities, with extensive resources for learning and troubleshooting. - -- **Case Studies**: Commonly used in research prototypes, many academic papers reference models deployed in PyTorch. - -- **Maintenance and Updates**: Regular updates with active development and support for new features. - -- **Security Considerations**: Regular patches for security issues, but security is largely dependent on the overall environment it’s deployed in. - -- **Hardware Acceleration**: Supports CUDA for GPU acceleration, essential for speeding up model training and inference. - -#### TorchScript - -TorchScript extends PyTorch’s capabilities by allowing the exportation of models to be run in a C++ runtime environment. This makes it suitable for production environments where Python is unavailable. - -- **Performance Benchmarks**: Can offer improved performance over native PyTorch, especially in production environments. - -- **Compatibility and Integration**: Designed for seamless transition from PyTorch to C++ production environments, though some advanced features might not translate perfectly. - -- **Community Support and Ecosystem**: Benefits from PyTorch’s large community but has a narrower scope of specialized developers. - -- **Case Studies**: Widely used in industry settings where Python’s performance overhead is a bottleneck. - -- **Maintenance and Updates**: Maintained alongside PyTorch with consistent updates. - -- **Security Considerations**: Offers improved security by enabling the running of models in environments without full Python installations. - -- **Hardware Acceleration**: Inherits PyTorch’s CUDA support, ensuring efficient GPU utilization. - -#### ONNX - -The Open Neural Network Exchange (ONNX) is a format that allows for model interoperability across different frameworks, which can be critical when deploying to various platforms. - -- **Performance Benchmarks**: ONNX models may experience a variable performance depending on the specific runtime they are deployed on. - -- **Compatibility and Integration**: High interoperability across multiple platforms and hardware due to its framework-agnostic nature. - -- **Community Support and Ecosystem**: Supported by many organizations, leading to a broad ecosystem and a variety of tools for optimization. - -- **Case Studies**: Frequently used to move models between different machine learning frameworks, demonstrating its flexibility. - -- **Maintenance and Updates**: As an open standard, ONNX is regularly updated to support new operations and models. - -- **Security Considerations**: As with any cross-platform tool, it's essential to ensure secure practices in the conversion and deployment pipeline. - -- **Hardware Acceleration**: With ONNX Runtime, models can leverage various hardware optimizations. - -#### OpenVINO - -OpenVINO is an Intel toolkit designed to facilitate the deployment of deep learning models across Intel hardware, enhancing performance and speed. - -- **Performance Benchmarks**: Specifically optimized for Intel CPUs, GPUs, and VPUs, offering significant performance boosts on compatible hardware. - -- **Compatibility and Integration**: Works best within the Intel ecosystem but also supports a range of other platforms. - -- **Community Support and Ecosystem**: Backed by Intel, with a solid user base especially in the computer vision domain. - -- **Case Studies**: Often utilized in IoT and edge computing scenarios where Intel hardware is prevalent. - -- **Maintenance and Updates**: Intel regularly updates OpenVINO to support the latest deep learning models and Intel hardware. - -- **Security Considerations**: Provides robust security features suitable for deployment in sensitive applications. - -- **Hardware Acceleration**: Tailored for acceleration on Intel hardware, leveraging dedicated instruction sets and hardware features. - -For more details on deployment using OpenVINO, refer to the Ultralytics Integration documentation: [Intel OpenVINO Export](../integrations/openvino.md). - -#### TensorRT - -TensorRT is a high-performance deep learning inference optimizer and runtime from NVIDIA, ideal for applications needing speed and efficiency. - -- **Performance Benchmarks**: Delivers top-tier performance on NVIDIA GPUs with support for high-speed inference. - -- **Compatibility and Integration**: Best suited for NVIDIA hardware, with limited support outside this environment. - -- **Community Support and Ecosystem**: Strong support network through NVIDIA’s developer forums and documentation. - -- **Case Studies**: Widely adopted in industries requiring real-time inference on video and image data. - -- **Maintenance and Updates**: NVIDIA maintains TensorRT with frequent updates to enhance performance and support new GPU architectures. - -- **Security Considerations**: Like many NVIDIA products, it has a strong emphasis on security, but specifics depend on the deployment environment. - -- **Hardware Acceleration**: Exclusively designed for NVIDIA GPUs, providing deep optimization and acceleration. - -#### CoreML - -CoreML is Apple’s machine learning framework, optimized for on-device performance in the Apple ecosystem, including iOS, macOS, watchOS, and tvOS. - -- **Performance Benchmarks**: Optimized for on-device performance on Apple hardware with minimal battery usage. - -- **Compatibility and Integration**: Exclusively for Apple's ecosystem, providing a streamlined workflow for iOS and macOS applications. - -- **Community Support and Ecosystem**: Strong support from Apple and a dedicated developer community, with extensive documentation and tools. - -- **Case Studies**: Commonly used in applications that require on-device machine learning capabilities on Apple products. - -- **Maintenance and Updates**: Regularly updated by Apple to support the latest machine learning advancements and Apple hardware. - -- **Security Considerations**: Benefits from Apple's focus on user privacy and data security. - -- **Hardware Acceleration**: Takes full advantage of Apple's neural engine and GPU for accelerated machine learning tasks. - -#### TF SavedModel - -TF SavedModel is TensorFlow’s format for saving and serving machine learning models, particularly suited for scalable server environments. - -- **Performance Benchmarks**: Offers scalable performance in server environments, especially when used with TensorFlow Serving. - -- **Compatibility and Integration**: Wide compatibility across TensorFlow's ecosystem, including cloud and enterprise server deployments. - -- **Community Support and Ecosystem**: Large community support due to TensorFlow's popularity, with a vast array of tools for deployment and optimization. - -- **Case Studies**: Extensively used in production environments for serving deep learning models at scale. - -- **Maintenance and Updates**: Supported by Google and the TensorFlow community, ensuring regular updates and new features. - -- **Security Considerations**: Deployment using TensorFlow Serving includes robust security features for enterprise-grade applications. - -- **Hardware Acceleration**: Supports various hardware accelerations through TensorFlow's backends. - -#### TF GraphDef - -TF GraphDef is a TensorFlow format that represents the model as a graph, which is beneficial for environments where a static computation graph is required. - -- **Performance Benchmarks**: Provides stable performance for static computation graphs, with a focus on consistency and reliability. - -- **Compatibility and Integration**: Easily integrates within TensorFlow's infrastructure but less flexible compared to SavedModel. - -- **Community Support and Ecosystem**: Good support from TensorFlow's ecosystem, with many resources available for optimizing static graphs. - -- **Case Studies**: Useful in scenarios where a static graph is necessary, such as in certain embedded systems. - -- **Maintenance and Updates**: Regular updates alongside TensorFlow's core updates. - -- **Security Considerations**: Ensures safe deployment with TensorFlow's established security practices. - -- **Hardware Acceleration**: Can utilize TensorFlow's hardware acceleration options, though not as flexible as SavedModel. - -#### TF Lite - -TF Lite is TensorFlow’s solution for mobile and embedded device machine learning, providing a lightweight library for on-device inference. - -- **Performance Benchmarks**: Designed for speed and efficiency on mobile and embedded devices. - -- **Compatibility and Integration**: Can be used on a wide range of devices due to its lightweight nature. - -- **Community Support and Ecosystem**: Backed by Google, it has a robust community and a growing number of resources for developers. - -- **Case Studies**: Popular in mobile applications that require on-device inference with minimal footprint. - -- **Maintenance and Updates**: Regularly updated to include the latest features and optimizations for mobile devices. - -- **Security Considerations**: Provides a secure environment for running models on end-user devices. - -- **Hardware Acceleration**: Supports a variety of hardware acceleration options, including GPU and DSP. - -#### TF Edge TPU - -TF Edge TPU is designed for high-speed, efficient computing on Google's Edge TPU hardware, perfect for IoT devices requiring real-time processing. - -- **Performance Benchmarks**: Specifically optimized for high-speed, efficient computing on Google's Edge TPU hardware. - -- **Compatibility and Integration**: Works exclusively with TensorFlow Lite models on Edge TPU devices. - -- **Community Support and Ecosystem**: Growing support with resources provided by Google and third-party developers. - -- **Case Studies**: Used in IoT devices and applications that require real-time processing with low latency. - -- **Maintenance and Updates**: Continually improved upon to leverage the capabilities of new Edge TPU hardware releases. - -- **Security Considerations**: Integrates with Google's robust security for IoT and edge devices. - -- **Hardware Acceleration**: Custom-designed to take full advantage of Google Coral devices. - -#### TF.js - -TensorFlow.js (TF.js) is a library that brings machine learning capabilities directly to the browser, offering a new realm of possibilities for web developers and users alike. It allows for the integration of machine learning models in web applications without the need for back-end infrastructure. - -- **Performance Benchmarks**: Enables machine learning directly in the browser with reasonable performance, depending on the client device. - -- **Compatibility and Integration**: High compatibility with web technologies, allowing for easy integration into web applications. - -- **Community Support and Ecosystem**: Support from a community of web and Node.js developers, with a variety of tools for deploying ML models in browsers. - -- **Case Studies**: Ideal for interactive web applications that benefit from client-side machine learning without the need for server-side processing. - -- **Maintenance and Updates**: Maintained by the TensorFlow team with contributions from the open-source community. - -- **Security Considerations**: Runs within the browser's secure context, utilizing the security model of the web platform. - -- **Hardware Acceleration**: Performance can be enhanced with web-based APIs that access hardware acceleration like WebGL. - -#### PaddlePaddle - -PaddlePaddle is an open-source deep learning framework developed by Baidu. It is designed to be both efficient for researchers and easy to use for developers. It's particularly popular in China and offers specialized support for Chinese language processing. - -- **Performance Benchmarks**: Offers competitive performance with a focus on ease of use and scalability. - -- **Compatibility and Integration**: Well-integrated within Baidu's ecosystem and supports a wide range of applications. - -- **Community Support and Ecosystem**: While the community is smaller globally, it's rapidly growing, especially in China. - -- **Case Studies**: Commonly used in Chinese markets and by developers looking for alternatives to other major frameworks. - -- **Maintenance and Updates**: Regularly updated with a focus on serving Chinese language AI applications and services. - -- **Security Considerations**: Emphasizes data privacy and security, catering to Chinese data governance standards. - -- **Hardware Acceleration**: Supports various hardware accelerations, including Baidu's own Kunlun chips. - -#### NCNN - -NCNN is a high-performance neural network inference framework optimized for the mobile platform. It stands out for its lightweight nature and efficiency, making it particularly well-suited for mobile and embedded devices where resources are limited. - -- **Performance Benchmarks**: Highly optimized for mobile platforms, offering efficient inference on ARM-based devices. - -- **Compatibility and Integration**: Suitable for applications on mobile phones and embedded systems with ARM architecture. - -- **Community Support and Ecosystem**: Supported by a niche but active community focused on mobile and embedded ML applications. - -- **Case Studies**: Favoured for mobile applications where efficiency and speed are critical on Android and other ARM-based systems. - -- **Maintenance and Updates**: Continuously improved to maintain high performance on a range of ARM devices. - -- **Security Considerations**: Focuses on running locally on the device, leveraging the inherent security of on-device processing. - -- **Hardware Acceleration**: Tailored for ARM CPUs and GPUs, with specific optimizations for these architectures. - -## Comparative Analysis of YOLOv8 Deployment Options - -The following table provides a snapshot of the various deployment options available for YOLOv8 models, helping you to assess which may best fit your project needs based on several critical criteria. For an in-depth look at each deployment option's format, please see the [Ultralytics documentation page on export formats](../modes/export.md#export-formats). - -| Deployment Option | Performance Benchmarks | Compatibility and Integration | Community Support and Ecosystem | Case Studies | Maintenance and Updates | Security Considerations | Hardware Acceleration | -|-------------------|-------------------------------------------------|------------------------------------------------|-----------------------------------------------|--------------------------------------------|---------------------------------------------|---------------------------------------------------|------------------------------------| -| PyTorch | Good flexibility; may trade off raw performance | Excellent with Python libraries | Extensive resources and community | Research and prototypes | Regular, active development | Dependent on deployment environment | CUDA support for GPU acceleration | -| TorchScript | Better for production than PyTorch | Smooth transition from PyTorch to C++ | Specialized but narrower than PyTorch | Industry where Python is a bottleneck | Consistent updates with PyTorch | Improved security without full Python | Inherits CUDA support from PyTorch | -| ONNX | Variable depending on runtime | High across different frameworks | Broad ecosystem, supported by many orgs | Flexibility across ML frameworks | Regular updates for new operations | Ensure secure conversion and deployment practices | Various hardware optimizations | -| OpenVINO | Optimized for Intel hardware | Best within Intel ecosystem | Solid in computer vision domain | IoT and edge with Intel hardware | Regular updates for Intel hardware | Robust features for sensitive applications | Tailored for Intel hardware | -| TensorRT | Top-tier on NVIDIA GPUs | Best for NVIDIA hardware | Strong network through NVIDIA | Real-time video and image inference | Frequent updates for new GPUs | Emphasis on security | Designed for NVIDIA GPUs | -| CoreML | Optimized for on-device Apple hardware | Exclusive to Apple ecosystem | Strong Apple and developer support | On-device ML on Apple products | Regular Apple updates | Focus on privacy and security | Apple neural engine and GPU | -| TF SavedModel | Scalable in server environments | Wide compatibility in TensorFlow ecosystem | Large support due to TensorFlow popularity | Serving models at scale | Regular updates by Google and community | Robust features for enterprise | Various hardware accelerations | -| TF GraphDef | Stable for static computation graphs | Integrates well with TensorFlow infrastructure | Resources for optimizing static graphs | Scenarios requiring static graphs | Updates alongside TensorFlow core | Established TensorFlow security practices | TensorFlow acceleration options | -| TF Lite | Speed and efficiency on mobile/embedded | Wide range of device support | Robust community, Google backed | Mobile applications with minimal footprint | Latest features for mobile | Secure environment on end-user devices | GPU and DSP among others | -| TF Edge TPU | Optimized for Google's Edge TPU hardware | Exclusive to Edge TPU devices | Growing with Google and third-party resources | IoT devices requiring real-time processing | Improvements for new Edge TPU hardware | Google's robust IoT security | Custom-designed for Google Coral | -| TF.js | Reasonable in-browser performance | High with web technologies | Web and Node.js developers support | Interactive web applications | TensorFlow team and community contributions | Web platform security model | Enhanced with WebGL and other APIs | -| PaddlePaddle | Competitive, easy to use and scalable | Baidu ecosystem, wide application support | Rapidly growing, especially in China | Chinese market and language processing | Focus on Chinese AI applications | Emphasizes data privacy and security | Including Baidu's Kunlun chips | -| NCNN | Optimized for mobile ARM-based devices | Mobile and embedded ARM systems | Niche but active mobile/embedded ML community | Android and ARM systems efficiency | High performance maintenance on ARM | On-device security advantages | ARM CPUs and GPUs optimizations | - -This comparative analysis gives you a high-level overview. For deployment, it's essential to consider the specific requirements and constraints of your project, and consult the detailed documentation and resources available for each option. - -## Community and Support - -When you're getting started with YOLOv8, having a helpful community and support can make a significant impact. Here's how to connect with others who share your interests and get the assistance you need. - -### Engage with the Broader Community - -- **GitHub Discussions:** The YOLOv8 repository on GitHub has a "Discussions" section where you can ask questions, report issues, and suggest improvements. - -- **Ultralytics Discord Server:** Ultralytics has a [Discord server](https://ultralytics.com/discord/) where you can interact with other users and developers. - -### Official Documentation and Resources - -- **Ultralytics YOLOv8 Docs:** The [official documentation](../index.md) provides a comprehensive overview of YOLOv8, along with guides on installation, usage, and troubleshooting. - -These resources will help you tackle challenges and stay updated on the latest trends and best practices in the YOLOv8 community. - -## Conclusion - -In this guide, we've explored the different deployment options for YOLOv8. We've also discussed the important factors to consider when making your choice. These options allow you to customize your model for various environments and performance requirements, making it suitable for real-world applications. - -Don't forget that the YOLOv8 and Ultralytics community is a valuable source of help. Connect with other developers and experts to learn unique tips and solutions you might not find in regular documentation. Keep seeking knowledge, exploring new ideas, and sharing your experiences. - -Happy deploying! diff --git a/ultralytics-main/docs/en/guides/object-blurring.md b/ultralytics-main/docs/en/guides/object-blurring.md deleted file mode 100644 index 0b6faa3..0000000 --- a/ultralytics-main/docs/en/guides/object-blurring.md +++ /dev/null @@ -1,91 +0,0 @@ ---- -comments: true -description: Learn to blur objects using Ultralytics YOLOv8 for privacy in images and videos. -keywords: Ultralytics, YOLOv8, Object Detection, Object Blurring, Privacy Protection, Image Processing, Video Analysis, AI, Machine Learning ---- - -# Object Blurring using Ultralytics YOLOv8 🚀 - -## What is Object Blurring? - -Object blurring with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves applying a blurring effect to specific detected objects in an image or video. This can be achieved using the YOLOv8 model capabilities to identify and manipulate objects within a given scene. - -## Advantages of Object Blurring? - -- **Privacy Protection**: Object blurring is an effective tool for safeguarding privacy by concealing sensitive or personally identifiable information in images or videos. -- **Selective Focus**: YOLOv8 allows for selective blurring, enabling users to target specific objects, ensuring a balance between privacy and retaining relevant visual information. -- **Real-time Processing**: YOLOv8's efficiency enables object blurring in real-time, making it suitable for applications requiring on-the-fly privacy enhancements in dynamic environments. - -!!! Example "Object Blurring using YOLOv8 Example" - - === "Object Blurring" - - ```python - from ultralytics import YOLO - from ultralytics.utils.plotting import Annotator, colors - import cv2 - - model = YOLO("yolov8n.pt") - names = model.names - - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Blur ratio - blur_ratio = 50 - - # Video writer - video_writer = cv2.VideoWriter("object_blurring_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, (w, h)) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - - results = model.predict(im0, show=False) - boxes = results[0].boxes.xyxy.cpu().tolist() - clss = results[0].boxes.cls.cpu().tolist() - annotator = Annotator(im0, line_width=2, example=names) - - if boxes is not None: - for box, cls in zip(boxes, clss): - annotator.box_label(box, color=colors(int(cls), True), label=names[int(cls)]) - - obj = im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])] - blur_obj = cv2.blur(obj, (blur_ratio, blur_ratio)) - - im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])] = blur_obj - - cv2.imshow("ultralytics", im0) - video_writer.write(im0) - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - -### Arguments `model.predict` - -| Name | Type | Default | Description | -|-----------------|----------------|------------------------|----------------------------------------------------------------------------| -| `source` | `str` | `'ultralytics/assets'` | source directory for images or videos | -| `conf` | `float` | `0.25` | object confidence threshold for detection | -| `iou` | `float` | `0.7` | intersection over union (IoU) threshold for NMS | -| `imgsz` | `int or tuple` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) | -| `half` | `bool` | `False` | use half precision (FP16) | -| `device` | `None or str` | `None` | device to run on, i.e. cuda device=0/1/2/3 or device=cpu | -| `max_det` | `int` | `300` | maximum number of detections per image | -| `vid_stride` | `bool` | `False` | video frame-rate stride | -| `stream_buffer` | `bool` | `False` | buffer all streaming frames (True) or return the most recent frame (False) | -| `visualize` | `bool` | `False` | visualize model features | -| `augment` | `bool` | `False` | apply image augmentation to prediction sources | -| `agnostic_nms` | `bool` | `False` | class-agnostic NMS | -| `classes` | `list[int]` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `retina_masks` | `bool` | `False` | use high-resolution segmentation masks | -| `embed` | `list[int]` | `None` | return feature vectors/embeddings from given layers | diff --git a/ultralytics-main/docs/en/guides/object-counting.md b/ultralytics-main/docs/en/guides/object-counting.md deleted file mode 100644 index 0c3ce72..0000000 --- a/ultralytics-main/docs/en/guides/object-counting.md +++ /dev/null @@ -1,246 +0,0 @@ ---- -comments: true -description: Object Counting Using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Object Counting, Object Tracking, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Object Counting using Ultralytics YOLOv8 🚀 - -## What is Object Counting? - -Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves accurate identification and counting of specific objects in videos and camera streams. YOLOv8 excels in real-time applications, providing efficient and precise object counting for various scenarios like crowd analysis and surveillance, thanks to its state-of-the-art algorithms and deep learning capabilities. - -

-
- -
- Watch: Object Counting using Ultralytics YOLOv8 -

- -## Advantages of Object Counting? - -- **Resource Optimization:** Object counting facilitates efficient resource management by providing accurate counts, and optimizing resource allocation in applications like inventory management. -- **Enhanced Security:** Object counting enhances security and surveillance by accurately tracking and counting entities, aiding in proactive threat detection. -- **Informed Decision-Making:** Object counting offers valuable insights for decision-making, optimizing processes in retail, traffic management, and various other domains. - -## Real World Applications - -| Logistics | Aquaculture | -|:-------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![Conveyor Belt Packets Counting Using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/70e2d106-510c-4c6c-a57a-d34a765aa757) | ![Fish Counting in Sea using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/c60d047b-3837-435f-8d29-bb9fc95d2191) | -| Conveyor Belt Packets Counting Using Ultralytics YOLOv8 | Fish Counting in Sea using Ultralytics YOLOv8 | - -!!! Example "Object Counting using YOLOv8 Example" - - === "Count in Region" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import object_counter - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Define region points - region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)] - - # Video writer - video_writer = cv2.VideoWriter("object_counting_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init Object Counter - counter = object_counter.ObjectCounter() - counter.set_args(view_img=True, - reg_pts=region_points, - classes_names=model.names, - draw_tracks=True) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = counter.start_counting(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - - === "Count in Polygon" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import object_counter - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Define region points as a polygon with 5 points - region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)] - - # Video writer - video_writer = cv2.VideoWriter("object_counting_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init Object Counter - counter = object_counter.ObjectCounter() - counter.set_args(view_img=True, - reg_pts=region_points, - classes_names=model.names, - draw_tracks=True) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = counter.start_counting(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - - === "Count in Line" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import object_counter - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Define line points - line_points = [(20, 400), (1080, 400)] - - # Video writer - video_writer = cv2.VideoWriter("object_counting_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init Object Counter - counter = object_counter.ObjectCounter() - counter.set_args(view_img=True, - reg_pts=line_points, - classes_names=model.names, - draw_tracks=True) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False) - - im0 = counter.start_counting(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - - === "Specific Classes" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import object_counter - import cv2 - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - line_points = [(20, 400), (1080, 400)] # line or region points - classes_to_count = [0, 2] # person and car classes for count - - # Video writer - video_writer = cv2.VideoWriter("object_counting_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - # Init Object Counter - counter = object_counter.ObjectCounter() - counter.set_args(view_img=True, - reg_pts=line_points, - classes_names=model.names, - draw_tracks=True) - - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - tracks = model.track(im0, persist=True, show=False, - classes=classes_to_count) - - im0 = counter.start_counting(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - -???+ tip "Region is Movable" - - You can move the region anywhere in the frame by clicking on its edges - -### Optional Arguments `set_args` - -| Name | Type | Default | Description | -|-----------------------|-------------|----------------------------|-----------------------------------------------| -| `view_img` | `bool` | `False` | Display frames with counts | -| `view_in_counts` | `bool` | `True` | Display in-counts only on video frame | -| `view_out_counts` | `bool` | `True` | Display out-counts only on video frame | -| `line_thickness` | `int` | `2` | Increase bounding boxes thickness | -| `reg_pts` | `list` | `[(20, 400), (1260, 400)]` | Points defining the Region Area | -| `classes_names` | `dict` | `model.model.names` | Dictionary of Class Names | -| `region_color` | `RGB Color` | `(255, 0, 255)` | Color of the Object counting Region or Line | -| `track_thickness` | `int` | `2` | Thickness of Tracking Lines | -| `draw_tracks` | `bool` | `False` | Enable drawing Track lines | -| `track_color` | `RGB Color` | `(0, 255, 0)` | Color for each track line | -| `line_dist_thresh` | `int` | `15` | Euclidean Distance threshold for line counter | -| `count_txt_thickness` | `int` | `2` | Thickness of Object counts text | -| `count_txt_color` | `RGB Color` | `(0, 0, 0)` | Foreground color for Object counts text | -| `count_color` | `RGB Color` | `(255, 255, 255)` | Background color for Object counts text | -| `region_thickness` | `int` | `5` | Thickness for object counter region or line | - -### Arguments `model.track` - -| Name | Type | Default | Description | -|-----------|---------|----------------|-------------------------------------------------------------| -| `source` | `im0` | `None` | source directory for images or videos | -| `persist` | `bool` | `False` | persisting tracks between frames | -| `tracker` | `str` | `botsort.yaml` | Tracking method 'bytetrack' or 'botsort' | -| `conf` | `float` | `0.3` | Confidence Threshold | -| `iou` | `float` | `0.5` | IOU Threshold | -| `classes` | `list` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `verbose` | `bool` | `True` | Display the object tracking results | diff --git a/ultralytics-main/docs/en/guides/object-cropping.md b/ultralytics-main/docs/en/guides/object-cropping.md deleted file mode 100644 index 240230a..0000000 --- a/ultralytics-main/docs/en/guides/object-cropping.md +++ /dev/null @@ -1,102 +0,0 @@ ---- -comments: true -description: Learn how to isolate and extract specific objects from images and videos using YOLOv8 object cropping. -keywords: Ultralytics, YOLOv8, Object Detection, Object Cropping, Image Analysis, Video Processing, Data Extraction, Python ---- - -# Object Cropping using Ultralytics YOLOv8 🚀 - -## What is Object Cropping? - -Object cropping with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves isolating and extracting specific detected objects from an image or video. The YOLOv8 model capabilities are utilized to accurately identify and delineate objects, enabling precise cropping for further analysis or manipulation. - -## Advantages of Object Cropping? - -- **Focused Analysis**: YOLOv8 facilitates targeted object cropping, allowing for in-depth examination or processing of individual items within a scene. -- **Reduced Data Volume**: By extracting only relevant objects, object cropping helps in minimizing data size, making it efficient for storage, transmission, or subsequent computational tasks. -- **Enhanced Precision**: YOLOv8's object detection accuracy ensures that the cropped objects maintain their spatial relationships, preserving the integrity of the visual information for detailed analysis. - -## Visuals - -| Airport Luggage | -|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![Conveyor Belt at Airport Suitcases Cropping using Ultralytics YOLOv8](https://github.com/RizwanMunawar/RizwanMunawar/assets/62513924/648f46be-f233-4307-a8e5-046eea38d2e4) | -| Suitcases Cropping at airport conveyor belt using Ultralytics YOLOv8 | - -!!! Example "Object Cropping using YOLOv8 Example" - - === "Object Cropping" - - ```python - from ultralytics import YOLO - from ultralytics.utils.plotting import Annotator, colors - import cv2 - import os - - model = YOLO("yolov8n.pt") - names = model.names - - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - crop_dir_name = "ultralytics_crop" - if not os.path.exists(crop_dir_name): - os.mkdir(crop_dir_name) - - # Video writer - video_writer = cv2.VideoWriter("object_cropping_output.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, (w, h)) - - idx = 0 - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - - results = model.predict(im0, show=False) - boxes = results[0].boxes.xyxy.cpu().tolist() - clss = results[0].boxes.cls.cpu().tolist() - annotator = Annotator(im0, line_width=2, example=names) - - if boxes is not None: - for box, cls in zip(boxes, clss): - idx += 1 - annotator.box_label(box, color=colors(int(cls), True), label=names[int(cls)]) - - crop_obj = im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])] - - cv2.imwrite(os.path.join(crop_dir_name, str(idx)+".png"), crop_obj) - - cv2.imshow("ultralytics", im0) - video_writer.write(im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - ``` - -### Arguments `model.predict` - -| Name | Type | Default | Description | -|-----------------|----------------|------------------------|----------------------------------------------------------------------------| -| `source` | `str` | `'ultralytics/assets'` | source directory for images or videos | -| `conf` | `float` | `0.25` | object confidence threshold for detection | -| `iou` | `float` | `0.7` | intersection over union (IoU) threshold for NMS | -| `imgsz` | `int or tuple` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) | -| `half` | `bool` | `False` | use half precision (FP16) | -| `device` | `None or str` | `None` | device to run on, i.e. cuda device=0/1/2/3 or device=cpu | -| `max_det` | `int` | `300` | maximum number of detections per image | -| `vid_stride` | `bool` | `False` | video frame-rate stride | -| `stream_buffer` | `bool` | `False` | buffer all streaming frames (True) or return the most recent frame (False) | -| `visualize` | `bool` | `False` | visualize model features | -| `augment` | `bool` | `False` | apply image augmentation to prediction sources | -| `agnostic_nms` | `bool` | `False` | class-agnostic NMS | -| `classes` | `list[int]` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `retina_masks` | `bool` | `False` | use high-resolution segmentation masks | -| `embed` | `list[int]` | `None` | return feature vectors/embeddings from given layers | diff --git a/ultralytics-main/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md b/ultralytics-main/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md deleted file mode 100644 index 8231be2..0000000 --- a/ultralytics-main/docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md +++ /dev/null @@ -1,69 +0,0 @@ ---- -comments: true -description: Learn how to optimize Ultralytics YOLOv8 models with Intel OpenVINO for maximum performance. Discover expert techniques to minimize latency and maximize throughput for real-time object detection applications. -keywords: Ultralytics, YOLOv8, OpenVINO, optimization, latency, throughput, inference, object detection, deep learning, machine learning, guide, Intel ---- - -# Optimizing OpenVINO Inference for Ultralytics YOLO Models: A Comprehensive Guide - -OpenVINO Ecosystem - -## Introduction - -When deploying deep learning models, particularly those for object detection such as Ultralytics YOLO models, achieving optimal performance is crucial. This guide delves into leveraging Intel's OpenVINO toolkit to optimize inference, focusing on latency and throughput. Whether you're working on consumer-grade applications or large-scale deployments, understanding and applying these optimization strategies will ensure your models run efficiently on various devices. - -## Optimizing for Latency - -Latency optimization is vital for applications requiring immediate response from a single model given a single input, typical in consumer scenarios. The goal is to minimize the delay between input and inference result. However, achieving low latency involves careful consideration, especially when running concurrent inferences or managing multiple models. - -### Key Strategies for Latency Optimization: - -- **Single Inference per Device:** The simplest way to achieve low latency is by limiting to one inference at a time per device. Additional concurrency often leads to increased latency. -- **Leveraging Sub-Devices:** Devices like multi-socket CPUs or multi-tile GPUs can execute multiple requests with minimal latency increase by utilizing their internal sub-devices. -- **OpenVINO Performance Hints:** Utilizing OpenVINO's `ov::hint::PerformanceMode::LATENCY` for the `ov::hint::performance_mode` property during model compilation simplifies performance tuning, offering a device-agnostic and future-proof approach. - -### Managing First-Inference Latency: - -- **Model Caching:** To mitigate model load and compile times impacting latency, use model caching where possible. For scenarios where caching isn't viable, CPUs generally offer the fastest model load times. -- **Model Mapping vs. Reading:** To reduce load times, OpenVINO replaced model reading with mapping. However, if the model is on a removable or network drive, consider using `ov::enable_mmap(false)` to switch back to reading. -- **AUTO Device Selection:** This mode begins inference on the CPU, shifting to an accelerator once ready, seamlessly reducing first-inference latency. - -## Optimizing for Throughput - -Throughput optimization is crucial for scenarios serving numerous inference requests simultaneously, maximizing resource utilization without significantly sacrificing individual request performance. - -### Approaches to Throughput Optimization: - -1. **OpenVINO Performance Hints:** A high-level, future-proof method to enhance throughput across devices using performance hints. - - ```python - import openvino.properties as props - import openvino.properties.hint as hints - - config = {hints.performance_mode: hints.PerformanceMode.THROUGHPUT} - compiled_model = core.compile_model(model, "GPU", config) - ``` - -2. **Explicit Batching and Streams:** A more granular approach involving explicit batching and the use of streams for advanced performance tuning. - -### Designing Throughput-Oriented Applications: - -To maximize throughput, applications should: - -- Process inputs in parallel, making full use of the device's capabilities. -- Decompose data flow into concurrent inference requests, scheduled for parallel execution. -- Utilize the Async API with callbacks to maintain efficiency and avoid device starvation. - -### Multi-Device Execution: - -OpenVINO's multi-device mode simplifies scaling throughput by automatically balancing inference requests across devices without requiring application-level device management. - -## Conclusion - -Optimizing Ultralytics YOLO models for latency and throughput with OpenVINO can significantly enhance your application's performance. By carefully applying the strategies outlined in this guide, developers can ensure their models run efficiently, meeting the demands of various deployment scenarios. Remember, the choice between optimizing for latency or throughput depends on your specific application needs and the characteristics of the deployment environment. - -For more detailed technical information and the latest updates, refer to the [OpenVINO documentation](https://docs.openvino.ai/latest/index.html) and [Ultralytics YOLO repository](https://github.com/ultralytics/ultralytics). These resources provide in-depth guides, tutorials, and community support to help you get the most out of your deep learning models. - ---- - -Ensuring your models achieve optimal performance is not just about tweaking configurations; it's about understanding your application's needs and making informed decisions. Whether you're optimizing for real-time responses or maximizing throughput for large-scale processing, the combination of Ultralytics YOLO models and OpenVINO offers a powerful toolkit for developers to deploy high-performance AI solutions. diff --git a/ultralytics-main/docs/en/guides/raspberry-pi.md b/ultralytics-main/docs/en/guides/raspberry-pi.md deleted file mode 100644 index 15c37fc..0000000 --- a/ultralytics-main/docs/en/guides/raspberry-pi.md +++ /dev/null @@ -1,196 +0,0 @@ ---- -comments: true -description: Quick start guide to setting up YOLO on a Raspberry Pi with a Pi Camera using the libcamera stack. Detailed comparison between Raspberry Pi 3, 4 and 5 models. -keywords: Ultralytics, YOLO, Raspberry Pi, Pi Camera, libcamera, quick start guide, Raspberry Pi 4 vs Raspberry Pi 5, YOLO on Raspberry Pi, hardware setup, machine learning, AI ---- - -# Quick Start Guide: Raspberry Pi and Pi Camera with YOLOv5 and YOLOv8 - -This comprehensive guide aims to expedite your journey with YOLO object detection models on a [Raspberry Pi](https://www.raspberrypi.com/) using a [Pi Camera](https://www.raspberrypi.com/products/camera-module-v2/). Whether you're a student, hobbyist, or a professional, this guide is designed to get you up and running in less than 30 minutes. The instructions here are rigorously tested to minimize setup issues, allowing you to focus on utilizing YOLO for your specific projects. - -

-
- -
- Watch: Raspberry Pi 5 updates and improvements. -

- -## Prerequisites - -- Raspberry Pi 3, 4 or 5 -- Pi Camera -- 64-bit Raspberry Pi Operating System - -Connect the Pi Camera to your Raspberry Pi via a CSI cable and install the 64-bit Raspberry Pi Operating System. Verify your camera with the following command: - -```bash -libcamera-hello -``` - -You should see a video feed from your camera. - -## Choose Your YOLO Version: YOLOv5 or YOLOv8 - -This guide offers you the flexibility to start with either [YOLOv5](https://github.com/ultralytics/yolov5) or [YOLOv8](https://github.com/ultralytics/ultralytics). Both versions have their unique advantages and use-cases. The choice is yours, but remember, the guide's aim is not just quick setup but also a robust foundation for your future work in object detection. - -## Hardware Specifics: At a Glance - -To assist you in making an informed hardware decision, we've summarized the key hardware specifics of Raspberry Pi 3, 4, and 5 in the table below: - -| Feature | Raspberry Pi 3 | Raspberry Pi 4 | Raspberry Pi 5 | -|----------------------------|------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------|----------------------------------------------------------------------| -| **CPU** | 1.2GHz Quad-Core ARM Cortex-A53 | 1.5GHz Quad-core 64-bit ARM Cortex-A72 | 2.4GHz Quad-core 64-bit Arm Cortex-A76 | -| **RAM** | 1GB LPDDR2 | 2GB, 4GB or 8GB LPDDR4 | *Details not yet available* | -| **USB Ports** | 4 x USB 2.0 | 2 x USB 2.0, 2 x USB 3.0 | 2 x USB 3.0, 2 x USB 2.0 | -| **Network** | Ethernet & Wi-Fi 802.11n | Gigabit Ethernet & Wi-Fi 802.11ac | Gigabit Ethernet with PoE+ support, Dual-band 802.11ac Wi-Fi® | -| **Performance** | Slower, may require lighter YOLO models | Faster, can run complex YOLO models | *Details not yet available* | -| **Power Requirement** | 2.5A power supply | 3.0A USB-C power supply | *Details not yet available* | -| **Official Documentation** | [Link](https://www.raspberrypi.org/documentation/hardware/raspberrypi/bcm2837/README.md) | [Link](https://www.raspberrypi.org/documentation/hardware/raspberrypi/bcm2711/README.md) | [Link](https://www.raspberrypi.com/news/introducing-raspberry-pi-5/) | - -Please make sure to follow the instructions specific to your Raspberry Pi model to ensure a smooth setup process. - -## Quick Start with YOLOv5 - -This section outlines how to set up YOLOv5 on a Raspberry Pi with a Pi Camera. These steps are designed to be compatible with the libcamera camera stack introduced in Raspberry Pi OS Bullseye. - -### Install Necessary Packages - -1. Update the Raspberry Pi: - - ```bash - sudo apt-get update - sudo apt-get upgrade -y - sudo apt-get autoremove -y - ``` - -2. Clone the YOLOv5 repository: - - ```bash - cd ~ - git clone https://github.com/Ultralytics/yolov5.git - ``` - -3. Install the required dependencies: - - ```bash - cd ~/yolov5 - pip3 install -r requirements.txt - ``` - -4. For Raspberry Pi 3, install compatible versions of PyTorch and Torchvision (skip for Raspberry Pi 4): - - ```bash - pip3 uninstall torch torchvision - pip3 install torch==1.11.0 torchvision==0.12.0 - ``` - -### Modify `detect.py` - -To enable TCP streams via SSH or the CLI, minor modifications are needed in `detect.py`. - -1. Open `detect.py`: - - ```bash - sudo nano ~/yolov5/detect.py - ``` - -2. Find and modify the `is_url` line to accept TCP streams: - - ```python - is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://', 'tcp://')) - ``` - -3. Comment out the `view_img` line: - - ```python - # view_img = check_imshow(warn=True) - ``` - -4. Save and exit: - - ```bash - CTRL + O -> ENTER -> CTRL + X - ``` - -### Initiate TCP Stream with Libcamera - -1. Start the TCP stream: - - ```bash - libcamera-vid -n -t 0 --width 1280 --height 960 --framerate 1 --inline --listen -o tcp://127.0.0.1:8888 - ``` - -Keep this terminal session running for the next steps. - -### Perform YOLOv5 Inference - -1. Run the YOLOv5 detection: - - ```bash - cd ~/yolov5 - python3 detect.py --source=tcp://127.0.0.1:8888 - ``` - -## Quick Start with YOLOv8 - -Follow this section if you are interested in setting up YOLOv8 instead. The steps are quite similar but are tailored for YOLOv8's specific needs. - -### Install Necessary Packages - -1. Update the Raspberry Pi: - - ```bash - sudo apt-get update - sudo apt-get upgrade -y - sudo apt-get autoremove -y - ``` - -2. Install the `ultralytics` Python package: - - ```bash - pip3 install ultralytics - ``` - -3. Reboot: - - ```bash - sudo reboot - ``` - -### Initiate TCP Stream with Libcamera - -1. Start the TCP stream: - - ```bash - libcamera-vid -n -t 0 --width 1280 --height 960 --framerate 1 --inline --listen -o tcp://127.0.0.1:8888 - ``` - -### Perform YOLOv8 Inference - -To perform inference with YOLOv8, you can use the following Python code snippet: - -```python -from ultralytics import YOLO - -model = YOLO('yolov8n.pt') -results = model('tcp://127.0.0.1:8888', stream=True) - -while True: - for result in results: - boxes = result.boxes - probs = result.probs -``` - -## Next Steps - -Congratulations on successfully setting up YOLO on your Raspberry Pi! For further learning and support, visit [Ultralytics](https://ultralytics.com/) and [Kashmir World Foundation](https://www.kashmirworldfoundation.org/). - -## Acknowledgements and Citations - -This guide was initially created by Daan Eeltink for Kashmir World Foundation, an organization dedicated to the use of YOLO for the conservation of endangered species. We acknowledge their pioneering work and educational focus in the realm of object detection technologies. - -For more information about Kashmir World Foundation's activities, you can visit their [website](https://www.kashmirworldfoundation.org/). diff --git a/ultralytics-main/docs/en/guides/region-counting.md b/ultralytics-main/docs/en/guides/region-counting.md deleted file mode 100644 index 7a922eb..0000000 --- a/ultralytics-main/docs/en/guides/region-counting.md +++ /dev/null @@ -1,86 +0,0 @@ ---- -comments: true -description: Object Counting in Different Region using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Object Counting, Object Tracking, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Object Counting in Different Regions using Ultralytics YOLOv8 🚀 - -## What is Object Counting in Regions? - -[Object counting](https://docs.ultralytics.com/guides/object-counting/) in regions with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) involves precisely determining the number of objects within specified areas using advanced computer vision. This approach is valuable for optimizing processes, enhancing security, and improving efficiency in various applications. - -

-
- -
- Watch: Ultralytics YOLOv8 Object Counting in Multiple & Movable Regions -

- -## Advantages of Object Counting in Regions? - -- **Precision and Accuracy:** Object counting in regions with advanced computer vision ensures precise and accurate counts, minimizing errors often associated with manual counting. -- **Efficiency Improvement:** Automated object counting enhances operational efficiency, providing real-time results and streamlining processes across different applications. -- **Versatility and Application:** The versatility of object counting in regions makes it applicable across various domains, from manufacturing and surveillance to traffic monitoring, contributing to its widespread utility and effectiveness. - -## Real World Applications - -| Retail | Market Streets | -|:------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![People Counting in Different Region using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/5ab3bbd7-fd12-4849-928e-5f294d6c3fcf) | ![Crowd Counting in Different Region using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/e7c1aea7-474d-4d78-8d48-b50854ffe1ca) | -| People Counting in Different Region using Ultralytics YOLOv8 | Crowd Counting in Different Region using Ultralytics YOLOv8 | - -## Steps to Run - -### Step 1: Install Required Libraries - -Begin by cloning the Ultralytics repository, installing dependencies, and navigating to the local directory using the provided commands in Step 2. - -```bash -# Clone Ultralytics repo -git clone https://github.com/ultralytics/ultralytics - -# Navigate to the local directory -cd ultralytics/examples/YOLOv8-Region-Counter -``` - -### Step 2: Run Region Counting Using Ultralytics YOLOv8 - -Execute the following basic commands for inference. - -???+ tip "Region is Movable" - - During video playback, you can interactively move the region within the video by clicking and dragging using the left mouse button. - -```bash -# Save results -python yolov8_region_counter.py --source "path/to/video.mp4" --save-img - -# Run model on CPU -python yolov8_region_counter.py --source "path/to/video.mp4" --device cpu - -# Change model file -python yolov8_region_counter.py --source "path/to/video.mp4" --weights "path/to/model.pt" - -# Detect specific classes (e.g., first and third classes) -python yolov8_region_counter.py --source "path/to/video.mp4" --classes 0 2 - -# View results without saving -python yolov8_region_counter.py --source "path/to/video.mp4" --view-img -``` - -### Optional Arguments - -| Name | Type | Default | Description | -|----------------------|--------|--------------|--------------------------------------------| -| `--source` | `str` | `None` | Path to video file, for webcam 0 | -| `--line_thickness` | `int` | `2` | Bounding Box thickness | -| `--save-img` | `bool` | `False` | Save the predicted video/image | -| `--weights` | `str` | `yolov8n.pt` | Weights file path | -| `--classes` | `list` | `None` | Detect specific classes i.e. --classes 0 2 | -| `--region-thickness` | `int` | `2` | Region Box thickness | -| `--track-thickness` | `int` | `2` | Tracking line thickness | diff --git a/ultralytics-main/docs/en/guides/sahi-tiled-inference.md b/ultralytics-main/docs/en/guides/sahi-tiled-inference.md deleted file mode 100644 index 9728703..0000000 --- a/ultralytics-main/docs/en/guides/sahi-tiled-inference.md +++ /dev/null @@ -1,185 +0,0 @@ ---- -comments: true -description: A comprehensive guide on how to use YOLOv8 with SAHI for standard and sliced inference in object detection tasks. -keywords: YOLOv8, SAHI, Sliced Inference, Object Detection, Ultralytics, Large Scale Image Analysis, High-Resolution Imagery ---- - -# Ultralytics Docs: Using YOLOv8 with SAHI for Sliced Inference - -Welcome to the Ultralytics documentation on how to use YOLOv8 with [SAHI](https://github.com/obss/sahi) (Slicing Aided Hyper Inference). This comprehensive guide aims to furnish you with all the essential knowledge you'll need to implement SAHI alongside YOLOv8. We'll deep-dive into what SAHI is, why sliced inference is critical for large-scale applications, and how to integrate these functionalities with YOLOv8 for enhanced object detection performance. - -

- SAHI Sliced Inference Overview -

- -## Introduction to SAHI - -SAHI (Slicing Aided Hyper Inference) is an innovative library designed to optimize object detection algorithms for large-scale and high-resolution imagery. Its core functionality lies in partitioning images into manageable slices, running object detection on each slice, and then stitching the results back together. SAHI is compatible with a range of object detection models, including the YOLO series, thereby offering flexibility while ensuring optimized use of computational resources. - -### Key Features of SAHI - -- **Seamless Integration**: SAHI integrates effortlessly with YOLO models, meaning you can start slicing and detecting without a lot of code modification. -- **Resource Efficiency**: By breaking down large images into smaller parts, SAHI optimizes the memory usage, allowing you to run high-quality detection on hardware with limited resources. -- **High Accuracy**: SAHI maintains the detection accuracy by employing smart algorithms to merge overlapping detection boxes during the stitching process. - -## What is Sliced Inference? - -Sliced Inference refers to the practice of subdividing a large or high-resolution image into smaller segments (slices), conducting object detection on these slices, and then recompiling the slices to reconstruct the object locations on the original image. This technique is invaluable in scenarios where computational resources are limited or when working with extremely high-resolution images that could otherwise lead to memory issues. - -### Benefits of Sliced Inference - -- **Reduced Computational Burden**: Smaller image slices are faster to process, and they consume less memory, enabling smoother operation on lower-end hardware. - -- **Preserved Detection Quality**: Since each slice is treated independently, there is no reduction in the quality of object detection, provided the slices are large enough to capture the objects of interest. - -- **Enhanced Scalability**: The technique allows for object detection to be more easily scaled across different sizes and resolutions of images, making it ideal for a wide range of applications from satellite imagery to medical diagnostics. - - - - - - - - - - -
YOLOv8 without SAHIYOLOv8 with SAHI
YOLOv8 without SAHIYOLOv8 with SAHI
- -## Installation and Preparation - -### Installation - -To get started, install the latest versions of SAHI and Ultralytics: - -```bash -pip install -U ultralytics sahi -``` - -### Import Modules and Download Resources - -Here's how to import the necessary modules and download a YOLOv8 model and some test images: - -```python -from sahi.utils.yolov8 import download_yolov8s_model -from sahi import AutoDetectionModel -from sahi.utils.cv import read_image -from sahi.utils.file import download_from_url -from sahi.predict import get_prediction, get_sliced_prediction, predict -from pathlib import Path -from IPython.display import Image - -# Download YOLOv8 model -yolov8_model_path = "models/yolov8s.pt" -download_yolov8s_model(yolov8_model_path) - -# Download test images -download_from_url('https://raw.githubusercontent.com/obss/sahi/main/demo/demo_data/small-vehicles1.jpeg', 'demo_data/small-vehicles1.jpeg') -download_from_url('https://raw.githubusercontent.com/obss/sahi/main/demo/demo_data/terrain2.png', 'demo_data/terrain2.png') -``` - -## Standard Inference with YOLOv8 - -### Instantiate the Model - -You can instantiate a YOLOv8 model for object detection like this: - -```python -detection_model = AutoDetectionModel.from_pretrained( - model_type='yolov8', - model_path=yolov8_model_path, - confidence_threshold=0.3, - device="cpu", # or 'cuda:0' -) -``` - -### Perform Standard Prediction - -Perform standard inference using an image path or a numpy image. - -```python -# With an image path -result = get_prediction("demo_data/small-vehicles1.jpeg", detection_model) - -# With a numpy image -result = get_prediction(read_image("demo_data/small-vehicles1.jpeg"), detection_model) -``` - -### Visualize Results - -Export and visualize the predicted bounding boxes and masks: - -```python -result.export_visuals(export_dir="demo_data/") -Image("demo_data/prediction_visual.png") -``` - -## Sliced Inference with YOLOv8 - -Perform sliced inference by specifying the slice dimensions and overlap ratios: - -```python -result = get_sliced_prediction( - "demo_data/small-vehicles1.jpeg", - detection_model, - slice_height=256, - slice_width=256, - overlap_height_ratio=0.2, - overlap_width_ratio=0.2 -) -``` - -## Handling Prediction Results - -SAHI provides a `PredictionResult` object, which can be converted into various annotation formats: - -```python -# Access the object prediction list -object_prediction_list = result.object_prediction_list - -# Convert to COCO annotation, COCO prediction, imantics, and fiftyone formats -result.to_coco_annotations()[:3] -result.to_coco_predictions(image_id=1)[:3] -result.to_imantics_annotations()[:3] -result.to_fiftyone_detections()[:3] -``` - -## Batch Prediction - -For batch prediction on a directory of images: - -```python -predict( - model_type="yolov8", - model_path="path/to/yolov8n.pt", - model_device="cpu", # or 'cuda:0' - model_confidence_threshold=0.4, - source="path/to/dir", - slice_height=256, - slice_width=256, - overlap_height_ratio=0.2, - overlap_width_ratio=0.2, -) -``` - -That's it! Now you're equipped to use YOLOv8 with SAHI for both standard and sliced inference. - -## Citations and Acknowledgments - -If you use SAHI in your research or development work, please cite the original SAHI paper and acknowledge the authors: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{akyon2022sahi, - title={Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection}, - author={Akyon, Fatih Cagatay and Altinuc, Sinan Onur and Temizel, Alptekin}, - journal={2022 IEEE International Conference on Image Processing (ICIP)}, - doi={10.1109/ICIP46576.2022.9897990}, - pages={966-970}, - year={2022} - } - ``` - -We extend our thanks to the SAHI research group for creating and maintaining this invaluable resource for the computer vision community. For more information about SAHI and its creators, visit the [SAHI GitHub repository](https://github.com/obss/sahi). diff --git a/ultralytics-main/docs/en/guides/security-alarm-system.md b/ultralytics-main/docs/en/guides/security-alarm-system.md deleted file mode 100644 index c572822..0000000 --- a/ultralytics-main/docs/en/guides/security-alarm-system.md +++ /dev/null @@ -1,166 +0,0 @@ ---- -comments: true -description: Security Alarm System Project Using Ultralytics YOLOv8. Learn How to implement a Security Alarm System Using ultralytics YOLOv8 -keywords: Object Detection, Security Alarm, Object Tracking, YOLOv8, Computer Vision Projects ---- - -# Security Alarm System Project Using Ultralytics YOLOv8 - -Security Alarm System - -The Security Alarm System Project utilizing Ultralytics YOLOv8 integrates advanced computer vision capabilities to enhance security measures. YOLOv8, developed by Ultralytics, provides real-time object detection, allowing the system to identify and respond to potential security threats promptly. This project offers several advantages: - -- **Real-time Detection:** YOLOv8's efficiency enables the Security Alarm System to detect and respond to security incidents in real-time, minimizing response time. -- **Accuracy:** YOLOv8 is known for its accuracy in object detection, reducing false positives and enhancing the reliability of the security alarm system. -- **Integration Capabilities:** The project can be seamlessly integrated with existing security infrastructure, providing an upgraded layer of intelligent surveillance. - -

-
- -
- Watch: Security Alarm System Project with Ultralytics YOLOv8 Object Detection -

- -### Code - -#### Import Libraries - -```python -import torch -import numpy as np -import cv2 -from time import time -from ultralytics import YOLO -from ultralytics.utils.plotting import Annotator, colors -import smtplib -from email.mime.multipart import MIMEMultipart -from email.mime.text import MIMEText -``` - -#### Set up the parameters of the message - -???+ tip "Note" - - App Password Generation is necessary - -- Navigate to [App Password Generator](https://myaccount.google.com/apppasswords), designate an app name such as "security project," and obtain a 16-digit password. Copy this password and paste it into the designated password field as instructed. - -```python -password = "" -from_email = "" # must match the email used to generate the password -to_email = "" # receiver email -``` - -#### Server creation and authentication - -```python -server = smtplib.SMTP('smtp.gmail.com: 587') -server.starttls() -server.login(from_email, password) -``` - -#### Email Send Function - -```python -def send_email(to_email, from_email, object_detected=1): - message = MIMEMultipart() - message['From'] = from_email - message['To'] = to_email - message['Subject'] = "Security Alert" - # Add in the message body - message_body = f'ALERT - {object_detected} objects has been detected!!' - - message.attach(MIMEText(message_body, 'plain')) - server.sendmail(from_email, to_email, message.as_string()) -``` - -#### Object Detection and Alert Sender - -```python -class ObjectDetection: - def __init__(self, capture_index): - # default parameters - self.capture_index = capture_index - self.email_sent = False - - # model information - self.model = YOLO("yolov8n.pt") - - # visual information - self.annotator = None - self.start_time = 0 - self.end_time = 0 - - # device information - self.device = 'cuda' if torch.cuda.is_available() else 'cpu' - - def predict(self, im0): - results = self.model(im0) - return results - - def display_fps(self, im0): - self.end_time = time() - fps = 1 / np.round(self.end_time - self.start_time, 2) - text = f'FPS: {int(fps)}' - text_size = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 1.0, 2)[0] - gap = 10 - cv2.rectangle(im0, (20 - gap, 70 - text_size[1] - gap), (20 + text_size[0] + gap, 70 + gap), (255, 255, 255), -1) - cv2.putText(im0, text, (20, 70), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 2) - - def plot_bboxes(self, results, im0): - class_ids = [] - self.annotator = Annotator(im0, 3, results[0].names) - boxes = results[0].boxes.xyxy.cpu() - clss = results[0].boxes.cls.cpu().tolist() - names = results[0].names - for box, cls in zip(boxes, clss): - class_ids.append(cls) - self.annotator.box_label(box, label=names[int(cls)], color=colors(int(cls), True)) - return im0, class_ids - - def __call__(self): - cap = cv2.VideoCapture(self.capture_index) - assert cap.isOpened() - cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640) - cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480) - frame_count = 0 - while True: - self.start_time = time() - ret, im0 = cap.read() - assert ret - results = self.predict(im0) - im0, class_ids = self.plot_bboxes(results, im0) - - if len(class_ids) > 0: # Only send email If not sent before - if not self.email_sent: - send_email(to_email, from_email, len(class_ids)) - self.email_sent = True - else: - self.email_sent = False - - self.display_fps(im0) - cv2.imshow('YOLOv8 Detection', im0) - frame_count += 1 - if cv2.waitKey(5) & 0xFF == 27: - break - cap.release() - cv2.destroyAllWindows() - server.quit() -``` - -#### Call the Object Detection class and Run the Inference - -```python -detector = ObjectDetection(capture_index=0) -detector() -``` - -That's it! When you execute the code, you'll receive a single notification on your email if any object is detected. The notification is sent immediately, not repeatedly. However, feel free to customize the code to suit your project requirements. - -#### Email Received Sample - -Email Received Sample diff --git a/ultralytics-main/docs/en/guides/speed-estimation.md b/ultralytics-main/docs/en/guides/speed-estimation.md deleted file mode 100644 index de3f527..0000000 --- a/ultralytics-main/docs/en/guides/speed-estimation.md +++ /dev/null @@ -1,110 +0,0 @@ ---- -comments: true -description: Speed Estimation Using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Speed Estimation, Object Tracking, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Speed Estimation using Ultralytics YOLOv8 🚀 - -## What is Speed Estimation? - -Speed estimation is the process of calculating the rate of movement of an object within a given context, often employed in computer vision applications. Using [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) you can now calculate the speed of object using [object tracking](https://docs.ultralytics.com/modes/track/) alongside distance and time data, crucial for tasks like traffic and surveillance. The accuracy of speed estimation directly influences the efficiency and reliability of various applications, making it a key component in the advancement of intelligent systems and real-time decision-making processes. - -

-
- -
- Watch: Speed Estimation using Ultralytics YOLOv8 -

- -## Advantages of Speed Estimation? - -- **Efficient Traffic Control:** Accurate speed estimation aids in managing traffic flow, enhancing safety, and reducing congestion on roadways. -- **Precise Autonomous Navigation:** In autonomous systems like self-driving cars, reliable speed estimation ensures safe and accurate vehicle navigation. -- **Enhanced Surveillance Security:** Speed estimation in surveillance analytics helps identify unusual behaviors or potential threats, improving the effectiveness of security measures. - -## Real World Applications - -| Transportation | Transportation | -|:-------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![Speed Estimation on Road using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/c8a0fd4a-d394-436d-8de3-d5b754755fc7) | ![Speed Estimation on Bridge using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/cee10e02-b268-4304-b73a-5b9cb42da669) | -| Speed Estimation on Road using Ultralytics YOLOv8 | Speed Estimation on Bridge using Ultralytics YOLOv8 | - -!!! Example "Speed Estimation using YOLOv8 Example" - - === "Speed Estimation" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import speed_estimation - import cv2 - - model = YOLO("yolov8n.pt") - names = model.model.names - - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - # Video writer - video_writer = cv2.VideoWriter("speed_estimation.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - line_pts = [(0, 360), (1280, 360)] - - # Init speed-estimation obj - speed_obj = speed_estimation.SpeedEstimator() - speed_obj.set_args(reg_pts=line_pts, - names=names, - view_img=True) - - while cap.isOpened(): - - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - - tracks = model.track(im0, persist=True, show=False) - - im0 = speed_obj.estimate_speed(im0, tracks) - video_writer.write(im0) - - cap.release() - video_writer.release() - cv2.destroyAllWindows() - - ``` - -???+ warning "Speed is Estimate" - - Speed will be an estimate and may not be completely accurate. Additionally, the estimation can vary depending on GPU speed. - -### Optional Arguments `set_args` - -| Name | Type | Default | Description | -|--------------------|--------|----------------------------|---------------------------------------------------| -| `reg_pts` | `list` | `[(20, 400), (1260, 400)]` | Points defining the Region Area | -| `names` | `dict` | `None` | Classes names | -| `view_img` | `bool` | `False` | Display frames with counts | -| `line_thickness` | `int` | `2` | Increase bounding boxes thickness | -| `region_thickness` | `int` | `5` | Thickness for object counter region or line | -| `spdl_dist_thresh` | `int` | `10` | Euclidean Distance threshold for speed check line | - -### Arguments `model.track` - -| Name | Type | Default | Description | -|-----------|---------|----------------|-------------------------------------------------------------| -| `source` | `im0` | `None` | source directory for images or videos | -| `persist` | `bool` | `False` | persisting tracks between frames | -| `tracker` | `str` | `botsort.yaml` | Tracking method 'bytetrack' or 'botsort' | -| `conf` | `float` | `0.3` | Confidence Threshold | -| `iou` | `float` | `0.5` | IOU Threshold | -| `classes` | `list` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `verbose` | `bool` | `True` | Display the object tracking results | diff --git a/ultralytics-main/docs/en/guides/triton-inference-server.md b/ultralytics-main/docs/en/guides/triton-inference-server.md deleted file mode 100644 index 6f3b1d2..0000000 --- a/ultralytics-main/docs/en/guides/triton-inference-server.md +++ /dev/null @@ -1,137 +0,0 @@ ---- -comments: true -description: A step-by-step guide on integrating Ultralytics YOLOv8 with Triton Inference Server for scalable and high-performance deep learning inference deployments. -keywords: YOLOv8, Triton Inference Server, ONNX, Deep Learning Deployment, Scalable Inference, Ultralytics, NVIDIA, Object Detection, Cloud Inference ---- - -# Triton Inference Server with Ultralytics YOLOv8 - -The [Triton Inference Server](https://developer.nvidia.com/nvidia-triton-inference-server) (formerly known as TensorRT Inference Server) is an open-source software solution developed by NVIDIA. It provides a cloud inference solution optimized for NVIDIA GPUs. Triton simplifies the deployment of AI models at scale in production. Integrating Ultralytics YOLOv8 with Triton Inference Server allows you to deploy scalable, high-performance deep learning inference workloads. This guide provides steps to set up and test the integration. - -

-
- -
- Watch: Getting Started with NVIDIA Triton Inference Server. -

- -## What is Triton Inference Server? - -Triton Inference Server is designed to deploy a variety of AI models in production. It supports a wide range of deep learning and machine learning frameworks, including TensorFlow, PyTorch, ONNX Runtime, and many others. Its primary use cases are: - -- Serving multiple models from a single server instance. -- Dynamic model loading and unloading without server restart. -- Ensemble inference, allowing multiple models to be used together to achieve results. -- Model versioning for A/B testing and rolling updates. - -## Prerequisites - -Ensure you have the following prerequisites before proceeding: - -- Docker installed on your machine. -- Install `tritonclient`: - ```bash - pip install tritonclient[all] - ``` - -## Exporting YOLOv8 to ONNX Format - -Before deploying the model on Triton, it must be exported to the ONNX format. ONNX (Open Neural Network Exchange) is a format that allows models to be transferred between different deep learning frameworks. Use the `export` function from the `YOLO` class: - -```python -from ultralytics import YOLO - -# Load a model -model = YOLO('yolov8n.pt') # load an official model - -# Export the model -onnx_file = model.export(format='onnx', dynamic=True) -``` - -## Setting Up Triton Model Repository - -The Triton Model Repository is a storage location where Triton can access and load models. - -1. Create the necessary directory structure: - - ```python - from pathlib import Path - - # Define paths - triton_repo_path = Path('tmp') / 'triton_repo' - triton_model_path = triton_repo_path / 'yolo' - - # Create directories - (triton_model_path / '1').mkdir(parents=True, exist_ok=True) - ``` - -2. Move the exported ONNX model to the Triton repository: - - ```python - from pathlib import Path - - # Move ONNX model to Triton Model path - Path(onnx_file).rename(triton_model_path / '1' / 'model.onnx') - - # Create config file - (triton_model_path / 'config.pbtxt').touch() - ``` - -## Running Triton Inference Server - -Run the Triton Inference Server using Docker: - -```python -import subprocess -import time - -from tritonclient.http import InferenceServerClient - -# Define image https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver -tag = 'nvcr.io/nvidia/tritonserver:23.09-py3' # 6.4 GB - -# Pull the image -subprocess.call(f'docker pull {tag}', shell=True) - -# Run the Triton server and capture the container ID -container_id = subprocess.check_output( - f'docker run -d --rm -v {triton_repo_path}:/models -p 8000:8000 {tag} tritonserver --model-repository=/models', - shell=True).decode('utf-8').strip() - -# Wait for the Triton server to start -triton_client = InferenceServerClient(url='localhost:8000', verbose=False, ssl=False) - -# Wait until model is ready -for _ in range(10): - with contextlib.suppress(Exception): - assert triton_client.is_model_ready(model_name) - break - time.sleep(1) -``` - -Then run inference using the Triton Server model: - -```python -from ultralytics import YOLO - -# Load the Triton Server model -model = YOLO(f'http://localhost:8000/yolo', task='detect') - -# Run inference on the server -results = model('path/to/image.jpg') -``` - -Cleanup the container: - -```python -# Kill and remove the container at the end of the test -subprocess.call(f'docker kill {container_id}', shell=True) -``` - ---- - -By following the above steps, you can deploy and run Ultralytics YOLOv8 models efficiently on Triton Inference Server, providing a scalable and high-performance solution for deep learning inference tasks. If you face any issues or have further queries, refer to the [official Triton documentation](https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html) or reach out to the Ultralytics community for support. diff --git a/ultralytics-main/docs/en/guides/view-results-in-terminal.md b/ultralytics-main/docs/en/guides/view-results-in-terminal.md deleted file mode 100644 index d0a00bb..0000000 --- a/ultralytics-main/docs/en/guides/view-results-in-terminal.md +++ /dev/null @@ -1,146 +0,0 @@ ---- -comments: true -description: Learn how to view image results inside a compatible VSCode terminal. -keywords: YOLOv8, VSCode, Terminal, Remote Development, Ultralytics, SSH, Object Detection, Inference, Results, Remote Tunnel, Images, Helpful, Productivity Hack ---- - -# Viewing Inference Results in a Terminal - -

- Sixel example of image in Terminal -

- -Image from the the [libsixel](https://saitoha.github.io/libsixel/) website. - -## Motivation - -When connecting to a remote machine, normally visualizing image results is not possible or requires moving data to a local device with a GUI. The VSCode integrated terminal allows for directly rendering images. This is a short demonstration on how to use this in conjunction with `ultralytics` with [prediction results](../modes/predict.md). - -!!! warning - - Only compatible with Linux and MacOS. Check the VSCode [repository](https://github.com/microsoft/vscode), check [Issue status](https://github.com/microsoft/vscode/issues/198622), or [documentation](https://code.visualstudio.com/docs) for updates about Windows support to view images in terminal with `sixel`. - -The VSCode compatible protocols for viewing images using the integrated terminal are [`sixel`](https://en.wikipedia.org/wiki/Sixel) and [`iTerm`](https://iterm2.com/documentation-images.html). This guide will demonstrate use of the `sixel` protocol. - -## Process - -1. First, you must enable settings `terminal.integrated.enableImages` and `terminal.integrated.gpuAcceleration` in VSCode. - - ```yaml - "terminal.integrated.gpuAcceleration": "auto" # "auto" is default, can also use "on" - "terminal.integrated.enableImages": false - ``` - -

- VSCode enable terminal images setting -

- -1. Install the `python-sixel` library in your virtual environment. This is a [fork](https://github.com/lubosz/python-sixel?tab=readme-ov-file) of the `PySixel` library, which is no longer maintained. - - ```bash - pip install sixel - ``` - -1. Import the relevant libraries - - ```py - import io - - import cv2 as cv - - from ultralytics import YOLO - from sixel import SixelWriter - ``` - -1. Load a model and execute inference, then plot the results and store in a variable. See more about inference arguments and working with results on the [predict mode](../modes/predict.md) page. - - ```{ .py .annotate } - from ultralytics import YOLO - - # Load a model - model = YOLO("yolov8n.pt") - - # Run inference on an image - results = model.predict(source="ultralytics/assets/bus.jpg") - - # Plot inference results - plot = results[0].plot() #(1)! - ``` - - 1. See [plot method parameters](../modes/predict.md#plot-method-parameters) to see possible arguments to use. - -1. Now, use OpenCV to convert the `numpy.ndarray` to `bytes` data. Then use `io.BytesIO` to make a "file-like" object. - - ```{ .py .annotate } - # Results image as bytes - im_bytes = cv.imencode( - ".png", #(1)! - plot, - )[1].tobytes() #(2)! - - # Image bytes as a file-like object - mem_file = io.BytesIO(im_bytes) - ``` - - 1. It's possible to use other image extensions as well. - 2. Only the object at index `1` that is returned is needed. - -1. Create a `SixelWriter` instance, and then use the `.draw()` method to draw the image in the terminal. - - ```py - # Create sixel writer object - w = SixelWriter() - - # Draw the sixel image in the terminal - w.draw(mem_file) - ``` - -## Example Inference Results - -

- View Image in Terminal -

- -!!! danger - - Using this example with videos or animated GIF frames has **not** been tested. Attempt at your own risk. - -## Full Code Example - -```{ .py .annotate } -import io - -import cv2 as cv - -from ultralytics import YOLO -from sixel import SixelWriter - -# Load a model -model = YOLO("yolov8n.pt") - -# Run inference on an image -results = model.predict(source="ultralytics/assets/bus.jpg") - -# Plot inference results -plot = results[0].plot() #(3)! - -# Results image as bytes -im_bytes = cv.imencode( - ".png", #(1)! - plot, - )[1].tobytes() #(2)! - -mem_file = io.BytesIO(im_bytes) -w = SixelWriter() -w.draw(mem_file) -``` - -1. It's possible to use other image extensions as well. -2. Only the object at index `1` that is returned is needed. -3. See [plot method parameters](../modes/predict.md#plot-method-parameters) to see possible arguments to use. - ---- - -!!! tip - - You may need to use `clear` to "erase" the view of the image in the terminal. diff --git a/ultralytics-main/docs/en/guides/vision-eye.md b/ultralytics-main/docs/en/guides/vision-eye.md deleted file mode 100644 index 3001772..0000000 --- a/ultralytics-main/docs/en/guides/vision-eye.md +++ /dev/null @@ -1,177 +0,0 @@ ---- -comments: true -description: VisionEye View Object Mapping using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Object Tracking, IDetection, VisionEye, Computer Vision, Notebook, IPython Kernel, CLI, Python SDK ---- - -# VisionEye View Object Mapping using Ultralytics YOLOv8 🚀 - -## What is VisionEye Object Mapping? - -[Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) VisionEye offers the capability for computers to identify and pinpoint objects, simulating the observational precision of the human eye. This functionality enables computers to discern and focus on specific objects, much like the way the human eye observes details from a particular viewpoint. - -## Samples - -| VisionEye View | VisionEye View With Object Tracking | VisionEye View With Distance Calculation | -|:------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| -| ![VisionEye View Object Mapping using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/7d593acc-2e37-41b0-ad0e-92b4ffae6647) | ![VisionEye View Object Mapping with Object Tracking using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/fcd85952-390f-451e-8fb0-b82e943af89c) | ![VisionEye View with Distance Calculation using Ultralytics YOLOv8](https://github.com/RizwanMunawar/RizwanMunawar/assets/62513924/18c4dafe-a22e-4fa9-a7d4-2bb293562a95) | -| VisionEye View Object Mapping using Ultralytics YOLOv8 | VisionEye View Object Mapping with Object Tracking using Ultralytics YOLOv8 | VisionEye View with Distance Calculation using Ultralytics YOLOv8 | - -!!! Example "VisionEye Object Mapping using YOLOv8" - - === "VisionEye Object Mapping" - - ```python - import cv2 - from ultralytics import YOLO - from ultralytics.utils.plotting import colors, Annotator - - model = YOLO("yolov8n.pt") - names = model.model.names - cap = cv2.VideoCapture("path/to/video/file.mp4") - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter('visioneye-pinpoint.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - - center_point = (-10, h) - - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - results = model.predict(im0) - boxes = results[0].boxes.xyxy.cpu() - clss = results[0].boxes.cls.cpu().tolist() - - annotator = Annotator(im0, line_width=2) - - for box, cls in zip(boxes, clss): - annotator.box_label(box, label=names[int(cls)], color=colors(int(cls))) - annotator.visioneye(box, center_point) - - out.write(im0) - cv2.imshow("visioneye-pinpoint", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - out.release() - cap.release() - cv2.destroyAllWindows() - ``` - - === "VisionEye Object Mapping with Object Tracking" - - ```python - import cv2 - from ultralytics import YOLO - from ultralytics.utils.plotting import colors, Annotator - - model = YOLO("yolov8n.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter('visioneye-pinpoint.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - - center_point = (-10, h) - - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - annotator = Annotator(im0, line_width=2) - - results = model.track(im0, persist=True) - boxes = results[0].boxes.xyxy.cpu() - - if results[0].boxes.id is not None: - track_ids = results[0].boxes.id.int().cpu().tolist() - - for box, track_id in zip(boxes, track_ids): - annotator.box_label(box, label=str(track_id), color=colors(int(track_id))) - annotator.visioneye(box, center_point) - - out.write(im0) - cv2.imshow("visioneye-pinpoint", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - out.release() - cap.release() - cv2.destroyAllWindows() - ``` - - === "VisionEye with Distance Calculation" - - ```python - import cv2 - import math - from ultralytics import YOLO - from ultralytics.utils.plotting import Annotator, colors - - model = YOLO("yolov8s.pt") - cap = cv2.VideoCapture("Path/to/video/file.mp4") - - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - out = cv2.VideoWriter('visioneye-distance-calculation.avi', cv2.VideoWriter_fourcc(*'MJPG'), fps, (w, h)) - - center_point = (0, h) - pixel_per_meter = 10 - - txt_color, txt_background, bbox_clr = ((0, 0, 0), (255, 255, 255), (255, 0, 255)) - - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - - annotator = Annotator(im0, line_width=2) - - results = model.track(im0, persist=True) - boxes = results[0].boxes.xyxy.cpu() - - if results[0].boxes.id is not None: - track_ids = results[0].boxes.id.int().cpu().tolist() - - for box, track_id in zip(boxes, track_ids): - annotator.box_label(box, label=str(track_id), color=bbox_clr) - annotator.visioneye(box, center_point) - - x1, y1 = int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2) # Bounding box centroid - - distance = (math.sqrt((x1 - center_point[0]) ** 2 + (y1 - center_point[1]) ** 2))/pixel_per_meter - - text_size, _ = cv2.getTextSize(f"Distance: {distance:.2f} m", cv2.FONT_HERSHEY_SIMPLEX,1.2, 3) - cv2.rectangle(im0, (x1, y1 - text_size[1] - 10),(x1 + text_size[0] + 10, y1), txt_background, -1) - cv2.putText(im0, f"Distance: {distance:.2f} m",(x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 1.2,txt_color, 3) - - out.write(im0) - cv2.imshow("visioneye-distance-calculation", im0) - - if cv2.waitKey(1) & 0xFF == ord('q'): - break - - out.release() - cap.release() - cv2.destroyAllWindows() - ``` - -### `visioneye` Arguments - -| Name | Type | Default | Description | -|---------------|---------|------------------|--------------------------------------------------| -| `color` | `tuple` | `(235, 219, 11)` | Line and object centroid color | -| `pin_color` | `tuple` | `(255, 0, 255)` | VisionEye pinpoint color | -| `thickness` | `int` | `2` | pinpoint to object line thickness | -| `pins_radius` | `int` | `10` | Pinpoint and object centroid point circle radius | - -## Note - -For any inquiries, feel free to post your questions in the [Ultralytics Issue Section](https://github.com/ultralytics/ultralytics/issues/new/choose) or the discussion section mentioned below. diff --git a/ultralytics-main/docs/en/guides/workouts-monitoring.md b/ultralytics-main/docs/en/guides/workouts-monitoring.md deleted file mode 100644 index fd4d7e0..0000000 --- a/ultralytics-main/docs/en/guides/workouts-monitoring.md +++ /dev/null @@ -1,134 +0,0 @@ ---- -comments: true -description: Workouts Monitoring Using Ultralytics YOLOv8 -keywords: Ultralytics, YOLOv8, Object Detection, Pose Estimation, PushUps, PullUps, Ab workouts, Notebook, IPython Kernel, CLI, Python SDK ---- - -# Workouts Monitoring using Ultralytics YOLOv8 🚀 - -Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) enhances exercise assessment by accurately tracking key body landmarks and joints in real-time. This technology provides instant feedback on exercise form, tracks workout routines, and measures performance metrics, optimizing training sessions for users and trainers alike. - -## Advantages of Workouts Monitoring? - -- **Optimized Performance:** Tailoring workouts based on monitoring data for better results. -- **Goal Achievement:** Track and adjust fitness goals for measurable progress. -- **Personalization:** Customized workout plans based on individual data for effectiveness. -- **Health Awareness:** Early detection of patterns indicating health issues or over-training. -- **Informed Decisions:** Data-driven decisions for adjusting routines and setting realistic goals. - -## Real World Applications - -| Workouts Monitoring | Workouts Monitoring | -|:----------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------:| -| ![PushUps Counting](https://github.com/RizwanMunawar/ultralytics/assets/62513924/cf016a41-589f-420f-8a8c-2cc8174a16de) | ![PullUps Counting](https://github.com/RizwanMunawar/ultralytics/assets/62513924/cb20f316-fac2-4330-8445-dcf5ffebe329) | -| PushUps Counting | PullUps Counting | - -!!! Example "Workouts Monitoring Example" - - === "Workouts Monitoring" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import ai_gym - import cv2 - - model = YOLO("yolov8n-pose.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - gym_object = ai_gym.AIGym() # init AI GYM module - gym_object.set_args(line_thickness=2, - view_img=True, - pose_type="pushup", - kpts_to_check=[6, 8, 10]) - - frame_count = 0 - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - frame_count += 1 - results = model.predict(im0, verbose=False) - im0 = gym_object.start_counting(im0, results, frame_count) - - cv2.destroyAllWindows() - ``` - - === "Workouts Monitoring with Save Output" - - ```python - from ultralytics import YOLO - from ultralytics.solutions import ai_gym - import cv2 - - model = YOLO("yolov8n-pose.pt") - cap = cv2.VideoCapture("path/to/video/file.mp4") - assert cap.isOpened(), "Error reading video file" - w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS)) - - video_writer = cv2.VideoWriter("workouts.avi", - cv2.VideoWriter_fourcc(*'mp4v'), - fps, - (w, h)) - - gym_object = ai_gym.AIGym() # init AI GYM module - gym_object.set_args(line_thickness=2, - view_img=True, - pose_type="pushup", - kpts_to_check=[6, 8, 10]) - - frame_count = 0 - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - frame_count += 1 - results = model.predict(im0, verbose=False) - im0 = gym_object.start_counting(im0, results, frame_count) - video_writer.write(im0) - - cv2.destroyAllWindows() - video_writer.release() - ``` - -???+ tip "Support" - - "pushup", "pullup" and "abworkout" supported - -### KeyPoints Map - -![keyPoints Order Ultralytics YOLOv8 Pose](https://github.com/ultralytics/ultralytics/assets/62513924/f45d8315-b59f-47b7-b9c8-c61af1ce865b) - -### Arguments `set_args` - -| Name | Type | Default | Description | -|-------------------|--------|----------|----------------------------------------------------------------------------------------| -| `kpts_to_check` | `list` | `None` | List of three keypoints index, for counting specific workout, followed by keypoint Map | -| `view_img` | `bool` | `False` | Display the frame with counts | -| `line_thickness` | `int` | `2` | Increase the thickness of count value | -| `pose_type` | `str` | `pushup` | Pose that need to be monitored, `pullup` and `abworkout` also supported | -| `pose_up_angle` | `int` | `145` | Pose Up Angle value | -| `pose_down_angle` | `int` | `90` | Pose Down Angle value | - -### Arguments `model.predict` - -| Name | Type | Default | Description | -|-----------------|----------------|------------------------|----------------------------------------------------------------------------| -| `source` | `str` | `'ultralytics/assets'` | source directory for images or videos | -| `conf` | `float` | `0.25` | object confidence threshold for detection | -| `iou` | `float` | `0.7` | intersection over union (IoU) threshold for NMS | -| `imgsz` | `int or tuple` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) | -| `half` | `bool` | `False` | use half precision (FP16) | -| `device` | `None or str` | `None` | device to run on, i.e. cuda device=0/1/2/3 or device=cpu | -| `max_det` | `int` | `300` | maximum number of detections per image | -| `vid_stride` | `bool` | `False` | video frame-rate stride | -| `stream_buffer` | `bool` | `False` | buffer all streaming frames (True) or return the most recent frame (False) | -| `visualize` | `bool` | `False` | visualize model features | -| `augment` | `bool` | `False` | apply image augmentation to prediction sources | -| `agnostic_nms` | `bool` | `False` | class-agnostic NMS | -| `classes` | `list[int]` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] | -| `retina_masks` | `bool` | `False` | use high-resolution segmentation masks | -| `embed` | `list[int]` | `None` | return feature vectors/embeddings from given layers | diff --git a/ultralytics-main/docs/en/guides/yolo-common-issues.md b/ultralytics-main/docs/en/guides/yolo-common-issues.md deleted file mode 100644 index 71083cf..0000000 --- a/ultralytics-main/docs/en/guides/yolo-common-issues.md +++ /dev/null @@ -1,276 +0,0 @@ ---- -comments: true -description: A comprehensive guide to troubleshooting common issues encountered while working with YOLOv8 in the Ultralytics ecosystem. -keywords: Troubleshooting, Ultralytics, YOLOv8, Installation Errors, Training Data, Model Performance, Hyperparameter Tuning, Deployment ---- - -# Troubleshooting Common YOLO Issues - -

- YOLO Common Issues Image -

- -## Introduction - -This guide serves as a comprehensive aid for troubleshooting common issues encountered while working with YOLOv8 on your Ultralytics projects. Navigating through these issues can be a breeze with the right guidance, ensuring your projects remain on track without unnecessary delays. - -## Common Issues - -### Installation Errors - -Installation errors can arise due to various reasons, such as incompatible versions, missing dependencies, or incorrect environment setups. First, check to make sure you are doing the following: - -- You're using Python 3.8 or later as recommended. - -- Ensure that you have the correct version of PyTorch (1.8 or later) installed. - -- Consider using virtual environments to avoid conflicts. - -- Follow the [official installation guide](../quickstart.md) step by step. - -Additionally, here are some common installation issues users have encountered, along with their respective solutions: - -- Import Errors or Dependency Issues - If you're getting errors during the import of YOLOv8, or you're having issues related to dependencies, consider the following troubleshooting steps: - - - **Fresh Installation**: Sometimes, starting with a fresh installation can resolve unexpected issues. Especially with libraries like Ultralytics, where updates might introduce changes to the file tree structure or functionalities. - - - **Update Regularly**: Ensure you're using the latest version of the library. Older versions might not be compatible with recent updates, leading to potential conflicts or issues. - - - **Check Dependencies**: Verify that all required dependencies are correctly installed and are of the compatible versions. - - - **Review Changes**: If you initially cloned or installed an older version, be aware that significant updates might affect the library's structure or functionalities. Always refer to the official documentation or changelogs to understand any major changes. - - - Remember, keeping your libraries and dependencies up-to-date is crucial for a smooth and error-free experience. - -- Running YOLOv8 on GPU - If you're having trouble running YOLOv8 on GPU, consider the following troubleshooting steps: - - - **Verify CUDA Compatibility and Installation**: Ensure your GPU is CUDA compatible and that CUDA is correctly installed. Use the `nvidia-smi` command to check the status of your NVIDIA GPU and CUDA version. - - - **Check PyTorch and CUDA Integration**: Ensure PyTorch can utilize CUDA by running `import torch; print(torch.cuda.is_available())` in a Python terminal. If it returns 'True', PyTorch is set up to use CUDA. - - - **Environment Activation**: Ensure you're in the correct environment where all necessary packages are installed. - - - **Update Your Packages**: Outdated packages might not be compatible with your GPU. Keep them updated. - - - **Program Configuration**: Check if the program or code specifies GPU usage. In YOLOv8, this might be in the settings or configuration. - -### Model Training Issues - -This section will address common issues faced while training and their respective explanations and solutions. - -#### Verification of Configuration Settings - -**Issue**: You are unsure whether the configuration settings in the `.yaml` file are being applied correctly during model training. - -**Solution**: The configuration settings in the `.yaml` file should be applied when using the `model.train()` function. To ensure that these settings are correctly applied, follow these steps: - -- Confirm that the path to your `.yaml` configuration file is correct. -- Make sure you pass the path to your `.yaml` file as the `data` argument when calling `model.train()`, as shown below: - -```python -model.train(data='/path/to/your/data.yaml', batch=4) -``` - -#### Accelerating Training with Multiple GPUs - -**Issue**: Training is slow on a single GPU, and you want to speed up the process using multiple GPUs. - -**Solution**: Increasing the batch size can accelerate training, but it's essential to consider GPU memory capacity. To speed up training with multiple GPUs, follow these steps: - -- Ensure that you have multiple GPUs available. - -- Modify your .yaml configuration file to specify the number of GPUs to use, e.g., gpus: 4. - -- Increase the batch size accordingly to fully utilize the multiple GPUs without exceeding memory limits. - -- Modify your training command to utilize multiple GPUs: - -```python -# Adjust the batch size and other settings as needed to optimize training speed -model.train(data='/path/to/your/data.yaml', batch=32, multi_scale=True) -``` - -#### Continuous Monitoring Parameters - -**Issue**: You want to know which parameters should be continuously monitored during training, apart from loss. - -**Solution**: While loss is a crucial metric to monitor, it's also essential to track other metrics for model performance optimization. Some key metrics to monitor during training include: - -- Precision -- Recall -- Mean Average Precision (mAP) - -You can access these metrics from the training logs or by using tools like TensorBoard or wandb for visualization. Implementing early stopping based on these metrics can help you achieve better results. - -#### Tools for Tracking Training Progress - -**Issue**: You are looking for recommendations on tools to track training progress. - -**Solution**: To track and visualize training progress, you can consider using the following tools: - -- [TensorBoard](https://www.tensorflow.org/tensorboard): TensorBoard is a popular choice for visualizing training metrics, including loss, accuracy, and more. You can integrate it with your YOLOv8 training process. -- [Comet](https://bit.ly/yolov8-readme-comet): Comet provides an extensive toolkit for experiment tracking and comparison. It allows you to track metrics, hyperparameters, and even model weights. Integration with YOLO models is also straightforward, providing you with a complete overview of your experiment cycle. -- [Ultralytics HUB](https://hub.ultralytics.com): Ultralytics HUB offers a specialized environment for tracking YOLO models, giving you a one-stop platform to manage metrics, datasets, and even collaborate with your team. Given its tailored focus on YOLO, it offers more customized tracking options. - -Each of these tools offers its own set of advantages, so you may want to consider the specific needs of your project when making a choice. - -#### How to Check if Training is Happening on the GPU - -**Issue**: The 'device' value in the training logs is 'null,' and you're unsure if training is happening on the GPU. - -**Solution**: The 'device' value being 'null' typically means that the training process is set to automatically use an available GPU, which is the default behavior. To ensure training occurs on a specific GPU, you can manually set the 'device' value to the GPU index (e.g., '0' for the first GPU) in your .yaml configuration file: - -```yaml -device: 0 -``` - -This will explicitly assign the training process to the specified GPU. If you wish to train on the CPU, set 'device' to 'cpu'. - -Keep an eye on the 'runs' folder for logs and metrics to monitor training progress effectively. - -#### Key Considerations for Effective Model Training - -Here are some things to keep in mind, if you are facing issues related to model training. - -**Dataset Format and Labels** - -- Importance: The foundation of any machine learning model lies in the quality and format of the data it is trained on. - -- Recommendation: Ensure that your custom dataset and its associated labels adhere to the expected format. It's crucial to verify that annotations are accurate and of high quality. Incorrect or subpar annotations can derail the model's learning process, leading to unpredictable outcomes. - -**Model Convergence** - -- Importance: Achieving model convergence ensures that the model has sufficiently learned from the training data. - -- Recommendation: When training a model 'from scratch', it's vital to ensure that the model reaches a satisfactory level of convergence. This might necessitate a longer training duration, with more epochs, compared to when you're fine-tuning an existing model. - -**Learning Rate and Batch Size** - -- Importance: These hyperparameters play a pivotal role in determining how the model updates its weights during training. - -- Recommendation: Regularly evaluate if the chosen learning rate and batch size are optimal for your specific dataset. Parameters that are not in harmony with the dataset's characteristics can hinder the model's performance. - -**Class Distribution** - -- Importance: The distribution of classes in your dataset can influence the model's prediction tendencies. - -- Recommendation: Regularly assess the distribution of classes within your dataset. If there's a class imbalance, there's a risk that the model will develop a bias towards the more prevalent class. This bias can be evident in the confusion matrix, where the model might predominantly predict the majority class. - -**Cross-Check with Pretrained Weights** - -- Importance: Leveraging pretrained weights can provide a solid starting point for model training, especially when data is limited. - -- Recommendation: As a diagnostic step, consider training your model using the same data but initializing it with pretrained weights. If this approach yields a well-formed confusion matrix, it could suggest that the 'from scratch' model might require further training or adjustments. - -### Issues Related to Model Predictions - -This section will address common issues faced during model prediction. - -#### Getting Bounding Box Predictions With Your YOLOv8 Custom Model - -**Issue**: When running predictions with a custom YOLOv8 model, there are challenges with the format and visualization of the bounding box coordinates. - -**Solution**: - -- Coordinate Format: YOLOv8 provides bounding box coordinates in absolute pixel values. To convert these to relative coordinates (ranging from 0 to 1), you need to divide by the image dimensions. For example, let’s say your image size is 640x640. Then you would do the following: - -```python -# Convert absolute coordinates to relative coordinates -x1 = x1 / 640 # Divide x-coordinates by image width -x2 = x2 / 640 -y1 = y1 / 640 # Divide y-coordinates by image height -y2 = y2 / 640 -``` - -- File Name: To obtain the file name of the image you're predicting on, access the image file path directly from the result object within your prediction loop. - -#### Filtering Objects in YOLOv8 Predictions - -**Issue**: Facing issues with how to filter and display only specific objects in the prediction results when running YOLOv8 using the Ultralytics library. - -**Solution**: To detect specific classes use the classes argument to specify the classes you want to include in the output. For instance, to detect only cars (assuming 'cars' have class index 2): - -```shell -yolo task=detect mode=segment model=yolov8n-seg.pt source='path/to/car.mp4' show=True classes=2 -``` - -#### Understanding Precision Metrics in YOLOv8 - -**Issue**: Confusion regarding the difference between box precision, mask precision, and confusion matrix precision in YOLOv8. - -**Solution**: Box precision measures the accuracy of predicted bounding boxes compared to the actual ground truth boxes using IoU (Intersection over Union) as the metric. Mask precision assesses the agreement between predicted segmentation masks and ground truth masks in pixel-wise object classification. Confusion matrix precision, on the other hand, focuses on overall classification accuracy across all classes and does not consider the geometric accuracy of predictions. It's important to note that a bounding box can be geometrically accurate (true positive) even if the class prediction is wrong, leading to differences between box precision and confusion matrix precision. These metrics evaluate distinct aspects of a model's performance, reflecting the need for different evaluation metrics in various tasks. - -#### Extracting Object Dimensions in YOLOv8 - -**Issue**: Difficulty in retrieving the length and height of detected objects in YOLOv8, especially when multiple objects are detected in an image. - -**Solution**: To retrieve the bounding box dimensions, first use the Ultralytics YOLOv8 model to predict objects in an image. Then, extract the width and height information of bounding boxes from the prediction results. - -```python -from ultralytics import YOLO - -# Load a pre-trained YOLOv8 model -model = YOLO('yolov8n.pt') - -# Specify the source image -source = 'https://ultralytics.com/images/bus.jpg' - -# Make predictions -results = model.predict(source, save=True, imgsz=320, conf=0.5) - -# Extract bounding box dimensions -boxes = results[0].boxes.xywh.cpu() -for box in boxes: - x, y, w, h = box - print(f"Width of Box: {w}, Height of Box: {h}") -``` - -### Deployment Challenges - -#### GPU Deployment Issues - -**Issue:** Deploying models in a multi-GPU environment can sometimes lead to unexpected behaviors like unexpected memory usage, inconsistent results across GPUs, etc. - -**Solution:** Check for default GPU initialization. Some frameworks, like PyTorch, might initialize CUDA operations on a default GPU before transitioning to the designated GPUs. To bypass unexpected default initializations, specify the GPU directly during deployment and prediction. Then, use tools to monitor GPU utilization and memory usage to identify any anomalies in real-time. Also, ensure you're using the latest version of the framework or library. - -#### Model Conversion/Exporting Issues - -**Issue:** During the process of converting or exporting machine learning models to different formats or platforms, users might encounter errors or unexpected behaviors. - -**Solution:** - -- Compatibility Check: Ensure that you are using versions of libraries and frameworks that are compatible with each other. Mismatched versions can lead to unexpected errors during conversion. - -- Environment Reset: If you're using an interactive environment like Jupyter or Colab, consider restarting your environment after making significant changes or installations. A fresh start can sometimes resolve underlying issues. - -- Official Documentation: Always refer to the official documentation of the tool or library you are using for conversion. It often contains specific guidelines and best practices for model exporting. - -- Community Support: Check the library or framework's official repository for similar issues reported by other users. The maintainers or community might have provided solutions or workarounds in discussion threads. - -- Update Regularly: Ensure that you are using the latest version of the tool or library. Developers frequently release updates that fix known bugs or improve functionality. - -- Test Incrementally: Before performing a full conversion, test the process with a smaller model or dataset to identify potential issues early on. - -## Community and Support - -Engaging with a community of like-minded individuals can significantly enhance your experience and success in working with YOLOv8. Below are some channels and resources you may find helpful. - -### Forums and Channels for Getting Help - -**GitHub Issues:** The YOLOv8 repository on GitHub has an [Issues tab](https://github.com/ultralytics/ultralytics/issues) where you can ask questions, report bugs, and suggest new features. The community and maintainers are active here, and it’s a great place to get help with specific problems. - -**Ultralytics Discord Server:** Ultralytics has a [Discord server](https://ultralytics.com/discord/) where you can interact with other users and the developers. - -### Official Documentation and Resources - -**Ultralytics YOLOv8 Docs**: The [official documentation](../index.md) provides a comprehensive overview of YOLOv8, along with guides on installation, usage, and troubleshooting. - -These resources should provide a solid foundation for troubleshooting and improving your YOLOv8 projects, as well as connecting with others in the YOLOv8 community. - -## Conclusion - -Troubleshooting is an integral part of any development process, and being equipped with the right knowledge can significantly reduce the time and effort spent in resolving issues. This guide aimed to address the most common challenges faced by users of the YOLOv8 model within the Ultralytics ecosystem. By understanding and addressing these common issues, you can ensure smoother project progress and achieve better results with your computer vision tasks. - -Remember, the Ultralytics community is a valuable resource. Engaging with fellow developers and experts can provide additional insights and solutions that might not be covered in standard documentation. Always keep learning, experimenting, and sharing your experiences to contribute to the collective knowledge of the community. - -Happy troubleshooting! diff --git a/ultralytics-main/docs/en/guides/yolo-performance-metrics.md b/ultralytics-main/docs/en/guides/yolo-performance-metrics.md deleted file mode 100644 index a34f161..0000000 --- a/ultralytics-main/docs/en/guides/yolo-performance-metrics.md +++ /dev/null @@ -1,176 +0,0 @@ ---- -comments: true -description: A comprehensive guide on various performance metrics related to YOLOv8, their significance, and how to interpret them. -keywords: YOLOv8, Performance metrics, Object detection, Intersection over Union (IoU), Average Precision (AP), Mean Average Precision (mAP), Precision, Recall, Validation mode, Ultralytics ---- - -# Performance Metrics Deep Dive - -## Introduction - -Performance metrics are key tools to evaluate the accuracy and efficiency of object detection models. They shed light on how effectively a model can identify and localize objects within images. Additionally, they help in understanding the model's handling of false positives and false negatives. These insights are crucial for evaluating and enhancing the model's performance. In this guide, we will explore various performance metrics associated with YOLOv8, their significance, and how to interpret them. - -

-
- -
- Watch: Ultralytics YOLOv8 Performance Metrics | MAP, F1 Score, Precision, IoU & Accuracy -

- -## Object Detection Metrics - -Let’s start by discussing some metrics that are not only important to YOLOv8 but are broadly applicable across different object detection models. - -- **Intersection over Union (IoU):** IoU is a measure that quantifies the overlap between a predicted bounding box and a ground truth bounding box. It plays a fundamental role in evaluating the accuracy of object localization. - -- **Average Precision (AP):** AP computes the area under the precision-recall curve, providing a single value that encapsulates the model's precision and recall performance. - -- **Mean Average Precision (mAP):** mAP extends the concept of AP by calculating the average AP values across multiple object classes. This is useful in multi-class object detection scenarios to provide a comprehensive evaluation of the model's performance. - -- **Precision and Recall:** Precision quantifies the proportion of true positives among all positive predictions, assessing the model's capability to avoid false positives. On the other hand, Recall calculates the proportion of true positives among all actual positives, measuring the model's ability to detect all instances of a class. - -- **F1 Score:** The F1 Score is the harmonic mean of precision and recall, providing a balanced assessment of a model's performance while considering both false positives and false negatives. - -## How to Calculate Metrics for YOLOv8 Model - -Now, we can explore [YOLOv8's Validation mode](../modes/val.md) that can be used to compute the above discussed evaluation metrics. - -Using the validation mode is simple. Once you have a trained model, you can invoke the model.val() function. This function will then process the validation dataset and return a variety of performance metrics. But what do these metrics mean? And how should you interpret them? - -### Interpreting the Output - -Let's break down the output of the model.val() function and understand each segment of the output. - -#### Class-wise Metrics - -One of the sections of the output is the class-wise breakdown of performance metrics. This granular information is useful when you are trying to understand how well the model is doing for each specific class, especially in datasets with a diverse range of object categories. For each class in the dataset the following is provided: - -- **Class**: This denotes the name of the object class, such as "person", "car", or "dog". - -- **Images**: This metric tells you the number of images in the validation set that contain the object class. - -- **Instances**: This provides the count of how many times the class appears across all images in the validation set. - -- **Box(P, R, mAP50, mAP50-95)**: This metric provides insights into the model's performance in detecting objects: - - - **P (Precision)**: The accuracy of the detected objects, indicating how many detections were correct. - - - **R (Recall)**: The ability of the model to identify all instances of objects in the images. - - - **mAP50**: Mean average precision calculated at an intersection over union (IoU) threshold of 0.50. It's a measure of the model's accuracy considering only the "easy" detections. - - - **mAP50-95**: The average of the mean average precision calculated at varying IoU thresholds, ranging from 0.50 to 0.95. It gives a comprehensive view of the model's performance across different levels of detection difficulty. - -#### Speed Metrics - -The speed of inference can be as critical as accuracy, especially in real-time object detection scenarios. This section breaks down the time taken for various stages of the validation process, from preprocessing to post-processing. - -#### COCO Metrics Evaluation - -For users validating on the COCO dataset, additional metrics are calculated using the COCO evaluation script. These metrics give insights into precision and recall at different IoU thresholds and for objects of different sizes. - -#### Visual Outputs - -The model.val() function, apart from producing numeric metrics, also yields visual outputs that can provide a more intuitive understanding of the model's performance. Here's a breakdown of the visual outputs you can expect: - -- **F1 Score Curve (`F1_curve.png`)**: This curve represents the F1 score across various thresholds. Interpreting this curve can offer insights into the model's balance between false positives and false negatives over different thresholds. - -- **Precision-Recall Curve (`PR_curve.png`)**: An integral visualization for any classification problem, this curve showcases the trade-offs between precision and recall at varied thresholds. It becomes especially significant when dealing with imbalanced classes. - -- **Precision Curve (`P_curve.png`)**: A graphical representation of precision values at different thresholds. This curve helps in understanding how precision varies as the threshold changes. - -- **Recall Curve (`R_curve.png`)**: Correspondingly, this graph illustrates how the recall values change across different thresholds. - -- **Confusion Matrix (`confusion_matrix.png`)**: The confusion matrix provides a detailed view of the outcomes, showcasing the counts of true positives, true negatives, false positives, and false negatives for each class. - -- **Normalized Confusion Matrix (`confusion_matrix_normalized.png`)**: This visualization is a normalized version of the confusion matrix. It represents the data in proportions rather than raw counts. This format makes it simpler to compare the performance across classes. - -- **Validation Batch Labels (`val_batchX_labels.jpg`)**: These images depict the ground truth labels for distinct batches from the validation dataset. They provide a clear picture of what the objects are and their respective locations as per the dataset. - -- **Validation Batch Predictions (`val_batchX_pred.jpg`)**: Contrasting the label images, these visuals display the predictions made by the YOLOv8 model for the respective batches. By comparing these to the label images, you can easily assess how well the model detects and classifies objects visually. - -#### Results Storage - -For future reference, the results are saved to a directory, typically named runs/detect/val. - -## Choosing the Right Metrics - -Choosing the right metrics to evaluate often depends on the specific application. - -- **mAP:** Suitable for a broad assessment of model performance. - -- **IoU:** Essential when precise object location is crucial. - -- **Precision:** Important when minimizing false detections is a priority. - -- **Recall:** Vital when it's important to detect every instance of an object. - -- **F1 Score:** Useful when a balance between precision and recall is needed. - -For real-time applications, speed metrics like FPS (Frames Per Second) and latency are crucial to ensure timely results. - -## Interpretation of Results - -It’s important to understand the metrics. Here's what some of the commonly observed lower scores might suggest: - -- **Low mAP:** Indicates the model may need general refinements. - -- **Low IoU:** The model might be struggling to pinpoint objects accurately. Different bounding box methods could help. - -- **Low Precision:** The model may be detecting too many non-existent objects. Adjusting confidence thresholds might reduce this. - -- **Low Recall:** The model could be missing real objects. Improving feature extraction or using more data might help. - -- **Imbalanced F1 Score:** There's a disparity between precision and recall. - -- **Class-specific AP:** Low scores here can highlight classes the model struggles with. - -## Case Studies - -Real-world examples can help clarify how these metrics work in practice. - -### Case 1 - -- **Situation:** mAP and F1 Score are suboptimal, but while Recall is good, Precision isn't. - -- **Interpretation & Action:** There might be too many incorrect detections. Tightening confidence thresholds could reduce these, though it might also slightly decrease recall. - -### Case 2 - -- **Situation:** mAP and Recall are acceptable, but IoU is lacking. - -- **Interpretation & Action:** The model detects objects well but might not be localizing them precisely. Refining bounding box predictions might help. - -### Case 3 - -- **Situation:** Some classes have a much lower AP than others, even with a decent overall mAP. - -- **Interpretation & Action:** These classes might be more challenging for the model. Using more data for these classes or adjusting class weights during training could be beneficial. - -## Connect and Collaborate - -Tapping into a community of enthusiasts and experts can amplify your journey with YOLOv8. Here are some avenues that can facilitate learning, troubleshooting, and networking. - -### Engage with the Broader Community - -- **GitHub Issues:** The YOLOv8 repository on GitHub has an [Issues tab](https://github.com/ultralytics/ultralytics/issues) where you can ask questions, report bugs, and suggest new features. The community and maintainers are active here, and it’s a great place to get help with specific problems. - -- **Ultralytics Discord Server:** Ultralytics has a [Discord server](https://ultralytics.com/discord/) where you can interact with other users and the developers. - -### Official Documentation and Resources: - -- **Ultralytics YOLOv8 Docs:** The [official documentation](../index.md) provides a comprehensive overview of YOLOv8, along with guides on installation, usage, and troubleshooting. - -Using these resources will not only guide you through any challenges but also keep you updated with the latest trends and best practices in the YOLOv8 community. - -## Conclusion - -In this guide, we've taken a close look at the essential performance metrics for YOLOv8. These metrics are key to understanding how well a model is performing and are vital for anyone aiming to fine-tune their models. They offer the necessary insights for improvements and to make sure the model works effectively in real-life situations. - -Remember, the YOLOv8 and Ultralytics community is an invaluable asset. Engaging with fellow developers and experts can open doors to insights and solutions not found in standard documentation. As you journey through object detection, keep the spirit of learning alive, experiment with new strategies, and share your findings. By doing so, you contribute to the community's collective wisdom and ensure its growth. - -Happy object detecting! diff --git a/ultralytics-main/docs/en/guides/yolo-thread-safe-inference.md b/ultralytics-main/docs/en/guides/yolo-thread-safe-inference.md deleted file mode 100644 index abf7a36..0000000 --- a/ultralytics-main/docs/en/guides/yolo-thread-safe-inference.md +++ /dev/null @@ -1,108 +0,0 @@ ---- -comments: true -description: This guide provides best practices for performing thread-safe inference with YOLO models, ensuring reliable and concurrent predictions in multi-threaded applications. -keywords: thread-safe, YOLO inference, multi-threading, concurrent predictions, YOLO models, Ultralytics, Python threading, safe YOLO usage, AI concurrency ---- - -# Thread-Safe Inference with YOLO Models - -Running YOLO models in a multi-threaded environment requires careful consideration to ensure thread safety. Python's `threading` module allows you to run several threads concurrently, but when it comes to using YOLO models across these threads, there are important safety issues to be aware of. This page will guide you through creating thread-safe YOLO model inference. - -## Understanding Python Threading - -Python threads are a form of parallelism that allow your program to run multiple operations at once. However, Python's Global Interpreter Lock (GIL) means that only one thread can execute Python bytecode at a time. - -

- Single vs Multi-Thread Examples -

- -While this sounds like a limitation, threads can still provide concurrency, especially for I/O-bound operations or when using operations that release the GIL, like those performed by YOLO's underlying C libraries. - -## The Danger of Shared Model Instances - -Instantiating a YOLO model outside your threads and sharing this instance across multiple threads can lead to race conditions, where the internal state of the model is inconsistently modified due to concurrent accesses. This is particularly problematic when the model or its components hold state that is not designed to be thread-safe. - -### Non-Thread-Safe Example: Single Model Instance - -When using threads in Python, it's important to recognize patterns that can lead to concurrency issues. Here is what you should avoid: sharing a single YOLO model instance across multiple threads. - -```python -# Unsafe: Sharing a single model instance across threads -from ultralytics import YOLO -from threading import Thread - -# Instantiate the model outside the thread -shared_model = YOLO("yolov8n.pt") - - -def predict(image_path): - results = shared_model.predict(image_path) - # Process results - - -# Starting threads that share the same model instance -Thread(target=predict, args=("image1.jpg",)).start() -Thread(target=predict, args=("image2.jpg",)).start() -``` - -In the example above, the `shared_model` is used by multiple threads, which can lead to unpredictable results because `predict` could be executed simultaneously by multiple threads. - -### Non-Thread-Safe Example: Multiple Model Instances - -Similarly, here is an unsafe pattern with multiple YOLO model instances: - -```python -# Unsafe: Sharing multiple model instances across threads can still lead to issues -from ultralytics import YOLO -from threading import Thread - -# Instantiate multiple models outside the thread -shared_model_1 = YOLO("yolov8n_1.pt") -shared_model_2 = YOLO("yolov8n_2.pt") - - -def predict(model, image_path): - results = model.predict(image_path) - # Process results - - -# Starting threads with individual model instances -Thread(target=predict, args=(shared_model_1, "image1.jpg")).start() -Thread(target=predict, args=(shared_model_2, "image2.jpg")).start() -``` - -Even though there are two separate model instances, the risk of concurrency issues still exists. If the internal implementation of `YOLO` is not thread-safe, using separate instances might not prevent race conditions, especially if these instances share any underlying resources or states that are not thread-local. - -## Thread-Safe Inference - -To perform thread-safe inference, you should instantiate a separate YOLO model within each thread. This ensures that each thread has its own isolated model instance, eliminating the risk of race conditions. - -### Thread-Safe Example - -Here's how to instantiate a YOLO model inside each thread for safe parallel inference: - -```python -# Safe: Instantiating a single model inside each thread -from ultralytics import YOLO -from threading import Thread - - -def thread_safe_predict(image_path): - # Instantiate a new model inside the thread - local_model = YOLO("yolov8n.pt") - results = local_model.predict(image_path) - # Process results - - -# Starting threads that each have their own model instance -Thread(target=thread_safe_predict, args=("image1.jpg",)).start() -Thread(target=thread_safe_predict, args=("image2.jpg",)).start() -``` - -In this example, each thread creates its own `YOLO` instance. This prevents any thread from interfering with the model state of another, thus ensuring that each thread performs inference safely and without unexpected interactions with the other threads. - -## Conclusion - -When using YOLO models with Python's `threading`, always instantiate your models within the thread that will use them to ensure thread safety. This practice avoids race conditions and makes sure that your inference tasks run reliably. - -For more advanced scenarios and to further optimize your multi-threaded inference performance, consider using process-based parallelism with `multiprocessing` or leveraging a task queue with dedicated worker processes. diff --git a/ultralytics-main/docs/en/help/CI.md b/ultralytics-main/docs/en/help/CI.md deleted file mode 100644 index 033cf71..0000000 --- a/ultralytics-main/docs/en/help/CI.md +++ /dev/null @@ -1,61 +0,0 @@ ---- -comments: true -description: Learn how Ultralytics leverages Continuous Integration (CI) for maintaining high-quality code. Explore our CI tests and the status of these tests for our repositories. -keywords: continuous integration, software development, CI tests, Ultralytics repositories, high-quality code, Docker Deployment, Broken Links, CodeQL, PyPi Publishing ---- - -# Continuous Integration (CI) - -Continuous Integration (CI) is an essential aspect of software development which involves integrating changes and testing them automatically. CI allows us to maintain high-quality code by catching issues early and often in the development process. At Ultralytics, we use various CI tests to ensure the quality and integrity of our codebase. - -## CI Actions - -Here's a brief description of our CI actions: - -- **[CI](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml):** This is our primary CI test that involves running unit tests, linting checks, and sometimes more comprehensive tests depending on the repository. -- **[Docker Deployment](https://github.com/ultralytics/ultralytics/actions/workflows/docker.yaml):** This test checks the deployment of the project using Docker to ensure the Dockerfile and related scripts are working correctly. -- **[Broken Links](https://github.com/ultralytics/ultralytics/actions/workflows/links.yml):** This test scans the codebase for any broken or dead links in our markdown or HTML files. -- **[CodeQL](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml):** CodeQL is a tool from GitHub that performs semantic analysis on our code, helping to find potential security vulnerabilities and maintain high-quality code. -- **[PyPi Publishing](https://github.com/ultralytics/ultralytics/actions/workflows/publish.yml):** This test checks if the project can be packaged and published to PyPi without any errors. - -### CI Results - -Below is the table showing the status of these CI tests for our main repositories: - -| Repository | CI | Docker Deployment | Broken Links | CodeQL | PyPi and Docs Publishing | -|-----------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| [yolov3](https://github.com/ultralytics/yolov3) | [![YOLOv3 CI](https://github.com/ultralytics/yolov3/actions/workflows/ci-testing.yml/badge.svg)](https://github.com/ultralytics/yolov3/actions/workflows/ci-testing.yml) | [![Publish Docker Images](https://github.com/ultralytics/yolov3/actions/workflows/docker.yml/badge.svg)](https://github.com/ultralytics/yolov3/actions/workflows/docker.yml) | [![Check Broken links](https://github.com/ultralytics/yolov3/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/yolov3/actions/workflows/links.yml) | [![CodeQL](https://github.com/ultralytics/yolov3/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/ultralytics/yolov3/actions/workflows/codeql-analysis.yml) | | -| [yolov5](https://github.com/ultralytics/yolov5) | [![YOLOv5 CI](https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg)](https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml) | [![Publish Docker Images](https://github.com/ultralytics/yolov5/actions/workflows/docker.yml/badge.svg)](https://github.com/ultralytics/yolov5/actions/workflows/docker.yml) | [![Check Broken links](https://github.com/ultralytics/yolov5/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/yolov5/actions/workflows/links.yml) | [![CodeQL](https://github.com/ultralytics/yolov5/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/ultralytics/yolov5/actions/workflows/codeql-analysis.yml) | | -| [ultralytics](https://github.com/ultralytics/ultralytics) | [![ultralytics CI](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml) | [![Publish Docker Images](https://github.com/ultralytics/ultralytics/actions/workflows/docker.yaml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/docker.yaml) | [![Check Broken links](https://github.com/ultralytics/ultralytics/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/links.yml) | [![CodeQL](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml) | [![Publish to PyPI and Deploy Docs](https://github.com/ultralytics/ultralytics/actions/workflows/publish.yml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/publish.yml) | -| [hub](https://github.com/ultralytics/hub) | [![HUB CI](https://github.com/ultralytics/hub/actions/workflows/ci.yaml/badge.svg)](https://github.com/ultralytics/hub/actions/workflows/ci.yaml) | | [![Check Broken links](https://github.com/ultralytics/hub/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/hub/actions/workflows/links.yml) | | | -| [docs](https://github.com/ultralytics/docs) | | | [![Check Broken links](https://github.com/ultralytics/docs/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/links.yml)[![Check Domains](https://github.com/ultralytics/docs/actions/workflows/check_domains.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/check_domains.yml) | | [![pages-build-deployment](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment) | - -Each badge shows the status of the last run of the corresponding CI test on the `main` branch of the respective repository. If a test fails, the badge will display a "failing" status, and if it passes, it will display a "passing" status. - -If you notice a test failing, it would be a great help if you could report it through a GitHub issue in the respective repository. - -Remember, a successful CI test does not mean that everything is perfect. It is always recommended to manually review the code before deployment or merging changes. - -## Code Coverage - -Code coverage is a metric that represents the percentage of your codebase that is executed when your tests run. It provides insight into how well your tests exercise your code and can be crucial in identifying untested parts of your application. A high code coverage percentage is often associated with a lower likelihood of bugs. However, it's essential to understand that code coverage does not guarantee the absence of defects. It merely indicates which parts of the code have been executed by the tests. - -### Integration with [codecov.io](https://codecov.io/) - -At Ultralytics, we have integrated our repositories with [codecov.io](https://codecov.io/), a popular online platform for measuring and visualizing code coverage. Codecov provides detailed insights, coverage comparisons between commits, and visual overlays directly on your code, indicating which lines were covered. - -By integrating with Codecov, we aim to maintain and improve the quality of our code by focusing on areas that might be prone to errors or need further testing. - -### Coverage Results - -To quickly get a glimpse of the code coverage status of the `ultralytics` python package, we have included a badge and sunburst visual of the `ultralytics` coverage results. These images show the percentage of code covered by our tests, offering an at-a-glance metric of our testing efforts. For full details please see https://codecov.io/github/ultralytics/ultralytics. - -| Repository | Code Coverage | -|-----------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------| -| [ultralytics](https://github.com/ultralytics/ultralytics) | [![codecov](https://codecov.io/gh/ultralytics/ultralytics/branch/main/graph/badge.svg?token=HHW7IIVFVY)](https://codecov.io/gh/ultralytics/ultralytics) | - -In the sunburst graphic below, the innermost circle is the entire project, moving away from the center are folders then, finally, a single file. The size and color of each slice is representing the number of statements and the coverage, respectively. - - - Ultralytics Codecov Image - diff --git a/ultralytics-main/docs/en/help/CLA.md b/ultralytics-main/docs/en/help/CLA.md deleted file mode 100644 index e24e955..0000000 --- a/ultralytics-main/docs/en/help/CLA.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Understand terms governing contributions to Ultralytics projects including source code, bug fixes, documentation and more. Read our Contributor License Agreement. -keywords: Ultralytics, Contributor License Agreement, Open Source Software, Contributions, Copyright License, Patent License, Moral Rights ---- - -# Ultralytics Individual Contributor License Agreement - -Thank you for your interest in contributing to open source software projects (“Projects”) made available by Ultralytics Inc. (“Ultralytics”). This Individual Contributor License Agreement (“Agreement”) sets out the terms governing any source code, object code, bug fixes, configuration changes, tools, specifications, documentation, data, materials, feedback, information or other works of authorship that you submit or have submitted, in any form and in any manner, to Ultralytics in respect of any Projects (collectively “Contributions”). If you have any questions respecting this Agreement, please contact hello@ultralytics.com. - -You agree that the following terms apply to all of your past, present and future Contributions. Except for the licenses granted in this Agreement, you retain all of your right, title and interest in and to your Contributions. - -**Copyright License.** You hereby grant, and agree to grant, to Ultralytics a non-exclusive, perpetual, irrevocable, worldwide, fully-paid, royalty-free, transferable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, and distribute your Contributions and such derivative works, with the right to sublicense the foregoing rights through multiple tiers of sublicensees. - -**Patent License.** You hereby grant, and agree to grant, to Ultralytics a non-exclusive, perpetual, irrevocable, worldwide, fully-paid, royalty-free, transferable patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer your Contributions, where such license applies only to those patent claims licensable by you that are necessarily infringed by your Contributions alone or by combination of your Contributions with the Project to which such Contributions were submitted, with the right to sublicense the foregoing rights through multiple tiers of sublicensees. - -**Moral Rights.** To the fullest extent permitted under applicable law, you hereby waive, and agree not to assert, all of your “moral rights” in or relating to your Contributions for the benefit of Ultralytics, its assigns, and their respective direct and indirect sublicensees. - -**Third Party Content/Rights.** If your Contribution includes or is based on any source code, object code, bug fixes, configuration changes, tools, specifications, documentation, data, materials, feedback, information or other works of authorship that were not authored by you (“Third Party Content”) or if you are aware of any third party intellectual property or proprietary rights associated with your Contribution (“Third Party Rights”), then you agree to include with the submission of your Contribution full details respecting such Third Party Content and Third Party Rights, including, without limitation, identification of which aspects of your Contribution contain Third Party Content or are associated with Third Party Rights, the owner/author of the Third Party Content and Third Party Rights, where you obtained the Third Party Content, and any applicable third party license terms or restrictions respecting the Third Party Content and Third Party Rights. For greater certainty, the foregoing obligations respecting the identification of Third Party Content and Third Party Rights do not apply to any portion of a Project that is incorporated into your Contribution to that same Project. - -**Representations.** You represent that, other than the Third Party Content and Third Party Rights identified by you in accordance with this Agreement, you are the sole author of your Contributions and are legally entitled to grant the foregoing licenses and waivers in respect of your Contributions. If your Contributions were created in the course of your employment with your past or present employer(s), you represent that such employer(s) has authorized you to make your Contributions on behalf of such employer(s) or such employer(s) has waived all of their right, title or interest in or to your Contributions. - -**Disclaimer.** To the fullest extent permitted under applicable law, your Contributions are provided on an "asis" basis, without any warranties or conditions, express or implied, including, without limitation, any implied warranties or conditions of non-infringement, merchantability or fitness for a particular purpose. You are not required to provide support for your Contributions, except to the extent you desire to provide support. - -**No Obligation.** You acknowledge that Ultralytics is under no obligation to use or incorporate your Contributions into any of the Projects. The decision to use or incorporate your Contributions into any of the Projects will be made at the sole discretion of Ultralytics or its authorized delegates. - -**Disputes.** This Agreement shall be governed by and construed in accordance with the laws of the State of New York, United States of America, without giving effect to its principles or rules regarding conflicts of laws, other than such principles directing application of New York law. The parties hereby submit to venue in, and jurisdiction of the courts located in New York, New York for purposes relating to this Agreement. In the event that any of the provisions of this Agreement shall be held by a court or other tribunal of competent jurisdiction to be unenforceable, the remaining portions hereof shall remain in full force and effect. - -**Assignment.** You agree that Ultralytics may assign this Agreement, and all of its rights, obligations and licenses hereunder. diff --git a/ultralytics-main/docs/en/help/FAQ.md b/ultralytics-main/docs/en/help/FAQ.md deleted file mode 100644 index 8e4430a..0000000 --- a/ultralytics-main/docs/en/help/FAQ.md +++ /dev/null @@ -1,39 +0,0 @@ ---- -comments: true -description: Find solutions to your common Ultralytics YOLO related queries. Learn about hardware requirements, fine-tuning YOLO models, conversion to ONNX/TensorFlow, and more. -keywords: Ultralytics, YOLO, FAQ, hardware requirements, ONNX, TensorFlow, real-time detection, YOLO accuracy ---- - -# Ultralytics YOLO Frequently Asked Questions (FAQ) - -This FAQ section addresses some common questions and issues users might encounter while working with Ultralytics YOLO repositories. - -## 1. What are the hardware requirements for running Ultralytics YOLO? - -Ultralytics YOLO can be run on a variety of hardware configurations, including CPUs, GPUs, and even some edge devices. However, for optimal performance and faster training and inference, we recommend using a GPU with a minimum of 8GB of memory. NVIDIA GPUs with CUDA support are ideal for this purpose. - -## 2. How do I fine-tune a pre-trained YOLO model on my custom dataset? - -To fine-tune a pre-trained YOLO model on your custom dataset, you'll need to create a dataset configuration file (YAML) that defines the dataset's properties, such as the path to the images, the number of classes, and class names. Next, you'll need to modify the model configuration file to match the number of classes in your dataset. Finally, use the `train.py` script to start the training process with your custom dataset and the pre-trained model. You can find a detailed guide on fine-tuning YOLO in the Ultralytics documentation. - -## 3. How do I convert a YOLO model to ONNX or TensorFlow format? - -Ultralytics provides built-in support for converting YOLO models to ONNX format. You can use the `export.py` script to convert a saved model to ONNX format. If you need to convert the model to TensorFlow format, you can use the ONNX model as an intermediary and then use the ONNX-TensorFlow converter to convert the ONNX model to TensorFlow format. - -## 4. Can I use Ultralytics YOLO for real-time object detection? - -Yes, Ultralytics YOLO is designed to be efficient and fast, making it suitable for real-time object detection tasks. The actual performance will depend on your hardware configuration and the complexity of the model. Using a GPU and optimizing the model for your specific use case can help achieve real-time performance. - -## 5. How can I improve the accuracy of my YOLO model? - -Improving the accuracy of a YOLO model may involve several strategies, such as: - -- Fine-tuning the model on more annotated data -- Data augmentation to increase the variety of training samples -- Using a larger or more complex model architecture -- Adjusting the learning rate, batch size, and other hyperparameters -- Using techniques like transfer learning or knowledge distillation - -Remember that there's often a trade-off between accuracy and inference speed, so finding the right balance is crucial for your specific application. - -If you have any more questions or need assistance, don't hesitate to consult the Ultralytics documentation or reach out to the community through GitHub Issues or the official discussion forum. diff --git a/ultralytics-main/docs/en/help/code_of_conduct.md b/ultralytics-main/docs/en/help/code_of_conduct.md deleted file mode 100644 index 46313c4..0000000 --- a/ultralytics-main/docs/en/help/code_of_conduct.md +++ /dev/null @@ -1,85 +0,0 @@ ---- -comments: true -description: Explore Ultralytics community’s Code of Conduct, ensuring a supportive, inclusive environment for contributors & members at all levels. Find our guidelines on acceptable behavior & enforcement. -keywords: Ultralytics, code of conduct, community, contribution, behavior guidelines, enforcement, open source contributions ---- - -# Ultralytics Contributor Covenant Code of Conduct - -## Our Pledge - -We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socioeconomic status, nationality, personal appearance, race, religion, or sexual identity and orientation. - -We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community. - -## Our Standards - -Examples of behavior that contributes to a positive environment for our community include: - -- Demonstrating empathy and kindness toward other people -- Being respectful of differing opinions, viewpoints, and experiences -- Giving and gracefully accepting constructive feedback -- Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience -- Focusing on what is best not just for us as individuals, but for the overall community - -Examples of unacceptable behavior include: - -- The use of sexualized language or imagery, and sexual attention or advances of any kind -- Trolling, insulting or derogatory comments, and personal or political attacks -- Public or private harassment -- Publishing others' private information, such as a physical or email address, without their explicit permission -- Other conduct which could reasonably be considered inappropriate in a professional setting - -## Enforcement Responsibilities - -Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful. - -Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate. - -## Scope - -This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. - -## Enforcement - -Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at hello@ultralytics.com. All complaints will be reviewed and investigated promptly and fairly. - -All community leaders are obligated to respect the privacy and security of the reporter of any incident. - -## Enforcement Guidelines - -Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct: - -### 1. Correction - -**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community. - -**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested. - -### 2. Warning - -**Community Impact**: A violation through a single incident or series of actions. - -**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban. - -### 3. Temporary Ban - -**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior. - -**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban. - -### 4. Permanent Ban - -**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals. - -**Consequence**: A permanent ban from any sort of public interaction within the community. - -## Attribution - -This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0, available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html. - -Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity). - -For answers to common questions about this code of conduct, see the FAQ at https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations. - -[homepage]: https://www.contributor-covenant.org diff --git a/ultralytics-main/docs/en/help/contributing.md b/ultralytics-main/docs/en/help/contributing.md deleted file mode 100644 index 7874d48..0000000 --- a/ultralytics-main/docs/en/help/contributing.md +++ /dev/null @@ -1,131 +0,0 @@ ---- -comments: true -description: Learn how to contribute to Ultralytics YOLO projects – guidelines for pull requests, reporting bugs, code conduct and CLA signing. -keywords: Ultralytics, YOLO, open-source, contribute, pull request, bug report, coding guidelines, CLA, code of conduct, GitHub ---- - -# Contributing to Ultralytics Open-Source YOLO Repositories - -First of all, thank you for your interest in contributing to Ultralytics open-source YOLO repositories! Your contributions will help improve the project and benefit the community. This document provides guidelines and best practices to get you started. - -## Table of Contents - -1. [Code of Conduct](#code-of-conduct) -2. [Contributing via Pull Requests](#contributing-via-pull-requests) - - [CLA Signing](#cla-signing) - - [Google-Style Docstrings](#google-style-docstrings) - - [GitHub Actions CI Tests](#github-actions-ci-tests) -3. [Reporting Bugs](#reporting-bugs) -4. [License](#license) -5. [Conclusion](#conclusion) - -## Code of Conduct - -All contributors are expected to adhere to the [Code of Conduct](code_of_conduct.md) to ensure a welcoming and inclusive environment for everyone. - -## Contributing via Pull Requests - -We welcome contributions in the form of pull requests. To make the review process smoother, please follow these guidelines: - -1. **[Fork the repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo)**: Fork the Ultralytics YOLO repository to your own GitHub account. - -2. **[Create a branch](https://docs.github.com/en/desktop/making-changes-in-a-branch/managing-branches-in-github-desktop)**: Create a new branch in your forked repository with a descriptive name for your changes. - -3. **Make your changes**: Make the changes you want to contribute. Ensure that your changes follow the coding style of the project and do not introduce new errors or warnings. - -4. **[Test your changes](https://github.com/ultralytics/ultralytics/tree/main/tests)**: Test your changes locally to ensure that they work as expected and do not introduce new issues. - -5. **[Commit your changes](https://docs.github.com/en/desktop/making-changes-in-a-branch/committing-and-reviewing-changes-to-your-project-in-github-desktop)**: Commit your changes with a descriptive commit message. Make sure to include any relevant issue numbers in your commit message. - -6. **[Create a pull request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request)**: Create a pull request from your forked repository to the main Ultralytics YOLO repository. In the pull request description, provide a clear explanation of your changes and how they improve the project. - -### CLA Signing - -Before we can accept your pull request, you need to sign a [Contributor License Agreement (CLA)](CLA.md). This is a legal document stating that you agree to the terms of contributing to the Ultralytics YOLO repositories. The CLA ensures that your contributions are properly licensed and that the project can continue to be distributed under the AGPL-3.0 license. - -To sign the CLA, follow the instructions provided by the CLA bot after you submit your PR and add a comment in your PR saying: - -``` -I have read the CLA Document and I sign the CLA -``` - -### Google-Style Docstrings - -When adding new functions or classes, please include a [Google-style docstring](https://google.github.io/styleguide/pyguide.html) to provide clear and concise documentation for other developers. This will help ensure that your contributions are easy to understand and maintain. - -!!! Example "Example Docstrings" - - === "Google-style" - - This example shows both Google-style docstrings. Note that both input and output `types` must always be enclosed by parentheses, i.e. `(bool)`. - ```python - def example_function(arg1, arg2=4): - """ - Example function that demonstrates Google-style docstrings. - - Args: - arg1 (int): The first argument. - arg2 (int): The second argument. Default value is 4. - - Returns: - (bool): True if successful, False otherwise. - - Examples: - >>> result = example_function(1, 2) # returns False - """ - if arg1 == arg2: - return True - return False - ``` - - === "Google-style with type hints" - - This example shows both Google-style docstrings and argument and return type hints, though both are not required, one can be used without the other. - ```python - def example_function(arg1: int, arg2: int = 4) -> bool: - """ - Example function that demonstrates Google-style docstrings. - - Args: - arg1: The first argument. - arg2: The second argument. Default value is 4. - - Returns: - True if successful, False otherwise. - - Examples: - >>> result = example_function(1, 2) # returns False - """ - if arg1 == arg2: - return True - return False - ``` - - === "Single-line" - - Smaller or simpler functions can utilize a single-line docstring. Note the docstring must use 3 double-quotes, and be a complete sentence starting with a capital letter and ending with a period. - ```python - def example_small_function(arg1: int, arg2: int = 4) -> bool: - """Example function that demonstrates a single-line docstring.""" - return arg1 == arg2 - ``` - -### GitHub Actions CI Tests - -Before your pull request can be merged, all GitHub Actions [Continuous Integration](CI.md) (CI) tests must pass. These tests include linting, unit tests, and other checks to ensure that your changes meet the quality standards of the project. Make sure to review the output of the GitHub Actions and fix any issues - -## Reporting Bugs - -We appreciate bug reports as they play a crucial role in maintaining the project's quality. When reporting bugs it is important to provide a [Minimum Reproducible Example](minimum_reproducible_example.md): a clear, concise code example that replicates the issue. This helps in quick identification and resolution of the bug. - -## License - -Ultralytics embraces the [GNU Affero General Public License v3.0 (AGPL-3.0)](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) for its repositories, promoting openness, transparency, and collaborative enhancement in software development. This strong copyleft license ensures that all users and developers retain the freedom to use, modify, and share the software. It fosters community collaboration, ensuring that any improvements remain accessible to all. - -Users and developers are encouraged to familiarize themselves with the terms of AGPL-3.0 to contribute effectively and ethically to the Ultralytics open-source community. - -## Conclusion - -Thank you for your interest in contributing to [Ultralytics open-source](https://github.com/ultralytics) YOLO projects. Your participation is crucial in shaping the future of our software and fostering a community of innovation and collaboration. Whether you're improving code, reporting bugs, or suggesting features, your contributions make a significant impact. - -We're eager to see your ideas in action and appreciate your commitment to advancing object detection technology. Let's continue to grow and innovate together in this exciting open-source journey. Happy coding! 🚀🌟 diff --git a/ultralytics-main/docs/en/help/environmental-health-safety.md b/ultralytics-main/docs/en/help/environmental-health-safety.md deleted file mode 100644 index 9fee240..0000000 --- a/ultralytics-main/docs/en/help/environmental-health-safety.md +++ /dev/null @@ -1,37 +0,0 @@ ---- -comments: false -description: Discover Ultralytics’ EHS policy principles and implementation measures. Committed to safety, environment, and continuous improvement for a sustainable future. -keywords: Ultralytics policy, EHS, environment, health and safety, compliance, prevention, continuous improvement, risk management, emergency preparedness, resource allocation, communication ---- - -# Ultralytics Environmental, Health and Safety (EHS) Policy - -At Ultralytics, we recognize that the long-term success of our company relies not only on the products and services we offer, but also the manner in which we conduct our business. We are committed to ensuring the safety and well-being of our employees, stakeholders, and the environment, and we will continuously strive to mitigate our impact on the environment while promoting health and safety. - -## Policy Principles - -1. **Compliance**: We will comply with all applicable laws, regulations, and standards related to EHS, and we will strive to exceed these standards where possible. - -2. **Prevention**: We will work to prevent accidents, injuries, and environmental harm by implementing risk management measures and ensuring all our operations and procedures are safe. - -3. **Continuous Improvement**: We will continuously improve our EHS performance by setting measurable objectives, monitoring our performance, auditing our operations, and revising our policies and procedures as needed. - -4. **Communication**: We will communicate openly about our EHS performance and will engage with stakeholders to understand and address their concerns and expectations. - -5. **Education and Training**: We will educate and train our employees and contractors in appropriate EHS procedures and practices. - -## Implementation Measures - -1. **Responsibility and Accountability**: Every employee and contractor working at or with Ultralytics is responsible for adhering to this policy. Managers and supervisors are accountable for ensuring this policy is implemented within their areas of control. - -2. **Risk Management**: We will identify, assess, and manage EHS risks associated with our operations and activities to prevent accidents, injuries, and environmental harm. - -3. **Resource Allocation**: We will allocate the necessary resources to ensure the effective implementation of our EHS policy, including the necessary equipment, personnel, and training. - -4. **Emergency Preparedness and Response**: We will develop, maintain, and test emergency preparedness and response plans to ensure we can respond effectively to EHS incidents. - -5. **Monitoring and Review**: We will monitor and review our EHS performance regularly to identify opportunities for improvement and ensure we are meeting our objectives. - -This policy reflects our commitment to minimizing our environmental footprint, ensuring the safety and well-being of our employees, and continuously improving our performance. - -Please remember that the implementation of an effective EHS policy requires the involvement and commitment of everyone working at or with Ultralytics. We encourage you to take personal responsibility for your safety and the safety of others, and to take care of the environment in which we live and work. diff --git a/ultralytics-main/docs/en/help/index.md b/ultralytics-main/docs/en/help/index.md deleted file mode 100644 index e8f7376..0000000 --- a/ultralytics-main/docs/en/help/index.md +++ /dev/null @@ -1,19 +0,0 @@ ---- -comments: true -description: Find comprehensive guides and documents on Ultralytics YOLO tasks. Includes FAQs, contributing guides, CI guide, CLA, MRE guide, code of conduct & more. -keywords: Ultralytics, YOLO, guides, documents, FAQ, contributing, CI guide, CLA, MRE guide, code of conduct, EHS policy, security policy, privacy policy ---- - -Welcome to the Ultralytics Help page! We are dedicated to providing you with detailed resources to enhance your experience with the Ultralytics YOLO models and repositories. This page serves as your portal to guides and documentation designed to assist you with various tasks and answer questions you may encounter while engaging with our repositories. - -- [Frequently Asked Questions (FAQ)](FAQ.md): Find answers to common questions and issues encountered by the community of Ultralytics YOLO users and contributors. -- [Contributing Guide](contributing.md): Discover the protocols for making contributions, including how to submit pull requests, report bugs, and more. -- [Continuous Integration (CI) Guide](CI.md): Gain insights into the CI processes we employ, complete with status reports for each Ultralytics repository. -- [Contributor License Agreement (CLA)](CLA.md): Review the CLA to understand the rights and responsibilities associated with contributing to Ultralytics projects. -- [Minimum Reproducible Example (MRE) Guide](minimum_reproducible_example.md): Learn the process for creating an MRE, which is crucial for the timely and effective resolution of bug reports. -- [Code of Conduct](code_of_conduct.md): Our community guidelines support a respectful and open atmosphere for all collaborators. -- [Environmental, Health and Safety (EHS) Policy](environmental-health-safety.md): Delve into our commitment to sustainability and the well-being of all our stakeholders. -- [Security Policy](security.md): Familiarize yourself with our security protocols and the procedure for reporting vulnerabilities. -- [Privacy Policy](privacy.md): Read our privacy policy to understand how we protect your data and respect your privacy in all our services and operations. - -We encourage you to review these resources for a seamless and productive experience. Our aim is to foster a helpful and friendly environment for everyone in the Ultralytics community. Should you require additional support, please feel free to reach out via GitHub Issues or our official discussion forums. Happy coding! diff --git a/ultralytics-main/docs/en/help/minimum_reproducible_example.md b/ultralytics-main/docs/en/help/minimum_reproducible_example.md deleted file mode 100644 index 47a0cdf..0000000 --- a/ultralytics-main/docs/en/help/minimum_reproducible_example.md +++ /dev/null @@ -1,78 +0,0 @@ ---- -comments: true -description: Learn how to create minimum reproducible examples (MRE) for efficient bug reporting in Ultralytics YOLO repositories with this step-by-step guide. -keywords: Ultralytics, YOLO, minimum reproducible example, MRE, bug reports, guide, dependencies, code, troubleshooting ---- - -# Creating a Minimum Reproducible Example for Bug Reports in Ultralytics YOLO Repositories - -When submitting a bug report for Ultralytics YOLO repositories, it's essential to provide a [minimum reproducible example](https://docs.ultralytics.com/help/minimum_reproducible_example/) (MRE). An MRE is a small, self-contained piece of code that demonstrates the problem you're experiencing. Providing an MRE helps maintainers and contributors understand the issue and work on a fix more efficiently. This guide explains how to create an MRE when submitting bug reports to Ultralytics YOLO repositories. - -## 1. Isolate the Problem - -The first step in creating an MRE is to isolate the problem. This means removing any unnecessary code or dependencies that are not directly related to the issue. Focus on the specific part of the code that is causing the problem and remove any irrelevant code. - -## 2. Use Public Models and Datasets - -When creating an MRE, use publicly available models and datasets to reproduce the issue. For example, use the 'yolov8n.pt' model and the 'coco8.yaml' dataset. This ensures that the maintainers and contributors can easily run your example and investigate the problem without needing access to proprietary data or custom models. - -## 3. Include All Necessary Dependencies - -Make sure to include all the necessary dependencies in your MRE. If your code relies on external libraries, specify the required packages and their versions. Ideally, provide a `requirements.txt` file or list the dependencies in your bug report. - -## 4. Write a Clear Description of the Issue - -Provide a clear and concise description of the issue you're experiencing. Explain the expected behavior and the actual behavior you're encountering. If applicable, include any relevant error messages or logs. - -## 5. Format Your Code Properly - -When submitting an MRE, format your code properly using code blocks in the issue description. This makes it easier for others to read and understand your code. In GitHub, you can create a code block by wrapping your code with triple backticks (\```) and specifying the language: - -
-```python
-# Your Python code goes here
-```
-
- -## 6. Test Your MRE - -Before submitting your MRE, test it to ensure that it accurately reproduces the issue. Make sure that others can run your example without any issues or modifications. - -## Example of an MRE - -Here's an example of an MRE for a hypothetical bug report: - -**Bug description:** - -When running the `detect.py` script on the sample image from the 'coco8.yaml' dataset, I get an error related to the dimensions of the input tensor. - -**MRE:** - -```python -import torch -from ultralytics import YOLO - -# Load the model -model = YOLO("yolov8n.pt") - -# Load a 0-channel image -image = torch.rand(1, 0, 640, 640) - -# Run the model -results = model(image) -``` - -**Error message:** - -``` -RuntimeError: Expected input[1, 0, 640, 640] to have 3 channels, but got 0 channels instead -``` - -**Dependencies:** - -- torch==2.0.0 -- ultralytics==8.0.90 - -In this example, the MRE demonstrates the issue with a minimal amount of code, uses a public model ('yolov8n.pt'), includes all necessary dependencies, and provides a clear description of the problem along with the error message. - -By following these guidelines, you'll help the maintainers and contributors of Ultralytics YOLO repositories to understand and resolve your issue more efficiently. diff --git a/ultralytics-main/docs/en/help/privacy.md b/ultralytics-main/docs/en/help/privacy.md deleted file mode 100644 index c9bc3a5..0000000 --- a/ultralytics-main/docs/en/help/privacy.md +++ /dev/null @@ -1,137 +0,0 @@ ---- -description: Learn about how Ultralytics collects and uses data to improve user experience, ensure software stability, and address privacy concerns, with options to opt-out. -keywords: Ultralytics, Data Collection, User Privacy, Google Analytics, Sentry, Crash Reporting, Anonymized Data, Privacy Settings, Opt-Out ---- - -# Data Collection for Ultralytics Python Package - -## Overview - -[Ultralytics](https://ultralytics.com) is dedicated to the continuous enhancement of the user experience and the capabilities of our Python package, including the advanced YOLO models we develop. Our approach involves the gathering of anonymized usage statistics and crash reports, helping us identify opportunities for improvement and ensuring the reliability of our software. This transparency document outlines what data we collect, its purpose, and the choice you have regarding this data collection. - -## Anonymized Google Analytics - -[Google Analytics](https://developers.google.com/analytics) is a web analytics service offered by Google that tracks and reports website traffic. It allows us to collect data about how our Python package is used, which is crucial for making informed decisions about design and functionality. - -### What We Collect - -- **Usage Metrics**: These metrics help us understand how frequently and in what ways the package is utilized, what features are favored, and the typical command-line arguments that are used. -- **System Information**: We collect general non-identifiable information about your computing environment to ensure our package performs well across various systems. -- **Performance Data**: Understanding the performance of our models during training, validation, and inference helps us in identifying optimization opportunities. - -For more information about Google Analytics and data privacy, visit [Google Analytics Privacy](https://support.google.com/analytics/answer/6004245). - -### How We Use This Data - -- **Feature Improvement**: Insights from usage metrics guide us in enhancing user satisfaction and interface design. -- **Optimization**: Performance data assist us in fine-tuning our models for better efficiency and speed across diverse hardware and software configurations. -- **Trend Analysis**: By studying usage trends, we can predict and respond to the evolving needs of our community. - -### Privacy Considerations - -We take several measures to ensure the privacy and security of the data you entrust to us: - -- **Anonymization**: We configure Google Analytics to anonymize the data collected, which means no personally identifiable information (PII) is gathered. You can use our services with the assurance that your personal details remain private. -- **Aggregation**: Data is analyzed only in aggregate form. This practice ensures that patterns can be observed without revealing any individual user's activity. -- **No Image Data Collection**: Ultralytics does not collect, process, or view any training or inference images. - -## Sentry Crash Reporting - -[Sentry](https://sentry.io/) is a developer-centric error tracking software that aids in identifying, diagnosing, and resolving issues in real-time, ensuring the robustness and reliability of applications. Within our package, it plays a crucial role by providing insights through crash reporting, significantly contributing to the stability and ongoing refinement of our software. - -!!! Note - - Crash reporting via Sentry is activated only if the `sentry-sdk` Python package is pre-installed on your system. This package isn't included in the `ultralytics` prerequisites and won't be installed automatically by Ultralytics. - -### What We Collect - -If the `sentry-sdk` Python package is pre-installed on your system a crash event may send the following information: - -- **Crash Logs**: Detailed reports on the application's condition at the time of a crash, which are vital for our debugging efforts. -- **Error Messages**: We record error messages generated during the operation of our package to understand and resolve potential issues quickly. - -To learn more about how Sentry handles data, please visit [Sentry's Privacy Policy](https://sentry.io/privacy/). - -### How We Use This Data - -- **Debugging**: Analyzing crash logs and error messages enables us to swiftly identify and correct software bugs. -- **Stability Metrics**: By constantly monitoring for crashes, we aim to improve the stability and reliability of our package. - -### Privacy Considerations - -- **Sensitive Information**: We ensure that crash logs are scrubbed of any personally identifiable or sensitive user data, safeguarding the confidentiality of your information. -- **Controlled Collection**: Our crash reporting mechanism is meticulously calibrated to gather only what is essential for troubleshooting while respecting user privacy. - -By detailing the tools used for data collection and offering additional background information with URLs to their respective privacy pages, users are provided with a comprehensive view of our practices, emphasizing transparency and respect for user privacy. - -## Disabling Data Collection - -We believe in providing our users with full control over their data. By default, our package is configured to collect analytics and crash reports to help improve the experience for all users. However, we respect that some users may prefer to opt out of this data collection. - -To opt out of sending analytics and crash reports, you can simply set `sync=False` in your YOLO settings. This ensures that no data is transmitted from your machine to our analytics tools. - -### Inspecting Settings - -To gain insight into the current configuration of your settings, you can view them directly: - -!!! Example "View settings" - - === "Python" - You can use Python to view your settings. Start by importing the `settings` object from the `ultralytics` module. Print and return settings using the following commands: - ```python - from ultralytics import settings - - # View all settings - print(settings) - - # Return analytics and crash reporting setting - value = settings['sync'] - ``` - - === "CLI" - Alternatively, the command-line interface allows you to check your settings with a simple command: - ```bash - yolo settings - ``` - -### Modifying Settings - -Ultralytics allows users to easily modify their settings. Changes can be performed in the following ways: - -!!! Example "Update settings" - - === "Python" - Within the Python environment, call the `update` method on the `settings` object to change your settings: - ```python - from ultralytics import settings - - # Disable analytics and crash reporting - settings.update({'sync': False}) - - # Reset settings to default values - settings.reset() - ``` - - === "CLI" - If you prefer using the command-line interface, the following commands will allow you to modify your settings: - ```bash - # Disable analytics and crash reporting - yolo settings sync=False - - # Reset settings to default values - yolo settings reset - ``` - -The `sync=False` setting will prevent any data from being sent to Google Analytics or Sentry. Your settings will be respected across all sessions using the Ultralytics package and saved to disk for future sessions. - -## Commitment to Privacy - -Ultralytics takes user privacy seriously. We design our data collection practices with the following principles: - -- **Transparency**: We are open about the data we collect and how it is used. -- **Control**: We give users full control over their data. -- **Security**: We employ industry-standard security measures to protect the data we collect. - -## Questions or Concerns - -If you have any questions or concerns about our data collection practices, please reach out to us via our [contact form](https://ultralytics.com/contact) or via [support@ultralytics.com](mailto:support@ultralytics.com). We are dedicated to ensuring our users feel informed and confident in their privacy when using our package. diff --git a/ultralytics-main/docs/en/help/security.md b/ultralytics-main/docs/en/help/security.md deleted file mode 100644 index 01ea1f8..0000000 --- a/ultralytics-main/docs/en/help/security.md +++ /dev/null @@ -1,36 +0,0 @@ ---- -description: Explore Ultralytics' comprehensive security strategies safeguarding user data and systems. Learn about our diverse security tools, including Snyk, GitHub CodeQL, and Dependabot Alerts. -keywords: Ultralytics, Comprehensive Security, user data protection, Snyk, GitHub CodeQL, Dependabot, vulnerability management, coding security practices ---- - -# Ultralytics Security Policy - -At [Ultralytics](https://ultralytics.com), the security of our users' data and systems is of utmost importance. To ensure the safety and security of our [open-source projects](https://github.com/ultralytics), we have implemented several measures to detect and prevent security vulnerabilities. - -## Snyk Scanning - -We utilize [Snyk](https://snyk.io/advisor/python/ultralytics) to conduct comprehensive security scans on Ultralytics repositories. Snyk's robust scanning capabilities extend beyond dependency checks; it also examines our code and Dockerfiles for various vulnerabilities. By identifying and addressing these issues proactively, we ensure a higher level of security and reliability for our users. - -[![ultralytics](https://snyk.io/advisor/python/ultralytics/badge.svg)](https://snyk.io/advisor/python/ultralytics) - -## GitHub CodeQL Scanning - -Our security strategy includes GitHub's [CodeQL](https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/about-code-scanning-with-codeql) scanning. CodeQL delves deep into our codebase, identifying complex vulnerabilities like SQL injection and XSS by analyzing the code's semantic structure. This advanced level of analysis ensures early detection and resolution of potential security risks. - -[![CodeQL](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml/badge.svg)](https://github.com/ultralytics/ultralytics/actions/workflows/codeql.yaml) - -## GitHub Dependabot Alerts - -[Dependabot](https://docs.github.com/en/code-security/dependabot) is integrated into our workflow to monitor dependencies for known vulnerabilities. When a vulnerability is identified in one of our dependencies, Dependabot alerts us, allowing for swift and informed remediation actions. - -## GitHub Secret Scanning Alerts - -We employ GitHub [secret scanning](https://docs.github.com/en/code-security/secret-scanning/managing-alerts-from-secret-scanning) alerts to detect sensitive data, such as credentials and private keys, accidentally pushed to our repositories. This early detection mechanism helps prevent potential security breaches and data exposures. - -## Private Vulnerability Reporting - -We enable private vulnerability reporting, allowing users to discreetly report potential security issues. This approach facilitates responsible disclosure, ensuring vulnerabilities are handled securely and efficiently. - -If you suspect or discover a security vulnerability in any of our repositories, please let us know immediately. You can reach out to us directly via our [contact form](https://ultralytics.com/contact) or via [security@ultralytics.com](mailto:security@ultralytics.com). Our security team will investigate and respond as soon as possible. - -We appreciate your help in keeping all Ultralytics open-source projects secure and safe for everyone 🙏. diff --git a/ultralytics-main/docs/en/hub/api/index.md b/ultralytics-main/docs/en/hub/api/index.md deleted file mode 100644 index f8d7802..0000000 --- a/ultralytics-main/docs/en/hub/api/index.md +++ /dev/null @@ -1,34 +0,0 @@ ---- -description: Discover what's next for Ultralytics with our under-construction page, previewing new, groundbreaking AI and ML features coming soon. -keywords: Ultralytics, coming soon, under construction, new features, AI updates, ML advancements, YOLO, technology preview ---- - -# Under Construction 🏗️🌟 - -Welcome to the Ultralytics "Under Construction" page! Here, we're hard at work developing the next generation of AI and ML innovations. This page serves as a teaser for the exciting updates and new features we're eager to share with you! - -## Exciting New Features on the Way 🎉 - -- **Innovative Breakthroughs:** Get ready for advanced features and services that will transform your AI and ML experience. -- **New Horizons:** Anticipate novel products that redefine AI and ML capabilities. -- **Enhanced Services:** We're upgrading our services for greater efficiency and user-friendliness. - -## Stay Updated 🚧 - -This placeholder page is your first stop for upcoming developments. Keep an eye out for: - -- **Newsletter:** Subscribe [here](https://ultralytics.com/#newsletter) for the latest news. -- **Social Media:** Follow us [here](https://www.linkedin.com/company/ultralytics) for updates and teasers. -- **Blog:** Visit our [blog](https://ultralytics.com/blog) for detailed insights. - -## We Value Your Input 🗣️ - -Your feedback shapes our future releases. Share your thoughts and suggestions [here](https://ultralytics.com/contact). - -## Thank You, Community! 🌍 - -Your [contributions](https://docs.ultralytics.com/help/contributing) inspire our continuous [innovation](https://github.com/ultralytics/ultralytics). Stay tuned for the big reveal of what's next in AI and ML at Ultralytics! - ---- - -Excited for what's coming? Bookmark this page and get ready for a transformative AI and ML journey with Ultralytics! 🛠️🤖 diff --git a/ultralytics-main/docs/en/hub/app/android.md b/ultralytics-main/docs/en/hub/app/android.md deleted file mode 100644 index 7a80474..0000000 --- a/ultralytics-main/docs/en/hub/app/android.md +++ /dev/null @@ -1,100 +0,0 @@ ---- -comments: true -description: Learn about the Ultralytics Android App, enabling real-time object detection using YOLO models. Discover in-app features, quantization methods, and delegate options for optimal performance. -keywords: Ultralytics, Android App, real-time object detection, YOLO models, TensorFlow Lite, FP16 quantization, INT8 quantization, CPU, GPU, Hexagon, NNAPI ---- - -# Ultralytics Android App: Real-time Object Detection with YOLO Models - - - Ultralytics HUB preview image -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
-
- - Google Play store  -
- -The Ultralytics Android App is a powerful tool that allows you to run YOLO models directly on your Android device for real-time object detection. This app utilizes TensorFlow Lite for model optimization and various hardware delegates for acceleration, enabling fast and efficient object detection. - -

-
- -
- Watch: Getting Started with the Ultralytics HUB App (IOS & Android) -

- -## Quantization and Acceleration - -To achieve real-time performance on your Android device, YOLO models are quantized to either FP16 or INT8 precision. Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's accuracy. - -### FP16 Quantization - -FP16 (or half-precision) quantization converts the model's 32-bit floating-point numbers to 16-bit floating-point numbers. This reduces the model's size by half and speeds up the inference process, while maintaining a good balance between accuracy and performance. - -### INT8 Quantization - -INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in mean average precision (mAP) due to the lower numerical precision. - -!!! Tip "mAP Reduction in INT8 Models" - - The reduced numerical precision in INT8 models can lead to some loss of information during the quantization process, which may result in a slight decrease in mAP. However, this trade-off is often acceptable considering the substantial performance gains offered by INT8 quantization. - -## Delegates and Performance Variability - -Different delegates are available on Android devices to accelerate model inference. These delegates include CPU, [GPU](https://www.tensorflow.org/lite/android/delegates/gpu), [Hexagon](https://www.tensorflow.org/lite/android/delegates/hexagon) and [NNAPI](https://www.tensorflow.org/lite/android/delegates/nnapi). The performance of these delegates varies depending on the device's hardware vendor, product line, and specific chipsets used in the device. - -1. **CPU**: The default option, with reasonable performance on most devices. -2. **GPU**: Utilizes the device's GPU for faster inference. It can provide a significant performance boost on devices with powerful GPUs. -3. **Hexagon**: Leverages Qualcomm's Hexagon DSP for faster and more efficient processing. This option is available on devices with Qualcomm Snapdragon processors. -4. **NNAPI**: The Android Neural Networks API (NNAPI) serves as an abstraction layer for running ML models on Android devices. NNAPI can utilize various hardware accelerators, such as CPU, GPU, and dedicated AI chips (e.g., Google's Edge TPU, or the Pixel Neural Core). - -Here's a table showing the primary vendors, their product lines, popular devices, and supported delegates: - -| Vendor | Product Lines | Popular Devices | Delegates Supported | -|-----------------------------------------|--------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------| -| [Qualcomm](https://www.qualcomm.com/) | [Snapdragon (e.g., 800 series)](https://www.qualcomm.com/snapdragon) | [Samsung Galaxy S21](https://www.samsung.com/global/galaxy/galaxy-s21-5g/), [OnePlus 9](https://www.oneplus.com/9), [Google Pixel 6](https://store.google.com/product/pixel_6) | CPU, GPU, Hexagon, NNAPI | -| [Samsung](https://www.samsung.com/) | [Exynos (e.g., Exynos 2100)](https://www.samsung.com/semiconductor/minisite/exynos/) | [Samsung Galaxy S21 (Global version)](https://www.samsung.com/global/galaxy/galaxy-s21-5g/) | CPU, GPU, NNAPI | -| [MediaTek](https://i.mediatek.com/) | [Dimensity (e.g., Dimensity 1200)](https://i.mediatek.com/dimensity-1200) | [Realme GT](https://www.realme.com/global/realme-gt), [Xiaomi Redmi Note](https://www.mi.com/en/phone/redmi/note-list) | CPU, GPU, NNAPI | -| [HiSilicon](https://www.hisilicon.com/) | [Kirin (e.g., Kirin 990)](https://www.hisilicon.com/en/products/Kirin) | [Huawei P40 Pro](https://consumer.huawei.com/en/phones/p40-pro/), [Huawei Mate 30 Pro](https://consumer.huawei.com/en/phones/mate30-pro/) | CPU, GPU, NNAPI | -| [NVIDIA](https://www.nvidia.com/) | [Tegra (e.g., Tegra X1)](https://developer.nvidia.com/content/tegra-x1) | [NVIDIA Shield TV](https://www.nvidia.com/en-us/shield/shield-tv/), [Nintendo Switch](https://www.nintendo.com/switch/) | CPU, GPU, NNAPI | - -Please note that the list of devices mentioned is not exhaustive and may vary depending on the specific chipsets and device models. Always test your models on your target devices to ensure compatibility and optimal performance. - -Keep in mind that the choice of delegate can affect performance and model compatibility. For example, some models may not work with certain delegates, or a delegate may not be available on a specific device. As such, it's essential to test your model and the chosen delegate on your target devices for the best results. - -## Getting Started with the Ultralytics Android App - -To get started with the Ultralytics Android App, follow these steps: - -1. Download the Ultralytics App from the [Google Play Store](https://play.google.com/store/apps/details?id=com.ultralytics.ultralytics_app). - -2. Launch the app on your Android device and sign in with your Ultralytics account. If you don't have an account yet, create one [here](https://hub.ultralytics.com/). - -3. Once signed in, you will see a list of your trained YOLO models. Select a model to use for object detection. - -4. Grant the app permission to access your device's camera. - -5. Point your device's camera at objects you want to detect. The app will display bounding boxes and class labels in real-time as it detects objects. - -6. Explore the app's settings to adjust the detection threshold, enable or disable specific object classes, and more. - -With the Ultralytics Android App, you now have the power of real-time object detection using YOLO models right at your fingertips. Enjoy exploring the app's features and optimizing its settings to suit your specific use cases. diff --git a/ultralytics-main/docs/en/hub/app/index.md b/ultralytics-main/docs/en/hub/app/index.md deleted file mode 100644 index ef962e8..0000000 --- a/ultralytics-main/docs/en/hub/app/index.md +++ /dev/null @@ -1,48 +0,0 @@ ---- -comments: true -description: Explore the Ultralytics HUB App, offering the ability to run YOLOv5 and YOLOv8 models on your iOS and Android devices with optimized performance. -keywords: Ultralytics, HUB App, YOLOv5, YOLOv8, mobile AI, real-time object detection, image recognition, mobile device, hardware acceleration, Apple Neural Engine, Android GPU, NNAPI, custom model training ---- - -# Ultralytics HUB App - - - Ultralytics HUB preview image -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
-
- - Apple App store - - Google Play store  -
- -Welcome to the Ultralytics HUB App! We are excited to introduce this powerful mobile app that allows you to run YOLOv5 and YOLOv8 models directly on your [iOS](https://apps.apple.com/xk/app/ultralytics/id1583935240) and [Android](https://play.google.com/store/apps/details?id=com.ultralytics.ultralytics_app) devices. With the HUB App, you can utilize hardware acceleration features like Apple's Neural Engine (ANE) or Android GPU and Neural Network API (NNAPI) delegates to achieve impressive performance on your mobile device. - -## Features - -- **Run YOLOv5 and YOLOv8 models**: Experience the power of YOLO models on your mobile device for real-time object detection and image recognition tasks. -- **Hardware Acceleration**: Benefit from Apple ANE on iOS devices or Android GPU and NNAPI delegates for optimized performance. -- **Custom Model Training**: Train custom models with the Ultralytics HUB platform and preview them live using the HUB App. -- **Mobile Compatibility**: The HUB App supports both iOS and Android devices, bringing the power of YOLO models to a wide range of users. - -## App Documentation - -- [**iOS**](ios.md): Learn about YOLO CoreML models accelerated on Apple's Neural Engine for iPhones and iPads. -- [**Android**](android.md): Explore TFLite acceleration on Android mobile devices. - -Get started today by downloading the Ultralytics HUB App on your mobile device and unlock the potential of YOLOv5 and YOLOv8 models on-the-go. Don't forget to check out our comprehensive [HUB Docs](../index.md) for more information on training, deploying, and using your custom models with the Ultralytics HUB platform. diff --git a/ultralytics-main/docs/en/hub/app/ios.md b/ultralytics-main/docs/en/hub/app/ios.md deleted file mode 100644 index 41e4b63..0000000 --- a/ultralytics-main/docs/en/hub/app/ios.md +++ /dev/null @@ -1,90 +0,0 @@ ---- -comments: true -description: Execute object detection in real-time on your iOS devices utilizing YOLO models. Leverage the power of the Apple Neural Engine and Core ML for fast and efficient object detection. -keywords: Ultralytics, iOS app, object detection, YOLO models, real time, Apple Neural Engine, Core ML, FP16, INT8, quantization ---- - -# Ultralytics iOS App: Real-time Object Detection with YOLO Models - - - Ultralytics HUB preview image -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
-
- - Apple App store -
- -The Ultralytics iOS App is a powerful tool that allows you to run YOLO models directly on your iPhone or iPad for real-time object detection. This app utilizes the Apple Neural Engine and Core ML for model optimization and acceleration, enabling fast and efficient object detection. - -

-
- -
- Watch: Getting Started with the Ultralytics HUB App (IOS & Android) -

- -## Quantization and Acceleration - -To achieve real-time performance on your iOS device, YOLO models are quantized to either FP16 or INT8 precision. Quantization is a process that reduces the numerical precision of the model's weights and biases, thus reducing the model's size and the amount of computation required. This results in faster inference times without significantly affecting the model's accuracy. - -### FP16 Quantization - -FP16 (or half-precision) quantization converts the model's 32-bit floating-point numbers to 16-bit floating-point numbers. This reduces the model's size by half and speeds up the inference process, while maintaining a good balance between accuracy and performance. - -### INT8 Quantization - -INT8 (or 8-bit integer) quantization further reduces the model's size and computation requirements by converting its 32-bit floating-point numbers to 8-bit integers. This quantization method can result in a significant speedup, but it may lead to a slight reduction in accuracy. - -## Apple Neural Engine - -The Apple Neural Engine (ANE) is a dedicated hardware component integrated into Apple's A-series and M-series chips. It's designed to accelerate machine learning tasks, particularly for neural networks, allowing for faster and more efficient execution of your YOLO models. - -By combining quantized YOLO models with the Apple Neural Engine, the Ultralytics iOS App achieves real-time object detection on your iOS device without compromising on accuracy or performance. - -| Release Year | iPhone Name | Chipset Name | Node Size | ANE TOPs | -|--------------|------------------------------------------------------|-------------------------------------------------------|-----------|----------| -| 2017 | [iPhone X](https://en.wikipedia.org/wiki/IPhone_X) | [A11 Bionic](https://en.wikipedia.org/wiki/Apple_A11) | 10 nm | 0.6 | -| 2018 | [iPhone XS](https://en.wikipedia.org/wiki/IPhone_XS) | [A12 Bionic](https://en.wikipedia.org/wiki/Apple_A12) | 7 nm | 5 | -| 2019 | [iPhone 11](https://en.wikipedia.org/wiki/IPhone_11) | [A13 Bionic](https://en.wikipedia.org/wiki/Apple_A13) | 7 nm | 6 | -| 2020 | [iPhone 12](https://en.wikipedia.org/wiki/IPhone_12) | [A14 Bionic](https://en.wikipedia.org/wiki/Apple_A14) | 5 nm | 11 | -| 2021 | [iPhone 13](https://en.wikipedia.org/wiki/IPhone_13) | [A15 Bionic](https://en.wikipedia.org/wiki/Apple_A15) | 5 nm | 15.8 | -| 2022 | [iPhone 14](https://en.wikipedia.org/wiki/IPhone_14) | [A16 Bionic](https://en.wikipedia.org/wiki/Apple_A16) | 4 nm | 17.0 | - -Please note that this list only includes iPhone models from 2017 onwards, and the ANE TOPs values are approximate. - -## Getting Started with the Ultralytics iOS App - -To get started with the Ultralytics iOS App, follow these steps: - -1. Download the Ultralytics App from the [App Store](https://apps.apple.com/xk/app/ultralytics/id1583935240). - -2. Launch the app on your iOS device and sign in with your Ultralytics account. If you don't have an account yet, create one [here](https://hub.ultralytics.com/). - -3. Once signed in, you will see a list of your trained YOLO models. Select a model to use for object detection. - -4. Grant the app permission to access your device's camera. - -5. Point your device's camera at objects you want to detect. The app will display bounding boxes and class labels in real-time as it detects objects. - -6. Explore the app's settings to adjust the detection threshold, enable or disable specific object classes, and more. - -With the Ultralytics iOS App, you can now leverage the power of YOLO models for real-time object detection on your iPhone or iPad, powered by the Apple Neural Engine and optimized with FP16 or INT8 quantization. diff --git a/ultralytics-main/docs/en/hub/cloud-training.md b/ultralytics-main/docs/en/hub/cloud-training.md deleted file mode 100644 index f774475..0000000 --- a/ultralytics-main/docs/en/hub/cloud-training.md +++ /dev/null @@ -1,89 +0,0 @@ ---- -comments: true -description: Learn how to use Ultralytics HUB for efficient and user-friendly AI model training in the cloud. Follow our detailed guide for easy model creation, training, evaluation, and deployment. -keywords: Ultralytics, HUB Models, AI model training, model creation, model training, model evaluation, model deployment ---- - -# Cloud Training - -[Ultralytics HUB](https://hub.ultralytics.com/) provides a powerful and user-friendly cloud platform to train custom object detection models. Easily select your dataset and the desired training method, then kick off the process with just a few clicks. Ultralytics HUB offers pre-built options and various model architectures to streamline your workflow. - -![cloud training cover](https://github.com/ultralytics/ultralytics/assets/19519529/cbfdb3b8-ad35-44a6-afe6-61ec0b8e8b8d) - -Read more about creating and other details of a Model at our [HUB Models page](models.md) - -

-
- -
- Watch: New Feature 🌟 Introducing Ultralytics HUB Cloud Training -

- -## Selecting an Instance - -For details on picking a model and instances for it, please read our [Instances guide Page](models.md) - -## Steps to Train the Model - -Once the instance has been selected, training a model using Ultralytics HUB is a three-step process, as below: - -1. Picking a Dataset - Read more about datasets, steps to add/remove datasets from the [Dataset page](datasets.md) -2. Picking a Model - Read more about models, steps to create/share and handle a model on the [HUB Models page](models.md) -3. Training the Model on the Chosen Dataset - -Ultralytics HUB offers three training options: - -- **Ultralytics Cloud** - Explained in this page. -- **Google Colab** - Train on Google's popular Colab notebooks. -- **Bring your own agent** - Train models locally on your own hardware or on-premise GPU servers. - -In order to start training your model, follow the instructions presented in these steps. - -## Training via Ultralytics Cloud - -To start training your model using Ultralytics Cloud, simply select the Training Duration, Available Instances, and Payment options. - -**Training Duration** - Ultralytics offers two kinds of training durations: - -1. Training based on `Epochs`: This option allows you to train your model based on the number of times your dataset needs to go through the cycle of train, label, and test. The exact pricing based on the number of epochs is hard to determine. Hence, if the credit gets exhausted before the intended number of epochs, the training pauses, and you get a prompt to top-up and resume training. -2. Timed Training: The timed training feature allows you to fix the time duration of the entire training process and also determines the estimated amount before the start of training. - -![Ultralytics cloud screenshot of training duration options](https://github.com/ultralytics/ultralytics/assets/19519529/47b96f3f-a9ea-441a-b065-cba97edc333f) - -When the training starts, you can click **Done** and monitor the training progress on the Model page. - -## Monitor Your Training - -Once the model and mode of training have been selected, you can monitor the training procedure on the `Train` section with the link provided in the terminal (on your agent/Google Colab) or a button from Ultralytics Cloud. - -![Monitor your Training](https://github.com/ultralytics/ultralytics/assets/19519529/316f8301-0d60-465e-8c99-aa3daf66433c) - -## Stopping and Resuming Your Training - -Once the training has started, you can `Stop` the training, which will also correspondingly pause the credit usage. You can then `Resume` the training from the point where it stopped. - -![Pausing and Resuming Training](https://github.com/ultralytics/ultralytics/assets/19519529/b2707a93-fa5c-4ee2-8443-6be9e1c2857d) - -## Payments and Billing Options - -Ultralytics HUB offers `Pay Now` as upfront and/or using `Ultralytics HUB Account` as a wallet to top up and fulfill the billing. You can choose from two types of accounts: `Free` and `Pro` user. - -To access your profile, click on the profile picture in the bottom left corner. - -![Clicking profile picture](https://github.com/ultralytics/ultralytics/assets/19519529/53e5410e-06f5-4b40-b29d-ef00b5779163) - -Click on the Billing tab to view your current plan and options to upgrade it. - -![Clicking Upgrade button](https://github.com/ultralytics/ultralytics/assets/19519529/361b43c7-a9d4-4d05-b80b-dc1fa8bce829) - -You will be prompted with different available plans, and you can pick from the available plans as shown below. - -![Picking a plan](https://github.com/ultralytics/ultralytics/assets/19519529/4326b01c-0d7d-4850-ac4f-ced2de3339ee) - -Navigate to the Payment page, fill in the details, and complete the payment. - -![Payment Page](https://github.com/ultralytics/ultralytics/assets/19519529/5deebabe-1d8a-485a-b290-e038729c849f) diff --git a/ultralytics-main/docs/en/hub/datasets.md b/ultralytics-main/docs/en/hub/datasets.md deleted file mode 100644 index aadc59d..0000000 --- a/ultralytics-main/docs/en/hub/datasets.md +++ /dev/null @@ -1,146 +0,0 @@ ---- -comments: true -description: Learn how Ultralytics HUB datasets streamline your ML workflow. Upload, format, validate, access, share, edit or delete datasets for Ultralytics YOLO model training. -keywords: Ultralytics, HUB datasets, YOLO model training, upload datasets, dataset validation, ML workflow, share datasets ---- - -# HUB Datasets - -[Ultralytics HUB](https://hub.ultralytics.com/) datasets are a practical solution for managing and leveraging your custom datasets. - -Once uploaded, datasets can be immediately utilized for model training. This integrated approach facilitates a seamless transition from dataset management to model training, significantly simplifying the entire process. - -

-
- -
- Watch: Watch: Upload Datasets to Ultralytics HUB | Complete Walkthrough of Dataset Upload Feature -

- -## Upload Dataset - -Ultralytics HUB datasets are just like YOLOv5 and YOLOv8 🚀 datasets. They use the same structure and the same label formats to keep everything simple. - -Before you upload a dataset to Ultralytics HUB, make sure to **place your dataset YAML file inside the dataset root directory** and that **your dataset YAML, directory and ZIP have the same name**, as shown in the example below, and then zip the dataset directory. - -For example, if your dataset is called "coco8", as our [COCO8](https://docs.ultralytics.com/datasets/detect/coco8) example dataset, then you should have a `coco8.yaml` inside your `coco8/` directory, which will create a `coco8.zip` when zipped: - -```bash -zip -r coco8.zip coco8 -``` - -You can download our [COCO8](https://github.com/ultralytics/hub/blob/main/example_datasets/coco8.zip) example dataset and unzip it to see exactly how to structure your dataset. - -

- COCO8 Dataset Structure -

- -The dataset YAML is the same standard YOLOv5 and YOLOv8 YAML format. - -!!! Example "coco8.yaml" - - ```yaml - --8<-- "ultralytics/cfg/datasets/coco8.yaml" - ``` - -After zipping your dataset, you should validate it before uploading it to Ultralytics HUB. Ultralytics HUB conducts the dataset validation check post-upload, so by ensuring your dataset is correctly formatted and error-free ahead of time, you can forestall any setbacks due to dataset rejection. - -```py -from ultralytics.hub import check_dataset - -check_dataset('path/to/coco8.zip') -``` - -Once your dataset ZIP is ready, navigate to the [Datasets](https://hub.ultralytics.com/datasets) page by clicking on the **Datasets** button in the sidebar. - -![Ultralytics HUB screenshot of the Home page with an arrow pointing to the Datasets button in the sidebar](https://github.com/ultralytics/ultralytics/assets/19519529/2d9f774c-100d-4ff4-a82b-2a38ced33c21) - -Click on the **Upload Dataset** button on the top right of the page. This action will trigger the **Upload Dataset** dialog. - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Upload Dataset button](https://github.com/ultralytics/ultralytics/assets/19519529/52ac10f5-ce42-483a-ac02-1d37d2cba3de) - -Upload your dataset in the _Dataset .zip file_ field. - -You have the additional option to set a custom name and description for your Ultralytics HUB dataset. - -When you're happy with your dataset configuration, click **Upload**. - -![Ultralytics HUB screenshot of the Upload Dataset dialog with an arrow pointing to the Upload button](https://github.com/ultralytics/ultralytics/assets/19519529/7d210ff6-bdb2-4535-a661-0470274bd7d6) - -After your dataset is uploaded and processed, you will be able to access it from the Datasets page. - -![Ultralytics HUB screenshot of the Datasets page with an arrow pointing to one of the datasets](https://github.com/ultralytics/ultralytics/assets/19519529/a05d9b66-f8ba-4474-b8ac-ebe0dd143831) - -You can view the images in your dataset grouped by splits (Train, Validation, Test). - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Images tab](https://github.com/ultralytics/ultralytics/assets/19519529/e07468e3-6284-4334-9783-84bfb11130f8) - -!!! tip "Tip" - - Each image can be enlarged for better visualization. - - ![Ultralytics HUB screenshot of the Images tab inside the Dataset page with an arrow pointing to the expand icon](https://github.com/ultralytics/ultralytics/assets/19519529/26f411a0-5153-4805-a8c1-cbd379708e28) - - ![Ultralytics HUB screenshot of the Images tab inside the Dataset page with one of the images expanded](https://github.com/ultralytics/ultralytics/assets/19519529/7d5e0d50-85e5-4014-9f5b-464284e5b291) - -Also, you can analyze your dataset by click on the **Overview** tab. - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Overview tab](https://github.com/ultralytics/ultralytics/assets/19519529/5eaacd5d-fedf-4332-9091-1418c9f333cb) - -Next, [train a model](https://docs.ultralytics.com/hub/models/#train-model) on your dataset. - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Train Model button](https://github.com/ultralytics/ultralytics/assets/19519529/cb709e5f-a10b-478f-a81d-a48f61c193fe) - -## Share Dataset - -!!! Info "Info" - - Ultralytics HUB's sharing functionality provides a convenient way to share datasets with others. This feature is designed to accommodate both existing Ultralytics HUB users and those who have yet to create an account. - -!!! note "Note" - - You have control over the general access of your datasets. - - You can choose to set the general access to "Private", in which case, only you will have access to it. Alternatively, you can set the general access to "Unlisted" which grants viewing access to anyone who has the direct link to the dataset, regardless of whether they have an Ultralytics HUB account or not. - -Navigate to the Dataset page of the dataset you want to share, open the dataset actions dropdown and click on the **Share** option. This action will trigger the **Share Dataset** dialog. - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Share option](https://github.com/ultralytics/ultralytics/assets/19519529/9a0e61e7-2838-42b3-8abe-a22980e6c680) - -!!! tip "Tip" - - You can also share a dataset directly from the [Datasets](https://hub.ultralytics.com/datasets) page. - - ![Ultralytics HUB screenshot of the Datasets page with an arrow pointing to the Share option of one of the datasets](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/datasets/hub_share_dataset_2.jpg) - -Set the general access to "Unlisted" and click **Save**. - -![Ultralytics HUB screenshot of the Share Dataset dialog with an arrow pointing to the dropdown and one to the Save button](https://github.com/ultralytics/ultralytics/assets/19519529/5818b928-19a3-48a8-892d-27ac1dc684dd) - -Now, anyone who has the direct link to your dataset can view it. - -!!! tip "Tip" - - You can easily click on the dataset's link shown in the **Share Dataset** dialog to copy it. - - ![Ultralytics HUB screenshot of the Share Dataset dialog with an arrow pointing to the dataset's link](https://github.com/ultralytics/ultralytics/assets/19519529/8ede7d20-2a68-411d-9de5-3175b5ba7038) - -## Edit / Delete Dataset - -Navigate to the Dataset page of the dataset you want to edit, open the dataset actions dropdown and click on the **Edit** option. This action will trigger the **Update Dataset** dialog. - -![Ultralytics HUB screenshot of the Dataset page with an arrow pointing to the Edit and Delete option](https://github.com/ultralytics/ultralytics/assets/19519529/6c248c8c-29cd-4bd5-b33d-43e90aa1d000) - -Apply the desired modifications to your dataset and then confirm the changes by clicking **Save**. - -Navigate to the Dataset page of the dataset you want to delete, open the dataset actions dropdown and click on the **Delete** option. This action will delete the dataset. - -!!! note "Note" - - If you change your mind, you can restore the dataset from the [Trash](https://hub.ultralytics.com/trash) page. - - ![Ultralytics HUB screenshot of the Trash page with an arrow pointing to the Restore option of one of the datasets](https://github.com/ultralytics/ultralytics/assets/19519529/56a9460c-0e06-4659-989d-715211b9d7ce) diff --git a/ultralytics-main/docs/en/hub/index.md b/ultralytics-main/docs/en/hub/index.md deleted file mode 100644 index 4b40240..0000000 --- a/ultralytics-main/docs/en/hub/index.md +++ /dev/null @@ -1,61 +0,0 @@ ---- -comments: true -description: Gain insights into training and deploying your YOLOv5 and YOLOv8 models with Ultralytics HUB. Explore pre-trained models, templates and various integrations. -keywords: Ultralytics HUB, YOLOv5, YOLOv8, model training, model deployment, pretrained models, model integrations ---- - -# Ultralytics HUB - - - Ultralytics HUB preview image -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
-
- - CI CPU - - Open In Colab -
- -👋 Hello from the [Ultralytics](https://ultralytics.com/) Team! We've been working hard these last few months to launch [Ultralytics HUB](https://bit.ly/ultralytics_hub), a new web tool for training and deploying all your YOLOv5 and YOLOv8 🚀 models from one spot! - -## Introduction - -HUB is designed to be user-friendly and intuitive, with a drag-and-drop interface that allows users to easily upload their data and train new models quickly. It offers a range of pre-trained models and templates to choose from, making it easy for users to get started with training their own models. Once a model is trained, it can be easily deployed and used for real-time object detection, instance segmentation and classification tasks. - -

-
- -
- Watch: Train Your Custom YOLO Models In A Few Clicks with Ultralytics HUB. -

- -We hope that the resources here will help you get the most out of HUB. Please browse the HUB Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions! - -- [**Quickstart**](quickstart.md). Start training and deploying YOLO models with HUB in seconds. -- [**Datasets: Preparing and Uploading**](datasets.md). Learn how to prepare and upload your datasets to HUB in YOLO format. -- [**Projects: Creating and Managing**](projects.md). Group your models into projects for improved organization. -- [**Models: Training and Exporting**](models.md). Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment. -- [**Integrations: Options**](integrations.md). Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle. -- [**Ultralytics HUB App**](app/index.md). Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device. - - [**iOS**](app/ios.md). Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads. - - [**Android**](app/android.md). Explore TFLite acceleration on mobile devices. -- [**Inference API**](inference-api.md). Understand how to use the Inference API for running your trained models in the cloud to generate predictions. diff --git a/ultralytics-main/docs/en/hub/inference-api.md b/ultralytics-main/docs/en/hub/inference-api.md deleted file mode 100644 index 869d21f..0000000 --- a/ultralytics-main/docs/en/hub/inference-api.md +++ /dev/null @@ -1,480 +0,0 @@ ---- -comments: true -description: Access object detection capabilities of YOLOv8 via our RESTful API. Learn how to use the YOLO Inference API with Python or cURL for swift object detection. -keywords: Ultralytics, YOLOv8, Inference API, object detection, RESTful API, Python, cURL, Quickstart ---- - -# YOLO Inference API - -The YOLO Inference API allows you to access the YOLOv8 object detection capabilities via a RESTful API. This enables you to run object detection on images without the need to install and set up the YOLOv8 environment locally. - -![Inference API Screenshot](https://github.com/ultralytics/ultralytics/assets/19519529/a8c00e55-1590-403b-bdee-ed456c60af4d) Screenshot of the Inference API section in the trained model Preview tab. - -

-
- -
- Watch: Ultralytics HUB Inference API Walkthrough -

- -## API URL - -The API URL is the address used to access the YOLO Inference API. In this case, the base URL is: - -``` -https://api.ultralytics.com/v1/predict -``` - -## Example Usage in Python - -To access the YOLO Inference API with the specified model and API key using Python, you can use the following code: - -```python -import requests - -# API URL, use actual MODEL_ID -url = f"https://api.ultralytics.com/v1/predict/MODEL_ID" - -# Headers, use actual API_KEY -headers = {"x-api-key": "API_KEY"} - -# Inference arguments (optional) -data = {"size": 640, "confidence": 0.25, "iou": 0.45} - -# Load image and send request -with open("path/to/image.jpg", "rb") as image_file: - files = {"image": image_file} - response = requests.post(url, headers=headers, files=files, data=data) - -print(response.json()) -``` - -In this example, replace `API_KEY` with your actual API key, `MODEL_ID` with the desired model ID, and `path/to/image.jpg` with the path to the image you want to analyze. - -## Example Usage with cURL - -You can use the YOLO Inference API with client URL (cURL) by utilizing the `curl` command. Replace `API_KEY` with your actual API key, `MODEL_ID` with the desired model ID, and `image.jpg` with the path to the image you want to analyze: - -```bash -curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \ - -H "x-api-key: API_KEY" \ - -F "image=@/path/to/image.jpg" \ - -F "size=640" \ - -F "confidence=0.25" \ - -F "iou=0.45" -``` - -## Passing Arguments - -This command sends a POST request to the YOLO Inference API with the specified `MODEL_ID` in the URL and the `API_KEY` in the request `headers`, along with the image file specified by `@path/to/image.jpg`. - -Here's an example of passing the `size`, `confidence`, and `iou` arguments via the API URL using the `requests` library in Python: - -```python -import requests - -# API URL, use actual MODEL_ID -url = f"https://api.ultralytics.com/v1/predict/MODEL_ID" - -# Headers, use actual API_KEY -headers = {"x-api-key": "API_KEY"} - -# Inference arguments (optional) -data = {"size": 640, "confidence": 0.25, "iou": 0.45} - -# Load image and send request -with open("path/to/image.jpg", "rb") as image_file: - files = {"image": image_file} - response = requests.post(url, headers=headers, files=files, data=data) - -print(response.json()) -``` - -In this example, the `data` dictionary contains the query arguments `size`, `confidence`, and `iou`, which tells the API to run inference at image size 640 with confidence and IoU thresholds of 0.25 and 0.45. - -This will send the query parameters along with the file in the POST request. See the table below for a full list of available inference arguments. - -| Inference Argument | Default | Type | Notes | -|--------------------|---------|---------|------------------------------------------------| -| `size` | `640` | `int` | valid range is `32` - `1280` pixels | -| `confidence` | `0.25` | `float` | valid range is `0.01` - `1.0` | -| `iou` | `0.45` | `float` | valid range is `0.0` - `0.95` | -| `url` | `''` | `str` | optional image URL if not image file is passed | -| `normalize` | `False` | `bool` | | - -## Return JSON format - -The YOLO Inference API returns a JSON list with the detection results. The format of the JSON list will be the same as the one produced locally by the `results[0].tojson()` command. - -The JSON list contains information about the detected objects, their coordinates, classes, and confidence scores. - -### Detect Model Format - -YOLO detection models, such as `yolov8n.pt`, can return JSON responses from local inference, cURL inference, and Python inference. All of these methods produce the same JSON response format. - -!!! Example "Detect Model JSON Response" - - === "`ultralytics`" - - ```python - from ultralytics import YOLO - - # Load model - model = YOLO('yolov8n.pt') - - # Run inference - results = model('image.jpg') - - # Print image.jpg results in JSON format - print(results[0].tojson()) - ``` - - === "cURL" - - ```bash - curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \ - -H "x-api-key: API_KEY" \ - -F "image=@/path/to/image.jpg" \ - -F "size=640" \ - -F "confidence=0.25" \ - -F "iou=0.45" - ``` - - === "Python" - - ```python - import requests - - # API URL, use actual MODEL_ID - url = f"https://api.ultralytics.com/v1/predict/MODEL_ID" - - # Headers, use actual API_KEY - headers = {"x-api-key": "API_KEY"} - - # Inference arguments (optional) - data = {"size": 640, "confidence": 0.25, "iou": 0.45} - - # Load image and send request - with open("path/to/image.jpg", "rb") as image_file: - files = {"image": image_file} - response = requests.post(url, headers=headers, files=files, data=data) - - print(response.json()) - ``` - - === "JSON Response" - - ```json - { - "success": True, - "message": "Inference complete.", - "data": [ - { - "name": "person", - "class": 0, - "confidence": 0.8359682559967041, - "box": { - "x1": 0.08974208831787109, - "y1": 0.27418340047200523, - "x2": 0.8706787109375, - "y2": 0.9887352837456598 - } - }, - { - "name": "person", - "class": 0, - "confidence": 0.8189555406570435, - "box": { - "x1": 0.5847355842590332, - "y1": 0.05813225640190972, - "x2": 0.8930277824401855, - "y2": 0.9903111775716146 - } - }, - { - "name": "tie", - "class": 27, - "confidence": 0.2909725308418274, - "box": { - "x1": 0.3433395862579346, - "y1": 0.6070465511745877, - "x2": 0.40964522361755373, - "y2": 0.9849439832899306 - } - } - ] - } - ``` - -### Segment Model Format - -YOLO segmentation models, such as `yolov8n-seg.pt`, can return JSON responses from local inference, cURL inference, and Python inference. All of these methods produce the same JSON response format. - -!!! Example "Segment Model JSON Response" - - === "`ultralytics`" - - ```python - from ultralytics import YOLO - - # Load model - model = YOLO('yolov8n-seg.pt') - - # Run inference - results = model('image.jpg') - - # Print image.jpg results in JSON format - print(results[0].tojson()) - ``` - - === "cURL" - - ```bash - curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \ - -H "x-api-key: API_KEY" \ - -F "image=@/path/to/image.jpg" \ - -F "size=640" \ - -F "confidence=0.25" \ - -F "iou=0.45" - ``` - - === "Python" - - ```python - import requests - - # API URL, use actual MODEL_ID - url = f"https://api.ultralytics.com/v1/predict/MODEL_ID" - - # Headers, use actual API_KEY - headers = {"x-api-key": "API_KEY"} - - # Inference arguments (optional) - data = {"size": 640, "confidence": 0.25, "iou": 0.45} - - # Load image and send request - with open("path/to/image.jpg", "rb") as image_file: - files = {"image": image_file} - response = requests.post(url, headers=headers, files=files, data=data) - - print(response.json()) - ``` - - === "JSON Response" - - Note `segments` `x` and `y` lengths may vary from one object to another. Larger or more complex objects may have more segment points. - ```json - { - "success": True, - "message": "Inference complete.", - "data": [ - { - "name": "person", - "class": 0, - "confidence": 0.856913149356842, - "box": { - "x1": 0.1064866065979004, - "y1": 0.2798851860894097, - "x2": 0.8738358497619629, - "y2": 0.9894873725043403 - }, - "segments": { - "x": [ - 0.421875, - 0.4203124940395355, - 0.41718751192092896 - ... - ], - "y": [ - 0.2888889014720917, - 0.2916666567325592, - 0.2916666567325592 - ... - ] - } - }, - { - "name": "person", - "class": 0, - "confidence": 0.8512625694274902, - "box": { - "x1": 0.5757311820983887, - "y1": 0.053943040635850696, - "x2": 0.8960096359252929, - "y2": 0.985154045952691 - }, - "segments": { - "x": [ - 0.7515624761581421, - 0.75, - 0.7437499761581421 - ... - ], - "y": [ - 0.0555555559694767, - 0.05833333358168602, - 0.05833333358168602 - ... - ] - } - }, - { - "name": "tie", - "class": 27, - "confidence": 0.6485961675643921, - "box": { - "x1": 0.33911995887756347, - "y1": 0.6057066175672743, - "x2": 0.4081430912017822, - "y2": 0.9916408962673611 - }, - "segments": { - "x": [ - 0.37187498807907104, - 0.37031251192092896, - 0.3687500059604645 - ... - ], - "y": [ - 0.6111111044883728, - 0.6138888597488403, - 0.6138888597488403 - ... - ] - } - } - ] - } - ``` - -### Pose Model Format - -YOLO pose models, such as `yolov8n-pose.pt`, can return JSON responses from local inference, cURL inference, and Python inference. All of these methods produce the same JSON response format. - -!!! Example "Pose Model JSON Response" - - === "`ultralytics`" - - ```python - from ultralytics import YOLO - - # Load model - model = YOLO('yolov8n-seg.pt') - - # Run inference - results = model('image.jpg') - - # Print image.jpg results in JSON format - print(results[0].tojson()) - ``` - - === "cURL" - - ```bash - curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \ - -H "x-api-key: API_KEY" \ - -F "image=@/path/to/image.jpg" \ - -F "size=640" \ - -F "confidence=0.25" \ - -F "iou=0.45" - ``` - - === "Python" - - ```python - import requests - - # API URL, use actual MODEL_ID - url = f"https://api.ultralytics.com/v1/predict/MODEL_ID" - - # Headers, use actual API_KEY - headers = {"x-api-key": "API_KEY"} - - # Inference arguments (optional) - data = {"size": 640, "confidence": 0.25, "iou": 0.45} - - # Load image and send request - with open("path/to/image.jpg", "rb") as image_file: - files = {"image": image_file} - response = requests.post(url, headers=headers, files=files, data=data) - - print(response.json()) - ``` - - === "JSON Response" - - Note COCO-keypoints pretrained models will have 17 human keypoints. The `visible` part of the keypoints indicates whether a keypoint is visible or obscured. Obscured keypoints may be outside the image or may not be visible, i.e. a person's eyes facing away from the camera. - ```json - { - "success": True, - "message": "Inference complete.", - "data": [ - { - "name": "person", - "class": 0, - "confidence": 0.8439509868621826, - "box": { - "x1": 0.1125, - "y1": 0.28194444444444444, - "x2": 0.7953125, - "y2": 0.9902777777777778 - }, - "keypoints": { - "x": [ - 0.5058594942092896, - 0.5103894472122192, - 0.4920862317085266 - ... - ], - "y": [ - 0.48964157700538635, - 0.4643048942089081, - 0.4465252459049225 - ... - ], - "visible": [ - 0.8726999163627625, - 0.653947651386261, - 0.9130823612213135 - ... - ] - } - }, - { - "name": "person", - "class": 0, - "confidence": 0.7474289536476135, - "box": { - "x1": 0.58125, - "y1": 0.0625, - "x2": 0.8859375, - "y2": 0.9888888888888889 - }, - "keypoints": { - "x": [ - 0.778544008731842, - 0.7976160049438477, - 0.7530890107154846 - ... - ], - "y": [ - 0.27595141530036926, - 0.2378823608160019, - 0.23644638061523438 - ... - ], - "visible": [ - 0.8900790810585022, - 0.789978563785553, - 0.8974530100822449 - ... - ] - } - } - ] - } - ``` diff --git a/ultralytics-main/docs/en/hub/integrations.md b/ultralytics-main/docs/en/hub/integrations.md deleted file mode 100644 index a69da48..0000000 --- a/ultralytics-main/docs/en/hub/integrations.md +++ /dev/null @@ -1,62 +0,0 @@ ---- -comments: true -description: Explore integration options for Ultralytics HUB. Currently featuring Roboflow for dataset integration and multiple export formats for your trained models. -keywords: Ultralytics HUB, Integrations, Roboflow, Dataset, Export, YOLOv5, YOLOv8, ONNX, CoreML, TensorRT, TensorFlow ---- - -# HUB Integrations - -🚧 **Under Construction** 🚧 - -Welcome to the Integrations guide for [Ultralytics HUB](https://hub.ultralytics.com/)! We are in the process of expanding this section to provide you with comprehensive guidance on integrating your YOLOv5 and YOLOv8 models with various platforms and formats. Currently, Roboflow is our available dataset integration, with a wide range of export integrations for your trained models. - -

-
- -
- Watch: Train Your Custom YOLO Models In A Few Clicks with Ultralytics HUB. -

- -## Available Integrations - -### Dataset Integrations - -- **Roboflow**: Seamlessly import your datasets for training. - -### Export Integrations - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | - -## Coming Soon - -- Additional Dataset Integrations -- Detailed Export Integration Guides -- Step-by-Step Tutorials for Each Integration - -## Need Immediate Assistance? - -While we're in the process of creating detailed guides: - -- Browse through other [HUB Docs](https://docs.ultralytics.com/hub/) for detailed guides and tutorials. -- Raise an issue on our [GitHub](https://github.com/ultralytics/hub/) for technical support. -- Join our [Discord Community](https://ultralytics.com/discord/) for live discussions and community support. - -We appreciate your patience as we work to make this section comprehensive and user-friendly. Stay tuned for updates! diff --git a/ultralytics-main/docs/en/hub/models.md b/ultralytics-main/docs/en/hub/models.md deleted file mode 100644 index 6a4bc3e..0000000 --- a/ultralytics-main/docs/en/hub/models.md +++ /dev/null @@ -1,130 +0,0 @@ ---- -comments: true -description: Learn how to efficiently train AI models using Ultralytics HUB, a streamlined solution for model creation, training, evaluation, and deployment. -keywords: Ultralytics, HUB Models, AI model training, model creation, model training, model evaluation, model deployment ---- - -# Ultralytics HUB Models - -[Ultralytics HUB](https://hub.ultralytics.com/) models provide a streamlined solution for training vision AI models on custom datasets. - -The process is user-friendly and efficient, involving a simple three-step creation and accelerated training powered by Ultralytics YOLOv8. Real-time updates on model metrics are available during training, allowing users to monitor progress at each step. Once training is completed, models can be previewed and easily deployed to real-world applications. Therefore, Ultralytics HUB offers a comprehensive yet straightforward system for model creation, training, evaluation, and deployment. - -The entire process of training a model is detailed on our [Cloud Training Page](cloud-training.md). - -![Preview of the Models](https://github.com/ultralytics/ultralytics/assets/19519529/a02e1441-f5f6-4935-ad75-ec18e425d8bd) - -## Train Model - -Navigate to the [Models](https://hub.ultralytics.com/models) page by clicking on the **Models** button in the sidebar. - -Training a model using HUB is a 4-step process: - -- **Execute the pre-requisites script**: Run the provided scripts to prepare the virtual environment. -- **Provide the API and start Training**: Once the model is prepared, provide the API key as instructed and execute the code block. -- **Check the results and Metrics**: Upon successful execution, a link is provided to the Metrics Page. This page offers comprehensive details on the trained model, including specifications, loss metrics, dataset information, and image distributions. Additionally, the 'Deploy' tab provides access to the trained model's documentation and license details. -- **Test your model**: Ultralytics HUB offers testing using custom images, device cameras, or links to test on `iPhone` or `Android` devices. - -![Ultralytics HUB screenshot of the Home page](https://github.com/ultralytics/ultralytics/assets/19519529/61428720-aa93-4689-b209-ead7f06fa488) - -!!! tip "Tip" - - You can also train a model directly from the [Home](https://hub.ultralytics.com/home) page. - - ![Ultralytics HUB screenshot of the Home page with an arrow pointing to the Train Model card](https://github.com/ultralytics/ultralytics/assets/19519529/6f9f06f7-e663-4fa7-800c-98675bf1405b) - -Click on the **Train Model** button on the top right of the page to trigger the **Train Model** dialog. - -The **Train Model** dialog has three simple steps: - -### 1. Dataset - -Select the dataset for training and click **Continue**. - -![Ultralytics HUB screenshot of the Train Model dialog with an arrow pointing to a dataset and one to the Continue button](https://github.com/ultralytics/ultralytics/assets/19519529/7ff90f2a-c61e-472f-a573-f725a5bddc1c) - -### 2. Model - -Choose the project, model name, and architecture. Read more about available architectures in our [YOLOv8](https://docs.ultralytics.com/models/yolov8) (and [YOLOv5](https://docs.ultralytics.com/models/yolov5)) documentation. - -Click **Continue** when satisfied with the configuration. - -![Ultralytics HUB screenshot of the Train Model dialog with an arrow pointing to a model architecture and one to the Continue button](https://github.com/ultralytics/ultralytics/assets/19519529/a7a412b3-3e87-48de-b117-c506338f36fb) - -!!! note "Note" - - By default, your model will use a pre-trained model (trained on the [COCO](https://docs.ultralytics.com/datasets/detect/coco) dataset) to reduce training time. - - Advanced options are available to modify this behavior. - -## Preview Model - -Ultralytics HUB offers various ways to preview trained models. - -You can upload an image in the **Test** card under the **Preview** tab to preview your model. - -![Ultralytics HUB screenshot of the Preview tab (Test card) inside the Model page](https://github.com/ultralytics/ultralytics/assets/19519529/a732d13a-8da9-40a8-9f5e-c766bec3fbe9) - -Use our Ultralytics Cloud API to effortlessly [run inference](inference-api.md) with your custom model. - -![Ultralytics HUB screenshot of the Preview tab (Ultralytics Cloud API card) inside the Model page](https://github.com/ultralytics/ultralytics/assets/19519529/77ae0f6c-d89e-433c-b404-77f71c06def5) - -Preview your model in real-time on your [iOS](https://apps.apple.com/xk/app/ultralytics/id1583935240) or [Android](https://play.google.com/store/apps/details?id=com.ultralytics.ultralytics_app) device by [downloading](https://ultralytics.com/app_install) our [Ultralytics HUB Mobile Application](app/index.md). - -![Ultralytics HUB screenshot of the Deploy tab inside the Model page with an arrow pointing to the Real-Time Preview card](https://github.com/ultralytics/ultralytics/assets/19519529/8d711052-5ab1-43bc-bc25-a8802a24b301) - -## Train the model - -Ultralytics HUB offers three training options: - -- **Ultralytics Cloud** - Learn more about training via the Ultralytics [Cloud Training Page](cloud-training.md) -- **Google Colab** -- **Bring your own agent** - -## Training the Model on Google Colab - -To start training using Google Colab, follow the instructions on the Google Colab notebook. - - - Open In Colab - - -![Google Colab Screenshot](https://github.com/ultralytics/ultralytics/assets/19519529/f19d2e04-d33c-446b-91f9-80396e02b68f) - -## Bring your own Agent - -Create an API endpoint through Ultralytics HUB to train the Model locally. Follow the provided steps, and access training details via the link generated on the Agent terminal. - -![Bring your own agent screenshot](https://github.com/ultralytics/ultralytics/assets/19519529/7d8dcd7a-19ec-4ada-87bf-1a1ba1d01ceb) - -## Deploy Model - -Export your model to 13 different formats, including ONNX, OpenVINO, CoreML, TensorFlow, Paddle, and more. - -![Ultralytics HUB screenshot of the Deploy tab inside the Model page with all formats exported](https://github.com/ultralytics/ultralytics/assets/19519529/083a929d-2bbd-45f8-9dec-2767949caaba) - -## Share Model - -Ultralytics HUB's sharing functionality provides a convenient way to share models. Control the general access of your models, setting them to "Private" or "Unlisted". - -Navigate to the Model page, open the model actions dropdown, and click on the **Share** option. - -![Ultralytics HUB screenshot of the Model page with an arrow pointing to the Share option](https://github.com/ultralytics/ultralytics/assets/19519529/ac98724e-9267-4557-a792-33073c47bbff) - -Set the general access and click **Save**. - -![Ultralytics HUB screenshot of the Share Model dialog with an arrow pointing to the dropdown and one to the Save button](https://github.com/ultralytics/ultralytics/assets/19519529/65afcd99-1f9e-4be8-b287-096a7c74fc0e) - -Now, anyone with the direct link can view your model. - -!!! tip "Tip" - - Easily copy the model's link shown in the **Share Model** dialog by clicking on it. - - ![Ultralytics HUB screenshot of the Share Model dialog with an arrow pointing to the model's link](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/models/hub_share_model_4.jpg) - -## Edit and Delete Model - -Navigate to the Model page, open the model actions dropdown, and click on the **Edit** option to update the model. To delete the model, select the **Delete** option. - -![Ultralytics HUB screenshot of the Model page with an arrow pointing to the Edit option](https://github.com/ultralytics/ultralytics/assets/19519529/5c2db731-45dc-4f04-ac0f-9ad600c140a1) diff --git a/ultralytics-main/docs/en/hub/on-premise/index.md b/ultralytics-main/docs/en/hub/on-premise/index.md deleted file mode 100644 index f8d7802..0000000 --- a/ultralytics-main/docs/en/hub/on-premise/index.md +++ /dev/null @@ -1,34 +0,0 @@ ---- -description: Discover what's next for Ultralytics with our under-construction page, previewing new, groundbreaking AI and ML features coming soon. -keywords: Ultralytics, coming soon, under construction, new features, AI updates, ML advancements, YOLO, technology preview ---- - -# Under Construction 🏗️🌟 - -Welcome to the Ultralytics "Under Construction" page! Here, we're hard at work developing the next generation of AI and ML innovations. This page serves as a teaser for the exciting updates and new features we're eager to share with you! - -## Exciting New Features on the Way 🎉 - -- **Innovative Breakthroughs:** Get ready for advanced features and services that will transform your AI and ML experience. -- **New Horizons:** Anticipate novel products that redefine AI and ML capabilities. -- **Enhanced Services:** We're upgrading our services for greater efficiency and user-friendliness. - -## Stay Updated 🚧 - -This placeholder page is your first stop for upcoming developments. Keep an eye out for: - -- **Newsletter:** Subscribe [here](https://ultralytics.com/#newsletter) for the latest news. -- **Social Media:** Follow us [here](https://www.linkedin.com/company/ultralytics) for updates and teasers. -- **Blog:** Visit our [blog](https://ultralytics.com/blog) for detailed insights. - -## We Value Your Input 🗣️ - -Your feedback shapes our future releases. Share your thoughts and suggestions [here](https://ultralytics.com/contact). - -## Thank You, Community! 🌍 - -Your [contributions](https://docs.ultralytics.com/help/contributing) inspire our continuous [innovation](https://github.com/ultralytics/ultralytics). Stay tuned for the big reveal of what's next in AI and ML at Ultralytics! - ---- - -Excited for what's coming? Bookmark this page and get ready for a transformative AI and ML journey with Ultralytics! 🛠️🤖 diff --git a/ultralytics-main/docs/en/hub/projects.md b/ultralytics-main/docs/en/hub/projects.md deleted file mode 100644 index a512331..0000000 --- a/ultralytics-main/docs/en/hub/projects.md +++ /dev/null @@ -1,180 +0,0 @@ ---- -comments: true -description: Learn how to manage Ultralytics HUB projects. Understand effective strategies to create, share, edit, delete, and compare models in an organized workspace. -keywords: Ultralytics, HUB projects, Create project, Edit project, Share project, Delete project, Compare Models, Model Management ---- - -# Ultralytics HUB Projects - -[Ultralytics HUB](https://hub.ultralytics.com/) projects provide an effective solution for consolidating and managing your models. If you are working with several models that perform similar tasks or have related purposes, Ultralytics HUB projects allow you to group these models together. - -This creates a unified and organized workspace that facilitates easier model management, comparison and development. Having similar models or various iterations together can facilitate rapid benchmarking, as you can compare their effectiveness. This can lead to faster, more insightful iterative development and refinement of your models. - -

-
- -
- Watch: Train YOLOv8 Pose Model on Tiger-Pose Dataset Using Ultralytics HUB -

- -## Create Project - -Navigate to the [Projects](https://hub.ultralytics.com/projects) page by clicking on the **Projects** button in the sidebar. - -![Ultralytics HUB screenshot of the Home page with an arrow pointing to the Projects button in the sidebar](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_1.jpg) - -??? tip "Tip" - - You can also create a project directly from the [Home](https://hub.ultralytics.com/home) page. - - ![Ultralytics HUB screenshot of the Home page with an arrow pointing to the Create Project card](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_2.jpg) - -Click on the **Create Project** button on the top right of the page. This action will trigger the **Create Project** dialog, opening up a suite of options for tailoring your project to your needs. - -![Ultralytics HUB screenshot of the Projects page with an arrow pointing to the Create Project button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_3.jpg) - -Type the name of your project in the _Project name_ field or keep the default name and finalize the project creation with a single click. - -You have the additional option to enrich your project with a description and a unique image, enhancing its recognizability on the Projects page. - -When you're happy with your project configuration, click **Create**. - -![Ultralytics HUB screenshot of the Create Project dialog with an arrow pointing to the Create button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_4.jpg) - -After your project is created, you will be able to access it from the Projects page. - -![Ultralytics HUB screenshot of the Projects page with an arrow pointing to one of the projects](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_5.jpg) - -Next, [train a model](https://docs.ultralytics.com/hub/models/#train-model) inside your project. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Train Model button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_create_project_6.jpg) - -## Share Project - -!!! Info "Info" - - Ultralytics HUB's sharing functionality provides a convenient way to share projects with others. This feature is designed to accommodate both existing Ultralytics HUB users and those who have yet to create an account. - -??? note "Note" - - You have control over the general access of your projects. - - You can choose to set the general access to "Private", in which case, only you will have access to it. Alternatively, you can set the general access to "Unlisted" which grants viewing access to anyone who has the direct link to the project, regardless of whether they have an Ultralytics HUB account or not. - -Navigate to the Project page of the project you want to share, open the project actions dropdown and click on the **Share** option. This action will trigger the **Share Project** dialog. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Share option](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_share_project_1.jpg) - -??? tip "Tip" - - You can also share a project directly from the [Projects](https://hub.ultralytics.com/projects) page. - - ![Ultralytics HUB screenshot of the Projects page with an arrow pointing to the Share option of one of the projects](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_share_project_2.jpg) - -Set the general access to "Unlisted" and click **Save**. - -![Ultralytics HUB screenshot of the Share Project dialog with an arrow pointing to the dropdown and one to the Save button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_share_project_3.jpg) - -!!! Warning "Warning" - - When changing the general access of a project, the general access of the models inside the project will be changed as well. - -Now, anyone who has the direct link to your project can view it. - -??? tip "Tip" - - You can easily click on the project's link shown in the **Share Project** dialog to copy it. - - ![Ultralytics HUB screenshot of the Share Project dialog with an arrow pointing to the project's link](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_share_project_4.jpg) - -## Edit Project - -Navigate to the Project page of the project you want to edit, open the project actions dropdown and click on the **Edit** option. This action will trigger the **Update Project** dialog. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Edit option](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_edit_project_1.jpg) - -??? tip "Tip" - - You can also edit a project directly from the [Projects](https://hub.ultralytics.com/projects) page. - - ![Ultralytics HUB screenshot of the Projects page with an arrow pointing to the Edit option of one of the projects](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_edit_project_2.jpg) - -Apply the desired modifications to your project and then confirm the changes by clicking **Save**. - -![Ultralytics HUB screenshot of the Update Project dialog with an arrow pointing to the Save button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_edit_project_3.jpg) - -## Delete Project - -Navigate to the Project page of the project you want to delete, open the project actions dropdown and click on the **Delete** option. This action will delete the project. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Delete option](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_delete_project_1.jpg) - -??? tip "Tip" - - You can also delete a project directly from the [Projects](https://hub.ultralytics.com/projects) page. - - ![Ultralytics HUB screenshot of the Projects page with an arrow pointing to the Delete option of one of the projects](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_delete_project_2.jpg) - -!!! Warning "Warning" - - When deleting a project, the models inside the project will be deleted as well. - -??? note "Note" - - If you change your mind, you can restore the project from the [Trash](https://hub.ultralytics.com/trash) page. - - ![Ultralytics HUB screenshot of the Trash page with an arrow pointing to the Restore option of one of the projects](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_delete_project_3.jpg) - -## Compare Models - -Navigate to the Project page of the project where the models you want to compare are located. To use the model comparison feature, click on the **Charts** tab. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Charts tab](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_compare_models_1.jpg) - -This will display all the relevant charts. Each chart corresponds to a different metric and contains the performance of each model for that metric. The models are represented by different colors, and you can hover over each data point to get more information. - -![Ultralytics HUB screenshot of the Charts tab inside the Project page](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_compare_models_2.jpg) - -??? tip "Tip" - - Each chart can be enlarged for better visualization. - - ![Ultralytics HUB screenshot of the Charts tab inside the Project page with an arrow pointing to the expand icon](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_compare_models_3.jpg) - - ![Ultralytics HUB screenshot of the Charts tab inside the Project page with one of the charts expanded](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_compare_models_4.jpg) - -??? tip "Tip" - - You have the flexibility to customize your view by selectively hiding certain models. This feature allows you to concentrate on the models of interest. - - ![Ultralytics HUB screenshot of the Charts tab inside the Project page with an arrow pointing to the hide/unhide icon of one of the model](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_compare_models_5.jpg) - -## Reorder Models - -??? note "Note" - - Ultralytics HUB's reordering functionality works only inside projects you own. - -Navigate to the Project page of the project where the models you want to reorder are located. Click on the designated reorder icon of the model you want to move and drag it to the desired location. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the reorder icon](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_reorder_models_1.jpg) - -## Transfer Models - -Navigate to the Project page of the project where the model you want to mode is located, open the project actions dropdown and click on the **Transfer** option. This action will trigger the **Transfer Model** dialog. - -![Ultralytics HUB screenshot of the Project page with an arrow pointing to the Transfer option of one of the models](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_transfer_models_1.jpg) - -??? tip "Tip" - - You can also transfer a model directly from the [Models](https://hub.ultralytics.com/models) page. - - ![Ultralytics HUB screenshot of the Models page with an arrow pointing to the Transfer option of one of the models](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_transfer_models_2.jpg) - -Select the project you want to transfer the model to and click **Save**. - -![Ultralytics HUB screenshot of the Transfer Model dialog with an arrow pointing to the dropdown and one to the Save button](https://raw.githubusercontent.com/ultralytics/assets/main/docs/hub/projects/hub_transfer_models_3.jpg) diff --git a/ultralytics-main/docs/en/hub/quickstart.md b/ultralytics-main/docs/en/hub/quickstart.md deleted file mode 100644 index 7f7253a..0000000 --- a/ultralytics-main/docs/en/hub/quickstart.md +++ /dev/null @@ -1,58 +0,0 @@ ---- -comments: true -description: Kickstart your journey with Ultralytics HUB. Learn how to train and deploy YOLOv5 and YOLOv8 models in seconds with our Quickstart guide. -keywords: Ultralytics HUB, Quickstart, YOLOv5, YOLOv8, model training, quick deployment, drag-and-drop interface, real-time object detection ---- - -# Quickstart Guide for Ultralytics HUB - -HUB is designed to be user-friendly and intuitive, with a drag-and-drop interface that allows users to easily upload their data and train new models quickly. It offers a range of pre-trained models and templates to choose from, making it easy for users to get started with training their own models. Once a model is trained, it can be easily deployed and used for real-time object detection, instance segmentation and classification tasks. - -

-
- -
- Watch: Train Your Custom YOLO Models In A Few Clicks with Ultralytics HUB. -

- -## Creating an Account - -[Ultralytics HUB](https://hub.ultralytics.com/) offers multiple easy account creation options. Users can register and sign in using Google, Apple, GitHub accounts, or a work email address. - -![Creating an Account](https://github.com/ultralytics/ultralytics/assets/19519529/1dcf454a-68ab-4821-9779-ee33a6e300cf) - -## The Dashboard - -Upon logging in, users are directed to the HUB dashboard, providing a comprehensive overview. The left pane conveniently offers links for tasks such as Uploading Datasets, Creating Projects, Training Models, Integrating Third-party Applications, Accessing Support, and Managing Trash. - -![HUB Dashboard](https://github.com/ultralytics/ultralytics/assets/19519529/108de60e-1b21-4f07-8d46-ed51d8439f67) - -## Selecting the Model - -Choose a Dataset and train the model by selecting the Project name, Model name, and Architecture. Ultralytics offers a range of YOLOv8, YOLOv5, and YOLOv5u6 Architectures, including pre-trained and custom options. - -Read more about Models on the [HUB Models page](models.md). - -## Training the Model - -There are three ways to train your model: using Google Colab, training locally, or through Ultralytics Cloud. Learn more about training options on the [Cloud Training Page](cloud-training.md). - -## Integrating the Model - -Integrate your trained model with third-party applications or connect HUB from an external agent. Ultralytics HUB currently supports simple one-click API Integration with Roboflow. Read more about integration on the [Integration Page](integrations.md). - -## Need Help? - -If you encounter any issues or have questions, we're here to assist you. You can report a bug, request a feature, or ask a question. - -![Support Page](https://github.com/ultralytics/ultralytics/assets/19519529/c29bf5c5-72d8-4be4-9f3f-b504968d0bef) - -## Data Management - -Manage your datasets efficiently with options to restore or permanently delete them from the Trash section in the left column. - -![Trash Page](https://github.com/ultralytics/ultralytics/assets/19519529/c3d46107-aa58-4b05-a7a8-44db1ad61bb2) diff --git a/ultralytics-main/docs/en/index.md b/ultralytics-main/docs/en/index.md deleted file mode 100644 index 484f51b..0000000 --- a/ultralytics-main/docs/en/index.md +++ /dev/null @@ -1,81 +0,0 @@ ---- -comments: true -description: Explore a complete guide to Ultralytics YOLOv8, a high-speed, high-accuracy object detection & image segmentation model. Installation, prediction, training tutorials and more. -keywords: Ultralytics, YOLOv8, object detection, image segmentation, machine learning, deep learning, computer vision, YOLOv8 installation, YOLOv8 prediction, YOLOv8 training, YOLO history, YOLO licenses ---- - -
-

- - Ultralytics YOLO banner -

- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
-
- Ultralytics CI - Ultralytics Code Coverage - YOLOv8 Citation - Docker Pulls - Discord -
- Run on Gradient - Open In Colab - Open In Kaggle -
- -Introducing [Ultralytics](https://ultralytics.com) [YOLOv8](https://github.com/ultralytics/ultralytics), the latest version of the acclaimed real-time object detection and image segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. Its streamlined design makes it suitable for various applications and easily adaptable to different hardware platforms, from edge devices to cloud APIs. - -Explore the YOLOv8 Docs, a comprehensive resource designed to help you understand and utilize its features and capabilities. Whether you are a seasoned machine learning practitioner or new to the field, this hub aims to maximize YOLOv8's potential in your projects - -## Where to Start - -- **Install** `ultralytics` with pip and get up and running in minutes   [:material-clock-fast: Get Started](quickstart.md){ .md-button } -- **Predict** new images and videos with YOLOv8   [:octicons-image-16: Predict on Images](modes/predict.md){ .md-button } -- **Train** a new YOLOv8 model on your own custom dataset   [:fontawesome-solid-brain: Train a Model](modes/train.md){ .md-button } -- **Tasks** YOLOv8 tasks like segment, classify, pose and track   [:material-magnify-expand: Explore Tasks](tasks/index.md){ .md-button } -- **NEW 🚀 Explore** datasets with advanced semantic and SQL search   [:material-magnify-expand: Explore a Dataset](datasets/explorer/index.md){ .md-button } - -

-
- -
- Watch: How to Train a YOLOv8 model on Your Custom Dataset in Google Colab. -

- -## YOLO: A Brief History - -[YOLO](https://arxiv.org/abs/1506.02640) (You Only Look Once), a popular object detection and image segmentation model, was developed by Joseph Redmon and Ali Farhadi at the University of Washington. Launched in 2015, YOLO quickly gained popularity for its high speed and accuracy. - -- [YOLOv2](https://arxiv.org/abs/1612.08242), released in 2016, improved the original model by incorporating batch normalization, anchor boxes, and dimension clusters. -- [YOLOv3](https://pjreddie.com/media/files/papers/YOLOv3.pdf), launched in 2018, further enhanced the model's performance using a more efficient backbone network, multiple anchors and spatial pyramid pooling. -- [YOLOv4](https://arxiv.org/abs/2004.10934) was released in 2020, introducing innovations like Mosaic data augmentation, a new anchor-free detection head, and a new loss function. -- [YOLOv5](https://github.com/ultralytics/yolov5) further improved the model's performance and added new features such as hyperparameter optimization, integrated experiment tracking and automatic export to popular export formats. -- [YOLOv6](https://github.com/meituan/YOLOv6) was open-sourced by [Meituan](https://about.meituan.com/) in 2022 and is in use in many of the company's autonomous delivery robots. -- [YOLOv7](https://github.com/WongKinYiu/yolov7) added additional tasks such as pose estimation on the COCO keypoints dataset. -- [YOLOv8](https://github.com/ultralytics/ultralytics) is the latest version of YOLO by Ultralytics. As a cutting-edge, state-of-the-art (SOTA) model, YOLOv8 builds on the success of previous versions, introducing new features and improvements for enhanced performance, flexibility, and efficiency. YOLOv8 supports a full range of vision AI tasks, including [detection](tasks/detect.md), [segmentation](tasks/segment.md), [pose estimation](tasks/pose.md), [tracking](modes/track.md), and [classification](tasks/classify.md). This versatility allows users to leverage YOLOv8's capabilities across diverse applications and domains. -- [YOLOv9](models/yolov9.md) Introduces innovative methods like Programmable Gradient Information (PGI) and the Generalized Efficient Layer Aggregation Network (GELAN). - -## YOLO Licenses: How is Ultralytics YOLO licensed? - -Ultralytics offers two licensing options to accommodate diverse use cases: - -- **AGPL-3.0 License**: This [OSI-approved](https://opensource.org/licenses/) open-source license is ideal for students and enthusiasts, promoting open collaboration and knowledge sharing. See the [LICENSE](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) file for more details. -- **Enterprise License**: Designed for commercial use, this license permits seamless integration of Ultralytics software and AI models into commercial goods and services, bypassing the open-source requirements of AGPL-3.0. If your scenario involves embedding our solutions into a commercial offering, reach out through [Ultralytics Licensing](https://ultralytics.com/license). - -Our licensing strategy is designed to ensure that any improvements to our open-source projects are returned to the community. We hold the principles of open source close to our hearts ❤️, and our mission is to guarantee that our contributions can be utilized and expanded upon in ways that are beneficial to all. diff --git a/ultralytics-main/docs/en/integrations/amazon-sagemaker.md b/ultralytics-main/docs/en/integrations/amazon-sagemaker.md deleted file mode 100644 index f57fc2e..0000000 --- a/ultralytics-main/docs/en/integrations/amazon-sagemaker.md +++ /dev/null @@ -1,169 +0,0 @@ ---- -comments: true -Description: Learn how to deploy YOLOv8 models on Amazon SageMaker Endpoints. This guide covers the essentials of AWS environment setup, model preparation, and deployment using AWS CloudFormation and the AWS Cloud Development Kit (CDK). -keywords: YOLOv8, Ultralytics, Amazon SageMaker, AWS, CloudFormation, AWS CDK, PyTorch, Model Deployment, Machine Learning, Computer Vision ---- - -# A Guide to Deploying YOLOv8 on Amazon SageMaker Endpoints - -Deploying advanced computer vision models like [Ultralytics’ YOLOv8](https://github.com/ultralytics/ultralytics) on Amazon SageMaker Endpoints opens up a wide range of possibilities for various machine learning applications. The key to effectively using these models lies in understanding their setup, configuration, and deployment processes. YOLOv8 becomes even more powerful when integrated seamlessly with Amazon SageMaker, a robust and scalable machine learning service by AWS. - -This guide will take you through the process of deploying YOLOv8 PyTorch models on Amazon SageMaker Endpoints step by step. You'll learn the essentials of preparing your AWS environment, configuring the model appropriately, and using tools like AWS CloudFormation and the AWS Cloud Development Kit (CDK) for deployment. - -## Amazon SageMaker - -

- Amazon SageMaker Overview -

- -[Amazon SageMaker](https://aws.amazon.com/sagemaker/) is a machine learning service from Amazon Web Services (AWS) that simplifies the process of building, training, and deploying machine learning models. It provides a broad range of tools for handling various aspects of machine learning workflows. This includes automated features for tuning models, options for training models at scale, and straightforward methods for deploying models into production. SageMaker supports popular machine learning frameworks, offering the flexibility needed for diverse projects. Its features also cover data labeling, workflow management, and performance analysis. - -## Deploying YOLOv8 on Amazon SageMaker Endpoints - -Deploying YOLOv8 on Amazon SageMaker lets you use its managed environment for real-time inference and take advantage of features like autoscaling. Take a look at the AWS architecture below. - -

- AWS Architecture -

- -### Step 1: Setup Your AWS Environment - -First, ensure you have the following prerequisites in place: - -- An AWS Account: If you don't already have one, sign up for an AWS account. - -- Configured IAM Roles: You’ll need an IAM role with the necessary permissions for Amazon SageMaker, AWS CloudFormation, and Amazon S3. This role should have policies that allow it to access these services. - -- AWS CLI: If not already installed, download and install the AWS Command Line Interface (CLI) and configure it with your account details. Follow [the AWS CLI instructions](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html) for installation. - -- AWS CDK: If not already installed, install the AWS Cloud Development Kit (CDK), which will be used for scripting the deployment. Follow [the AWS CDK instructions](https://docs.aws.amazon.com/cdk/v2/guide/getting_started.html#getting_started_install) for installation. - -- Adequate Service Quota: Confirm that you have sufficient quotas for two separate resources in Amazon SageMaker: one for `ml.m5.4xlarge` for endpoint usage and another for `ml.m5.4xlarge` for notebook instance usage. Each of these requires a minimum of one quota value. If your current quotas are below this requirement, it's important to request an increase for each. You can request a quota increase by following the detailed instructions in the [AWS Service Quotas documentation](https://docs.aws.amazon.com/servicequotas/latest/userguide/request-quota-increase.html#quota-console-increase). - -### Step 2: Clone the YOLOv8 SageMaker Repository - -The next step is to clone the specific AWS repository that contains the resources for deploying YOLOv8 on SageMaker. This repository, hosted on GitHub, includes the necessary CDK scripts and configuration files. - -- Clone the GitHub Repository: Execute the following command in your terminal to clone the host-yolov8-on-sagemaker-endpoint repository: - -```bash -git clone https://github.com/aws-samples/host-yolov8-on-sagemaker-endpoint.git -``` - -- Navigate to the Cloned Directory: Change your directory to the cloned repository: - -```bash -cd host-yolov8-on-sagemaker-endpoint/yolov8-pytorch-cdk -``` - -### Step 3: Set Up the CDK Environment - -Now that you have the necessary code, set up your environment for deploying with AWS CDK. - -- Create a Python Virtual Environment: This isolates your Python environment and dependencies. Run: - -```bash -python3 -m venv .venv -``` - -- Activate the Virtual Environment: - -```bash -source .venv/bin/activate -``` - -- Install Dependencies: Install the required Python dependencies for the project: - -```bash -pip3 install -r requirements.txt -``` - -- Upgrade AWS CDK Library: Ensure you have the latest version of the AWS CDK library: - -```bash -pip install --upgrade aws-cdk-lib -``` - -### Step 4: Create the AWS CloudFormation Stack - -- Synthesize the CDK Application: Generate the AWS CloudFormation template from your CDK code: - -```bash -cdk synth -``` - -- Bootstrap the CDK Application: Prepare your AWS environment for CDK deployment: - -```bash -cdk bootstrap -``` - -- Deploy the Stack: This will create the necessary AWS resources and deploy your model: - -```bash -cdk deploy -``` - -### Step 5: Deploy the YOLOv8 Model - -Before diving into the deployment instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -After creating the AWS CloudFormation Stack, the next step is to deploy YOLOv8. - -- Open the Notebook Instance: Go to the AWS Console and navigate to the Amazon SageMaker service. Select "Notebook Instances" from the dashboard, then locate the notebook instance that was created by your CDK deployment script. Open the notebook instance to access the Jupyter environment. - -- Access and Modify inference.py: After opening the SageMaker notebook instance in Jupyter, locate the inference.py file. Edit the output_fn function in inference.py as shown below and save your changes to the script, ensuring that there are no syntax errors. - -```python -import json - -def output_fn(prediction_output, content_type): - print("Executing output_fn from inference.py ...") - infer = {} - for result in prediction_output: - if result.boxes is not None: - infer['boxes'] = result.boxes.numpy().data.tolist() - if result.masks is not None: - infer['masks'] = result.masks.numpy().data.tolist() - if result.keypoints is not None: - infer['keypoints'] = result.keypoints.numpy().data.tolist() - if result.obb is not None: - infer['obb'] = result.obb.numpy().data.tolist() - if result.probs is not None: - infer['probs'] = result.probs.numpy().data.tolist() - return json.dumps(infer) -``` - -- Deploy the Endpoint Using 1_DeployEndpoint.ipynb: In the Jupyter environment, open the 1_DeployEndpoint.ipynb notebook located in the sm-notebook directory. Follow the instructions in the notebook and run the cells to download the YOLOv8 model, package it with the updated inference code, and upload it to an Amazon S3 bucket. The notebook will guide you through creating and deploying a SageMaker endpoint for the YOLOv8 model. - -### Step 6: Testing Your Deployment - -Now that your YOLOv8 model is deployed, it's important to test its performance and functionality. - -- Open the Test Notebook: In the same Jupyter environment, locate and open the 2_TestEndpoint.ipynb notebook, also in the sm-notebook directory. - -- Run the Test Notebook: Follow the instructions within the notebook to test the deployed SageMaker endpoint. This includes sending an image to the endpoint and running inferences. Then, you’ll plot the output to visualize the model’s performance and accuracy, as shown below. - -

- Testing Results YOLOv8 -

- -- Clean-Up Resources: The test notebook will also guide you through the process of cleaning up the endpoint and the hosted model. This is an important step to manage costs and resources effectively, especially if you do not plan to use the deployed model immediately. - -### Step 7: Monitoring and Management - -After testing, continuous monitoring and management of your deployed model are essential. - -- Monitor with Amazon CloudWatch: Regularly check the performance and health of your SageMaker endpoint using [Amazon CloudWatch](https://aws.amazon.com/cloudwatch/). - -- Manage the Endpoint: Use the SageMaker console for ongoing management of the endpoint. This includes scaling, updating, or redeploying the model as required. - -By completing these steps, you will have successfully deployed and tested a YOLOv8 model on Amazon SageMaker Endpoints. This process not only equips you with practical experience in using AWS services for machine learning deployment but also lays the foundation for deploying other advanced models in the future. - -## Summary - -This guide took you step by step through deploying YOLOv8 on Amazon SageMaker Endpoints using AWS CloudFormation and the AWS Cloud Development Kit (CDK). The process includes cloning the necessary GitHub repository, setting up the CDK environment, deploying the model using AWS services, and testing its performance on SageMaker. - -For more technical details, refer to [this article](https://aws.amazon.com/blogs/machine-learning/hosting-yolov8-pytorch-model-on-amazon-sagemaker-endpoints/) on the AWS Machine Learning Blog. You can also check out the official [Amazon SageMaker Documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html) for more insights into various features and functionalities. - -Are you interested in learning more about different YOLOv8 integrations? Visit the [Ultralytics integrations guide page](../integrations/index.md) to discover additional tools and capabilities that can enhance your machine-learning projects. diff --git a/ultralytics-main/docs/en/integrations/clearml.md b/ultralytics-main/docs/en/integrations/clearml.md deleted file mode 100644 index 92b069a..0000000 --- a/ultralytics-main/docs/en/integrations/clearml.md +++ /dev/null @@ -1,189 +0,0 @@ ---- -comments: true -description: Learn how to streamline and optimize your YOLOv8 model training with ClearML. This guide provides insights into integrating ClearML's MLOps tools for efficient model training, from initial setup to advanced experiment tracking and model management. -keywords: Ultralytics, YOLOv8, Object Detection, ClearML, Model Training, MLOps, Experiment Tracking, Workflow Optimization ---- - -# Training YOLOv8 with ClearML: Streamlining Your MLOps Workflow - -MLOps bridges the gap between creating and deploying machine learning models in real-world settings. It focuses on efficient deployment, scalability, and ongoing management to ensure models perform well in practical applications. - -[Ultralytics YOLOv8](https://ultralytics.com) effortlessly integrates with ClearML, streamlining and enhancing your object detection model's training and management. This guide will walk you through the integration process, detailing how to set up ClearML, manage experiments, automate model management, and collaborate effectively. - -## ClearML - -

- ClearML Overview -

- -[ClearML](https://clear.ml/) is an innovative open-source MLOps platform that is skillfully designed to automate, monitor, and orchestrate machine learning workflows. Its key features include automated logging of all training and inference data for full experiment reproducibility, an intuitive web UI for easy data visualization and analysis, advanced hyperparameter optimization algorithms, and robust model management for efficient deployment across various platforms. - -## YOLOv8 Training with ClearML - -You can bring automation and efficiency to your machine learning workflow by improving your training process by integrating YOLOv8 with ClearML. - -## Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required packages for YOLOv8 and ClearML - pip install ultralytics clearml - ``` - -For detailed instructions and best practices related to the installation process, be sure to check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -## Configuring ClearML - -Once you have installed the necessary packages, the next step is to initialize and configure your ClearML SDK. This involves setting up your ClearML account and obtaining the necessary credentials for a seamless connection between your development environment and the ClearML server. - -Begin by initializing the ClearML SDK in your environment. The ‘clearml-init’ command starts the setup process and prompts you for the necessary credentials. - -!!! Tip "Initial SDK Setup" - - === "CLI" - - ```bash - # Initialize your ClearML SDK setup process - clearml-init - ``` - -After executing this command, visit the [ClearML Settings page](https://app.clear.ml/settings/workspace-configuration). Navigate to the top right corner and select "Settings." Go to the "Workspace" section and click on "Create new credentials." Use the credentials provided in the "Create Credentials" pop-up to complete the setup as instructed, depending on whether you are configuring ClearML in a Jupyter Notebook or a local Python environment. - -## Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from clearml import Task - from ultralytics import YOLO - - # Step 1: Creating a ClearML Task - task = Task.init( - project_name="my_project", - task_name="my_yolov8_task" - ) - - # Step 2: Selecting the YOLOv8 Model - model_variant = "yolov8n" - task.set_parameter("model_variant", model_variant) - - # Step 3: Loading the YOLOv8 Model - model = YOLO(f'{model_variant}.pt') - - # Step 4: Setting Up Training Arguments - args = dict(data="coco128.yaml", epochs=16) - task.connect(args) - - # Step 5: Initiating Model Training - results = model.train(**args) - ``` - -### Understanding the Code - -Let’s understand the steps showcased in the usage code snippet above. - -**Step 1: Creating a ClearML Task**: A new task is initialized in ClearML, specifying your project and task names. This task will track and manage your model's training. - -**Step 2: Selecting the YOLOv8 Model**: The `model_variant` variable is set to 'yolov8n', one of the YOLOv8 models. This variant is then logged in ClearML for tracking. - -**Step 3: Loading the YOLOv8 Model**: The selected YOLOv8 model is loaded using Ultralytics' YOLO class, preparing it for training. - -**Step 4: Setting Up Training Arguments**: Key training arguments like the dataset (`coco128.yaml`) and the number of epochs (`16`) are organized in a dictionary and connected to the ClearML task. This allows for tracking and potential modification via the ClearML UI. For a detailed understanding of the model training process and best practices, refer to our [YOLOv8 Model Training guide](../modes/train.md). - -**Step 5: Initiating Model Training**: The model training is started with the specified arguments. The results of the training process are captured in the `results` variable. - -### Understanding the Output - -Upon running the usage code snippet above, you can expect the following output: - -- A confirmation message indicating the creation of a new ClearML task, along with its unique ID. -- An informational message about the script code being stored, indicating that the code execution is being tracked by ClearML. -- A URL link to the ClearML results page where you can monitor the training progress and view detailed logs. -- Download progress for the YOLOv8 model and the specified dataset, followed by a summary of the model architecture and training configuration. -- Initialization messages for various training components like TensorBoard, Automatic Mixed Precision (AMP), and dataset preparation. -- Finally, the training process starts, with progress updates as the model trains on the specified dataset. For an in-depth understanding of the performance metrics used during training, read [our guide on performance metrics](../guides/yolo-performance-metrics.md). - -### Viewing the ClearML Results Page - -By clicking on the URL link to the ClearML results page in the output of the usage code snippet, you can access a comprehensive view of your model's training process. - -#### Key Features of the ClearML Results Page - -- **Real-Time Metrics Tracking** - - - Track critical metrics like loss, accuracy, and validation scores as they occur. - - Provides immediate feedback for timely model performance adjustments. - -- **Experiment Comparison** - - - Compare different training runs side-by-side. - - Essential for hyperparameter tuning and identifying the most effective models. - -- **Detailed Logs and Outputs** - - - Access comprehensive logs, graphical representations of metrics, and console outputs. - - Gain a deeper understanding of model behavior and issue resolution. - -- **Resource Utilization Monitoring** - - - Monitor the utilization of computational resources, including CPU, GPU, and memory. - - Key to optimizing training efficiency and costs. - -- **Model Artifacts Management** - - - View, download, and share model artifacts like trained models and checkpoints. - - Enhances collaboration and streamlines model deployment and sharing. - -For a visual walkthrough of what the ClearML Results Page looks like, watch the video below: - -

-
- -
- Watch: YOLOv8 MLOps Integration using ClearML -

- -### Advanced Features in ClearML - -ClearML offers several advanced features to enhance your MLOps experience. - -#### Remote Execution - -ClearML's remote execution feature facilitates the reproduction and manipulation of experiments on different machines. It logs essential details like installed packages and uncommitted changes. When a task is enqueued, the ClearML Agent pulls it, recreates the environment, and runs the experiment, reporting back with detailed results. - -Deploying a ClearML Agent is straightforward and can be done on various machines using the following command: - -```bash -clearml-agent daemon --queue [--docker] -``` - -This setup is applicable to cloud VMs, local GPUs, or laptops. ClearML Autoscalers help manage cloud workloads on platforms like AWS, GCP, and Azure, automating the deployment of agents and adjusting resources based on your resource budget. - -### Cloning, Editing, and Enqueuing - -ClearML's user-friendly interface allows easy cloning, editing, and enqueuing of tasks. Users can clone an existing experiment, adjust parameters or other details through the UI, and enqueue the task for execution. This streamlined process ensures that the ClearML Agent executing the task uses updated configurations, making it ideal for iterative experimentation and model fine-tuning. - -


- Cloning, Editing, and Enqueuing with ClearML -

- -## Summary - -This guide has led you through the process of integrating ClearML with Ultralytics' YOLOv8. Covering everything from initial setup to advanced model management, you've discovered how to leverage ClearML for efficient training, experiment tracking, and workflow optimization in your machine learning projects. - -For further details on usage, visit [ClearML's official documentation](https://clear.ml/docs/latest/docs/integrations/yolov8/). - -Additionally, explore more integrations and capabilities of Ultralytics by visiting the [Ultralytics integration guide page](../integrations/index.md), which is a treasure trove of resources and insights. diff --git a/ultralytics-main/docs/en/integrations/comet.md b/ultralytics-main/docs/en/integrations/comet.md deleted file mode 100644 index 95ada28..0000000 --- a/ultralytics-main/docs/en/integrations/comet.md +++ /dev/null @@ -1,178 +0,0 @@ ---- -comments: true -description: Discover how to track and enhance YOLOv8 model training with Comet ML's logging tools, from setup to monitoring key metrics and managing experiments for in-depth analysis. -keywords: Ultralytics, YOLOv8, Object Detection, Comet ML, Model Training, Model Metrics Logging, Experiment Tracking, Offline Experiment Management ---- - -# Elevating YOLOv8 Training: Simplify Your Logging Process with Comet ML - -Logging key training details such as parameters, metrics, image predictions, and model checkpoints is essential in machine learning—it keeps your project transparent, your progress measurable, and your results repeatable. - -[Ultralytics YOLOv8](https://ultralytics.com) seamlessly integrates with Comet ML, efficiently capturing and optimizing every aspect of your YOLOv8 object detection model's training process. In this guide, we'll cover the installation process, Comet ML setup, real-time insights, custom logging, and offline usage, ensuring that your YOLOv8 training is thoroughly documented and fine-tuned for outstanding results. - -## Comet ML - -

- Comet ML Overview -

- -[Comet ML](https://www.comet.ml/) is a platform for tracking, comparing, explaining, and optimizing machine learning models and experiments. It allows you to log metrics, parameters, media, and more during your model training and monitor your experiments through an aesthetically pleasing web interface. Comet ML helps data scientists iterate more rapidly, enhances transparency and reproducibility, and aids in the development of production models. - -## Harnessing the Power of YOLOv8 and Comet ML - -By combining Ultralytics YOLOv8 with Comet ML, you unlock a range of benefits. These include simplified experiment management, real-time insights for quick adjustments, flexible and tailored logging options, and the ability to log experiments offline when internet access is limited. This integration empowers you to make data-driven decisions, analyze performance metrics, and achieve exceptional results. - -## Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required packages for YOLOv8 and Comet ML - pip install ultralytics comet_ml torch torchvision - ``` - -## Configuring Comet ML - -After installing the required packages, you’ll need to sign up, get a [Comet API Key](https://www.comet.com/signup), and configure it. - -!!! Tip "Configuring Comet ML" - - === "CLI" - - ```bash - # Set your Comet Api Key - export COMET_API_KEY= - ``` - -Then, you can initialize your Comet project. Comet will automatically detect the API key and proceed with the setup. - -```python -import comet_ml - -comet_ml.init(project_name="comet-example-yolov8-coco128") -``` - -If you are using a Google Colab notebook, the code above will prompt you to enter your API key for initialization. - -## Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO("yolov8n.pt") - - # train the model - results = model.train( - data="coco128.yaml", - project="comet-example-yolov8-coco128", - batch=32, - save_period=1, - save_json=True, - epochs=3 - ) - ``` - -After running the training code, Comet ML will create an experiment in your Comet workspace to track the run automatically. You will then be provided with a link to view the detailed logging of your [YOLOv8 model's training](../modes/train.md) process. - -Comet automatically logs the following data with no additional configuration: metrics such as mAP and loss, hyperparameters, model checkpoints, interactive confusion matrix, and image bounding box predictions. - -## Understanding Your Model's Performance with Comet ML Visualizations - -Let's dive into what you'll see on the Comet ML dashboard once your YOLOv8 model begins training. The dashboard is where all the action happens, presenting a range of automatically logged information through visuals and statistics. Here’s a quick tour: - -**Experiment Panels** - -The experiment panels section of the Comet ML dashboard organize and present the different runs and their metrics, such as segment mask loss, class loss, precision, and mean average precision. - -

- Comet ML Overview -

- -**Metrics** - -In the metrics section, you have the option to examine the metrics in a tabular format as well, which is displayed in a dedicated pane as illustrated here. - -

- Comet ML Overview -

- -**Interactive Confusion Matrix** - -The confusion matrix, found in the Confusion Matrix tab, provides an interactive way to assess the model's classification accuracy. It details the correct and incorrect predictions, allowing you to understand the model's strengths and weaknesses. - -

- Comet ML Overview -

- -**System Metrics** - -Comet ML logs system metrics to help identify any bottlenecks in the training process. It includes metrics such as GPU utilization, GPU memory usage, CPU utilization, and RAM usage. These are essential for monitoring the efficiency of resource usage during model training. - -

- Comet ML Overview -

- -## Customizing Comet ML Logging - -Comet ML offers the flexibility to customize its logging behavior by setting environment variables. These configurations allow you to tailor Comet ML to your specific needs and preferences. Here are some helpful customization options: - -### Logging Image Predictions - -You can control the number of image predictions that Comet ML logs during your experiments. By default, Comet ML logs 100 image predictions from the validation set. However, you can change this number to better suit your requirements. For example, to log 200 image predictions, use the following code: - -```python -import os - -os.environ["COMET_MAX_IMAGE_PREDICTIONS"] = "200" -``` - -### Batch Logging Interval - -Comet ML allows you to specify how often batches of image predictions are logged. The `COMET_EVAL_BATCH_LOGGING_INTERVAL` environment variable controls this frequency. The default setting is 1, which logs predictions from every validation batch. You can adjust this value to log predictions at a different interval. For instance, setting it to 4 will log predictions from every fourth batch. - -```python -import os - -os.environ['COMET_EVAL_BATCH_LOGGING_INTERVAL'] = "4" -``` - -### Disabling Confusion Matrix Logging - -In some cases, you may not want to log the confusion matrix from your validation set after every epoch. You can disable this feature by setting the `COMET_EVAL_LOG_CONFUSION_MATRIX` environment variable to "false." The confusion matrix will only be logged once, after the training is completed. - -```python -import os - -os.environ["COMET_EVAL_LOG_CONFUSION_MATRIX"] = "false" -``` - -### Offline Logging - -If you find yourself in a situation where internet access is limited, Comet ML provides an offline logging option. You can set the `COMET_MODE` environment variable to "offline" to enable this feature. Your experiment data will be saved locally in a directory that you can later upload to Comet ML when internet connectivity is available. - -```python -import os - -os.environ["COMET_MODE"] = "offline" -``` - -## Summary - -This guide has walked you through integrating Comet ML with Ultralytics' YOLOv8. From installation to customization, you've learned to streamline experiment management, gain real-time insights, and adapt logging to your project's needs. - -Explore [Comet ML's official documentation](https://www.comet.com/docs/v2/integrations/third-party-tools/yolov8/) for more insights on integrating with YOLOv8. - -Furthermore, if you're looking to dive deeper into the practical applications of YOLOv8, specifically for image segmentation tasks, this detailed guide on [fine-tuning YOLOv8 with Comet ML](https://www.comet.com/site/blog/fine-tuning-yolov8-for-image-segmentation-with-comet/) offers valuable insights and step-by-step instructions to enhance your model's performance. - -Additionally, to explore other exciting integrations with Ultralytics, check out the [integration guide page](../integrations/index.md), which offers a wealth of resources and information. diff --git a/ultralytics-main/docs/en/integrations/coreml.md b/ultralytics-main/docs/en/integrations/coreml.md deleted file mode 100644 index 5533da5..0000000 --- a/ultralytics-main/docs/en/integrations/coreml.md +++ /dev/null @@ -1,126 +0,0 @@ ---- -comments: true -description: Explore the process of exporting Ultralytics YOLOv8 models to CoreML format, enabling efficient object detection capabilities for iOS and macOS applications on Apple devices. -keywords: Ultralytics, YOLOv8, CoreML Export, Model Deployment, Apple Devices, Object Detection, Machine Learning ---- - -# CoreML Export for YOLOv8 Models - -Deploying computer vision models on Apple devices like iPhones and Macs requires a format that ensures seamless performance. - -The CoreML export format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for efficient object detection in iOS and macOS applications. In this guide, we'll walk you through the steps for converting your models to the CoreML format, making it easier for your models to perform well on Apple devices. - -## CoreML - -

- CoreML Overview -

- -[CoreML](https://developer.apple.com/documentation/coreml) is Apple's foundational machine learning framework that builds upon Accelerate, BNNS, and Metal Performance Shaders. It provides a machine-learning model format that seamlessly integrates into iOS applications and supports tasks such as image analysis, natural language processing, audio-to-text conversion, and sound analysis. - -Applications can take advantage of Core ML without the need to have a network connection or API calls because the Core ML framework works using on-device computing. This means model inference can be performed locally on the user's device. - -## Key Features of CoreML Models - -Apple's CoreML framework offers robust features for on-device machine learning. Here are the key features that make CoreML a powerful tool for developers: - -- **Comprehensive Model Support**: Converts and runs models from popular frameworks like TensorFlow, PyTorch, scikit-learn, XGBoost, and LibSVM. - -

- CoreML Supported Models -

- -- **On-device Machine Learning**: Ensures data privacy and swift processing by executing models directly on the user's device, eliminating the need for network connectivity. - -- **Performance and Optimization**: Uses the device's CPU, GPU, and Neural Engine for optimal performance with minimal power and memory usage. Offers tools for model compression and optimization while maintaining accuracy. - -- **Ease of Integration**: Provides a unified format for various model types and a user-friendly API for seamless integration into apps. Supports domain-specific tasks through frameworks like Vision and Natural Language. - -- **Advanced Features**: Includes on-device training capabilities for personalized experiences, asynchronous predictions for interactive ML experiences, and model inspection and validation tools. - -## CoreML Deployment Options - -Before we look at the code for exporting YOLOv8 models to the CoreML format, let’s understand where CoreML models are usually used. - -CoreML offers various deployment options for machine learning models, including: - -- **On-Device Deployment**: This method directly integrates CoreML models into your iOS app. It's particularly advantageous for ensuring low latency, enhanced privacy (since data remains on the device), and offline functionality. This approach, however, may be limited by the device's hardware capabilities, especially for larger and more complex models. On-device deployment can be executed in the following two ways. - - - **Embedded Models**: These models are included in the app bundle and are immediately accessible. They are ideal for small models that do not require frequent updates. - - - **Downloaded Models**: These models are fetched from a server as needed. This approach is suitable for larger models or those needing regular updates. It helps keep the app bundle size smaller. - -- **Cloud-Based Deployment**: CoreML models are hosted on servers and accessed by the iOS app through API requests. This scalable and flexible option enables easy model updates without app revisions. It’s ideal for complex models or large-scale apps requiring regular updates. However, it does require an internet connection and may pose latency and security issues​. - -## Exporting YOLOv8 Models to CoreML - -Exporting YOLOv8 to CoreML enables optimized, on-device machine learning performance within Apple's ecosystem, offering benefits in terms of efficiency, security, and seamless integration with iOS, macOS, watchOS, and tvOS platforms. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to CoreML format - model.export(format='coreml') # creates 'yolov8n.mlpackage' - - # Load the exported CoreML model - coreml_model = YOLO('yolov8n.mlpackage') - - # Run inference - results = coreml_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to CoreML format - yolo export model=yolov8n.pt format=coreml # creates 'yolov8n.mlpackage'' - - # Run inference with the exported model - yolo predict model=yolov8n.mlpackage source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -## Deploying Exported YOLOv8 CoreML Models - -Having successfully exported your Ultralytics YOLOv8 models to CoreML, the next critical phase is deploying these models effectively. For detailed guidance on deploying CoreML models in various environments, check out these resources: - -- **[CoreML Tools](https://apple.github.io/coremltools/docs-guides/)**: This guide includes instructions and examples to convert models from TensorFlow, PyTorch, and other libraries to Core ML. - -- **[ML and Vision](https://developer.apple.com/videos/ml-vision)**: A collection of comprehensive videos that cover various aspects of using and implementing CoreML models. - -- **[Integrating a Core ML Model into Your App](https://developer.apple.com/documentation/coreml/integrating_a_core_ml_model_into_your_app)**: A comprehensive guide on integrating a CoreML model into an iOS application, detailing steps from preparing the model to implementing it in the app for various functionalities. - -## Summary - -In this guide, we went over how to export Ultralytics YOLOv8 models to CoreML format. By following the steps outlined in this guide, you can ensure maximum compatibility and performance when exporting YOLOv8 models to CoreML. - -For further details on usage, visit the [CoreML official documentation](https://developer.apple.com/documentation/coreml). - -Also, if you’d like to know more about other Ultralytics YOLOv8 integrations, visit our [integration guide page](../integrations/index.md). You'll find plenty of valuable resources and insights there. diff --git a/ultralytics-main/docs/en/integrations/dvc.md b/ultralytics-main/docs/en/integrations/dvc.md deleted file mode 100644 index 542a91a..0000000 --- a/ultralytics-main/docs/en/integrations/dvc.md +++ /dev/null @@ -1,171 +0,0 @@ ---- -comments: true -description: This guide provides a step-by-step approach to integrating DVCLive with Ultralytics YOLOv8 for advanced experiment tracking. Learn how to set up your environment, run experiments with varied configurations, and analyze results using DVCLive's powerful tracking and visualization tools. -keywords: DVCLive, Ultralytics, YOLOv8, Machine Learning, Experiment Tracking, Data Version Control, ML Workflows, Model Training, Hyperparameter Tuning ---- - -# Advanced YOLOv8 Experiment Tracking with DVCLive - -Experiment tracking in machine learning is critical to model development and evaluation. It involves recording and analyzing various parameters, metrics, and outcomes from numerous training runs. This process is essential for understanding model performance and making data-driven decisions to refine and optimize models. - -Integrating DVCLive with [Ultralytics YOLOv8](https://ultralytics.com) transforms the way experiments are tracked and managed. This integration offers a seamless solution for automatically logging key experiment details, comparing results across different runs, and visualizing data for in-depth analysis. In this guide, we'll understand how DVCLive can be used to streamline the process. - -## DVCLive - -

- DVCLive Overview -

- -[DVCLive](https://dvc.org/doc/dvclive), developed by DVC, is an innovative open-source tool for experiment tracking in machine learning. Integrating seamlessly with Git and DVC, it automates the logging of crucial experiment data like model parameters and training metrics. Designed for simplicity, DVCLive enables effortless comparison and analysis of multiple runs, enhancing the efficiency of machine learning projects with intuitive data visualization and analysis tools. - -## YOLOv8 Training with DVCLive - -YOLOv8 training sessions can be effectively monitored with DVCLive. Additionally, DVC provides integral features for visualizing these experiments, including the generation of a report that enables the comparison of metric plots across all tracked experiments, offering a comprehensive view of the training process. - -## Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required packages for YOLOv8 and DVCLive - pip install ultralytics dvclive - ``` - -For detailed instructions and best practices related to the installation process, be sure to check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -## Configuring DVCLive - -Once you have installed the necessary packages, the next step is to set up and configure your environment with the necessary credentials. This setup ensures a smooth integration of DVCLive into your existing workflow. - -Begin by initializing a Git repository, as Git plays a crucial role in version control for both your code and DVCLive configurations. - -!!! Tip "Initial Environment Setup" - - === "CLI" - - ```bash - # Initialize a Git repository - git init -q - - # Configure Git with your details - git config --local user.email "you@example.com" - git config --local user.name "Your Name" - - # Initialize DVCLive in your project - dvc init -q - - # Commit the DVCLive setup to your Git repository - git commit -m "DVC init" - ``` - -In these commands, ensure to replace "you@example.com" with the email address associated with your Git account, and "Your Name" with your Git account username. - -## Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -### Training YOLOv8 Models with DVCLive - -Start by running your YOLOv8 training sessions. You can use different model configurations and training parameters to suit your project needs. For instance: - -```bash -# Example training commands for YOLOv8 with varying configurations -yolo train model=yolov8n.pt data=coco8.yaml epochs=5 imgsz=512 -yolo train model=yolov8n.pt data=coco8.yaml epochs=5 imgsz=640 -``` - -Adjust the model, data, epochs, and imgsz parameters according to your specific requirements. For a detailed understanding of the model training process and best practices, refer to our [YOLOv8 Model Training guide](../modes/train.md). - -### Monitoring Experiments with DVCLive - -DVCLive enhances the training process by enabling the tracking and visualization of key metrics. When installed, Ultralytics YOLOv8 automatically integrates with DVCLive for experiment tracking, which you can later analyze for performance insights. For a comprehensive understanding of the specific performance metrics used during training, be sure to explore [our detailed guide on performance metrics](../guides/yolo-performance-metrics.md). - -### Analyzing Results - -After your YOLOv8 training sessions are complete, you can leverage DVCLive's powerful visualization tools for in-depth analysis of the results. DVCLive's integration ensures that all training metrics are systematically logged, facilitating a comprehensive evaluation of your model's performance. - -To start the analysis, you can extract the experiment data using DVC's API and process it with Pandas for easier handling and visualization: - -```python -import dvc.api -import pandas as pd - -# Define the columns of interest -columns = ["Experiment", "epochs", "imgsz", "model", "metrics.mAP50-95(B)"] - -# Retrieve experiment data -df = pd.DataFrame(dvc.api.exp_show(), columns=columns) - -# Clean the data -df.dropna(inplace=True) -df.reset_index(drop=True, inplace=True) - -# Display the DataFrame -print(df) -``` - -The output of the code snippet above provides a clear tabular view of the different experiments conducted with YOLOv8 models. Each row represents a different training run, detailing the experiment's name, the number of epochs, image size (imgsz), the specific model used, and the mAP50-95(B) metric. This metric is crucial for evaluating the model's accuracy, with higher values indicating better performance. - -#### Visualizing Results with Plotly - -For a more interactive and visual analysis of your experiment results, you can use Plotly's parallel coordinates plot. This type of plot is particularly useful for understanding the relationships and trade-offs between different parameters and metrics. - -```python -from plotly.express import parallel_coordinates - -# Create a parallel coordinates plot -fig = parallel_coordinates(df, columns, color="metrics.mAP50-95(B)") - -# Display the plot -fig.show() -``` - -The output of the code snippet above generates a plot that will visually represent the relationships between epochs, image size, model type, and their corresponding mAP50-95(B) scores, enabling you to spot trends and patterns in your experiment data. - -#### Generating Comparative Visualizations with DVC - -DVC provides a useful command to generate comparative plots for your experiments. This can be especially helpful to compare the performance of different models over various training runs. - -```bash -# Generate DVC comparative plots -dvc plots diff $(dvc exp list --names-only) -``` - -After executing this command, DVC generates plots comparing the metrics across different experiments, which are saved as HTML files. Below is an example image illustrating typical plots generated by this process. The image showcases various graphs, including those representing mAP, recall, precision, loss values, and more, providing a visual overview of key performance metrics: - -

- DVCLive Plots -

- -### Displaying DVC Plots - -If you are using a Jupyter Notebook and you want to display the generated DVC plots, you can use the IPython display functionality. - -```python -from IPython.display import HTML - -# Display the DVC plots as HTML -HTML(filename='./dvc_plots/index.html') -``` - -This code will render the HTML file containing the DVC plots directly in your Jupyter Notebook, providing an easy and convenient way to analyze the visualized experiment data. - -### Making Data-Driven Decisions - -Use the insights gained from these visualizations to make informed decisions about model optimizations, hyperparameter tuning, and other modifications to enhance your model's performance. - -### Iterating on Experiments - -Based on your analysis, iterate on your experiments. Adjust model configurations, training parameters, or even the data inputs, and repeat the training and analysis process. This iterative approach is key to refining your model for the best possible performance. - -## Summary - -This guide has led you through the process of integrating DVCLive with Ultralytics' YOLOv8. You have learned how to harness the power of DVCLive for detailed experiment monitoring, effective visualization, and insightful analysis in your machine learning endeavors. - -For further details on usage, visit [DVCLive’s official documentation](https://dvc.org/doc/dvclive/ml-frameworks/yolo). - -Additionally, explore more integrations and capabilities of Ultralytics by visiting the [Ultralytics integration guide page](../integrations/index.md), which is a collection of great resources and insights. diff --git a/ultralytics-main/docs/en/integrations/edge-tpu.md b/ultralytics-main/docs/en/integrations/edge-tpu.md deleted file mode 100644 index aa83c44..0000000 --- a/ultralytics-main/docs/en/integrations/edge-tpu.md +++ /dev/null @@ -1,118 +0,0 @@ ---- -comments: true -description: Discover how to uplift your Ultralytics YOLOv8 model's overall performance with the TFLite Edge TPU export format, which is perfect for mobile and embedded devices. -keywords: Ultralytics, YOLOv8, TFLite edge TPU format, Export YOLOv8, Model Deployment, Flexible Deployment ---- - -# Learn to Export to TFLite Edge TPU Format From YOLOv8 Model - -Deploying computer vision models on devices with limited computational power, such as mobile or embedded systems, can be tricky. Using a model format that is optimized for faster performance simplifies the process. The [TensorFlow Lite](https://www.tensorflow.org/lite) [Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) or TFLite Edge TPU model format is designed to use minimal power while delivering fast performance for neural networks. - -The export to TFLite Edge TPU format feature allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for high-speed and low-power inferencing. In this guide, we'll walk you through converting your models to the TFLite Edge TPU format, making it easier for your models to perform well on various mobile and embedded devices. - -## Why Should You Export to TFLite Edge TPU? - -Exporting models to TensorFlow Edge TPU makes machine learning tasks fast and efficient. This technology suits applications with limited power, computing resources, and connectivity. The Edge TPU is a hardware accelerator by Google. It speeds up TensorFlow Lite models on edge devices. The image below shows an example of the process involved. - -

- TFLite Edge TPU -

- -The Edge TPU works with quantized models. Quantization makes models smaller and faster without losing much accuracy. It is ideal for the limited resources of edge computing, allowing applications to respond quickly by reducing latency and allowing for quick data processing locally, without cloud dependency. Local processing also keeps user data private and secure since it's not sent to a remote server​​​​. - -## Key Features of TFLite Edge TPU - -Here are the key features that make TFLite Edge TPU a great model format choice for developers: - -- **Optimized Performance on Edge Devices**: The TFLite Edge TPU achieves high-speed neural networking performance through quantization, model optimization, hardware acceleration, and compiler optimization. Its minimalistic architecture contributes to its smaller size and cost-efficiency. - -- **High Computational Throughput**: TFLite Edge TPU combines specialized hardware acceleration and efficient runtime execution to achieve high computational throughput. It is well-suited for deploying machine learning models with stringent performance requirements on edge devices. - -- **Efficient Matrix Computations**: The TensorFlow Edge TPU is optimized for matrix operations, which are crucial for neural network computations. This efficiency is key in machine learning models, particularly those requiring numerous and complex matrix multiplications and transformations. - -## Deployment Options with TFLite Edge TPU - -Before we jump into how to export YOLOv8 models to the TFLite Edge TPU format, let’s understand where TFLite Edge TPU models are usually used. - -TFLite Edge TPU offers various deployment options for machine learning models, including: - -- **On-Device Deployment**: TensorFlow Edge TPU models can be directly deployed on mobile and embedded devices. On-device deployment allows the models to execute directly on the hardware, eliminating the need for cloud connectivity. - -- **Edge Computing with Cloud TensorFlow TPUs**: In scenarios where edge devices have limited processing capabilities, TensorFlow Edge TPUs can offload inference tasks to cloud servers equipped with TPUs. - -- **Hybrid Deployment**: A hybrid approach combines on-device and cloud deployment and offers a versatile and scalable solution for deploying machine learning models. Advantages include on-device processing for quick responses and cloud computing for more complex computations. - -## Exporting YOLOv8 Models to TFLite Edge TPU - -You can expand model compatibility and deployment flexibility by converting YOLOv8 models to TensorFlow Edge TPU. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [Ultralytics Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, it's important to note that while all [Ultralytics YOLOv8 models](../models/index.md) are available for exporting, you can ensure that the model you select supports export functionality [here](../modes/export.md). - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to TFLite Edge TPU format - model.export(format='edgetpu') # creates 'yolov8n_full_integer_quant_edgetpu.tflite’ - - # Load the exported TFLite Edge TPU model - edgetpu_model = YOLO('yolov8n_full_integer_quant_edgetpu.tflite') - - # Run inference - results = edgetpu_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to TFLite Edge TPU format - yolo export model=yolov8n.pt format=edgetpu # creates 'yolov8n_full_integer_quant_edgetpu.tflite' - - # Run inference with the exported model - yolo predict model=yolov8n_full_integer_quant_edgetpu.tflite source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about supported export options, visit the [Ultralytics documentation page on deployment options](../guides/model-deployment-options.md). - -## Deploying Exported YOLOv8 TFLite Edge TPU Models - -After successfully exporting your Ultralytics YOLOv8 models to TFLite Edge TPU format, you can now deploy them. The primary and recommended first step for running a TFLite Edge TPU model is to use the YOLO("model_edgetpu.tflite") method, as outlined in the previous usage code snippet. - -However, for in-depth instructions on deploying your TFLite Edge TPU models, take a look at the following resources: - -- **[Coral Edge TPU on a Raspberry Pi with Ultralytics YOLOv8](../guides/coral-edge-tpu-on-raspberry-pi.md)**: Discover how to integrate Coral Edge TPUs with Raspberry Pi for enhanced machine learning capabilities. - -- **[Code Examples](https://coral.ai/docs/edgetpu/compiler/)**: Access practical TensorFlow Edge TPU deployment examples to kickstart your projects. - -- **[Run Inference on the Edge TPU with Python](https://coral.ai/docs/edgetpu/tflite-python/#overview)**: Explore how to use the TensorFlow Lite Python API for Edge TPU applications, including setup and usage guidelines. - -## Summary - -In this guide, we’ve learned how to export Ultralytics YOLOv8 models to TFLite Edge TPU format. By following the steps mentioned above, you can increase the speed and power of your computer vision applications. - -For further details on usage, visit the [Edge TPU official website](https://cloud.google.com/edge-tpu). - -Also, for more information on other Ultralytics YOLOv8 integrations, please visit our [integration guide page](index.md). There, you'll discover valuable resources and insights. diff --git a/ultralytics-main/docs/en/integrations/gradio.md b/ultralytics-main/docs/en/integrations/gradio.md deleted file mode 100644 index 3845b4f..0000000 --- a/ultralytics-main/docs/en/integrations/gradio.md +++ /dev/null @@ -1,106 +0,0 @@ ---- -comments: true -description: Learn to use Gradio and Ultralytics YOLOv8 for interactive object detection. Upload images and adjust detection parameters in real-time. -keywords: Gradio, Ultralytics YOLOv8, object detection, interactive AI, Python ---- - -# Interactive Object Detection: Gradio & Ultralytics YOLOv8 🚀 - -## Introduction to Interactive Object Detection - -This Gradio interface provides an easy and interactive way to perform object detection using the [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) model. Users can upload images and adjust parameters like confidence threshold and intersection-over-union (IoU) threshold to get real-time detection results. - -## Why Use Gradio for Object Detection? - -* **User-Friendly Interface:** Gradio offers a straightforward platform for users to upload images and visualize detection results without any coding requirement. -* **Real-Time Adjustments:** Parameters such as confidence and IoU thresholds can be adjusted on the fly, allowing for immediate feedback and optimization of detection results. -* **Broad Accessibility:** The Gradio web interface can be accessed by anyone, making it an excellent tool for demonstrations, educational purposes, and quick experiments. - -

- Gradio example screenshot -

- -## How to Install the Gradio - -```bash -pip install gradio -``` - -## How to Use the Interface - -1. **Upload Image:** Click on 'Upload Image' to choose an image file for object detection. -2. **Adjust Parameters:** - * **Confidence Threshold:** Slider to set the minimum confidence level for detecting objects. - * **IoU Threshold:** Slider to set the IoU threshold for distinguishing different objects. -3. **View Results:** The processed image with detected objects and their labels will be displayed. - -## Example Use Cases - -* **Sample Image 1:** Bus detection with default thresholds. -* **Sample Image 2:** Detection on a sports image with default thresholds. - -## Usage Example - -This section provides the Python code used to create the Gradio interface with the Ultralytics YOLOv8 model. Supports classification tasks, detection tasks, segmentation tasks, and key point tasks. - -```python -import PIL.Image as Image -import gradio as gr - -from ultralytics import ASSETS, YOLO - -model = YOLO("yolov8n.pt") - - -def predict_image(img, conf_threshold, iou_threshold): - results = model.predict( - source=img, - conf=conf_threshold, - iou=iou_threshold, - show_labels=True, - show_conf=True, - imgsz=640, - ) - - for r in results: - im_array = r.plot() - im = Image.fromarray(im_array[..., ::-1]) - - return im - - -iface = gr.Interface( - fn=predict_image, - inputs=[ - gr.Image(type="pil", label="Upload Image"), - gr.Slider(minimum=0, maximum=1, value=0.25, label="Confidence threshold"), - gr.Slider(minimum=0, maximum=1, value=0.45, label="IoU threshold") - ], - outputs=gr.Image(type="pil", label="Result"), - title="Ultralytics Gradio", - description="Upload images for inference. The Ultralytics YOLOv8n model is used by default.", - examples=[ - [ASSETS / "bus.jpg", 0.25, 0.45], - [ASSETS / "zidane.jpg", 0.25, 0.45], - ] -) - -if __name__ == '__main__': - iface.launch() -``` - -## Parameters Explanation - -| Parameter Name | Type | Description | -|------------------|---------|----------------------------------------------------------| -| `img` | `Image` | The image on which object detection will be performed. | -| `conf_threshold` | `float` | Confidence threshold for detecting objects. | -| `iou_threshold` | `float` | Intersection-over-union threshold for object separation. | - -### Gradio Interface Components - -| Component | Description | -|--------------|------------------------------------------| -| Image Input | To upload the image for detection. | -| Sliders | To adjust confidence and IoU thresholds. | -| Image Output | To display the detection results. | diff --git a/ultralytics-main/docs/en/integrations/index.md b/ultralytics-main/docs/en/integrations/index.md deleted file mode 100644 index 6195f54..0000000 --- a/ultralytics-main/docs/en/integrations/index.md +++ /dev/null @@ -1,104 +0,0 @@ ---- -comments: true -description: Explore Ultralytics integrations with tools for dataset management, model optimization, ML workflows automation, experiment tracking, version control, and more. Learn about our support for various model export formats for deployment. -keywords: Ultralytics integrations, Roboflow, Neural Magic, ClearML, Comet ML, DVC, Ultralytics HUB, MLFlow, Neptune, Ray Tune, TensorBoard, W&B, model export formats, PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, CoreML, TF SavedModel, TF GraphDef, TF Lite, TF Edge TPU, TF.js, PaddlePaddle, NCNN ---- - -# Ultralytics Integrations - -Welcome to the Ultralytics Integrations page! This page provides an overview of our partnerships with various tools and platforms, designed to streamline your machine learning workflows, enhance dataset management, simplify model training, and facilitate efficient deployment. - -Ultralytics YOLO ecosystem and integrations - -

-
- -
- Watch: Ultralytics YOLOv8 Deployment and Integrations -

- -## Datasets Integrations - -- [Roboflow](roboflow.md): Facilitate seamless dataset management for Ultralytics models, offering robust annotation, preprocessing, and augmentation capabilities. - -## Training Integrations - -- [ClearML](clearml.md): Automate your Ultralytics ML workflows, monitor experiments, and foster team collaboration. - -- [Comet ML](comet.md): Enhance your model development with Ultralytics by tracking, comparing, and optimizing your machine learning experiments. - -- [DVC](dvc.md): Implement version control for your Ultralytics machine learning projects, synchronizing data, code, and models effectively. - -- [MLFlow](mlflow.md): Streamline the entire ML lifecycle of Ultralytics models, from experimentation and reproducibility to deployment. - -- [Ultralytics HUB](https://hub.ultralytics.com): Access and contribute to a community of pre-trained Ultralytics models. - -- [Neptune](https://neptune.ai/): Maintain a comprehensive log of your ML experiments with Ultralytics in this metadata store designed for MLOps. - -- [Ray Tune](ray-tune.md): Optimize the hyperparameters of your Ultralytics models at any scale. - -- [TensorBoard](tensorboard.md): Visualize your Ultralytics ML workflows, monitor model metrics, and foster team collaboration. - -- [Weights & Biases (W&B)](weights-biases.md): Monitor experiments, visualize metrics, and foster reproducibility and collaboration on Ultralytics projects. - -- [Amazon SageMaker](amazon-sagemaker.md): Leverage Amazon SageMaker to efficiently build, train, and deploy Ultralytics models, providing an all-in-one platform for the ML lifecycle. - -## Deployment Integrations - -- [Neural Magic](neural-magic.md): Leverage Quantization Aware Training (QAT) and pruning techniques to optimize Ultralytics models for superior performance and leaner size. - -- [Gradio](gradio.md) 🚀 NEW: Deploy Ultralytics models with Gradio for real-time, interactive object detection demos. - -- [TorchScript](torchscript.md): Developed as part of the [PyTorch](https://pytorch.org/) framework, TorchScript enables efficient execution and deployment of machine learning models in various production environments without the need for Python dependencies. - -- [ONNX](onnx.md): An open-source format created by [Microsoft](https://www.microsoft.com) for facilitating the transfer of AI models between various frameworks, enhancing the versatility and deployment flexibility of Ultralytics models. - -- [OpenVINO](openvino.md): Intel's toolkit for optimizing and deploying computer vision models efficiently across various Intel CPU and GPU platforms. - -- [TensorRT](tensorrt.md): Developed by [NVIDIA](https://www.nvidia.com/), this high-performance deep learning inference framework and model format optimizes AI models for accelerated speed and efficiency on NVIDIA GPUs, ensuring streamlined deployment. - -- [CoreML](coreml.md): CoreML, developed by [Apple](https://www.apple.com/), is a framework designed for efficiently integrating machine learning models into applications across iOS, macOS, watchOS, and tvOS, using Apple's hardware for effective and secure model deployment. - -- [TFLite](tflite.md): Developed by [Google](https://www.google.com), TFLite is a lightweight framework for deploying machine learning models on mobile and edge devices, ensuring fast, efficient inference with minimal memory footprint. - -- [TFLite Edge TPU](edge-tpu.md): Developed by [Google](https://www.google.com) for optimizing TensorFlow Lite models on Edge TPUs, this model format ensures high-speed, efficient edge computing. - -- [PaddlePaddle](paddlepaddle.md): An open-source deep learning platform by [Baidu](https://www.baidu.com/), PaddlePaddle enables the efficient deployment of AI models and focuses on the scalability of industrial applications. - -- [NCNN](ncnn.md): Developed by [Tencent](http://www.tencent.com/), NCNN is an efficient neural network inference framework tailored for mobile devices. It enables direct deployment of AI models into apps, optimizing performance across various mobile platforms. - -### Export Formats - -We also support a variety of model export formats for deployment in different environments. Here are the available formats: - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](onnx.md) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | - -Explore the links to learn more about each integration and how to get the most out of them with Ultralytics. - -## Contribute to Our Integrations - -We're always excited to see how the community integrates Ultralytics YOLO with other technologies, tools, and platforms! If you have successfully integrated YOLO with a new system or have valuable insights to share, consider contributing to our Integrations Docs. - -By writing a guide or tutorial, you can help expand our documentation and provide real-world examples that benefit the community. It's an excellent way to contribute to the growing ecosystem around Ultralytics YOLO. - -To contribute, please check out our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for instructions on how to submit a Pull Request (PR) 🛠️. We eagerly await your contributions! - -Let's collaborate to make the Ultralytics YOLO ecosystem more expansive and feature-rich 🙏! diff --git a/ultralytics-main/docs/en/integrations/mlflow.md b/ultralytics-main/docs/en/integrations/mlflow.md deleted file mode 100644 index 0dcf4da..0000000 --- a/ultralytics-main/docs/en/integrations/mlflow.md +++ /dev/null @@ -1,117 +0,0 @@ ---- -comments: true -description: Uncover the utility of MLflow for effective experiment logging in your Ultralytics YOLO projects. -keywords: ultralytics docs, YOLO, MLflow, experiment logging, metrics tracking, parameter logging, artifact logging ---- - -# MLflow Integration for Ultralytics YOLO - -MLflow ecosystem - -## Introduction - -Experiment logging is a crucial aspect of machine learning workflows that enables tracking of various metrics, parameters, and artifacts. It helps to enhance model reproducibility, debug issues, and improve model performance. [Ultralytics](https://ultralytics.com) YOLO, known for its real-time object detection capabilities, now offers integration with [MLflow](https://mlflow.org/), an open-source platform for complete machine learning lifecycle management. - -This documentation page is a comprehensive guide to setting up and utilizing the MLflow logging capabilities for your Ultralytics YOLO project. - -## What is MLflow? - -[MLflow](https://mlflow.org/) is an open-source platform developed by [Databricks](https://www.databricks.com/) for managing the end-to-end machine learning lifecycle. It includes tools for tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow is designed to work with any machine learning library and programming language. - -## Features - -- **Metrics Logging**: Logs metrics at the end of each epoch and at the end of the training. -- **Parameter Logging**: Logs all the parameters used in the training. -- **Artifacts Logging**: Logs model artifacts, including weights and configuration files, at the end of the training. - -## Setup and Prerequisites - -Ensure MLflow is installed. If not, install it using pip: - -```bash -pip install mlflow -``` - -Make sure that MLflow logging is enabled in Ultralytics settings. Usually, this is controlled by the settings `mflow` key. See the [settings](https://docs.ultralytics.com/quickstart/#ultralytics-settings) page for more info. - -!!! Example "Update Ultralytics MLflow Settings" - - === "Python" - Within the Python environment, call the `update` method on the `settings` object to change your settings: - ```python - from ultralytics import settings - - # Update a setting - settings.update({'mlflow': True}) - - # Reset settings to default values - settings.reset() - ``` - - === "CLI" - If you prefer using the command-line interface, the following commands will allow you to modify your settings: - ```bash - # Update a setting - yolo settings runs_dir='/path/to/runs' - - # Reset settings to default values - yolo settings reset - ``` - -## How to Use - -### Commands - -1. **Set a Project Name**: You can set the project name via an environment variable: - - ```bash - export MLFLOW_EXPERIMENT_NAME= - ``` - - Or use the `project=` argument when training a YOLO model, i.e. `yolo train project=my_project`. - -2. **Set a Run Name**: Similar to setting a project name, you can set the run name via an environment variable: - - ```bash - export MLFLOW_RUN= - ``` - - Or use the `name=` argument when training a YOLO model, i.e. `yolo train project=my_project name=my_name`. - -3. **Start Local MLflow Server**: To start tracking, use: - - ```bash - mlflow server --backend-store-uri runs/mlflow' - ``` - - This will start a local server at http://127.0.0.1:5000 by default and save all mlflow logs to the 'runs/mlflow' directory. To specify a different URI, set the `MLFLOW_TRACKING_URI` environment variable. - -4. **Kill MLflow Server Instances**: To stop all running MLflow instances, run: - - ```bash - ps aux | grep 'mlflow' | grep -v 'grep' | awk '{print $2}' | xargs kill -9 - ``` - -### Logging - -The logging is taken care of by the `on_pretrain_routine_end`, `on_fit_epoch_end`, and `on_train_end` callback functions. These functions are automatically called during the respective stages of the training process, and they handle the logging of parameters, metrics, and artifacts. - -## Examples - -1. **Logging Custom Metrics**: You can add custom metrics to be logged by modifying the `trainer.metrics` dictionary before `on_fit_epoch_end` is called. - -2. **View Experiment**: To view your logs, navigate to your MLflow server (usually http://127.0.0.1:5000) and select your experiment and run. YOLO MLflow Experiment - -3. **View Run**: Runs are individual models inside an experiment. Click on a Run and see the Run details, including uploaded artifacts and model weights. YOLO MLflow Run - -## Disabling MLflow - -To turn off MLflow logging: - -```bash -yolo settings mlflow=False -``` - -## Conclusion - -MLflow logging integration with Ultralytics YOLO offers a streamlined way to keep track of your machine learning experiments. It empowers you to monitor performance metrics and manage artifacts effectively, thus aiding in robust model development and deployment. For further details please visit the MLflow [official documentation](https://mlflow.org/docs/latest/index.html). diff --git a/ultralytics-main/docs/en/integrations/ncnn.md b/ultralytics-main/docs/en/integrations/ncnn.md deleted file mode 100644 index 835f8fc..0000000 --- a/ultralytics-main/docs/en/integrations/ncnn.md +++ /dev/null @@ -1,120 +0,0 @@ ---- -comments: true -description: Uncover how to improve your Ultralytics YOLOv8 model's performance using the NCNN export format that is suitable for devices with limited computation resources. -keywords: Ultralytics, YOLOv8, NCNN Export, Export YOLOv8, Model Deployment ---- - -# How to Export to NCNN from YOLOv8 for Smooth Deployment - -Deploying computer vision models on devices with limited computational power, such as mobile or embedded systems, can be tricky. You need to make sure you use a format optimized for optimal performance. This makes sure that even devices with limited processing power can handle advanced computer vision tasks well. - -The export to NCNN format feature allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for lightweight device-based applications. In this guide, we'll walk you through how to convert your models to the NCNN format, making it easier for your models to perform well on various mobile and embedded devices. - -## Why should you export to NCNN? - -

- NCNN overview -

- -The [NCNN](https://github.com/Tencent/ncnn) framework, developed by Tencent, is a high-performance neural network inference computing framework optimized specifically for mobile platforms, including mobile phones, embedded devices, and IoT devices. NCNN is compatible with a wide range of platforms, including Linux, Android, iOS, and macOS. - -NCNN is known for its fast processing speed on mobile CPUs and enables rapid deployment of deep learning models to mobile platforms. This makes it easier to build smart apps, putting the power of AI right at your fingertips. - -## Key Features of NCNN Models - -NCNN models offer a wide range of key features that enable on-device machine learning by helping developers run their models on mobile, embedded, and edge devices: - -- **Efficient and High-Performance**: NCNN models are made to be efficient and lightweight, optimized for running on mobile and embedded devices like Raspberry Pi with limited resources. They can also achieve high performance with high accuracy on various computer vision-based tasks. - -- **Quantization**: NCNN models often support quantization which is a technique that reduces the precision of the model's weights and activations. This leads to further improvements in performance and reduces memory footprint. - -- **Compatibility**: NCNN models are compatible with popular deep learning frameworks like [TensorFlow](https://www.tensorflow.org/), [Caffe](https://caffe.berkeleyvision.org/), and [ONNX](https://onnx.ai/). This compatibility allows developers to use existing models and workflows easily. - -- **Easy to Use**: NCNN models are designed for easy integration into various applications, thanks to their compatibility with popular deep learning frameworks. Additionally, NCNN offers user-friendly tools for converting models between different formats, ensuring smooth interoperability across the development landscape. - -## Deployment Options with NCNN - -Before we look at the code for exporting YOLOv8 models to the NCNN format, let’s understand how NCNN models are normally used. - -NCNN models, designed for efficiency and performance, are compatible with a variety of deployment platforms: - -- **Mobile Deployment**: Specifically optimized for Android and iOS, allowing for seamless integration into mobile applications for efficient on-device inference. - -- **Embedded Systems and IoT Devices**: If you find that running inference on a Raspberry Pi with the [Ultralytics Guide](../guides/raspberry-pi.md) isn't fast enough, switching to an NCNN exported model could help speed things up. NCNN is great for devices like Raspberry Pi and NVIDIA Jetson, especially in situations where you need quick processing right on the device. - -- **Desktop and Server Deployment**: Capable of being deployed in desktop and server environments across Linux, Windows, and macOS, supporting development, training, and evaluation with higher computational capacities. - -## Export to NCNN: Converting Your YOLOv8 Model - -You can expand model compatibility and deployment flexibility by converting YOLOv8 models to NCNN format. - -### Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [Ultralytics Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, it's important to note that while all [Ultralytics YOLOv8 models](../models/index.md) are available for exporting, you can ensure that the model you select supports export functionality [here](../modes/export.md). - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to NCNN format - model.export(format='ncnn') # creates '/yolov8n_ncnn_model' - - # Load the exported NCNN model - ncnn_model = YOLO('./yolov8n_ncnn_model') - - # Run inference - results = ncnn_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to NCNN format - yolo export model=yolov8n.pt format=ncnn # creates '/yolov8n_ncnn_model' - - # Run inference with the exported model - yolo predict model='./yolov8n_ncnn_model' source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about supported export options, visit the [Ultralytics documentation page on deployment options](../guides/model-deployment-options.md). - -## Deploying Exported YOLOv8 NCNN Models - -After successfully exporting your Ultralytics YOLOv8 models to NCNN format, you can now deploy them. The primary and recommended first step for running a NCNN model is to utilize the YOLO("./model_ncnn_model") method, as outlined in the previous usage code snippet. However, for in-depth instructions on deploying your NCNN models in various other settings, take a look at the following resources: - -- **[Android](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-android)**: This blog explains how to use NCNN models for performing tasks like object detection through Android applications. - -- **[macOS](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-macos)**: Understand how to use NCNN models for performing tasks through macOS. - -- **[Linux](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-linux)**: Explore this page to learn how to deploy NCNN models on limited resource devices like Raspberry Pi and other similar devices. - -- **[Windows x64 using VS2017](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-windows-x64-using-visual-studio-community-2017)**: Explore this blog to learn how to deploy NCNN models on windows x64 using Visual Studio Community 2017. - -## Summary - -In this guide, we've gone over exporting Ultralytics YOLOv8 models to the NCNN format. This conversion step is crucial for improving the efficiency and speed of YOLOv8 models, making them more effective and suitable for limited-resource computing environments. - -For detailed instructions on usage, please refer to the [official NCNN documentation](https://ncnn.readthedocs.io/en/latest/index.html). - -Also, if you're interested in exploring other integration options for Ultralytics YOLOv8, be sure to visit our [integration guide page](index.md) for further insights and information. diff --git a/ultralytics-main/docs/en/integrations/neural-magic.md b/ultralytics-main/docs/en/integrations/neural-magic.md deleted file mode 100644 index 293c199..0000000 --- a/ultralytics-main/docs/en/integrations/neural-magic.md +++ /dev/null @@ -1,165 +0,0 @@ ---- -comments: true -description: Learn how to deploy your YOLOv8 models rapidly using Neural Magic’s DeepSparse. This guide focuses on integrating Ultralytics YOLOv8 with the DeepSparse Engine for high-speed, CPU-based inference, leveraging advanced neural network sparsity techniques. -keywords: YOLOv8, DeepSparse Engine, Ultralytics, CPU Inference, Neural Network Sparsity, Object Detection, Model Optimization ---- - -# Optimizing YOLOv8 Inferences with Neural Magic’s DeepSparse Engine - -When deploying object detection models like [Ultralytics YOLOv8](https://ultralytics.com) on various hardware, you can bump into unique issues like optimization. This is where YOLOv8’s integration with Neural Magic’s DeepSparse Engine steps in. It transforms the way YOLOv8 models are executed and enables GPU-level performance directly on CPUs. - -This guide shows you how to deploy YOLOv8 using Neural Magic's DeepSparse, how to run inferences, and also how to benchmark performance to ensure it is optimized. - -## Neural Magic’s DeepSparse - -

- Neural Magic’s DeepSparse Overview -

- -[Neural Magic’s DeepSparse](https://neuralmagic.com/deepsparse/) is an inference run-time designed to optimize the execution of neural networks on CPUs. It applies advanced techniques like sparsity, pruning, and quantization to dramatically reduce computational demands while maintaining accuracy. DeepSparse offers an agile solution for efficient and scalable neural network execution across various devices. - -## Benefits of Integrating Neural Magic’s DeepSparse with YOLOv8 - -Before diving into how to deploy YOLOV8 using DeepSparse, let’s understand the benefits of using DeepSparse. Some key advantages include: - -- **Enhanced Inference Speed**: Achieves up to 525 FPS (on YOLOv8n), significantly speeding up YOLOv8's inference capabilities compared to traditional methods. - -

- Enhanced Inference Speed -

- -- **Optimized Model Efficiency**: Uses pruning and quantization to enhance YOLOv8's efficiency, reducing model size and computational requirements while maintaining accuracy. - -

- Optimized Model Efficiency -

- -- **High Performance on Standard CPUs**: Delivers GPU-like performance on CPUs, providing a more accessible and cost-effective option for various applications. - -- **Streamlined Integration and Deployment**: Offers user-friendly tools for easy integration of YOLOv8 into applications, including image and video annotation features. - -- **Support for Various Model Types**: Compatible with both standard and sparsity-optimized YOLOv8 models, adding deployment flexibility. - -- **Cost-Effective and Scalable Solution**: Reduces operational expenses and offers scalable deployment of advanced object detection models. - -## How Does Neural Magic's DeepSparse Technology Works? - -Neural Magic’s Deep Sparse technology is inspired by the human brain’s efficiency in neural network computation. It adopts two key principles from the brain as follows: - -- **Sparsity**: The process of sparsification involves pruning redundant information from deep learning networks, leading to smaller and faster models without compromising accuracy. This technique reduces the network's size and computational needs significantly. - -- **Locality of Reference**: DeepSparse uses a unique execution method, breaking the network into Tensor Columns. These columns are executed depth-wise, fitting entirely within the CPU's cache. This approach mimics the brain's efficiency, minimizing data movement and maximizing the CPU's cache use. - -

- How Neural Magic's DeepSparse Technology Works -

- -For more details on how Neural Magic's DeepSparse technology work, check out [their blog post](https://neuralmagic.com/blog/how-neural-magics-deep-sparse-technology-works/). - -## Creating A Sparse Version of YOLOv8 Trained on a Custom Dataset - -SparseZoo, an open-source model repository by Neural Magic, offers [a collection of pre-sparsified YOLOv8 model checkpoints](https://sparsezoo.neuralmagic.com/?modelSet=computer_vision&searchModels=yolo). With SparseML, seamlessly integrated with Ultralytics, users can effortlessly fine-tune these sparse checkpoints on their specific datasets using a straightforward command-line interface. - -Checkout [Neural Magic's SparseML YOLOv8 documentation](https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov8) for more details. - -## Usage: Deploying YOLOV8 using DeepSparse - -Deploying YOLOv8 with Neural Magic's DeepSparse involves a few straightforward steps. Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. Here's how you can get started. - -### Step 1: Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required packages - pip install deepsparse[yolov8] - ``` - -### Step 2: Exporting YOLOv8 to ONNX Format - -DeepSparse Engine requires YOLOv8 models in ONNX format. Exporting your model to this format is essential for compatibility with DeepSparse. Use the following command to export YOLOv8 models: - -!!! Tip "Model Export" - - === "CLI" - - ```bash - # Export YOLOv8 model to ONNX format - yolo task=detect mode=export model=yolov8n.pt format=onnx opset=13 - ``` - -This command will save the `yolov8n.onnx` model to your disk. - -### Step 3: Deploying and Running Inferences - -With your YOLOv8 model in ONNX format, you can deploy and run inferences using DeepSparse. This can be done easily with their intuitive Python API: - -!!! Tip "Deploying and Running Inferences" - - === "Python" - - ```python - from deepsparse import Pipeline - - # Specify the path to your YOLOv8 ONNX model - model_path = "path/to/yolov8n.onnx" - - # Set up the DeepSparse Pipeline - yolo_pipeline = Pipeline.create( - task="yolov8", - model_path=model_path - ) - - # Run the model on your images - images = ["path/to/image.jpg"] - pipeline_outputs = yolo_pipeline(images=images) - ``` - -### Step 4: Benchmarking Performance - -It's important to check that your YOLOv8 model is performing optimally on DeepSparse. You can benchmark your model's performance to analyze throughput and latency: - -!!! Tip "Benchmarking" - - === "CLI" - - ```bash - # Benchmark performance - deepsparse.benchmark model_path="path/to/yolov8n.onnx" --scenario=sync --input_shapes="[1,3,640,640]" - ``` - -### Step 5: Additional Features - -DeepSparse provides additional features for practical integration of YOLOv8 in applications, such as image annotation and dataset evaluation. - -!!! Tip "Additional Features" - - === "CLI" - - ```bash - # For image annotation - deepsparse.yolov8.annotate --source "path/to/image.jpg" --model_filepath "path/to/yolov8n.onnx" - - # For evaluating model performance on a dataset - deepsparse.yolov8.eval --model_path "path/to/yolov8n.onnx" - ``` - -Running the annotate command processes your specified image, detecting objects, and saving the annotated image with bounding boxes and classifications. The annotated image will be stored in an annotation-results folder. This helps provide a visual representation of the model's detection capabilities. - -

- Image Annotation Feature -

- -After running the eval command, you will receive detailed output metrics such as precision, recall, and mAP (mean Average Precision). This provides a comprehensive view of your model's performance on the dataset. This functionality is particularly useful for fine-tuning and optimizing your YOLOv8 models for specific use cases, ensuring high accuracy and efficiency. - -## Summary - -This guide explored integrating Ultralytics’ YOLOv8 with Neural Magic's DeepSparse Engine. It highlighted how this integration enhances YOLOv8's performance on CPU platforms, offering GPU-level efficiency and advanced neural network sparsity techniques. - -For more detailed information and advanced usage, visit [Neural Magic’s DeepSparse documentation](https://docs.neuralmagic.com/products/deepsparse/). Also, check out Neural Magic’s documentation on the integration with YOLOv8 [here](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/yolov8#yolov8-inference-pipelines) and watch a great session on it [here](https://www.youtube.com/watch?v=qtJ7bdt52x8). - -Additionally, for a broader understanding of various YOLOv8 integrations, visit the [Ultralytics integration guide page](../integrations/index.md), where you can discover a range of other exciting integration possibilities. diff --git a/ultralytics-main/docs/en/integrations/onnx.md b/ultralytics-main/docs/en/integrations/onnx.md deleted file mode 100644 index b869b04..0000000 --- a/ultralytics-main/docs/en/integrations/onnx.md +++ /dev/null @@ -1,134 +0,0 @@ ---- -comments: true -description: Explore how to improve your Ultralytics YOLOv8 model's performance and interoperability using the ONNX (Open Neural Network Exchange) export format that is suitable for diverse hardware and software environments. -keywords: Ultralytics, YOLOv8, ONNX Format, Export YOLOv8, CUDA Support, Model Deployment ---- - -# ONNX Export for YOLOv8 Models - -Often, when deploying computer vision models, you’ll need a model format that's both flexible and compatible with multiple platforms. - -Exporting [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models to ONNX format streamlines deployment and ensures optimal performance across various environments. This guide will show you how to easily convert your YOLOv8 models to ONNX and enhance their scalability and effectiveness in real-world applications. - -## ONNX and ONNX Runtime - -[ONNX](https://onnx.ai/), which stands for Open Neural Network Exchange, is a community project that Facebook and Microsoft initially developed. The ongoing development of ONNX is a collaborative effort supported by various organizations like IBM, Amazon (through AWS), and Google. The project aims to create an open file format designed to represent machine learning models in a way that allows them to be used across different AI frameworks and hardware. - -ONNX models can be used to transition between different frameworks seamlessly. For instance, a deep learning model trained in PyTorch can be exported to ONNX format and then easily imported into TensorFlow. - -

- ONNX -

- -Alternatively, ONNX models can be used with ONNX Runtime. [ONNX Runtime](https://onnxruntime.ai/) is a versatile cross-platform accelerator for machine learning models that is compatible with frameworks like PyTorch, TensorFlow, TFLite, scikit-learn, etc. - -ONNX Runtime optimizes the execution of ONNX models by leveraging hardware-specific capabilities. This optimization allows the models to run efficiently and with high performance on various hardware platforms, including CPUs, GPUs, and specialized accelerators. - -

- ONNX with ONNX Runtime -

- -Whether used independently or in tandem with ONNX Runtime, ONNX provides a flexible solution for machine learning model deployment and compatibility. - -## Key Features of ONNX Models - -The ability of ONNX to handle various formats can be attributed to the following key features: - -- **Common Model Representation**: ONNX defines a common set of operators (like convolutions, layers, etc.) and a standard data format. When a model is converted to ONNX format, its architecture and weights are translated into this common representation. This uniformity ensures that the model can be understood by any framework that supports ONNX. - -- **Versioning and Backward Compatibility**: ONNX maintains a versioning system for its operators. This ensures that even as the standard evolves, models created in older versions remain usable. Backward compatibility is a crucial feature that prevents models from becoming obsolete quickly. - -- **Graph-based Model Representation**: ONNX represents models as computational graphs. This graph-based structure is a universal way of representing machine learning models, where nodes represent operations or computations, and edges represent the tensors flowing between them. This format is easily adaptable to various frameworks which also represent models as graphs. - -- **Tools and Ecosystem**: There is a rich ecosystem of tools around ONNX that assist in model conversion, visualization, and optimization. These tools make it easier for developers to work with ONNX models and to convert models between different frameworks seamlessly. - -## Common Usage of ONNX - -Before we jump into how to export YOLOv8 models to the ONNX format, let’s take a look at where ONNX models are usually used. - -### CPU Deployment - -ONNX models are often deployed on CPUs due to their compatibility with ONNX Runtime. This runtime is optimized for CPU execution. It significantly improves inference speed and makes real-time CPU deployments feasible. - -### Supported Deployment Options - -While ONNX models are commonly used on CPUs, they can also be deployed on the following platforms: - -- **GPU Acceleration**: ONNX fully supports GPU acceleration, particularly NVIDIA CUDA. This enables efficient execution on NVIDIA GPUs for tasks that demand high computational power. - -- **Edge and Mobile Devices**: ONNX extends to edge and mobile devices, perfect for on-device and real-time inference scenarios. It's lightweight and compatible with edge hardware. - -- **Web Browsers**: ONNX can run directly in web browsers, powering interactive and dynamic web-based AI applications. - -## Exporting YOLOv8 Models to ONNX - -You can expand model compatibility and deployment flexibility by converting YOLOv8 models to ONNX format. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to ONNX format - model.export(format='onnx') # creates 'yolov8n.onnx' - - # Load the exported ONNX model - onnx_model = YOLO('yolov8n.onnx') - - # Run inference - results = onnx_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to ONNX format - yolo export model=yolov8n.pt format=onnx # creates 'yolov8n.onnx' - - # Run inference with the exported model - yolo predict model=yolov8n.onnx source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -## Deploying Exported YOLOv8 ONNX Models - -Once you've successfully exported your Ultralytics YOLOv8 models to ONNX format, the next step is deploying these models in various environments. For detailed instructions on deploying your ONNX models, take a look at the following resources: - -- **[ONNX Runtime Python API Documentation](https://onnxruntime.ai/docs/api/python/api_summary.html)**: This guide provides essential information for loading and running ONNX models using ONNX Runtime. - -- **[Deploying on Edge Devices](https://onnxruntime.ai/docs/tutorials/iot-edge/)**: Check out this docs page for different examples of deploying ONNX models on edge. - -- **[ONNX Tutorials on GitHub](https://github.com/onnx/tutorials)**: A collection of comprehensive tutorials that cover various aspects of using and implementing ONNX models in different scenarios. - -## Summary - -In this guide, you've learned how to export Ultralytics YOLOv8 models to ONNX format to increase their interoperability and performance across various platforms. You were also introduced to the ONNX Runtime and ONNX deployment options. - -For further details on usage, visit the [ONNX official documentation](https://onnx.ai/onnx/intro/). - -Also, if you’d like to know more about other Ultralytics YOLOv8 integrations, visit our [integration guide page](../integrations/index.md). You'll find plenty of useful resources and insights there. diff --git a/ultralytics-main/docs/en/integrations/openvino.md b/ultralytics-main/docs/en/integrations/openvino.md deleted file mode 100644 index 4234d78..0000000 --- a/ultralytics-main/docs/en/integrations/openvino.md +++ /dev/null @@ -1,284 +0,0 @@ ---- -comments: true -description: Discover the power of deploying your Ultralytics YOLOv8 model using OpenVINO format for up to 10x speedup vs PyTorch. -keywords: ultralytics docs, YOLOv8, export YOLOv8, YOLOv8 model deployment, exporting YOLOv8, OpenVINO, OpenVINO format ---- - -# Intel OpenVINO Export - -OpenVINO Ecosystem - -In this guide, we cover exporting YOLOv8 models to the [OpenVINO](https://docs.openvino.ai/) format, which can provide up to 3x [CPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/cpu-device.html) speedup, as well as accelerating YOLO inference on Intel [GPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/gpu-device.html) and [NPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/npu-device.html) hardware. - -OpenVINO, short for Open Visual Inference & Neural Network Optimization toolkit, is a comprehensive toolkit for optimizing and deploying AI inference models. Even though the name contains Visual, OpenVINO also supports various additional tasks including language, audio, time series, etc. - -

-
- -
- Watch: How To Export and Optimize an Ultralytics YOLOv8 Model for Inference with OpenVINO. -

- -## Usage Examples - -Export a YOLOv8n model to OpenVINO format and run inference with the exported model. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a YOLOv8n PyTorch model - model = YOLO('yolov8n.pt') - - # Export the model - model.export(format='openvino') # creates 'yolov8n_openvino_model/' - - # Load the exported OpenVINO model - ov_model = YOLO('yolov8n_openvino_model/') - - # Run inference - results = ov_model('https://ultralytics.com/images/bus.jpg') - ``` - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to OpenVINO format - yolo export model=yolov8n.pt format=openvino # creates 'yolov8n_openvino_model/' - - # Run inference with the exported model - yolo predict model=yolov8n_openvino_model source='https://ultralytics.com/images/bus.jpg' - ``` - -## Arguments - -| Key | Value | Description | -|----------|--------------|------------------------------------------------------| -| `format` | `'openvino'` | format to export to | -| `imgsz` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) | -| `half` | `False` | FP16 quantization | - -## Benefits of OpenVINO - -1. **Performance**: OpenVINO delivers high-performance inference by utilizing the power of Intel CPUs, integrated and discrete GPUs, and FPGAs. -2. **Support for Heterogeneous Execution**: OpenVINO provides an API to write once and deploy on any supported Intel hardware (CPU, GPU, FPGA, VPU, etc.). -3. **Model Optimizer**: OpenVINO provides a Model Optimizer that imports, converts, and optimizes models from popular deep learning frameworks such as PyTorch, TensorFlow, TensorFlow Lite, Keras, ONNX, PaddlePaddle, and Caffe. -4. **Ease of Use**: The toolkit comes with more than [80 tutorial notebooks](https://github.com/openvinotoolkit/openvino_notebooks) (including [YOLOv8 optimization](https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/230-yolov8-optimization)) teaching different aspects of the toolkit. - -## OpenVINO Export Structure - -When you export a model to OpenVINO format, it results in a directory containing the following: - -1. **XML file**: Describes the network topology. -2. **BIN file**: Contains the weights and biases binary data. -3. **Mapping file**: Holds mapping of original model output tensors to OpenVINO tensor names. - -You can use these files to run inference with the OpenVINO Inference Engine. - -## Using OpenVINO Export in Deployment - -Once you have the OpenVINO files, you can use the OpenVINO Runtime to run the model. The Runtime provides a unified API to inference across all supported Intel hardware. It also provides advanced capabilities like load balancing across Intel hardware and asynchronous execution. For more information on running the inference, refer to the [Inference with OpenVINO Runtime Guide](https://docs.openvino.ai/2024/openvino-workflow/running-inference.html). - -Remember, you'll need the XML and BIN files as well as any application-specific settings like input size, scale factor for normalization, etc., to correctly set up and use the model with the Runtime. - -In your deployment application, you would typically do the following steps: - -1. Initialize OpenVINO by creating `core = Core()`. -2. Load the model using the `core.read_model()` method. -3. Compile the model using the `core.compile_model()` function. -4. Prepare the input (image, text, audio, etc.). -5. Run inference using `compiled_model(input_data)`. - -For more detailed steps and code snippets, refer to the [OpenVINO documentation](https://docs.openvino.ai/) or [API tutorial](https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/002-openvino-api/002-openvino-api.ipynb). - -## OpenVINO YOLOv8 Benchmarks - -YOLOv8 benchmarks below were run by the Ultralytics team on 4 different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX and OpenVINO. Benchmarks were run on Intel Flex and Arc GPUs, and on Intel Xeon CPUs at FP32 precision (with the `half=False` argument). - -!!! Note - - The benchmarking results below are for reference and might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. - - All benchmarks run with `openvino` Python package version [2023.0.1](https://pypi.org/project/openvino/2023.0.1/). - -### Intel Flex GPU - -The Intel® Data Center GPU Flex Series is a versatile and robust solution designed for the intelligent visual cloud. This GPU supports a wide array of workloads including media streaming, cloud gaming, AI visual inference, and virtual desktop Infrastructure workloads. It stands out for its open architecture and built-in support for the AV1 encode, providing a standards-based software stack for high-performance, cross-architecture applications. The Flex Series GPU is optimized for density and quality, offering high reliability, availability, and scalability. - -Benchmarks below run on Intel® Data Center GPU Flex 170 at FP32 precision. - -
-Flex GPU benchmarks -
- -| Model | Format | Status | Size (MB) | mAP50-95(B) | Inference time (ms/im) | -|---------|-------------|--------|-----------|-------------|------------------------| -| YOLOv8n | PyTorch | ✅ | 6.2 | 0.3709 | 21.79 | -| YOLOv8n | TorchScript | ✅ | 12.4 | 0.3704 | 23.24 | -| YOLOv8n | ONNX | ✅ | 12.2 | 0.3704 | 37.22 | -| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.3703 | 3.29 | -| YOLOv8s | PyTorch | ✅ | 21.5 | 0.4471 | 31.89 | -| YOLOv8s | TorchScript | ✅ | 42.9 | 0.4472 | 32.71 | -| YOLOv8s | ONNX | ✅ | 42.8 | 0.4472 | 43.42 | -| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.4470 | 3.92 | -| YOLOv8m | PyTorch | ✅ | 49.7 | 0.5013 | 50.75 | -| YOLOv8m | TorchScript | ✅ | 99.2 | 0.4999 | 47.90 | -| YOLOv8m | ONNX | ✅ | 99.0 | 0.4999 | 63.16 | -| YOLOv8m | OpenVINO | ✅ | 49.8 | 0.4997 | 7.11 | -| YOLOv8l | PyTorch | ✅ | 83.7 | 0.5293 | 77.45 | -| YOLOv8l | TorchScript | ✅ | 167.2 | 0.5268 | 85.71 | -| YOLOv8l | ONNX | ✅ | 166.8 | 0.5268 | 88.94 | -| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.5264 | 9.37 | -| YOLOv8x | PyTorch | ✅ | 130.5 | 0.5404 | 100.09 | -| YOLOv8x | TorchScript | ✅ | 260.7 | 0.5371 | 114.64 | -| YOLOv8x | ONNX | ✅ | 260.4 | 0.5371 | 110.32 | -| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.5367 | 15.02 | - -This table represents the benchmark results for five different models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x) across four different formats (PyTorch, TorchScript, ONNX, OpenVINO), giving us the status, size, mAP50-95(B) metric, and inference time for each combination. - -### Intel Arc GPU - -Intel® Arc™ represents Intel's foray into the dedicated GPU market. The Arc™ series, designed to compete with leading GPU manufacturers like AMD and Nvidia, caters to both the laptop and desktop markets. The series includes mobile versions for compact devices like laptops, and larger, more powerful versions for desktop computers. - -The Arc™ series is divided into three categories: Arc™ 3, Arc™ 5, and Arc™ 7, with each number indicating the performance level. Each category includes several models, and the 'M' in the GPU model name signifies a mobile, integrated variant. - -Early reviews have praised the Arc™ series, particularly the integrated A770M GPU, for its impressive graphics performance. The availability of the Arc™ series varies by region, and additional models are expected to be released soon. Intel® Arc™ GPUs offer high-performance solutions for a range of computing needs, from gaming to content creation. - -Benchmarks below run on Intel® Arc 770 GPU at FP32 precision. - -
-Arc GPU benchmarks -
- -| Model | Format | Status | Size (MB) | metrics/mAP50-95(B) | Inference time (ms/im) | -|---------|-------------|--------|-----------|---------------------|------------------------| -| YOLOv8n | PyTorch | ✅ | 6.2 | 0.3709 | 88.79 | -| YOLOv8n | TorchScript | ✅ | 12.4 | 0.3704 | 102.66 | -| YOLOv8n | ONNX | ✅ | 12.2 | 0.3704 | 57.98 | -| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.3703 | 8.52 | -| YOLOv8s | PyTorch | ✅ | 21.5 | 0.4471 | 189.83 | -| YOLOv8s | TorchScript | ✅ | 42.9 | 0.4472 | 227.58 | -| YOLOv8s | ONNX | ✅ | 42.7 | 0.4472 | 142.03 | -| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.4469 | 9.19 | -| YOLOv8m | PyTorch | ✅ | 49.7 | 0.5013 | 411.64 | -| YOLOv8m | TorchScript | ✅ | 99.2 | 0.4999 | 517.12 | -| YOLOv8m | ONNX | ✅ | 98.9 | 0.4999 | 298.68 | -| YOLOv8m | OpenVINO | ✅ | 99.1 | 0.4996 | 12.55 | -| YOLOv8l | PyTorch | ✅ | 83.7 | 0.5293 | 725.73 | -| YOLOv8l | TorchScript | ✅ | 167.1 | 0.5268 | 892.83 | -| YOLOv8l | ONNX | ✅ | 166.8 | 0.5268 | 576.11 | -| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.5262 | 17.62 | -| YOLOv8x | PyTorch | ✅ | 130.5 | 0.5404 | 988.92 | -| YOLOv8x | TorchScript | ✅ | 260.7 | 0.5371 | 1186.42 | -| YOLOv8x | ONNX | ✅ | 260.4 | 0.5371 | 768.90 | -| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.5367 | 19 | - -### Intel Xeon CPU - -The Intel® Xeon® CPU is a high-performance, server-grade processor designed for complex and demanding workloads. From high-end cloud computing and virtualization to artificial intelligence and machine learning applications, Xeon® CPUs provide the power, reliability, and flexibility required for today's data centers. - -Notably, Xeon® CPUs deliver high compute density and scalability, making them ideal for both small businesses and large enterprises. By choosing Intel® Xeon® CPUs, organizations can confidently handle their most demanding computing tasks and foster innovation while maintaining cost-effectiveness and operational efficiency. - -Benchmarks below run on 4th Gen Intel® Xeon® Scalable CPU at FP32 precision. - -
-Xeon CPU benchmarks -
- -| Model | Format | Status | Size (MB) | metrics/mAP50-95(B) | Inference time (ms/im) | -|---------|-------------|--------|-----------|---------------------|------------------------| -| YOLOv8n | PyTorch | ✅ | 6.2 | 0.3709 | 24.36 | -| YOLOv8n | TorchScript | ✅ | 12.4 | 0.3704 | 23.93 | -| YOLOv8n | ONNX | ✅ | 12.2 | 0.3704 | 39.86 | -| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.3704 | 11.34 | -| YOLOv8s | PyTorch | ✅ | 21.5 | 0.4471 | 33.77 | -| YOLOv8s | TorchScript | ✅ | 42.9 | 0.4472 | 34.84 | -| YOLOv8s | ONNX | ✅ | 42.8 | 0.4472 | 43.23 | -| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.4471 | 13.86 | -| YOLOv8m | PyTorch | ✅ | 49.7 | 0.5013 | 53.91 | -| YOLOv8m | TorchScript | ✅ | 99.2 | 0.4999 | 53.51 | -| YOLOv8m | ONNX | ✅ | 99.0 | 0.4999 | 64.16 | -| YOLOv8m | OpenVINO | ✅ | 99.1 | 0.4996 | 28.79 | -| YOLOv8l | PyTorch | ✅ | 83.7 | 0.5293 | 75.78 | -| YOLOv8l | TorchScript | ✅ | 167.2 | 0.5268 | 79.13 | -| YOLOv8l | ONNX | ✅ | 166.8 | 0.5268 | 88.45 | -| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.5263 | 56.23 | -| YOLOv8x | PyTorch | ✅ | 130.5 | 0.5404 | 96.60 | -| YOLOv8x | TorchScript | ✅ | 260.7 | 0.5371 | 114.28 | -| YOLOv8x | ONNX | ✅ | 260.4 | 0.5371 | 111.02 | -| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.5371 | 83.28 | - -### Intel Core CPU - -The Intel® Core® series is a range of high-performance processors by Intel. The lineup includes Core i3 (entry-level), Core i5 (mid-range), Core i7 (high-end), and Core i9 (extreme performance). Each series caters to different computing needs and budgets, from everyday tasks to demanding professional workloads. With each new generation, improvements are made to performance, energy efficiency, and features. - -Benchmarks below run on 13th Gen Intel® Core® i7-13700H CPU at FP32 precision. - -
-Core CPU benchmarks -
- -| Model | Format | Status | Size (MB) | metrics/mAP50-95(B) | Inference time (ms/im) | -|---------|-------------|--------|-----------|---------------------|------------------------| -| YOLOv8n | PyTorch | ✅ | 6.2 | 0.4478 | 104.61 | -| YOLOv8n | TorchScript | ✅ | 12.4 | 0.4525 | 112.39 | -| YOLOv8n | ONNX | ✅ | 12.2 | 0.4525 | 28.02 | -| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.4504 | 23.53 | -| YOLOv8s | PyTorch | ✅ | 21.5 | 0.5885 | 194.83 | -| YOLOv8s | TorchScript | ✅ | 43.0 | 0.5962 | 202.01 | -| YOLOv8s | ONNX | ✅ | 42.8 | 0.5962 | 65.74 | -| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.5966 | 38.66 | -| YOLOv8m | PyTorch | ✅ | 49.7 | 0.6101 | 355.23 | -| YOLOv8m | TorchScript | ✅ | 99.2 | 0.6120 | 424.78 | -| YOLOv8m | ONNX | ✅ | 99.0 | 0.6120 | 173.39 | -| YOLOv8m | OpenVINO | ✅ | 99.1 | 0.6091 | 69.80 | -| YOLOv8l | PyTorch | ✅ | 83.7 | 0.6591 | 593.00 | -| YOLOv8l | TorchScript | ✅ | 167.2 | 0.6580 | 697.54 | -| YOLOv8l | ONNX | ✅ | 166.8 | 0.6580 | 342.15 | -| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.0708 | 117.69 | -| YOLOv8x | PyTorch | ✅ | 130.5 | 0.6651 | 804.65 | -| YOLOv8x | TorchScript | ✅ | 260.8 | 0.6650 | 921.46 | -| YOLOv8x | ONNX | ✅ | 260.4 | 0.6650 | 526.66 | -| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.6619 | 158.73 | - -## Reproduce Our Results - -To reproduce the Ultralytics benchmarks above on all export [formats](../modes/export.md) run this code: - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a YOLOv8n PyTorch model - model = YOLO('yolov8n.pt') - - # Benchmark YOLOv8n speed and accuracy on the COCO128 dataset for all all export formats - results= model.benchmarks(data='coco128.yaml') - ``` - === "CLI" - - ```bash - # Benchmark YOLOv8n speed and accuracy on the COCO128 dataset for all all export formats - yolo benchmark model=yolov8n.pt data=coco128.yaml - ``` - - Note that benchmarking results might vary based on the exact hardware and software configuration of a system, as well as the current workload of the system at the time the benchmarks are run. For the most reliable results use a dataset with a large number of images, i.e. `data='coco128.yaml' (128 val images), or `data='coco.yaml'` (5000 val images). - -## Conclusion - -The benchmarking results clearly demonstrate the benefits of exporting the YOLOv8 model to the OpenVINO format. Across different models and hardware platforms, the OpenVINO format consistently outperforms other formats in terms of inference speed while maintaining comparable accuracy. - -For the Intel® Data Center GPU Flex Series, the OpenVINO format was able to deliver inference speeds almost 10 times faster than the original PyTorch format. On the Xeon CPU, the OpenVINO format was twice as fast as the PyTorch format. The accuracy of the models remained nearly identical across the different formats. - -The benchmarks underline the effectiveness of OpenVINO as a tool for deploying deep learning models. By converting models to the OpenVINO format, developers can achieve significant performance improvements, making it easier to deploy these models in real-world applications. - -For more detailed information and instructions on using OpenVINO, refer to the [official OpenVINO documentation](https://docs.openvino.ai/). diff --git a/ultralytics-main/docs/en/integrations/paddlepaddle.md b/ultralytics-main/docs/en/integrations/paddlepaddle.md deleted file mode 100644 index f41116f..0000000 --- a/ultralytics-main/docs/en/integrations/paddlepaddle.md +++ /dev/null @@ -1,122 +0,0 @@ ---- -comments: true -description: This guide explains how to export Ultralytics YOLOv8 models to the PaddlePaddle format for wide device support and harnessing the power of Baidu's ML framework. -keywords: Ultralytics, YOLOv8, PaddlePaddle Export, Model Deployment, Flexible Deployment, Industrial-Grade Deep Learning, Baidu, Cross-Platform Compatibility ---- - -# How to Export to PaddlePaddle Format from YOLOv8 Models - -Bridging the gap between developing and deploying computer vision models in real-world scenarios with varying conditions can be difficult. PaddlePaddle makes this process easier with its focus on flexibility, performance, and its capability for parallel processing in distributed environments. This means you can use your YOLOv8 computer vision models on a wide variety of devices and platforms, from smartphones to cloud-based servers. - -The ability to export to PaddlePaddle model format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for use within the PaddlePaddle framework. PaddlePaddle is known for facilitating industrial deployments and is a good choice for deploying computer vision applications in real-world settings across various domains. - -## Why should you export to PaddlePaddle? - -

- PaddlePaddle Logo -

- -Developed by Baidu, [PaddlePaddle](https://www.paddlepaddle.org.cn/en) (**PA**rallel **D**istributed **D**eep **LE**arning) is China's first open-source deep learning platform. Unlike some frameworks built mainly for research, PaddlePaddle prioritizes ease of use and smooth integration across industries. - -It offers tools and resources similar to popular frameworks like TensorFlow and PyTorch, making it accessible for developers of all experience levels. From farming and factories to service businesses, PaddlePaddle's large developer community of over 4.77 million is helping create and deploy AI applications. - -By exporting your Ultralytics YOLOv8 models to PaddlePaddle format, you can tap into PaddlePaddle’s strengths in performance optimization. PaddlePaddle prioritizes efficient model execution and reduced memory usage. As a result, your YOLOv8 models can potentially achieve even better performance, delivering top-notch results in practical scenarios. - -## Key Features of PaddlePaddle Models - -PaddlePaddle models offer a range of key features that contribute to their flexibility, performance, and scalability across diverse deployment scenarios: - - - **Dynamic-to-Static Graph**: PaddlePaddle supports [dynamic-to-static compilation](https://www.paddlepaddle.org.cn/documentation/docs/en/guides/jit/index_en.html), where models can be translated into a static computational graph. This enables optimizations that reduce runtime overhead and boost inference performance. - - - **Operator Fusion**: PaddlePaddle, like TensorRT, uses [operator fusion](https://developer.nvidia.com/gtc/2020/video/s21436-vid) to streamline computation and reduce overhead. The framework minimizes memory transfers and computational steps by merging compatible operations, resulting in faster inference. - - - **Quantization**: PaddlePaddle supports [quantization techniques](https://www.paddlepaddle.org.cn/documentation/docs/en/api/paddle/quantization/PTQ_en.html), including post-training quantization and quantization-aware training. These techniques allow for the use of lower-precision data representations, effectively boosting performance and reducing model size. - -## Deployment Options in PaddlePaddle - -Before diving into the code for exporting YOLOv8 models to PaddlePaddle, let's take a look at the different deployment scenarios in which PaddlePaddle models excel. - -PaddlePaddle provides a range of options, each offering a distinct balance of ease of use, flexibility, and performance: - -- **Paddle Serving**: This framework simplifies the deployment of PaddlePaddle models as high-performance RESTful APIs. Paddle Serving is ideal for production environments, providing features like model versioning, online A/B testing, and scalability for handling large volumes of requests. - -- **Paddle Inference API**: The Paddle Inference API gives you low-level control over model execution. This option is well-suited for scenarios where you need to integrate the model tightly within a custom application or optimize performance for specific hardware. - -- **Paddle Lite**: Paddle Lite is designed for deployment on mobile and embedded devices where resources are limited. It optimizes models for smaller sizes and faster inference on ARM CPUs, GPUs, and other specialized hardware. - -- **Paddle.js**: Paddle.js enables you to deploy PaddlePaddle models directly within web browsers. Paddle.js can either load a pre-trained model or transform a model from [paddle-hub](https://github.com/PaddlePaddle/PaddleHub) with model transforming tools provided by Paddle.js. It can run in browsers that support WebGL/WebGPU/WebAssembly. - -## Export to PaddlePaddle: Converting Your YOLOv8 Model - -Converting YOLOv8 models to the PaddlePaddle format can improve execution flexibility and optimize performance for various deployment scenarios. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [Ultralytics Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, it's important to note that while all [Ultralytics YOLOv8 models](../models/index.md) are available for exporting, you can ensure that the model you select supports export functionality [here](../modes/export.md). - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to PaddlePaddle format - model.export(format='paddle') # creates '/yolov8n_paddle_model' - - # Load the exported PaddlePaddle model - paddle_model = YOLO('./yolov8n_paddle_model') - - # Run inference - results = paddle_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to PaddlePaddle format - yolo export model=yolov8n.pt format=paddle # creates '/yolov8n_paddle_model' - - # Run inference with the exported model - yolo predict model='./yolov8n_paddle_model' source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about supported export options, visit the [Ultralytics documentation page on deployment options](../guides/model-deployment-options.md). - -## Deploying Exported YOLOv8 PaddlePaddle Models - -After successfully exporting your Ultralytics YOLOv8 models to PaddlePaddle format, you can now deploy them. The primary and recommended first step for running a PaddlePaddle model is to use the YOLO("./model_paddle_model") method, as outlined in the previous usage code snippet. - -However, for in-depth instructions on deploying your PaddlePaddle models in various other settings, take a look at the following resources: - -- **[Paddle Serving](https://github.com/PaddlePaddle/Serving/blob/v0.9.0/README_CN.md)**: Learn how to deploy your PaddlePaddle models as performant services using Paddle Serving. - -- **[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite/blob/develop/README_en.md)**: Explore how to optimize and deploy models on mobile and embedded devices using Paddle Lite. - -- **[Paddle.js](https://github.com/PaddlePaddle/Paddle.js)**: Discover how to run PaddlePaddle models in web browsers for client-side AI using Paddle.js. - -## Summary - -In this guide, we explored the process of exporting Ultralytics YOLOv8 models to the PaddlePaddle format. By following these steps, you can leverage PaddlePaddle's strengths in diverse deployment scenarios, optimizing your models for different hardware and software environments. - -For further details on usage, visit the [PaddlePaddle official documentation](https://www.paddlepaddle.org.cn/documentation/docs/en/guides/index_en.html) - -Want to explore more ways to integrate your Ultralytics YOLOv8 models? Our [integration guide page](index.md) explores various options, equipping you with valuable resources and insights. diff --git a/ultralytics-main/docs/en/integrations/ray-tune.md b/ultralytics-main/docs/en/integrations/ray-tune.md deleted file mode 100644 index 3825cf7..0000000 --- a/ultralytics-main/docs/en/integrations/ray-tune.md +++ /dev/null @@ -1,179 +0,0 @@ ---- -comments: true -description: Discover how to streamline hyperparameter tuning for YOLOv8 models with Ray Tune. Learn to accelerate tuning, integrate with Weights & Biases, and analyze results. -keywords: Ultralytics, YOLOv8, Ray Tune, hyperparameter tuning, machine learning optimization, Weights & Biases integration, result analysis ---- - -# Efficient Hyperparameter Tuning with Ray Tune and YOLOv8 - -Hyperparameter tuning is vital in achieving peak model performance by discovering the optimal set of hyperparameters. This involves running trials with different hyperparameters and evaluating each trial’s performance. - -## Accelerate Tuning with Ultralytics YOLOv8 and Ray Tune - -[Ultralytics YOLOv8](https://ultralytics.com) incorporates Ray Tune for hyperparameter tuning, streamlining the optimization of YOLOv8 model hyperparameters. With Ray Tune, you can utilize advanced search strategies, parallelism, and early stopping to expedite the tuning process. - -### Ray Tune - -

- Ray Tune Overview -

- -[Ray Tune](https://docs.ray.io/en/latest/tune/index.html) is a hyperparameter tuning library designed for efficiency and flexibility. It supports various search strategies, parallelism, and early stopping strategies, and seamlessly integrates with popular machine learning frameworks, including Ultralytics YOLOv8. - -### Integration with Weights & Biases - -YOLOv8 also allows optional integration with [Weights & Biases](https://wandb.ai/site) for monitoring the tuning process. - -## Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install and update Ultralytics and Ray Tune packages - pip install -U ultralytics "ray[tune]" - - # Optionally install W&B for logging - pip install wandb - ``` - -## Usage - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a YOLOv8n model - model = YOLO('yolov8n.pt') - - # Start tuning hyperparameters for YOLOv8n training on the COCO8 dataset - result_grid = model.tune(data='coco8.yaml', use_ray=True) - ``` - -## `tune()` Method Parameters - -The `tune()` method in YOLOv8 provides an easy-to-use interface for hyperparameter tuning with Ray Tune. It accepts several arguments that allow you to customize the tuning process. Below is a detailed explanation of each parameter: - -| Parameter | Type | Description | Default Value | -|-----------------|------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------| -| `data` | `str` | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | | -| `space` | `dict, optional` | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | | -| `grace_period` | `int, optional` | The grace period in epochs for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 | -| `gpu_per_trial` | `int, optional` | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None | -| `iterations` | `int, optional` | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 | -| `**train_args` | `dict, optional` | Additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} | - -By customizing these parameters, you can fine-tune the hyperparameter optimization process to suit your specific needs and available computational resources. - -## Default Search Space Description - -The following table lists the default search space parameters for hyperparameter tuning in YOLOv8 with Ray Tune. Each parameter has a specific value range defined by `tune.uniform()`. - -| Parameter | Value Range | Description | -|-------------------|----------------------------|------------------------------------------| -| `lr0` | `tune.uniform(1e-5, 1e-1)` | Initial learning rate | -| `lrf` | `tune.uniform(0.01, 1.0)` | Final learning rate factor | -| `momentum` | `tune.uniform(0.6, 0.98)` | Momentum | -| `weight_decay` | `tune.uniform(0.0, 0.001)` | Weight decay | -| `warmup_epochs` | `tune.uniform(0.0, 5.0)` | Warmup epochs | -| `warmup_momentum` | `tune.uniform(0.0, 0.95)` | Warmup momentum | -| `box` | `tune.uniform(0.02, 0.2)` | Box loss weight | -| `cls` | `tune.uniform(0.2, 4.0)` | Class loss weight | -| `hsv_h` | `tune.uniform(0.0, 0.1)` | Hue augmentation range | -| `hsv_s` | `tune.uniform(0.0, 0.9)` | Saturation augmentation range | -| `hsv_v` | `tune.uniform(0.0, 0.9)` | Value (brightness) augmentation range | -| `degrees` | `tune.uniform(0.0, 45.0)` | Rotation augmentation range (degrees) | -| `translate` | `tune.uniform(0.0, 0.9)` | Translation augmentation range | -| `scale` | `tune.uniform(0.0, 0.9)` | Scaling augmentation range | -| `shear` | `tune.uniform(0.0, 10.0)` | Shear augmentation range (degrees) | -| `perspective` | `tune.uniform(0.0, 0.001)` | Perspective augmentation range | -| `flipud` | `tune.uniform(0.0, 1.0)` | Vertical flip augmentation probability | -| `fliplr` | `tune.uniform(0.0, 1.0)` | Horizontal flip augmentation probability | -| `mosaic` | `tune.uniform(0.0, 1.0)` | Mosaic augmentation probability | -| `mixup` | `tune.uniform(0.0, 1.0)` | Mixup augmentation probability | -| `copy_paste` | `tune.uniform(0.0, 1.0)` | Copy-paste augmentation probability | - -## Custom Search Space Example - -In this example, we demonstrate how to use a custom search space for hyperparameter tuning with Ray Tune and YOLOv8. By providing a custom search space, you can focus the tuning process on specific hyperparameters of interest. - -!!! Example "Usage" - - ```python - from ultralytics import YOLO - - # Define a YOLO model - model = YOLO("yolov8n.pt") - - # Run Ray Tune on the model - result_grid = model.tune(data="coco128.yaml", - space={"lr0": tune.uniform(1e-5, 1e-1)}, - epochs=50, - use_ray=True) - ``` - -In the code snippet above, we create a YOLO model with the "yolov8n.pt" pretrained weights. Then, we call the `tune()` method, specifying the dataset configuration with "coco128.yaml". We provide a custom search space for the initial learning rate `lr0` using a dictionary with the key "lr0" and the value `tune.uniform(1e-5, 1e-1)`. Finally, we pass additional training arguments, such as the number of epochs directly to the tune method as `epochs=50`. - -## Processing Ray Tune Results - -After running a hyperparameter tuning experiment with Ray Tune, you might want to perform various analyses on the obtained results. This guide will take you through common workflows for processing and analyzing these results. - -### Loading Tune Experiment Results from a Directory - -After running the tuning experiment with `tuner.fit()`, you can load the results from a directory. This is useful, especially if you're performing the analysis after the initial training script has exited. - -```python -experiment_path = f"{storage_path}/{exp_name}" -print(f"Loading results from {experiment_path}...") - -restored_tuner = tune.Tuner.restore(experiment_path, trainable=train_mnist) -result_grid = restored_tuner.get_results() -``` - -### Basic Experiment-Level Analysis - -Get an overview of how trials performed. You can quickly check if there were any errors during the trials. - -```python -if result_grid.errors: - print("One or more trials failed!") -else: - print("No errors!") -``` - -### Basic Trial-Level Analysis - -Access individual trial hyperparameter configurations and the last reported metrics. - -```python -for i, result in enumerate(result_grid): - print(f"Trial #{i}: Configuration: {result.config}, Last Reported Metrics: {result.metrics}") -``` - -### Plotting the Entire History of Reported Metrics for a Trial - -You can plot the history of reported metrics for each trial to see how the metrics evolved over time. - -```python -import matplotlib.pyplot as plt - -for result in result_grid: - plt.plot(result.metrics_dataframe["training_iteration"], result.metrics_dataframe["mean_accuracy"], label=f"Trial {i}") - -plt.xlabel('Training Iterations') -plt.ylabel('Mean Accuracy') -plt.legend() -plt.show() -``` - -## Summary - -In this documentation, we covered common workflows to analyze the results of experiments run with Ray Tune using Ultralytics. The key steps include loading the experiment results from a directory, performing basic experiment-level and trial-level analysis and plotting metrics. - -Explore further by looking into Ray Tune’s [Analyze Results](https://docs.ray.io/en/latest/tune/examples/tune_analyze_results.html) docs page to get the most out of your hyperparameter tuning experiments. diff --git a/ultralytics-main/docs/en/integrations/roboflow.md b/ultralytics-main/docs/en/integrations/roboflow.md deleted file mode 100644 index 9d19c8f..0000000 --- a/ultralytics-main/docs/en/integrations/roboflow.md +++ /dev/null @@ -1,243 +0,0 @@ ---- -comments: true -description: Learn how to use Roboflow with Ultralytics for labeling and managing images for use in training, and for evaluating model performance. -keywords: Ultralytics, YOLOv8, Roboflow, vector analysis, confusion matrix, data management, image labeling ---- - -# Roboflow - -[Roboflow](https://roboflow.com/?ref=ultralytics) has everything you need to build and deploy computer vision models. Connect Roboflow at any step in your pipeline with APIs and SDKs, or use the end-to-end interface to automate the entire process from image to inference. Whether you’re in need of [data labeling](https://roboflow.com/annotate?ref=ultralytics), [model training](https://roboflow.com/train?ref=ultralytics), or [model deployment](https://roboflow.com/deploy?ref=ultralytics), Roboflow gives you building blocks to bring custom computer vision solutions to your project. - -!!! Question "Licensing" - - Ultralytics offers two licensing options: - - - The [AGPL-3.0 License](https://github.com/ultralytics/ultralytics/blob/main/LICENSE), an [OSI-approved](https://opensource.org/licenses/) open-source license ideal for students and enthusiasts. - - The [Enterprise License](https://ultralytics.com/license) for businesses seeking to incorporate our AI models into their products and services. - - For more details see [Ultralytics Licensing](https://ultralytics.com/license). - -In this guide, we are going to showcase how to find, label, and organize data for use in training a custom Ultralytics YOLOv8 model. Use the table of contents below to jump directly to a specific section: - -- Gather data for training a custom YOLOv8 model -- Upload, convert and label data for YOLOv8 format -- Pre-process and augment data for model robustness -- Dataset management for [YOLOv8](https://docs.ultralytics.com/models/yolov8/) -- Export data in 40+ formats for model training -- Upload custom YOLOv8 model weights for testing and deployment -- Gather Data for Training a Custom YOLOv8 Model - -Roboflow provides two services that can help you collect data for YOLOv8 models: [Universe](https://universe.roboflow.com/?ref=ultralytics) and [Collect](https://roboflow.com/collect?ref=ultralytics). - -Universe is an online repository with over 250,000 vision datasets totalling over 100 million images. - -

-Roboflow Universe -

- -With a [free Roboflow account](https://app.roboflow.com/?ref=ultralytics), you can export any dataset available on Universe. To export a dataset, click the "Download this Dataset" button on any dataset. - -

-Roboflow Universe dataset export -

- -For YOLOv8, select "YOLOv8" as the export format: - -

-Roboflow Universe dataset export -

- -Universe also has a page that aggregates all [public fine-tuned YOLOv8 models uploaded to Roboflow](https://universe.roboflow.com/search?q=model:yolov8). You can use this page to explore pre-trained models you can use for testing or [for automated data labeling](https://docs.roboflow.com/annotate/use-roboflow-annotate/model-assisted-labeling) or to prototype with [Roboflow inference](https://roboflow.com/inference?ref=ultralytics). - -If you want to gather images yourself, try [Collect](https://github.com/roboflow/roboflow-collect), an open source project that allows you to automatically gather images using a webcam on the edge. You can use text or image prompts with Collect to instruct what data should be collected, allowing you to capture only the useful data you need to build your vision model. - -## Upload, Convert and Label Data for YOLOv8 Format - -[Roboflow Annotate](https://docs.roboflow.com/annotate/use-roboflow-annotate) is an online annotation tool for use in labeling images for object detection, classification, and segmentation. - -To label data for a YOLOv8 object detection, instance segmentation, or classification model, first create a project in Roboflow. - -

-Create a Roboflow project -

- -Next, upload your images, and any pre-existing annotations you have from other tools ([using one of the 40+ supported import formats](https://roboflow.com/formats?ref=ultralytics)), into Roboflow. - -

-Upload images to Roboflow -

- -Select the batch of images you have uploaded on the Annotate page to which you are taken after uploading images. Then, click "Start Annotating" to label images. - -To label with bounding boxes, press the `B` key on your keyboard or click the box icon in the sidebar. Click on a point where you want to start your bounding box, then drag to create the box: - -

-Annotating an image in Roboflow -

- -A pop-up will appear asking you to select a class for your annotation once you have created an annotation. - -To label with polygons, press the `P` key on your keyboard, or the polygon icon in the sidebar. With the polygon annotation tool enabled, click on individual points in the image to draw a polygon. - -Roboflow offers a SAM-based label assistant with which you can label images faster than ever. SAM (Segment Anything Model) is a state-of-the-art computer vision model that can precisely label images. With SAM, you can significantly speed up the image labeling process. Annotating images with polygons becomes as simple as a few clicks, rather than the tedious process of precisely clicking points around an object. - -To use the label assistant, click the cursor icon in the sidebar, SAM will be loaded for use in your project. - -

-Annotating an image in Roboflow with SAM-powered label assist -

- -Hover over any object in the image and SAM will recommend an annotation. You can hover to find the right place to annotate, then click to create your annotation. To amend your annotation to be more or less specific, you can click inside or outside the annotation SAM has created on the document. - -You can also add tags to images from the Tags panel in the sidebar. You can apply tags to data from a particular area, taken from a specific camera, and more. You can then use these tags to search through data for images matching a tag and generate versions of a dataset with images that contain a particular tag or set of tags. - -

-Adding tags to an image in Roboflow -

- -Models hosted on Roboflow can be used with Label Assist, an automated annotation tool that uses your YOLOv8 model to recommend annotations. To use Label Assist, first upload a YOLOv8 model to Roboflow (see instructions later in the guide). Then, click the magic wand icon in the left sidebar and select your model for use in Label Assist. - -Choose a model, then click "Continue" to enable Label Assist: - -

-Enabling Label Assist -

- -When you open new images for annotation, Label Assist will trigger and recommend annotations. - -

-ALabel Assist recommending an annotation -

- -## Dataset Management for YOLOv8 - -Roboflow provides a suite of tools for understanding computer vision datasets. - -First, you can use dataset search to find images that meet a semantic text description (i.e. find all images that contain people), or that meet a specified label (i.e. the image is associated with a specific tag). To use dataset search, click "Dataset" in the sidebar. Then, input a search query using the search bar and associated filters at the top of the page. - -For example, the following text query finds images that contain people in a dataset: - -

-Searching for an image -

- -You can narrow your search to images with a particular tag using the "Tags" selector: - -

-Filter images by tag -

- -Before you start training a model with your dataset, we recommend using Roboflow [Health Check](https://docs.roboflow.com/datasets/dataset-health-check), a web tool that provides an insight into your dataset and how you can improve the dataset prior to training a vision model. - -To use Health Check, click the "Health Check" sidebar link. A list of statistics will appear that show the average size of images in your dataset, class balance, a heatmap of where annotations are in your images, and more. - -

-Roboflow Health Check analysis -

- -Health Check may recommend changes to help enhance dataset performance. For example, the class balance feature may show that there is an imbalance in labels that, if solved, may boost performance or your model. - -## Export Data in 40+ Formats for Model Training - -To export your data, you will need a dataset version. A version is a state of your dataset frozen-in-time. To create a version, first click "Versions" in the sidebar. Then, click the "Create New Version" button. On this page, you will be able to choose augmentations and preprocessing steps to apply to your dataset: - -

-Creating a dataset version on Roboflow -

- -For each augmentation you select, a pop-up will appear allowing you to tune the augmentation to your needs. Here is an example of tuning a brightness augmentation within specified parameters: - -

-Applying augmentations to a dataset -

- -When your dataset version has been generated, you can export your data into a range of formats. Click the "Export Dataset" button on your dataset version page to export your data: - -

-Exporting a dataset -

- -You are now ready to train YOLOv8 on a custom dataset. Follow this [written guide](https://blog.roboflow.com/how-to-train-yolov8-on-a-custom-dataset/) and [YouTube video](https://www.youtube.com/watch?v=wuZtUMEiKWY) for step-by-step instructions or refer to the [Ultralytics documentation](https://docs.ultralytics.com/modes/train/). - -## Upload Custom YOLOv8 Model Weights for Testing and Deployment - -Roboflow offers an infinitely scalable API for deployed models and SDKs for use with NVIDIA Jetsons, Luxonis OAKs, Raspberry Pis, GPU-based devices, and more. - -You can deploy YOLOv8 models by uploading YOLOv8 weights to Roboflow. You can do this in a few lines of Python code. Create a new Python file and add the following code: - -```python -import roboflow # install with 'pip install roboflow' - -roboflow.login() - -rf = roboflow.Roboflow() - -project = rf.workspace(WORKSPACE_ID).project("football-players-detection-3zvbc") -dataset = project.version(VERSION).download("yolov8") - -project.version(dataset.version).deploy(model_type="yolov8", model_path=f"{HOME}/runs/detect/train/") -``` - -In this code, replace the project ID and version ID with the values for your account and project. [Learn how to retrieve your Roboflow API key](https://docs.roboflow.com/api-reference/authentication#retrieve-an-api-key). - -When you run the code above, you will be asked to authenticate. Then, your model will be uploaded and an API will be created for your project. This process can take up to 30 minutes to complete. - -To test your model and find deployment instructions for supported SDKs, go to the "Deploy" tab in the Roboflow sidebar. At the top of this page, a widget will appear with which you can test your model. You can use your webcam for live testing or upload images or videos. - -

-Running inference on an example image -

- -You can also use your uploaded model as a [labeling assistant](https://docs.roboflow.com/annotate/use-roboflow-annotate/model-assisted-labeling). This feature uses your trained model to recommend annotations on images uploaded to Roboflow. - -## How to Evaluate YOLOv8 Models - -Roboflow provides a range of features for use in evaluating models. - -Once you have uploaded a model to Roboflow, you can access our model evaluation tool, which provides a confusion matrix showing the performance of your model as well as an interactive vector analysis plot. These features can help you find opportunities to improve your model. - -To access a confusion matrix, go to your model page on the Roboflow dashboard, then click "View Detailed Evaluation": - -

-Start a Roboflow model evaluation -

- -A pop-up will appear showing a confusion matrix: - -

-A confusion matrix -

- -Hover over a box on the confusion matrix to see the value associated with the box. Click on a box to see images in the respective category. Click on an image to view the model predictions and ground truth data associated with that image. - -For more insights, click Vector Analysis. This will show a scatter plot of the images in your dataset, calculated using CLIP. The closer images are in the plot, the more similar they are, semantically. Each image is represented as a dot with a color between white and red. The more red the dot, the worse the model performed. - -

-A vector analysis plot -

- -You can use Vector Analysis to: - -- Find clusters of images; -- Identify clusters where the model performs poorly, and; -- Visualize commonalities between images on which the model performs poorly. - -## Learning Resources - -Want to learn more about using Roboflow for creating YOLOv8 models? The following resources may be helpful in your work. - -- [Train YOLOv8 on a Custom Dataset](https://github.com/roboflow/notebooks/blob/main/notebooks/train-yolov8-object-detection-on-custom-dataset.ipynb): Follow our interactive notebook that shows you how to train a YOLOv8 model on a custom dataset. -- [Autodistill](https://autodistill.github.io/autodistill/): Use large foundation vision models to label data for specific models. You can label images for use in training YOLOv8 classification, detection, and segmentation models with Autodistill. -- [Supervision](https://roboflow.github.io/supervision/): A Python package with helpful utilities for use in working with computer vision models. You can use supervision to filter detections, compute confusion matrices, and more, all in a few lines of Python code. -- [Roboflow Blog](https://blog.roboflow.com/): The Roboflow Blog features over 500 articles on computer vision, covering topics from how to train a YOLOv8 model to annotation best practices. -- [Roboflow YouTube channel](https://www.youtube.com/@Roboflow): Browse dozens of in-depth computer vision guides on our YouTube channel, covering topics from training YOLOv8 models to automated image labeling. - -## Project Showcase - -Below are a few of the many pieces of feedback we have received for using YOLOv8 and Roboflow together to create computer vision models. - -

-Showcase image -Showcase image -Showcase image -

diff --git a/ultralytics-main/docs/en/integrations/tensorboard.md b/ultralytics-main/docs/en/integrations/tensorboard.md deleted file mode 100644 index 5e0cbf1..0000000 --- a/ultralytics-main/docs/en/integrations/tensorboard.md +++ /dev/null @@ -1,153 +0,0 @@ ---- -comments: true -description: Walk through the integration of YOLOv8 with TensorBoard to be able to use TensorFlow's visualization toolkit for enhanced model training analysis, offering capabilities like metric tracking, model graph visualization, and more. -keywords: TensorBoard, YOLOv8, Visualization, TensorFlow, Training Analysis, Metric Tracking, Model Graphs, Experimentation, Ultralytics ---- - -# Gain Visual Insights with YOLOv8’s Integration with TensorBoard - -Understanding and fine-tuning computer vision models like [Ultralytics’ YOLOv8](https://ultralytics.com) becomes more straightforward when you take a closer look at their training processes. Model training visualization helps with getting insights into the model's learning patterns, performance metrics, and overall behavior. YOLOv8's integration with TensorBoard makes this process of visualization and analysis easier and enables more efficient and informed adjustments to the model. - -This guide covers how to use TensorBoard with YOLOv8. You'll learn about various visualizations, from tracking metrics to analyzing model graphs. These tools will help you understand your YOLOv8 model's performance better. - -## TensorBoard - -

- Tensorboard Overview -

- -[TensorBoard](https://www.tensorflow.org/tensorboard), TensorFlow's visualization toolkit, is essential for machine learning experimentation. TensorBoard features a range of visualization tools, crucial for monitoring machine learning models. These tools include tracking key metrics like loss and accuracy, visualizing model graphs, and viewing histograms of weights and biases over time. It also provides capabilities for projecting embeddings to lower-dimensional spaces and displaying multimedia data. - -## YOLOv8 Training with TensorBoard - -Using TensorBoard while training YOLOv8 models is straightforward and offers significant benefits. - -## Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 and Tensorboard - pip install ultralytics - ``` - -TensorBoard is conveniently pre-installed with YOLOv8, eliminating the need for additional setup for visualization purposes. - -For detailed instructions and best practices related to the installation process, be sure to check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -## Configuring TensorBoard for Google Collab - -When using Google Colab, it's important to set up TensorBoard before starting your training code: - -!!! Example "Configure TensorBoard for Google Collab" - - === "Python" - - ```python - %load_ext tensorboard - %tensorboard --logdir path/to/runs - ``` - -## Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a pre-trained model - model = YOLO('yolov8n.pt') - - # Train the model - results = model.train(data='coco128.yaml', epochs=100, imgsz=640) - ``` - -Upon running the usage code snippet above, you can expect the following output: - -```plaintext -TensorBoard: Start with 'tensorboard --logdir path_to_your_tensorboard_logs', view at http://localhost:6006/ -``` - -This output indicates that TensorBoard is now actively monitoring your YOLOv8 training session. You can access the TensorBoard dashboard by visiting the provided URL (http://localhost:6006/) to view real-time training metrics and model performance. For users working in Google Colab, the TensorBoard will be displayed in the same cell where you executed the TensorBoard configuration commands. - -For more information related to the model training process, be sure to check our [YOLOv8 Model Training guide](../modes/train.md). If you are interested in learning more about logging, checkpoints, plotting, and file management, read our [usage guide on configuration](../usage/cfg.md). - -## Understanding Your TensorBoard for YOLOv8 Training - -Now, let’s focus on understanding the various features and components of TensorBoard in the context of YOLOv8 training. The three key sections of the TensorBoard are Time Series, Scalars, and Graphs. - -### Time Series - -The Time Series feature in the TensorBoard offers a dynamic and detailed perspective of various training metrics over time for YOLOv8 models. It focuses on the progression and trends of metrics across training epochs. Here's an example of what you can expect to see. - -![image](https://github.com/ultralytics/ultralytics/assets/25847604/20b3e038-0356-465e-a37e-1ea232c68354) - -#### Key Features of Time Series in TensorBoard - -- **Filter Tags and Pinned Cards**: This functionality allows users to filter specific metrics and pin cards for quick comparison and access. It's particularly useful for focusing on specific aspects of the training process. - -- **Detailed Metric Cards**: Time Series divides metrics into different categories like learning rate (lr), training (train), and validation (val) metrics, each represented by individual cards. - -- **Graphical Display**: Each card in the Time Series section shows a detailed graph of a specific metric over the course of training. This visual representation aids in identifying trends, patterns, or anomalies in the training process. - -- **In-Depth Analysis**: Time Series provides an in-depth analysis of each metric. For instance, different learning rate segments are shown, offering insights into how adjustments in learning rate impact the model's learning curve. - -#### Importance of Time Series in YOLOv8 Training - -The Time Series section is essential for a thorough analysis of the YOLOv8 model's training progress. It lets you track the metrics in real time to promptly identify and solve issues. It also offers a detailed view of each metric's progression, which is crucial for fine-tuning the model and enhancing its performance. - -### Scalars - -Scalars in the TensorBoard are crucial for plotting and analyzing simple metrics like loss and accuracy during the training of YOLOv8 models. They offer a clear and concise view of how these metrics evolve with each training epoch, providing insights into the model's learning effectiveness and stability. Here's an example of what you can expect to see. - -![image](https://github.com/ultralytics/ultralytics/assets/25847604/f9228193-13e9-4768-9edf-8fa15ecd24fa) - -#### Key Features of Scalars in TensorBoard - -- **Learning Rate (lr) Tags**: These tags show the variations in the learning rate across different segments (e.g., `pg0`, `pg1`, `pg2`). This helps us understand the impact of learning rate adjustments on the training process. - -- **Metrics Tags**: Scalars include performance indicators such as: - - - `mAP50 (B)`: Mean Average Precision at 50% Intersection over Union (IoU), crucial for assessing object detection accuracy. - - - `mAP50-95 (B)`: Mean Average Precision calculated over a range of IoU thresholds, offering a more comprehensive evaluation of accuracy. - - - `Precision (B)`: Indicates the ratio of correctly predicted positive observations, key to understanding prediction accuracy. - - - `Recall (B)`: Important for models where missing a detection is significant, this metric measures the ability to detect all relevant instances. - - - To learn more about the different metrics, read our guide on [performance metrics](../guides/yolo-performance-metrics.md). - -- **Training and Validation Tags (`train`, `val`)**: These tags display metrics specifically for the training and validation datasets, allowing for a comparative analysis of model performance across different data sets. - -#### Importance of Monitoring Scalars - -Observing scalar metrics is crucial for fine-tuning the YOLOv8 model. Variations in these metrics, such as spikes or irregular patterns in loss graphs, can highlight potential issues such as overfitting, underfitting, or inappropriate learning rate settings. By closely monitoring these scalars, you can make informed decisions to optimize the training process, ensuring that the model learns effectively and achieves the desired performance. - -### Difference Between Scalars and Time Series - -While both Scalars and Time Series in TensorBoard are used for tracking metrics, they serve slightly different purposes. Scalars focus on plotting simple metrics such as loss and accuracy as scalar values. They provide a high-level overview of how these metrics change with each training epoch. While, the time-series section of the TensorBoard offers a more detailed timeline view of various metrics. It is particularly useful for monitoring the progression and trends of metrics over time, providing a deeper dive into the specifics of the training process. - -### Graphs - -The Graphs section of the TensorBoard visualizes the computational graph of the YOLOv8 model, showing how operations and data flow within the model. It's a powerful tool for understanding the model's structure, ensuring that all layers are connected correctly, and for identifying any potential bottlenecks in data flow. Here's an example of what you can expect to see. - -![image](https://github.com/ultralytics/ultralytics/assets/25847604/039028e0-4ab3-4170-bfa8-f93ce483f615) - -Graphs are particularly useful for debugging the model, especially in complex architectures typical in deep learning models like YOLOv8. They help in verifying layer connections and the overall design of the model. - -## Summary - -This guide aims to help you use TensorBoard with YOLOv8 for visualization and analysis of machine learning model training. It focuses on explaining how key TensorBoard features can provide insights into training metrics and model performance during YOLOv8 training sessions. - -For a more detailed exploration of these features and effective utilization strategies, you can refer to TensorFlow’s official [TensorBoard documentation](https://www.tensorflow.org/tensorboard/get_started) and their [GitHub repository](https://github.com/tensorflow/tensorboard). - -Want to learn more about the various integrations of Ultralytics? Check out the [Ultralytics integrations guide page](../integrations/index.md) to see what other exciting capabilities are waiting to be discovered! diff --git a/ultralytics-main/docs/en/integrations/tensorrt.md b/ultralytics-main/docs/en/integrations/tensorrt.md deleted file mode 100644 index aa89675..0000000 --- a/ultralytics-main/docs/en/integrations/tensorrt.md +++ /dev/null @@ -1,128 +0,0 @@ ---- -comments: true -description: Discover the power and flexibility of exporting Ultralytics YOLOv8 models to TensorRT format for enhanced performance and efficiency on NVIDIA GPUs. -keywords: Ultralytics, YOLOv8, TensorRT Export, Model Deployment, GPU Acceleration, NVIDIA Support, CUDA Deployment ---- - -# TensorRT Export for YOLOv8 Models - -Deploying computer vision models in high-performance environments can require a format that maximizes speed and efficiency. This is especially true when you are deploying your model on NVIDIA GPUs. - -By using the TensorRT export format, you can enhance your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for swift and efficient inference on NVIDIA hardware. This guide will give you easy-to-follow steps for the conversion process and help you make the most of NVIDIA's advanced technology in your deep learning projects. - -## TensorRT - -

- TensorRT Overview -

- -[TensorRT](https://developer.nvidia.com/tensorrt), developed by NVIDIA, is an advanced software development kit (SDK) designed for high-speed deep learning inference. It’s well-suited for real-time applications like object detection. - -This toolkit optimizes deep learning models for NVIDIA GPUs and results in faster and more efficient operations. TensorRT models undergo TensorRT optimization, which includes techniques like layer fusion, precision calibration (INT8 and FP16), dynamic tensor memory management, and kernel auto-tuning. Converting deep learning models into the TensorRT format allows developers to realize the potential of NVIDIA GPUs fully. - -TensorRT is known for its compatibility with various model formats, including TensorFlow, PyTorch, and ONNX, providing developers with a flexible solution for integrating and optimizing models from different frameworks. This versatility enables efficient model deployment across diverse hardware and software environments. - -## Key Features of TensorRT Models - -TensorRT models offer a range of key features that contribute to their efficiency and effectiveness in high-speed deep learning inference: - -- **Precision Calibration**: TensorRT supports precision calibration, allowing models to be fine-tuned for specific accuracy requirements. This includes support for reduced precision formats like INT8 and FP16, which can further boost inference speed while maintaining acceptable accuracy levels. - -- **Layer Fusion**: The TensorRT optimization process includes layer fusion, where multiple layers of a neural network are combined into a single operation. This reduces computational overhead and improves inference speed by minimizing memory access and computation. - -

- TensorRT Layer Fusion -

- -- **Dynamic Tensor Memory Management**: TensorRT efficiently manages tensor memory usage during inference, reducing memory overhead and optimizing memory allocation. This results in more efficient GPU memory utilization. - -- **Automatic Kernel Tuning**: TensorRT applies automatic kernel tuning to select the most optimized GPU kernel for each layer of the model. This adaptive approach ensures that the model takes full advantage of the GPU's computational power. - -## Deployment Options in TensorRT - -Before we look at the code for exporting YOLOv8 models to the TensorRT format, let’s understand where TensorRT models are normally used. - -TensorRT offers several deployment options, and each option balances ease of integration, performance optimization, and flexibility differently: - -- **Deploying within TensorFlow**: This method integrates TensorRT into TensorFlow, allowing optimized models to run in a familiar TensorFlow environment. It's useful for models with a mix of supported and unsupported layers, as TF-TRT can handle these efficiently. - -

- TensorRT Overview -

- -- **Standalone TensorRT Runtime API**: Offers granular control, ideal for performance-critical applications. It's more complex but allows for custom implementation of unsupported operators. - -- **NVIDIA Triton Inference Server**: An option that supports models from various frameworks. Particularly suited for cloud or edge inference, it provides features like concurrent model execution and model analysis. - -## Exporting YOLOv8 Models to TensorRT - -You can improve execution efficiency and optimize performance by converting YOLOv8 models to TensorRT format. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to TensorRT format - model.export(format='engine') # creates 'yolov8n.engine' - - # Load the exported TensorRT model - tensorrt_model = YOLO('yolov8n.engine') - - # Run inference - results = tensorrt_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to TensorRT format - yolo export model=yolov8n.pt format=engine # creates 'yolov8n.engine'' - - # Run inference with the exported model - yolo predict model=yolov8n.engine source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -## Deploying Exported YOLOv8 TensorRT Models - -Having successfully exported your Ultralytics YOLOv8 models to TensorRT format, you're now ready to deploy them. For in-depth instructions on deploying your TensorRT models in various settings, take a look at the following resources: - -- **[Deploying Deep Neural Networks with NVIDIA TensorRT](https://developer.nvidia.com/blog/deploying-deep-learning-nvidia-tensorrt/)**: This article explains how to use NVIDIA TensorRT to deploy deep neural networks on GPU-based deployment platforms efficiently. - -- **[End-to-End AI for NVIDIA-Based PCs: NVIDIA TensorRT Deployment](https://developer.nvidia.com/blog/end-to-end-ai-for-nvidia-based-pcs-nvidia-tensorrt-deployment/)**: This blog post explains the use of NVIDIA TensorRT for optimizing and deploying AI models on NVIDIA-based PCs. - -- **[GitHub Repository for NVIDIA TensorRT:](https://github.com/NVIDIA/TensorRT)**: This is the official GitHub repository that contains the source code and documentation for NVIDIA TensorRT. - -## Summary - -In this guide, we focused on converting Ultralytics YOLOv8 models to NVIDIA's TensorRT model format. This conversion step is crucial for improving the efficiency and speed of YOLOv8 models, making them more effective and suitable for diverse deployment environments. - -For more information on usage details, take a look at the [TensorRT official documentation](https://docs.nvidia.com/deeplearning/tensorrt/). - -If you're curious about additional Ultralytics YOLOv8 integrations, our [integration guide page](../integrations/index.md) provides an extensive selection of informative resources and insights. diff --git a/ultralytics-main/docs/en/integrations/tflite.md b/ultralytics-main/docs/en/integrations/tflite.md deleted file mode 100644 index 03fe156..0000000 --- a/ultralytics-main/docs/en/integrations/tflite.md +++ /dev/null @@ -1,122 +0,0 @@ ---- -comments: true -description: Explore how to improve your Ultralytics YOLOv8 model's performance and interoperability using the TFLite export format suitable for edge computing environments. -keywords: Ultralytics, YOLOv8, TFLite Export, Export YOLOv8, Model Deployment ---- - -# A Guide on YOLOv8 Model Export to TFLite for Deployment - -

- TFLite Logo -

- -Deploying computer vision models on edge devices or embedded devices requires a format that can ensure seamless performance. - -The TensorFlow Lite or TFLite export format allows you to optimize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for tasks like object detection and image classification in edge device-based applications. In this guide, we'll walk through the steps for converting your models to the TFLite format, making it easier for your models to perform well on various edge devices. - -## Why should you export to TFLite? - -Introduced by Google in May 2017 as part of their TensorFlow framework, [TensorFlow Lite](https://www.tensorflow.org/lite/guide), or TFLite for short, is an open-source deep learning framework designed for on-device inference, also known as edge computing. It gives developers the necessary tools to execute their trained models on mobile, embedded, and IoT devices, as well as traditional computers. - -TensorFlow Lite is compatible with a wide range of platforms, including embedded Linux, Android, iOS, and MCU. Exporting your model to TFLite makes your applications faster, more reliable, and capable of running offline. - -## Key Features of TFLite Models - -TFLite models offer a wide range of key features that enable on-device machine learning by helping developers run their models on mobile, embedded, and edge devices: - -- **On-device Optimization**: TFLite optimizes for on-device ML, reducing latency by processing data locally, enhancing privacy by not transmitting personal data, and minimizing model size to save space. - -- **Multiple Platform Support**: TFLite offers extensive platform compatibility, supporting Android, iOS, embedded Linux, and microcontrollers. - -- **Diverse Language Support**: TFLite is compatible with various programming languages, including Java, Swift, Objective-C, C++, and Python. - -- **High Performance**: Achieves superior performance through hardware acceleration and model optimization. - -## Deployment Options in TFLite - -Before we look at the code for exporting YOLOv8 models to the TFLite format, let’s understand how TFLite models are normally used. - -TFLite offers various on-device deployment options for machine learning models, including: - -- **Deploying with Android and iOS**: Both Android and iOS applications with TFLite can analyze edge-based camera feeds and sensors to detect and identify objects. TFLite also offers native iOS libraries written in [Swift](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/swift) and [Objective-C](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/objc). The architecture diagram below shows the process of deploying a trained model onto Android and iOS platforms using TensorFlow Lite. - -

- Architecture -

- -- **Implementing with Embedded Linux**: If running inferences on a [Raspberry Pi](https://www.raspberrypi.org/) using the [Ultralytics Guide](../guides/raspberry-pi.md) does not meet the speed requirements for your use case, you can use an exported TFLite model to accelerate inference times. Additionally, it's possible to further improve performance by utilizing a [Coral Edge TPU device](https://coral.withgoogle.com/). - -- **Deploying with Microcontrollers**: TFLite models can also be deployed on microcontrollers and other devices with only a few kilobytes of memory. The core runtime just fits in 16 KB on an Arm Cortex M3 and can run many basic models. It doesn't require operating system support, any standard C or C++ libraries, or dynamic memory allocation. - -## Export to TFLite: Converting Your YOLOv8 Model - -You can improve on-device model execution efficiency and optimize performance by converting them to TFLite format. - -### Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [Ultralytics Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, it's important to note that while all [Ultralytics YOLOv8 models](../models/index.md) are available for exporting, you can ensure that the model you select supports export functionality [here](../modes/export.md). - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to TFLite format - model.export(format='tflite') # creates 'yolov8n_float32.tflite' - - # Load the exported TFLite model - tflite_model = YOLO('yolov8n_float32.tflite') - - # Run inference - results = tflite_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to TFLite format - yolo export model=yolov8n.pt format=tflite # creates 'yolov8n_float32.tflite' - - # Run inference with the exported model - yolo predict model='yolov8n_float32.tflite' source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -## Deploying Exported YOLOv8 TFLite Models - -After successfully exporting your Ultralytics YOLOv8 models to TFLite format, you can now deploy them. The primary and recommended first step for running a TFLite model is to utilize the YOLO("model.tflite") method, as outlined in the previous usage code snippet. However, for in-depth instructions on deploying your TFLite models in various other settings, take a look at the following resources: - -- **[Android](https://www.tensorflow.org/lite/android/quickstart)**: A quick start guide for integrating TensorFlow Lite into Android applications, providing easy-to-follow steps for setting up and running machine learning models. - -- **[iOS](https://www.tensorflow.org/lite/guide/ios)**: Check out this detailed guide for developers on integrating and deploying TensorFlow Lite models in iOS applications, offering step-by-step instructions and resources. - -- **[End-To-End Examples](https://www.tensorflow.org/lite/examples)**: This page provides an overview of various TensorFlow Lite examples, showcasing practical applications and tutorials designed to help developers implement TensorFlow Lite in their machine learning projects on mobile and edge devices. - -## Summary - -In this guide, we focused on how to export to TFLite format. By converting your Ultralytics YOLOv8 models to TFLite model format, you can improve the efficiency and speed of YOLOv8 models, making them more effective and suitable for edge computing environments. - -For further details on usage, visit [TFLite’s official documentation](https://www.tensorflow.org/lite/guide). - -Also, if you're curious about other Ultralytics YOLOv8 integrations, make sure to check out our [integration guide page](../integrations/index.md). You'll find tons of helpful info and insights waiting for you there. diff --git a/ultralytics-main/docs/en/integrations/torchscript.md b/ultralytics-main/docs/en/integrations/torchscript.md deleted file mode 100644 index f050986..0000000 --- a/ultralytics-main/docs/en/integrations/torchscript.md +++ /dev/null @@ -1,126 +0,0 @@ ---- -comments: true -description: Learn to export your Ultralytics YOLOv8 models to TorchScript format for deployment through platforms like embedded systems, web browsers, and C++ applications. -keywords: Ultralytics, YOLOv8, Export to Torchscript, Model Optimization, Deployment, PyTorch, C++, Faster Inference ---- - -# YOLOv8 Model Export to TorchScript for Quick Deployment - -Deploying computer vision models across different environments, including embedded systems, web browsers, or platforms with limited Python support, requires a flexible and portable solution. TorchScript focuses on portability and the ability to run models in environments where the entire Python framework is unavailable. This makes it ideal for scenarios where you need to deploy your computer vision capabilities across various devices or platforms. - -Export to Torchscript to serialize your [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) models for cross-platform compatibility and streamlined deployment. In this guide, we'll show you how to export your YOLOv8 models to the TorchScript format, making it easier for you to use them across a wider range of applications. - -## Why should you export to TorchScript? - -![Torchscript Overview](https://github.com/ultralytics/ultralytics/assets/26833433/6873349d-c2f6-4620-b3cc-7b26b0698d0b) - -Developed by the creators of PyTorch, TorchScript is a powerful tool for optimizing and deploying PyTorch models across a variety of platforms. Exporting YOLOv8 models to [TorchScript](https://pytorch.org/docs/stable/jit.html) is crucial for moving from research to real-world applications. TorchScript, part of the PyTorch framework, helps make this transition smoother by allowing PyTorch models to be used in environments that don't support Python. - -The process involves two techniques: tracing and scripting. Tracing records operations during model execution, while scripting allows for the definition of models using a subset of Python. These techniques ensure that models like YOLOv8 can still work their magic even outside their usual Python environment. - -![TorchScript Script and Trace](https://github.com/ultralytics/ultralytics/assets/26833433/ea9ea24f-a3a9-44bb-aca7-9c358d7490d7) - -TorchScript models can also be optimized through techniques such as operator fusion and refinements in memory usage, ensuring efficient execution. Another advantage of exporting to TorchScript is its potential to accelerate model execution across various hardware platforms. It creates a standalone, production-ready representation of your PyTorch model that can be integrated into C++ environments, embedded systems, or deployed in web or mobile applications. - -## Key Features of TorchScript Models - -TorchScript, a key part of the PyTorch ecosystem, provides powerful features for optimizing and deploying deep learning models. - -![TorchScript Features](https://github.com/ultralytics/ultralytics/assets/26833433/44c7c5e3-1146-42db-952a-9060f070fead) - -Here are the key features that make TorchScript a valuable tool for developers: - -- **Static Graph Execution**: TorchScript uses a static graph representation of the model’s computation, which is different from PyTorch’s dynamic graph execution. In static graph execution, the computational graph is defined and compiled once before the actual execution, resulting in improved performance during inference. - -- **Model Serialization**: TorchScript allows you to serialize PyTorch models into a platform-independent format. Serialized models can be loaded without requiring the original Python code, enabling deployment in different runtime environments. - -- **JIT Compilation**: TorchScript uses Just-In-Time (JIT) compilation to convert PyTorch models into an optimized intermediate representation. JIT compiles the model’s computational graph, enabling efficient execution on target devices. - -- **Cross-Language Integration**: With TorchScript, you can export PyTorch models to other languages such as C++, Java, and JavaScript. This makes it easier to integrate PyTorch models into existing software systems written in different languages. - -- **Gradual Conversion**: TorchScript provides a gradual conversion approach, allowing you to incrementally convert parts of your PyTorch model into TorchScript. This flexibility is particularly useful when dealing with complex models or when you want to optimize specific portions of the code. - -## Deployment Options in TorchScript - -Before we look at the code for exporting YOLOv8 models to the TorchScript format, let’s understand where TorchScript models are normally used. - -TorchScript offers various deployment options for machine learning models, such as: - -- **C++ API**: The most common use case for TorchScript is its C++ API, which allows you to load and execute optimized TorchScript models directly within C++ applications. This is ideal for production environments where Python may not be suitable or available. The C++ API offers low-overhead and efficient execution of TorchScript models, maximizing performance potential. - -- **Mobile Deployment**: TorchScript offers tools for converting models into formats readily deployable on mobile devices. PyTorch Mobile provides a runtime for executing these models within iOS and Android apps. This enables low-latency, offline inference capabilities, enhancing user experience and data privacy. - -- **Cloud Deployment**: TorchScript models can be deployed to cloud-based servers using solutions like TorchServe. It provides features like model versioning, batching, and metrics monitoring for scalable deployment in production environments. Cloud deployment with TorchScript can make your models accessible via APIs or other web services. - -## Export to TorchScript: Converting Your YOLOv8 Model - -Exporting YOLOv8 models to TorchScript makes it easier to use them in different places and helps them run faster and more efficiently. This is great for anyone looking to use deep learning models more effectively in real-world applications. - -### Installation - -To install the required package, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required package for YOLOv8 - pip install ultralytics - ``` - -For detailed instructions and best practices related to the installation process, check our [Ultralytics Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -### Usage - -Before diving into the usage instructions, it's important to note that while all [Ultralytics YOLOv8 models](../models/index.md) are available for exporting, you can ensure that the model you select supports export functionality [here](../modes/export.md). - -!!! Example "Usage" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Export the model to TorchScript format - model.export(format='torchscript') # creates 'yolov8n.torchscript' - - # Load the exported TorchScript model - torchscript_model = YOLO('yolov8n.torchscript') - - # Run inference - results = torchscript_model('https://ultralytics.com/images/bus.jpg') - ``` - - === "CLI" - - ```bash - # Export a YOLOv8n PyTorch model to TorchScript format - yolo export model=yolov8n.pt format=torchscript # creates 'yolov8n.torchscript' - - # Run inference with the exported model - yolo predict model=yolov8n.torchscript source='https://ultralytics.com/images/bus.jpg' - ``` - -For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md). - -## Deploying Exported YOLOv8 TorchScript Models - -After successfully exporting your Ultralytics YOLOv8 models to TorchScript format, you can now deploy them. The primary and recommended first step for running a TorchScript model is to utilize the YOLO("model.torchscript") method, as outlined in the previous usage code snippet. However, for in-depth instructions on deploying your TorchScript models in various other settings, take a look at the following resources: - -- **[Explore Mobile Deployment](https://pytorch.org/mobile/home/)**: The PyTorch Mobile Documentation provides comprehensive guidelines for deploying models on mobile devices, ensuring your applications are efficient and responsive. - -- **[Master Server-Side Deployment](https://pytorch.org/serve/getting_started.html)**: Learn how to deploy models server-side with TorchServe, offering a step-by-step tutorial for scalable, efficient model serving. - -- **[Implement C++ Deployment](https://pytorch.org/tutorials/advanced/cpp_export.html)**: Dive into the Tutorial on Loading a TorchScript Model in C++, facilitating the integration of your TorchScript models into C++ applications for enhanced performance and versatility. - -## Summary - -In this guide, we explored the process of exporting Ultralytics YOLOv8 models to the TorchScript format. By following the provided instructions, you can optimize YOLOv8 models for performance and gain the flexibility to deploy them across various platforms and environments. - -For further details on usage, visit [TorchScript’s official documentation](https://pytorch.org/docs/stable/jit.html). - -Also, if you’d like to know more about other Ultralytics YOLOv8 integrations, visit our [integration guide page](../integrations/index.md). You'll find plenty of useful resources and insights there. diff --git a/ultralytics-main/docs/en/integrations/weights-biases.md b/ultralytics-main/docs/en/integrations/weights-biases.md deleted file mode 100644 index 6a69a18..0000000 --- a/ultralytics-main/docs/en/integrations/weights-biases.md +++ /dev/null @@ -1,156 +0,0 @@ ---- -comments: true -description: Discover how to train your YOLOv8 models efficiently with Weights & Biases. This guide walks through integrating Weights & Biases with YOLOv8 to enable seamless experiment tracking, result visualization, and model explainability. -keywords: Ultralytics, YOLOv8, Object Detection, Weights & Biases, Model Training, Experiment Tracking, Visualizing Results ---- - -# Enhancing YOLOv8 Experiment Tracking and Visualization with Weights & Biases - -Object detection models like [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) have become integral to many computer vision applications. However, training, evaluating, and deploying these complex models introduces several challenges. Tracking key training metrics, comparing model variants, analyzing model behavior, and detecting issues require substantial instrumentation and experiment management. - -This guide showcases Ultralytics YOLOv8 integration with Weights & Biases’ for enhanced experiment tracking, model-checkpointing, and visualization of model performance. It also includes instructions for setting up the integration, training, fine-tuning, and visualizing results using Weights & Biases’ interactive features. - -## Weights & Biases - -

- Weights & Biases Overview -

- -[Weights & Biases](https://wandb.ai/site) is a cutting-edge MLOps platform designed for tracking, visualizing, and managing machine learning experiments. It features automatic logging of training metrics for full experiment reproducibility, an interactive UI for streamlined data analysis, and efficient model management tools for deploying across various environments. - -## YOLOv8 Training with Weights & Biases - -You can use Weights & Biases to bring efficiency and automation to your YOLOv8 training process. - -## Installation - -To install the required packages, run: - -!!! Tip "Installation" - - === "CLI" - - ```bash - # Install the required packages for YOLOv8 and Weights & Biases - pip install --upgrade ultralytics==8.0.186 wandb - ``` - -For detailed instructions and best practices related to the installation process, be sure to check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips. - -## Configuring Weights & Biases - -After installing the necessary packages, the next step is to set up your Weights & Biases environment. This includes creating a Weights & Biases account and obtaining the necessary API key for a smooth connection between your development environment and the W&B platform. - -Start by initializing the Weights & Biases environment in your workspace. You can do this by running the following command and following the prompted instructions. - -!!! Tip "Initial SDK Setup" - - === "CLI" - - ```bash - # Initialize your Weights & Biases environment - import wandb - wandb.login() - ``` - -Navigate to the Weights & Biases authorization page to create and retrieve your API key. Use this key to authenticate your environment with W&B. - -## Usage: Training YOLOv8 with Weights & Biases - -Before diving into the usage instructions for YOLOv8 model training with Weights & Biases, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements. - -!!! Example "Usage: Training YOLOv8 with Weights & Biases" - - === "Python" - ```python - from ultralytics import YOLO - from wandb.integration.ultralytics import add_wandb_callback - import wandb - - # Step 1: Initialize a Weights & Biases run - wandb.init(project="ultralytics", job_type="training") - - # Step 2: Define the YOLOv8 Model and Dataset - model_name = "yolov8n" - dataset_name = "coco128.yaml" - model = YOLO(f"{model_name}.pt") - - # Step 3: Add W&B Callback for Ultralytics - add_wandb_callback(model, enable_model_checkpointing=True) - - # Step 4: Train and Fine-Tune the Model - model.train(project="ultralytics", data=dataset_name, epochs=5, imgsz=640) - - # Step 5: Validate the Model - model.val() - - # Step 6: Perform Inference and Log Results - model(["path/to/image1", "path/to/image2"]) - - # Step 7: Finalize the W&B Run - wandb.finish() - ``` - -### Understanding the Code - -Let’s understand the steps showcased in the usage code snippet above. - -- **Step 1: Initialize a Weights & Biases Run**: Start by initializing a Weights & Biases run, specifying the project name and the job type. This run will track and manage the training and validation processes of your model. - -- **Step 2: Define the YOLOv8 Model and Dataset**: Specify the model variant and the dataset you wish to use. The YOLO model is then initialized with the specified model file. - -- **Step 3: Add Weights & Biases Callback for Ultralytics**: This step is crucial as it enables the automatic logging of training metrics and validation results to Weights & Biases, providing a detailed view of the model's performance. - -- **Step 4: Train and Fine-Tune the Model**: Begin training the model with the specified dataset, number of epochs, and image size. The training process includes logging of metrics and predictions at the end of each epoch, offering a comprehensive view of the model's learning progress. - -- **Step 5: Validate the Model**: After training, the model is validated. This step is crucial for assessing the model's performance on unseen data and ensuring its generalizability. - -- **Step 6: Perform Inference and Log Results**: The model performs predictions on specified images. These predictions, along with visual overlays and insights, are automatically logged in a W&B Table for interactive exploration. - -- **Step 7: Finalize the W&B Run**: This step marks the end of data logging and saves the final state of your model's training and validation process in the W&B dashboard. - -### Understanding the Output - -Upon running the usage code snippet above, you can expect the following key outputs: - -- The setup of a new run with its unique ID, indicating the start of the training process. -- A concise summary of the model’s structure, including the number of layers and parameters. -- Regular updates on important metrics such as box loss, cls loss, dfl loss, precision, recall, and mAP scores during each training epoch. -- At the end of training, detailed metrics including the model's inference speed, and overall accuracy metrics are displayed. -- Links to the Weights & Biases dashboard for in-depth analysis and visualization of the training process, along with information on local log file locations. - -### Viewing the Weights & Biases Dashboard - -After running the usage code snippet, you can access the Weights & Biases (W&B) dashboard through the provided link in the output. This dashboard offers a comprehensive view of your model's training process with YOLOv8. - -## Key Features of the Weights & Biases Dashboard - -- **Real-Time Metrics Tracking**: Observe metrics like loss, accuracy, and validation scores as they evolve during the training, offering immediate insights for model tuning. - - - -- **Hyperparameter Optimization**: Weights & Biases aids in fine-tuning critical parameters such as learning rate, batch size, and more, enhancing the performance of YOLOv8. - -- **Comparative Analysis**: The platform allows side-by-side comparisons of different training runs, essential for assessing the impact of various model configurations. - -- **Visualization of Training Progress**: Graphical representations of key metrics provide an intuitive understanding of the model's performance across epochs. - - - -- **Resource Monitoring**: Keep track of CPU, GPU, and memory usage to optimize the efficiency of the training process. - -- **Model Artifacts Management**: Access and share model checkpoints, facilitating easy deployment and collaboration. - -- **Viewing Inference Results with Image Overlay**: Visualize the prediction results on images using interactive overlays in Weights & Biases, providing a clear and detailed view of model performance on real-world data. For more detailed information on Weights & Biases’ image overlay capabilities, check out this [link](https://docs.wandb.ai/guides/track/log/media#image-overlays). - - - -By using these features, you can effectively track, analyze, and optimize your YOLOv8 model's training, ensuring the best possible performance and efficiency. - -## Summary - -This guide helped you explore Ultralytics’ YOLOv8 integration with Weights & Biases. It illustrates the ability of this integration to efficiently track and visualize model training and prediction results. - -For further details on usage, visit [Weights & Biases' official documentation](https://docs.wandb.ai/guides/integrations/ultralytics). - -Also, be sure to check out the [Ultralytics integration guide page](../integrations/index.md), to learn more about different exciting integrations. diff --git a/ultralytics-main/docs/en/models/fast-sam.md b/ultralytics-main/docs/en/models/fast-sam.md deleted file mode 100644 index e358992..0000000 --- a/ultralytics-main/docs/en/models/fast-sam.md +++ /dev/null @@ -1,203 +0,0 @@ ---- -comments: true -description: Explore FastSAM, a CNN-based solution for real-time object segmentation in images. Enhanced user interaction, computational efficiency and adaptable across vision tasks. -keywords: FastSAM, machine learning, CNN-based solution, object segmentation, real-time solution, Ultralytics, vision tasks, image processing, industrial applications, user interaction ---- - -# Fast Segment Anything Model (FastSAM) - -The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. FastSAM significantly reduces computational demands while maintaining competitive performance, making it a practical choice for a variety of vision tasks. - -![Fast Segment Anything Model (FastSAM) architecture overview](https://user-images.githubusercontent.com/26833433/248551984-d98f0f6d-7535-45d0-b380-2e1440b52ad7.jpg) - -## Overview - -FastSAM is designed to address the limitations of the [Segment Anything Model (SAM)](sam.md), a heavy Transformer model with substantial computational resource requirements. The FastSAM decouples the segment anything task into two sequential stages: all-instance segmentation and prompt-guided selection. The first stage uses [YOLOv8-seg](../tasks/segment.md) to produce the segmentation masks of all instances in the image. In the second stage, it outputs the region-of-interest corresponding to the prompt. - -## Key Features - -1. **Real-time Solution:** By leveraging the computational efficiency of CNNs, FastSAM provides a real-time solution for the segment anything task, making it valuable for industrial applications that require quick results. - -2. **Efficiency and Performance:** FastSAM offers a significant reduction in computational and resource demands without compromising on performance quality. It achieves comparable performance to SAM but with drastically reduced computational resources, enabling real-time application. - -3. **Prompt-guided Segmentation:** FastSAM can segment any object within an image guided by various possible user interaction prompts, providing flexibility and adaptability in different scenarios. - -4. **Based on YOLOv8-seg:** FastSAM is based on [YOLOv8-seg](../tasks/segment.md), an object detector equipped with an instance segmentation branch. This allows it to effectively produce the segmentation masks of all instances in an image. - -5. **Competitive Results on Benchmarks:** On the object proposal task on MS COCO, FastSAM achieves high scores at a significantly faster speed than [SAM](sam.md) on a single NVIDIA RTX 3090, demonstrating its efficiency and capability. - -6. **Practical Applications:** The proposed approach provides a new, practical solution for a large number of vision tasks at a really high speed, tens or hundreds of times faster than current methods. - -7. **Model Compression Feasibility:** FastSAM demonstrates the feasibility of a path that can significantly reduce the computational effort by introducing an artificial prior to the structure, thus opening new possibilities for large model architecture for general vision tasks. - -## Available Models, Supported Tasks, and Operating Modes - -This table presents the available models with their specific pre-trained weights, the tasks they support, and their compatibility with different operating modes like [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), indicated by ✅ emojis for supported modes and ❌ emojis for unsupported modes. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|---------------------------------------------------------------------------------------------|----------------------------------------------|-----------|------------|----------|--------| -| FastSAM-s | [FastSAM-s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/FastSAM-s.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ✅ | -| FastSAM-x | [FastSAM-x.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/FastSAM-x.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ✅ | - -## Usage Examples - -The FastSAM models are easy to integrate into your Python applications. Ultralytics provides user-friendly Python API and CLI commands to streamline development. - -### Predict Usage - -To perform object detection on an image, use the `predict` method as shown below: - -!!! Example - - === "Python" - - ```python - from ultralytics import FastSAM - from ultralytics.models.fastsam import FastSAMPrompt - - # Define an inference source - source = 'path/to/bus.jpg' - - # Create a FastSAM model - model = FastSAM('FastSAM-s.pt') # or FastSAM-x.pt - - # Run inference on an image - everything_results = model(source, device='cpu', retina_masks=True, imgsz=1024, conf=0.4, iou=0.9) - - # Prepare a Prompt Process object - prompt_process = FastSAMPrompt(source, everything_results, device='cpu') - - # Everything prompt - ann = prompt_process.everything_prompt() - - # Bbox default shape [0,0,0,0] -> [x1,y1,x2,y2] - ann = prompt_process.box_prompt(bbox=[200, 200, 300, 300]) - - # Text prompt - ann = prompt_process.text_prompt(text='a photo of a dog') - - # Point prompt - # points default [[0,0]] [[x1,y1],[x2,y2]] - # point_label default [0] [1,0] 0:background, 1:foreground - ann = prompt_process.point_prompt(points=[[200, 200]], pointlabel=[1]) - prompt_process.plot(annotations=ann, output='./') - ``` - - === "CLI" - - ```bash - # Load a FastSAM model and segment everything with it - yolo segment predict model=FastSAM-s.pt source=path/to/bus.jpg imgsz=640 - ``` - -This snippet demonstrates the simplicity of loading a pre-trained model and running a prediction on an image. - -### Val Usage - -Validation of the model on a dataset can be done as follows: - -!!! Example - - === "Python" - - ```python - from ultralytics import FastSAM - - # Create a FastSAM model - model = FastSAM('FastSAM-s.pt') # or FastSAM-x.pt - - # Validate the model - results = model.val(data='coco8-seg.yaml') - ``` - - === "CLI" - - ```bash - # Load a FastSAM model and validate it on the COCO8 example dataset at image size 640 - yolo segment val model=FastSAM-s.pt data=coco8.yaml imgsz=640 - ``` - -Please note that FastSAM only supports detection and segmentation of a single class of object. This means it will recognize and segment all objects as the same class. Therefore, when preparing the dataset, you need to convert all object category IDs to 0. - -## FastSAM official Usage - -FastSAM is also available directly from the [https://github.com/CASIA-IVA-Lab/FastSAM](https://github.com/CASIA-IVA-Lab/FastSAM) repository. Here is a brief overview of the typical steps you might take to use FastSAM: - -### Installation - -1. Clone the FastSAM repository: - - ```shell - git clone https://github.com/CASIA-IVA-Lab/FastSAM.git - ``` - -2. Create and activate a Conda environment with Python 3.9: - - ```shell - conda create -n FastSAM python=3.9 - conda activate FastSAM - ``` - -3. Navigate to the cloned repository and install the required packages: - - ```shell - cd FastSAM - pip install -r requirements.txt - ``` - -4. Install the CLIP model: - ```shell - pip install git+https://github.com/openai/CLIP.git - ``` - -### Example Usage - -1. Download a [model checkpoint](https://drive.google.com/file/d/1m1sjY4ihXBU1fZXdQ-Xdj-mDltW-2Rqv/view?usp=sharing). - -2. Use FastSAM for inference. Example commands: - - - Segment everything in an image: - - ```shell - python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg - ``` - - - Segment specific objects using text prompt: - - ```shell - python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg --text_prompt "the yellow dog" - ``` - - - Segment objects within a bounding box (provide box coordinates in xywh format): - - ```shell - python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg --box_prompt "[570,200,230,400]" - ``` - - - Segment objects near specific points: - ```shell - python Inference.py --model_path ./weights/FastSAM.pt --img_path ./images/dogs.jpg --point_prompt "[[520,360],[620,300]]" --point_label "[1,0]" - ``` - -Additionally, you can try FastSAM through a [Colab demo](https://colab.research.google.com/drive/1oX14f6IneGGw612WgVlAiy91UHwFAvr9?usp=sharing) or on the [HuggingFace web demo](https://huggingface.co/spaces/An-619/FastSAM) for a visual experience. - -## Citations and Acknowledgements - -We would like to acknowledge the FastSAM authors for their significant contributions in the field of real-time instance segmentation: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{zhao2023fast, - title={Fast Segment Anything}, - author={Xu Zhao and Wenchao Ding and Yongqi An and Yinglong Du and Tao Yu and Min Li and Ming Tang and Jinqiao Wang}, - year={2023}, - eprint={2306.12156}, - archivePrefix={arXiv}, - primaryClass={cs.CV} - } - ``` - -The original FastSAM paper can be found on [arXiv](https://arxiv.org/abs/2306.12156). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/CASIA-IVA-Lab/FastSAM). We appreciate their efforts in advancing the field and making their work accessible to the broader community. diff --git a/ultralytics-main/docs/en/models/index.md b/ultralytics-main/docs/en/models/index.md deleted file mode 100644 index 70a70ef..0000000 --- a/ultralytics-main/docs/en/models/index.md +++ /dev/null @@ -1,96 +0,0 @@ ---- -comments: true -description: Explore the diverse range of YOLO family, SAM, MobileSAM, FastSAM, YOLO-NAS, YOLO-World and RT-DETR models supported by Ultralytics. Get started with examples for both CLI and Python usage. -keywords: Ultralytics, documentation, YOLO, SAM, MobileSAM, FastSAM, YOLO-NAS, RT-DETR, YOLO-World, models, architectures, Python, CLI ---- - -# Models Supported by Ultralytics - -Welcome to Ultralytics' model documentation! We offer support for a wide range of models, each tailored to specific tasks like [object detection](../tasks/detect.md), [instance segmentation](../tasks/segment.md), [image classification](../tasks/classify.md), [pose estimation](../tasks/pose.md), and [multi-object tracking](../modes/track.md). If you're interested in contributing your model architecture to Ultralytics, check out our [Contributing Guide](../help/contributing.md). - -## Featured Models - -Here are some of the key models supported: - -1. **[YOLOv3](yolov3.md)**: The third iteration of the YOLO model family, originally by Joseph Redmon, known for its efficient real-time object detection capabilities. -2. **[YOLOv4](yolov4.md)**: A darknet-native update to YOLOv3, released by Alexey Bochkovskiy in 2020. -3. **[YOLOv5](yolov5.md)**: An improved version of the YOLO architecture by Ultralytics, offering better performance and speed trade-offs compared to previous versions. -4. **[YOLOv6](yolov6.md)**: Released by [Meituan](https://about.meituan.com/) in 2022, and in use in many of the company's autonomous delivery robots. -5. **[YOLOv7](yolov7.md)**: Updated YOLO models released in 2022 by the authors of YOLOv4. -6. **[YOLOv8](yolov8.md) NEW 🚀**: The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification. -7. **[YOLOv9](yolov9.md)**: An experimental model trained on the Ultralytics [YOLOv5](yolov5.md) codebase implementing Programmable Gradient Information (PGI). -8. **[Segment Anything Model (SAM)](sam.md)**: Meta's Segment Anything Model (SAM). -9. **[Mobile Segment Anything Model (MobileSAM)](mobile-sam.md)**: MobileSAM for mobile applications, by Kyung Hee University. -10. **[Fast Segment Anything Model (FastSAM)](fast-sam.md)**: FastSAM by Image & Video Analysis Group, Institute of Automation, Chinese Academy of Sciences. -11. **[YOLO-NAS](yolo-nas.md)**: YOLO Neural Architecture Search (NAS) Models. -12. **[Realtime Detection Transformers (RT-DETR)](rtdetr.md)**: Baidu's PaddlePaddle Realtime Detection Transformer (RT-DETR) models. -13. **[YOLO-World](yolo-world.md)**: Real-time Open Vocabulary Object Detection models from Tencent AI Lab. - -

-
- -
- Watch: Run Ultralytics YOLO models in just a few lines of code. -

- -## Getting Started: Usage Examples - -This example provides simple YOLO training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -Note the below example is for YOLOv8 [Detect](../tasks/detect.md) models for object detection. For additional supported tasks see the [Segment](../tasks/segment.md), [Classify](../tasks/classify.md) and [Pose](../tasks/pose.md) docs. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()`, `SAM()`, `NAS()` and `RTDETR()` classes to create a model instance in Python: - - ```python - from ultralytics import YOLO - - # Load a COCO-pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv8n model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Load a COCO-pretrained YOLOv8n model and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov8n.pt data=coco8.yaml epochs=100 imgsz=640 - - # Load a COCO-pretrained YOLOv8n model and run inference on the 'bus.jpg' image - yolo predict model=yolov8n.pt source=path/to/bus.jpg - ``` - -## Contributing New Models - -Interested in contributing your model to Ultralytics? Great! We're always open to expanding our model portfolio. - -1. **Fork the Repository**: Start by forking the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics). - -2. **Clone Your Fork**: Clone your fork to your local machine and create a new branch to work on. - -3. **Implement Your Model**: Add your model following the coding standards and guidelines provided in our [Contributing Guide](../help/contributing.md). - -4. **Test Thoroughly**: Make sure to test your model rigorously, both in isolation and as part of the pipeline. - -5. **Create a Pull Request**: Once you're satisfied with your model, create a pull request to the main repository for review. - -6. **Code Review & Merging**: After review, if your model meets our criteria, it will be merged into the main repository. - -For detailed steps, consult our [Contributing Guide](../help/contributing.md). diff --git a/ultralytics-main/docs/en/models/mobile-sam.md b/ultralytics-main/docs/en/models/mobile-sam.md deleted file mode 100644 index bd97e03..0000000 --- a/ultralytics-main/docs/en/models/mobile-sam.md +++ /dev/null @@ -1,119 +0,0 @@ ---- -comments: true -description: Learn more about MobileSAM, its implementation, comparison with the original SAM, and how to download and test it in the Ultralytics framework. Improve your mobile applications today. -keywords: MobileSAM, Ultralytics, SAM, mobile applications, Arxiv, GPU, API, image encoder, mask decoder, model download, testing method ---- - -![MobileSAM Logo](https://github.com/ChaoningZhang/MobileSAM/blob/master/assets/logo2.png?raw=true) - -# Mobile Segment Anything (MobileSAM) - -The MobileSAM paper is now available on [arXiv](https://arxiv.org/pdf/2306.14289.pdf). - -A demonstration of MobileSAM running on a CPU can be accessed at this [demo link](https://huggingface.co/spaces/dhkim2810/MobileSAM). The performance on a Mac i5 CPU takes approximately 3 seconds. On the Hugging Face demo, the interface and lower-performance CPUs contribute to a slower response, but it continues to function effectively. - -MobileSAM is implemented in various projects including [Grounding-SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything), [AnyLabeling](https://github.com/vietanhdev/anylabeling), and [Segment Anything in 3D](https://github.com/Jumpat/SegmentAnythingin3D). - -MobileSAM is trained on a single GPU with a 100k dataset (1% of the original images) in less than a day. The code for this training will be made available in the future. - -## Available Models, Supported Tasks, and Operating Modes - -This table presents the available models with their specific pre-trained weights, the tasks they support, and their compatibility with different operating modes like [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), indicated by ✅ emojis for supported modes and ❌ emojis for unsupported modes. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|-----------------------------------------------------------------------------------------------|----------------------------------------------|-----------|------------|----------|--------| -| MobileSAM | [mobile_sam.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/mobile_sam.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ❌ | - -## Adapting from SAM to MobileSAM - -Since MobileSAM retains the same pipeline as the original SAM, we have incorporated the original's pre-processing, post-processing, and all other interfaces. Consequently, those currently using the original SAM can transition to MobileSAM with minimal effort. - -MobileSAM performs comparably to the original SAM and retains the same pipeline except for a change in the image encoder. Specifically, we replace the original heavyweight ViT-H encoder (632M) with a smaller Tiny-ViT (5M). On a single GPU, MobileSAM operates at about 12ms per image: 8ms on the image encoder and 4ms on the mask decoder. - -The following table provides a comparison of ViT-based image encoders: - -| Image Encoder | Original SAM | MobileSAM | -|---------------|--------------|-----------| -| Parameters | 611M | 5M | -| Speed | 452ms | 8ms | - -Both the original SAM and MobileSAM utilize the same prompt-guided mask decoder: - -| Mask Decoder | Original SAM | MobileSAM | -|--------------|--------------|-----------| -| Parameters | 3.876M | 3.876M | -| Speed | 4ms | 4ms | - -Here is the comparison of the whole pipeline: - -| Whole Pipeline (Enc+Dec) | Original SAM | MobileSAM | -|--------------------------|--------------|-----------| -| Parameters | 615M | 9.66M | -| Speed | 456ms | 12ms | - -The performance of MobileSAM and the original SAM are demonstrated using both a point and a box as prompts. - -![Image with Point as Prompt](https://raw.githubusercontent.com/ChaoningZhang/MobileSAM/master/assets/mask_box.jpg?raw=true) - -![Image with Box as Prompt](https://raw.githubusercontent.com/ChaoningZhang/MobileSAM/master/assets/mask_box.jpg?raw=true) - -With its superior performance, MobileSAM is approximately 5 times smaller and 7 times faster than the current FastSAM. More details are available at the [MobileSAM project page](https://github.com/ChaoningZhang/MobileSAM). - -## Testing MobileSAM in Ultralytics - -Just like the original SAM, we offer a straightforward testing method in Ultralytics, including modes for both Point and Box prompts. - -### Model Download - -You can download the model [here](https://github.com/ChaoningZhang/MobileSAM/blob/master/weights/mobile_sam.pt). - -### Point Prompt - -!!! Example - - === "Python" - - ```python - from ultralytics import SAM - - # Load the model - model = SAM('mobile_sam.pt') - - # Predict a segment based on a point prompt - model.predict('ultralytics/assets/zidane.jpg', points=[900, 370], labels=[1]) - ``` - -### Box Prompt - -!!! Example - - === "Python" - - ```python - from ultralytics import SAM - - # Load the model - model = SAM('mobile_sam.pt') - - # Predict a segment based on a box prompt - model.predict('ultralytics/assets/zidane.jpg', bboxes=[439, 437, 524, 709]) - ``` - -We have implemented `MobileSAM` and `SAM` using the same API. For more usage information, please see the [SAM page](sam.md). - -## Citations and Acknowledgements - -If you find MobileSAM useful in your research or development work, please consider citing our paper: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{mobile_sam, - title={Faster Segment Anything: Towards Lightweight SAM for Mobile Applications}, - author={Zhang, Chaoning and Han, Dongshen and Qiao, Yu and Kim, Jung Uk and Bae, Sung Ho and Lee, Seungkyu and Hong, Choong Seon}, - journal={arXiv preprint arXiv:2306.14289}, - year={2023} - } - ``` diff --git a/ultralytics-main/docs/en/models/rtdetr.md b/ultralytics-main/docs/en/models/rtdetr.md deleted file mode 100644 index 844356e..0000000 --- a/ultralytics-main/docs/en/models/rtdetr.md +++ /dev/null @@ -1,92 +0,0 @@ ---- -comments: true -description: Discover the features and benefits of RT-DETR, Baidu’s efficient and adaptable real-time object detector powered by Vision Transformers, including pre-trained models. -keywords: RT-DETR, Baidu, Vision Transformers, object detection, real-time performance, CUDA, TensorRT, IoU-aware query selection, Ultralytics, Python API, PaddlePaddle ---- - -# Baidu's RT-DETR: A Vision Transformer-Based Real-Time Object Detector - -## Overview - -Real-Time Detection Transformer (RT-DETR), developed by Baidu, is a cutting-edge end-to-end object detector that provides real-time performance while maintaining high accuracy. It leverages the power of Vision Transformers (ViT) to efficiently process multiscale features by decoupling intra-scale interaction and cross-scale fusion. RT-DETR is highly adaptable, supporting flexible adjustment of inference speed using different decoder layers without retraining. The model excels on accelerated backends like CUDA with TensorRT, outperforming many other real-time object detectors. - -![Model example image](https://user-images.githubusercontent.com/26833433/238963168-90e8483f-90aa-4eb6-a5e1-0d408b23dd33.png) **Overview of Baidu's RT-DETR.** The RT-DETR model architecture diagram shows the last three stages of the backbone {S3, S4, S5} as the input to the encoder. The efficient hybrid encoder transforms multiscale features into a sequence of image features through intrascale feature interaction (AIFI) and cross-scale feature-fusion module (CCFM). The IoU-aware query selection is employed to select a fixed number of image features to serve as initial object queries for the decoder. Finally, the decoder with auxiliary prediction heads iteratively optimizes object queries to generate boxes and confidence scores ([source](https://arxiv.org/pdf/2304.08069.pdf)). - -### Key Features - -- **Efficient Hybrid Encoder:** Baidu's RT-DETR uses an efficient hybrid encoder that processes multiscale features by decoupling intra-scale interaction and cross-scale fusion. This unique Vision Transformers-based design reduces computational costs and allows for real-time object detection. -- **IoU-aware Query Selection:** Baidu's RT-DETR improves object query initialization by utilizing IoU-aware query selection. This allows the model to focus on the most relevant objects in the scene, enhancing the detection accuracy. -- **Adaptable Inference Speed:** Baidu's RT-DETR supports flexible adjustments of inference speed by using different decoder layers without the need for retraining. This adaptability facilitates practical application in various real-time object detection scenarios. - -## Pre-trained Models - -The Ultralytics Python API provides pre-trained PaddlePaddle RT-DETR models with different scales: - -- RT-DETR-L: 53.0% AP on COCO val2017, 114 FPS on T4 GPU -- RT-DETR-X: 54.8% AP on COCO val2017, 74 FPS on T4 GPU - -## Usage Examples - -This example provides simple RT-DETR training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -!!! Example - - === "Python" - - ```python - from ultralytics import RTDETR - - # Load a COCO-pretrained RT-DETR-l model - model = RTDETR('rtdetr-l.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the RT-DETR-l model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - ```bash - # Load a COCO-pretrained RT-DETR-l model and train it on the COCO8 example dataset for 100 epochs - yolo train model=rtdetr-l.pt data=coco8.yaml epochs=100 imgsz=640 - - # Load a COCO-pretrained RT-DETR-l model and run inference on the 'bus.jpg' image - yolo predict model=rtdetr-l.pt source=path/to/bus.jpg - ``` - -## Supported Tasks and Modes - -This table presents the model types, the specific pre-trained weights, the tasks supported by each model, and the various modes ([Train](../modes/train.md) , [Val](../modes/val.md), [Predict](../modes/predict.md), [Export](../modes/export.md)) that are supported, indicated by ✅ emojis. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|---------------------|-------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| -| RT-DETR Large | [rtdetr-l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/rtdetr-l.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| RT-DETR Extra-Large | [rtdetr-x.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/rtdetr-x.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | - -## Citations and Acknowledgements - -If you use Baidu's RT-DETR in your research or development work, please cite the [original paper](https://arxiv.org/abs/2304.08069): - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{lv2023detrs, - title={DETRs Beat YOLOs on Real-time Object Detection}, - author={Wenyu Lv and Shangliang Xu and Yian Zhao and Guanzhong Wang and Jinman Wei and Cheng Cui and Yuning Du and Qingqing Dang and Yi Liu}, - year={2023}, - eprint={2304.08069}, - archivePrefix={arXiv}, - primaryClass={cs.CV} - } - ``` - -We would like to acknowledge Baidu and the [PaddlePaddle](https://github.com/PaddlePaddle/PaddleDetection) team for creating and maintaining this valuable resource for the computer vision community. Their contribution to the field with the development of the Vision Transformers-based real-time object detector, RT-DETR, is greatly appreciated. - -_Keywords: RT-DETR, Transformer, ViT, Vision Transformers, Baidu RT-DETR, PaddlePaddle, Paddle Paddle RT-DETR, real-time object detection, Vision Transformers-based object detection, pre-trained PaddlePaddle RT-DETR models, Baidu's RT-DETR usage, Ultralytics Python API_ diff --git a/ultralytics-main/docs/en/models/sam.md b/ultralytics-main/docs/en/models/sam.md deleted file mode 100644 index e931b9e..0000000 --- a/ultralytics-main/docs/en/models/sam.md +++ /dev/null @@ -1,227 +0,0 @@ ---- -comments: true -description: Explore the cutting-edge Segment Anything Model (SAM) from Ultralytics that allows real-time image segmentation. Learn about its promptable segmentation, zero-shot performance, and how to use it. -keywords: Ultralytics, image segmentation, Segment Anything Model, SAM, SA-1B dataset, real-time performance, zero-shot transfer, object detection, image analysis, machine learning ---- - -# Segment Anything Model (SAM) - -Welcome to the frontier of image segmentation with the Segment Anything Model, or SAM. This revolutionary model has changed the game by introducing promptable image segmentation with real-time performance, setting new standards in the field. - -## Introduction to SAM: The Segment Anything Model - -The Segment Anything Model, or SAM, is a cutting-edge image segmentation model that allows for promptable segmentation, providing unparalleled versatility in image analysis tasks. SAM forms the heart of the Segment Anything initiative, a groundbreaking project that introduces a novel model, task, and dataset for image segmentation. - -SAM's advanced design allows it to adapt to new image distributions and tasks without prior knowledge, a feature known as zero-shot transfer. Trained on the expansive [SA-1B dataset](https://ai.facebook.com/datasets/segment-anything/), which contains more than 1 billion masks spread over 11 million carefully curated images, SAM has displayed impressive zero-shot performance, surpassing previous fully supervised results in many cases. - -![Dataset sample image](https://user-images.githubusercontent.com/26833433/238056229-0e8ffbeb-f81a-477e-a490-aff3d82fd8ce.jpg) **SA-1B Example images.** Dataset images overlaid masks from the newly introduced SA-1B dataset. SA-1B contains 11M diverse, high-resolution, licensed, and privacy protecting images and 1.1B high-quality segmentation masks. These masks were annotated fully automatically by SAM, and as verified by human ratings and numerous experiments, are of high quality and diversity. Images are grouped by number of masks per image for visualization (there are ∼100 masks per image on average). - -## Key Features of the Segment Anything Model (SAM) - -- **Promptable Segmentation Task:** SAM was designed with a promptable segmentation task in mind, allowing it to generate valid segmentation masks from any given prompt, such as spatial or text clues identifying an object. -- **Advanced Architecture:** The Segment Anything Model employs a powerful image encoder, a prompt encoder, and a lightweight mask decoder. This unique architecture enables flexible prompting, real-time mask computation, and ambiguity awareness in segmentation tasks. -- **The SA-1B Dataset:** Introduced by the Segment Anything project, the SA-1B dataset features over 1 billion masks on 11 million images. As the largest segmentation dataset to date, it provides SAM with a diverse and large-scale training data source. -- **Zero-Shot Performance:** SAM displays outstanding zero-shot performance across various segmentation tasks, making it a ready-to-use tool for diverse applications with minimal need for prompt engineering. - -For an in-depth look at the Segment Anything Model and the SA-1B dataset, please visit the [Segment Anything website](https://segment-anything.com) and check out the research paper [Segment Anything](https://arxiv.org/abs/2304.02643). - -## Available Models, Supported Tasks, and Operating Modes - -This table presents the available models with their specific pre-trained weights, the tasks they support, and their compatibility with different operating modes like [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), indicated by ✅ emojis for supported modes and ❌ emojis for unsupported modes. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|-------------------------------------------------------------------------------------|----------------------------------------------|-----------|------------|----------|--------| -| SAM base | [sam_b.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/sam_b.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ❌ | -| SAM large | [sam_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/sam_l.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ❌ | - -## How to Use SAM: Versatility and Power in Image Segmentation - -The Segment Anything Model can be employed for a multitude of downstream tasks that go beyond its training data. This includes edge detection, object proposal generation, instance segmentation, and preliminary text-to-mask prediction. With prompt engineering, SAM can swiftly adapt to new tasks and data distributions in a zero-shot manner, establishing it as a versatile and potent tool for all your image segmentation needs. - -### SAM prediction example - -!!! Example "Segment with prompts" - - Segment image with given prompts. - - === "Python" - - ```python - from ultralytics import SAM - - # Load a model - model = SAM('sam_b.pt') - - # Display model information (optional) - model.info() - - # Run inference with bboxes prompt - model('ultralytics/assets/zidane.jpg', bboxes=[439, 437, 524, 709]) - - # Run inference with points prompt - model('ultralytics/assets/zidane.jpg', points=[900, 370], labels=[1]) - ``` - -!!! Example "Segment everything" - - Segment the whole image. - - === "Python" - - ```python - from ultralytics import SAM - - # Load a model - model = SAM('sam_b.pt') - - # Display model information (optional) - model.info() - - # Run inference - model('path/to/image.jpg') - ``` - - === "CLI" - - ```bash - # Run inference with a SAM model - yolo predict model=sam_b.pt source=path/to/image.jpg - ``` - -- The logic here is to segment the whole image if you don't pass any prompts(bboxes/points/masks). - -!!! Example "SAMPredictor example" - - This way you can set image once and run prompts inference multiple times without running image encoder multiple times. - - === "Prompt inference" - - ```python - from ultralytics.models.sam import Predictor as SAMPredictor - - # Create SAMPredictor - overrides = dict(conf=0.25, task='segment', mode='predict', imgsz=1024, model="mobile_sam.pt") - predictor = SAMPredictor(overrides=overrides) - - # Set image - predictor.set_image("ultralytics/assets/zidane.jpg") # set with image file - predictor.set_image(cv2.imread("ultralytics/assets/zidane.jpg")) # set with np.ndarray - results = predictor(bboxes=[439, 437, 524, 709]) - results = predictor(points=[900, 370], labels=[1]) - - # Reset image - predictor.reset_image() - ``` - - Segment everything with additional args. - - === "Segment everything" - - ```python - from ultralytics.models.sam import Predictor as SAMPredictor - - # Create SAMPredictor - overrides = dict(conf=0.25, task='segment', mode='predict', imgsz=1024, model="mobile_sam.pt") - predictor = SAMPredictor(overrides=overrides) - - # Segment with additional args - results = predictor(source="ultralytics/assets/zidane.jpg", crop_n_layers=1, points_stride=64) - ``` - -- More additional args for `Segment everything` see [`Predictor/generate` Reference](../reference/models/sam/predict.md). - -## SAM comparison vs YOLOv8 - -Here we compare Meta's smallest SAM model, SAM-b, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md): - -| Model | Size | Parameters | Speed (CPU) | -|------------------------------------------------|----------------------------|------------------------|----------------------------| -| Meta's SAM-b | 358 MB | 94.7 M | 51096 ms/im | -| [MobileSAM](mobile-sam.md) | 40.7 MB | 10.1 M | 46122 ms/im | -| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 MB | 11.8 M | 115 ms/im | -| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7 MB** (53.4x smaller) | **3.4 M** (27.9x less) | **59 ms/im** (866x faster) | - -This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient. - -Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test: - -!!! Example - - === "Python" - - ```python - from ultralytics import FastSAM, SAM, YOLO - - # Profile SAM-b - model = SAM('sam_b.pt') - model.info() - model('ultralytics/assets') - - # Profile MobileSAM - model = SAM('mobile_sam.pt') - model.info() - model('ultralytics/assets') - - # Profile FastSAM-s - model = FastSAM('FastSAM-s.pt') - model.info() - model('ultralytics/assets') - - # Profile YOLOv8n-seg - model = YOLO('yolov8n-seg.pt') - model.info() - model('ultralytics/assets') - ``` - -## Auto-Annotation: A Quick Path to Segmentation Datasets - -Auto-annotation is a key feature of SAM, allowing users to generate a [segmentation dataset](https://docs.ultralytics.com/datasets/segment) using a pre-trained detection model. This feature enables rapid and accurate annotation of a large number of images, bypassing the need for time-consuming manual labeling. - -### Generate Your Segmentation Dataset Using a Detection Model - -To auto-annotate your dataset with the Ultralytics framework, use the `auto_annotate` function as shown below: - -!!! Example - - === "Python" - - ```python - from ultralytics.data.annotator import auto_annotate - - auto_annotate(data="path/to/images", det_model="yolov8x.pt", sam_model='sam_b.pt') - ``` - -| Argument | Type | Description | Default | -|------------|---------------------|---------------------------------------------------------------------------------------------------------|--------------| -| data | str | Path to a folder containing images to be annotated. | | -| det_model | str, optional | Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'. | 'yolov8x.pt' | -| sam_model | str, optional | Pre-trained SAM segmentation model. Defaults to 'sam_b.pt'. | 'sam_b.pt' | -| device | str, optional | Device to run the models on. Defaults to an empty string (CPU or GPU, if available). | | -| output_dir | str, None, optional | Directory to save the annotated results. Defaults to a 'labels' folder in the same directory as 'data'. | None | - -The `auto_annotate` function takes the path to your images, with optional arguments for specifying the pre-trained detection and SAM segmentation models, the device to run the models on, and the output directory for saving the annotated results. - -Auto-annotation with pre-trained models can dramatically cut down the time and effort required for creating high-quality segmentation datasets. This feature is especially beneficial for researchers and developers dealing with large image collections, as it allows them to focus on model development and evaluation rather than manual annotation. - -## Citations and Acknowledgements - -If you find SAM useful in your research or development work, please consider citing our paper: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{kirillov2023segment, - title={Segment Anything}, - author={Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick}, - year={2023}, - eprint={2304.02643}, - archivePrefix={arXiv}, - primaryClass={cs.CV} - } - ``` - -We would like to express our gratitude to Meta AI for creating and maintaining this valuable resource for the computer vision community. - -_keywords: Segment Anything, Segment Anything Model, SAM, Meta SAM, image segmentation, promptable segmentation, zero-shot performance, SA-1B dataset, advanced architecture, auto-annotation, Ultralytics, pre-trained models, SAM base, SAM large, instance segmentation, computer vision, AI, artificial intelligence, machine learning, data annotation, segmentation masks, detection model, YOLO detection model, bibtex, Meta AI._ diff --git a/ultralytics-main/docs/en/models/yolo-nas.md b/ultralytics-main/docs/en/models/yolo-nas.md deleted file mode 100644 index cc041e7..0000000 --- a/ultralytics-main/docs/en/models/yolo-nas.md +++ /dev/null @@ -1,120 +0,0 @@ ---- -comments: true -description: Explore detailed documentation of YOLO-NAS, a superior object detection model. Learn about its features, pre-trained models, usage with Ultralytics Python API, and more. -keywords: YOLO-NAS, Deci AI, object detection, deep learning, neural architecture search, Ultralytics Python API, YOLO model, pre-trained models, quantization, optimization, COCO, Objects365, Roboflow 100 ---- - -# YOLO-NAS - -## Overview - -Developed by Deci AI, YOLO-NAS is a groundbreaking object detection foundational model. It is the product of advanced Neural Architecture Search technology, meticulously designed to address the limitations of previous YOLO models. With significant improvements in quantization support and accuracy-latency trade-offs, YOLO-NAS represents a major leap in object detection. - -![Model example image](https://learnopencv.com/wp-content/uploads/2023/05/yolo-nas_COCO_map_metrics.png) **Overview of YOLO-NAS.** YOLO-NAS employs quantization-aware blocks and selective quantization for optimal performance. The model, when converted to its INT8 quantized version, experiences a minimal precision drop, a significant improvement over other models. These advancements culminate in a superior architecture with unprecedented object detection capabilities and outstanding performance. - -### Key Features - -- **Quantization-Friendly Basic Block:** YOLO-NAS introduces a new basic block that is friendly to quantization, addressing one of the significant limitations of previous YOLO models. -- **Sophisticated Training and Quantization:** YOLO-NAS leverages advanced training schemes and post-training quantization to enhance performance. -- **AutoNAC Optimization and Pre-training:** YOLO-NAS utilizes AutoNAC optimization and is pre-trained on prominent datasets such as COCO, Objects365, and Roboflow 100. This pre-training makes it extremely suitable for downstream object detection tasks in production environments. - -## Pre-trained Models - -Experience the power of next-generation object detection with the pre-trained YOLO-NAS models provided by Ultralytics. These models are designed to deliver top-notch performance in terms of both speed and accuracy. Choose from a variety of options tailored to your specific needs: - -| Model | mAP | Latency (ms) | -|------------------|-------|--------------| -| YOLO-NAS S | 47.5 | 3.21 | -| YOLO-NAS M | 51.55 | 5.85 | -| YOLO-NAS L | 52.22 | 7.87 | -| YOLO-NAS S INT-8 | 47.03 | 2.36 | -| YOLO-NAS M INT-8 | 51.0 | 3.78 | -| YOLO-NAS L INT-8 | 52.1 | 4.78 | - -Each model variant is designed to offer a balance between Mean Average Precision (mAP) and latency, helping you optimize your object detection tasks for both performance and speed. - -## Usage Examples - -Ultralytics has made YOLO-NAS models easy to integrate into your Python applications via our `ultralytics` python package. The package provides a user-friendly Python API to streamline the process. - -The following examples show how to use YOLO-NAS models with the `ultralytics` package for inference and validation: - -### Inference and Validation Examples - -In this example we validate YOLO-NAS-s on the COCO8 dataset. - -!!! Example - - This example provides simple inference and validation code for YOLO-NAS. For handling inference results see [Predict](../modes/predict.md) mode. For using YOLO-NAS with additional modes see [Val](../modes/val.md) and [Export](../modes/export.md). YOLO-NAS on the `ultralytics` package does not support training. - - === "Python" - - PyTorch pretrained `*.pt` models files can be passed to the `NAS()` class to create a model instance in python: - - ```python - from ultralytics import NAS - - # Load a COCO-pretrained YOLO-NAS-s model - model = NAS('yolo_nas_s.pt') - - # Display model information (optional) - model.info() - - # Validate the model on the COCO8 example dataset - results = model.val(data='coco8.yaml') - - # Run inference with the YOLO-NAS-s model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Load a COCO-pretrained YOLO-NAS-s model and validate it's performance on the COCO8 example dataset - yolo val model=yolo_nas_s.pt data=coco8.yaml - - # Load a COCO-pretrained YOLO-NAS-s model and run inference on the 'bus.jpg' image - yolo predict model=yolo_nas_s.pt source=path/to/bus.jpg - ``` - -## Supported Tasks and Modes - -We offer three variants of the YOLO-NAS models: Small (s), Medium (m), and Large (l). Each variant is designed to cater to different computational and performance needs: - -- **YOLO-NAS-s**: Optimized for environments where computational resources are limited but efficiency is key. -- **YOLO-NAS-m**: Offers a balanced approach, suitable for general-purpose object detection with higher accuracy. -- **YOLO-NAS-l**: Tailored for scenarios requiring the highest accuracy, where computational resources are less of a constraint. - -Below is a detailed overview of each model, including links to their pre-trained weights, the tasks they support, and their compatibility with different operating modes. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|-----------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLO-NAS-s | [yolo_nas_s.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_s.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | -| YOLO-NAS-m | [yolo_nas_m.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_m.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | -| YOLO-NAS-l | [yolo_nas_l.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolo_nas_l.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | - -## Citations and Acknowledgements - -If you employ YOLO-NAS in your research or development work, please cite SuperGradients: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{supergradients, - doi = {10.5281/ZENODO.7789328}, - url = {https://zenodo.org/record/7789328}, - author = {Aharon, Shay and {Louis-Dupont} and {Ofri Masad} and Yurkova, Kate and {Lotem Fridman} and {Lkdci} and Khvedchenya, Eugene and Rubin, Ran and Bagrov, Natan and Tymchenko, Borys and Keren, Tomer and Zhilko, Alexander and {Eran-Deci}}, - title = {Super-Gradients}, - publisher = {GitHub}, - journal = {GitHub repository}, - year = {2021}, - } - ``` - -We express our gratitude to Deci AI's [SuperGradients](https://github.com/Deci-AI/super-gradients/) team for their efforts in creating and maintaining this valuable resource for the computer vision community. We believe YOLO-NAS, with its innovative architecture and superior object detection capabilities, will become a critical tool for developers and researchers alike. - -_Keywords: YOLO-NAS, Deci AI, object detection, deep learning, neural architecture search, Ultralytics Python API, YOLO model, SuperGradients, pre-trained models, quantization-friendly basic block, advanced training schemes, post-training quantization, AutoNAC optimization, COCO, Objects365, Roboflow 100_ diff --git a/ultralytics-main/docs/en/models/yolo-world.md b/ultralytics-main/docs/en/models/yolo-world.md deleted file mode 100644 index 116d62d..0000000 --- a/ultralytics-main/docs/en/models/yolo-world.md +++ /dev/null @@ -1,216 +0,0 @@ ---- -comments: true -description: Discover YOLO-World, a YOLOv8-based framework for real-time open-vocabulary object detection in images. It enhances user interaction, boosts computational efficiency, and adapts across various vision tasks. -keywords: YOLO-World, YOLOv8, machine learning, CNN-based framework, object detection, real-time detection, Ultralytics, vision tasks, image processing, industrial applications, user interaction ---- - -# YOLO-World Model - -The YOLO-World Model introduces an advanced, real-time [Ultralytics](https://ultralytics.com) [YOLOv8](yolov8.md)-based approach for Open-Vocabulary Detection tasks. This innovation enables the detection of any object within an image based on descriptive texts. By significantly lowering computational demands while preserving competitive performance, YOLO-World emerges as a versatile tool for numerous vision-based applications. - -![YOLO-World Model architecture overview](https://github.com/ultralytics/ultralytics/assets/26833433/31105058-78c1-43ef-9573-4f41b06df531) - -## Overview - -YOLO-World tackles the challenges faced by traditional Open-Vocabulary detection models, which often rely on cumbersome Transformer models requiring extensive computational resources. These models' dependence on pre-defined object categories also restricts their utility in dynamic scenarios. YOLO-World revitalizes the YOLOv8 framework with open-vocabulary detection capabilities, employing vision-language modeling and pre-training on expansive datasets to excel at identifying a broad array of objects in zero-shot scenarios with unmatched efficiency. - -## Key Features - -1. **Real-time Solution:** Harnessing the computational speed of CNNs, YOLO-World delivers a swift open-vocabulary detection solution, catering to industries in need of immediate results. - -2. **Efficiency and Performance:** YOLO-World slashes computational and resource requirements without sacrificing performance, offering a robust alternative to models like SAM but at a fraction of the computational cost, enabling real-time applications. - -3. **Inference with Offline Vocabulary:** YOLO-World introduces a "prompt-then-detect" strategy, employing an offline vocabulary to enhance efficiency further. This approach enables the use of custom prompts computed apriori, including captions or categories, to be encoded and stored as offline vocabulary embeddings, streamlining the detection process. - -4. **Powered by YOLOv8:** Built upon [Ultralytics YOLOv8](yolov8.md), YOLO-World leverages the latest advancements in real-time object detection to facilitate open-vocabulary detection with unparalleled accuracy and speed. - -5. **Benchmark Excellence:** YOLO-World outperforms existing open-vocabulary detectors, including MDETR and GLIP series, in terms of speed and efficiency on standard benchmarks, showcasing YOLOv8's superior capability on a single NVIDIA V100 GPU. - -6. **Versatile Applications:** YOLO-World's innovative approach unlocks new possibilities for a multitude of vision tasks, delivering speed improvements by orders of magnitude over existing methods. - -## Available Models, Supported Tasks, and Operating Modes - -This section details the models available with their specific pre-trained weights, the tasks they support, and their compatibility with various operating modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), denoted by ✅ for supported modes and ❌ for unsupported modes. - -!!! Note - - All the YOLOv8-World weights have been directly migrated from the official [YOLO-World](https://github.com/AILab-CVC/YOLO-World) repository, highlighting their excellent contributions. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|-----------------|-------------------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLOv8s-world | [yolov8s-world.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-world.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ❌ | -| YOLOv8s-worldv2 | [yolov8s-worldv2.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-worldv2.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | -| YOLOv8m-world | [yolov8m-world.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-world.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ❌ | -| YOLOv8m-worldv2 | [yolov8m-worldv2.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-worldv2.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | -| YOLOv8l-world | [yolov8l-world.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-world.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ❌ | -| YOLOv8l-worldv2 | [yolov8l-worldv2.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-worldv2.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | -| YOLOv8x-world | [yolov8x-world.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-world.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ❌ | -| YOLOv8x-worldv2 | [yolov8x-worldv2.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-worldv2.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ❌ | ✅ | - -## Zero-shot Transfer on COCO Dataset - -| Model Type | mAP | mAP50 | mAP75 | -|-----------------|------|-------|-------| -| yolov8s-world | 37.4 | 52.0 | 40.6 | -| yolov8s-worldv2 | 37.7 | 52.2 | 41.0 | -| yolov8m-world | 42.0 | 57.0 | 45.6 | -| yolov8m-worldv2 | 43.0 | 58.4 | 46.8 | -| yolov8l-world | 45.7 | 61.3 | 49.8 | -| yolov8l-worldv2 | 45.8 | 61.3 | 49.8 | -| yolov8x-world | 47.0 | 63.0 | 51.2 | -| yolov8x-worldv2 | 47.1 | 62.8 | 51.4 | - -## Usage Examples - -The YOLO-World models are easy to integrate into your Python applications. Ultralytics provides user-friendly Python API and CLI commands to streamline development. - -### Predict Usage - -Object detection is straightforward with the `predict` method, as illustrated below: - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLOWorld - - # Initialize a YOLO-World model - model = YOLOWorld('yolov8s-world.pt') # or select yolov8m/l-world.pt for different sizes - - # Execute inference with the YOLOv8s-world model on the specified image - results = model.predict('path/to/image.jpg') - - # Show results - results[0].show() - ``` - - === "CLI" - - ```bash - # Perform object detection using a YOLO-World model - yolo predict model=yolov8s-world.pt source=path/to/image.jpg imgsz=640 - ``` - -This snippet demonstrates the simplicity of loading a pre-trained model and running a prediction on an image. - -### Val Usage - -Model validation on a dataset is streamlined as follows: - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Create a YOLO-World model - model = YOLO('yolov8s-world.pt') # or select yolov8m/l-world.pt for different sizes - - # Conduct model validation on the COCO8 example dataset - metrics = model.val(data='coco8.yaml') - ``` - - === "CLI" - - ```bash - # Validate a YOLO-World model on the COCO8 dataset with a specified image size - yolo val model=yolov8s-world.pt data=coco8.yaml imgsz=640 - ``` - -!!! Note - - The YOLO-World models provided by Ultralytics come pre-configured with [COCO dataset](../datasets/detect/coco.md) categories as part of their offline vocabulary, enhancing efficiency for immediate application. This integration allows the YOLOv8-World models to directly recognize and predict the 80 standard categories defined in the COCO dataset without requiring additional setup or customization. - -### Set prompts - -![YOLO-World prompt class names overview](https://github.com/ultralytics/ultralytics/assets/26833433/4f609ec0-ae6d-4a85-a034-c1c1c30968ff) - -The YOLO-World framework allows for the dynamic specification of classes through custom prompts, empowering users to tailor the model to their specific needs **without retraining**. This feature is particularly useful for adapting the model to new domains or specific tasks that were not originally part of the training data. By setting custom prompts, users can essentially guide the model's focus towards objects of interest, enhancing the relevance and accuracy of the detection results. - -For instance, if your application only requires detecting 'person' and 'bus' objects, you can specify these classes directly: - -!!! Example - - === "Custom Inference Prompts" - - ```python - from ultralytics import YOLO - - # Initialize a YOLO-World model - model = YOLO('yolov8s-world.pt') # or choose yolov8m/l-world.pt - - # Define custom classes - model.set_classes(["person", "bus"]) - - # Execute prediction for specified categories on an image - results = model.predict('path/to/image.jpg') - - # Show results - results[0].show() - ``` - -You can also save a model after setting custom classes. By doing this you create a version of the YOLO-World model that is specialized for your specific use case. This process embeds your custom class definitions directly into the model file, making the model ready to use with your specified classes without further adjustments. Follow these steps to save and load your custom YOLOv8 model: - -!!! Example - - === "Persisting Models with Custom Vocabulary" - - First load a YOLO-World model, set custom classes for it and save it: - - ```python - from ultralytics import YOLO - - # Initialize a YOLO-World model - model = YOLO('yolov8s-world.pt') # or select yolov8m/l-world.pt - - # Define custom classes - model.set_classes(["person", "bus"]) - - # Save the model with the defined offline vocabulary - model.save("custom_yolov8s.pt") - ``` - - After saving, the custom_yolov8s.pt model behaves like any other pre-trained YOLOv8 model but with a key difference: it is now optimized to detect only the classes you have defined. This customization can significantly improve detection performance and efficiency for your specific application scenarios. - - ```python - from ultralytics import YOLO - - # Load your custom model - model = YOLO('custom_yolov8s.pt') - - # Run inference to detect your custom classes - results = model.predict('path/to/image.jpg') - - # Show results - results[0].show() - ``` - -### Benefits of Saving with Custom Vocabulary - -- **Efficiency**: Streamlines the detection process by focusing on relevant objects, reducing computational overhead and speeding up inference. -- **Flexibility**: Allows for easy adaptation of the model to new or niche detection tasks without the need for extensive retraining or data collection. -- **Simplicity**: Simplifies deployment by eliminating the need to repeatedly specify custom classes at runtime, making the model directly usable with its embedded vocabulary. -- **Performance**: Enhances detection accuracy for specified classes by focusing the model's attention and resources on recognizing the defined objects. - -This approach provides a powerful means of customizing state-of-the-art object detection models for specific tasks, making advanced AI more accessible and applicable to a broader range of practical applications. - -## Citations and Acknowledgements - -We extend our gratitude to the [Tencent AILab Computer Vision Center](https://ai.tencent.com/) for their pioneering work in real-time open-vocabulary object detection with YOLO-World: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{cheng2024yolow, - title={YOLO-World: Real-Time Open-Vocabulary Object Detection}, - author={Cheng, Tianheng and Song, Lin and Ge, Yixiao and Liu, Wenyu and Wang, Xinggang and Shan, Ying}, - journal={arXiv preprint arXiv:2401.17270}, - year={2024} - } - ``` - -For further reading, the original YOLO-World paper is available on [arXiv](https://arxiv.org/pdf/2401.17270v2.pdf). The project's source code and additional resources can be accessed via their [GitHub repository](https://github.com/AILab-CVC/YOLO-World). We appreciate their commitment to advancing the field and sharing their valuable insights with the community. diff --git a/ultralytics-main/docs/en/models/yolov3.md b/ultralytics-main/docs/en/models/yolov3.md deleted file mode 100644 index f24562f..0000000 --- a/ultralytics-main/docs/en/models/yolov3.md +++ /dev/null @@ -1,98 +0,0 @@ ---- -comments: true -description: Get an overview of YOLOv3, YOLOv3-Ultralytics and YOLOv3u. Learn about their key features, usage, and supported tasks for object detection. -keywords: YOLOv3, YOLOv3-Ultralytics, YOLOv3u, Object Detection, Inference, Training, Ultralytics ---- - -# YOLOv3, YOLOv3-Ultralytics, and YOLOv3u - -## Overview - -This document presents an overview of three closely related object detection models, namely [YOLOv3](https://pjreddie.com/darknet/yolo/), [YOLOv3-Ultralytics](https://github.com/ultralytics/yolov3), and [YOLOv3u](https://github.com/ultralytics/ultralytics). - -1. **YOLOv3:** This is the third version of the You Only Look Once (YOLO) object detection algorithm. Originally developed by Joseph Redmon, YOLOv3 improved on its predecessors by introducing features such as multiscale predictions and three different sizes of detection kernels. - -2. **YOLOv3-Ultralytics:** This is Ultralytics' implementation of the YOLOv3 model. It reproduces the original YOLOv3 architecture and offers additional functionalities, such as support for more pre-trained models and easier customization options. - -3. **YOLOv3u:** This is an updated version of YOLOv3-Ultralytics that incorporates the anchor-free, objectness-free split head used in YOLOv8 models. YOLOv3u maintains the same backbone and neck architecture as YOLOv3 but with the updated detection head from YOLOv8. - -![Ultralytics YOLOv3](https://raw.githubusercontent.com/ultralytics/assets/main/yolov3/banner-yolov3.png) - -## Key Features - -- **YOLOv3:** Introduced the use of three different scales for detection, leveraging three different sizes of detection kernels: 13x13, 26x26, and 52x52. This significantly improved detection accuracy for objects of different sizes. Additionally, YOLOv3 added features such as multi-label predictions for each bounding box and a better feature extractor network. - -- **YOLOv3-Ultralytics:** Ultralytics' implementation of YOLOv3 provides the same performance as the original model but comes with added support for more pre-trained models, additional training methods, and easier customization options. This makes it more versatile and user-friendly for practical applications. - -- **YOLOv3u:** This updated model incorporates the anchor-free, objectness-free split head from YOLOv8. By eliminating the need for pre-defined anchor boxes and objectness scores, this detection head design can improve the model's ability to detect objects of varying sizes and shapes. This makes YOLOv3u more robust and accurate for object detection tasks. - -## Supported Tasks and Modes - -The YOLOv3 series, including YOLOv3, YOLOv3-Ultralytics, and YOLOv3u, are designed specifically for object detection tasks. These models are renowned for their effectiveness in various real-world scenarios, balancing accuracy and speed. Each variant offers unique features and optimizations, making them suitable for a range of applications. - -All three models support a comprehensive set of modes, ensuring versatility in various stages of model deployment and development. These modes include [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), providing users with a complete toolkit for effective object detection. - -| Model Type | Tasks Supported | Inference | Validation | Training | Export | -|--------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLOv3 | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv3-Ultralytics | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv3u | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | - -This table provides an at-a-glance view of the capabilities of each YOLOv3 variant, highlighting their versatility and suitability for various tasks and operational modes in object detection workflows. - -## Usage Examples - -This example provides simple YOLOv3 training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: - - ```python - from ultralytics import YOLO - - # Load a COCO-pretrained YOLOv3n model - model = YOLO('yolov3n.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv3n model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Load a COCO-pretrained YOLOv3n model and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov3n.pt data=coco8.yaml epochs=100 imgsz=640 - - # Load a COCO-pretrained YOLOv3n model and run inference on the 'bus.jpg' image - yolo predict model=yolov3n.pt source=path/to/bus.jpg - ``` - -## Citations and Acknowledgements - -If you use YOLOv3 in your research, please cite the original YOLO papers and the Ultralytics YOLOv3 repository: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{redmon2018yolov3, - title={YOLOv3: An Incremental Improvement}, - author={Redmon, Joseph and Farhadi, Ali}, - journal={arXiv preprint arXiv:1804.02767}, - year={2018} - } - ``` - -Thank you to Joseph Redmon and Ali Farhadi for developing the original YOLOv3. diff --git a/ultralytics-main/docs/en/models/yolov4.md b/ultralytics-main/docs/en/models/yolov4.md deleted file mode 100644 index bcc55b0..0000000 --- a/ultralytics-main/docs/en/models/yolov4.md +++ /dev/null @@ -1,70 +0,0 @@ ---- -comments: true -description: Explore our detailed guide on YOLOv4, a state-of-the-art real-time object detector. Understand its architectural highlights, innovative features, and application examples. -keywords: ultralytics, YOLOv4, object detection, neural network, real-time detection, object detector, machine learning ---- - -# YOLOv4: High-Speed and Precise Object Detection - -Welcome to the Ultralytics documentation page for YOLOv4, a state-of-the-art, real-time object detector launched in 2020 by Alexey Bochkovskiy at [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet). YOLOv4 is designed to provide the optimal balance between speed and accuracy, making it an excellent choice for many applications. - -![YOLOv4 architecture diagram](https://user-images.githubusercontent.com/26833433/246185689-530b7fe8-737b-4bb0-b5dd-de10ef5aface.png) **YOLOv4 architecture diagram**. Showcasing the intricate network design of YOLOv4, including the backbone, neck, and head components, and their interconnected layers for optimal real-time object detection. - -## Introduction - -YOLOv4 stands for You Only Look Once version 4. It is a real-time object detection model developed to address the limitations of previous YOLO versions like [YOLOv3](yolov3.md) and other object detection models. Unlike other convolutional neural network (CNN) based object detectors, YOLOv4 is not only applicable for recommendation systems but also for standalone process management and human input reduction. Its operation on conventional graphics processing units (GPUs) allows for mass usage at an affordable price, and it is designed to work in real-time on a conventional GPU while requiring only one such GPU for training. - -## Architecture - -YOLOv4 makes use of several innovative features that work together to optimize its performance. These include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT), Mish-activation, Mosaic data augmentation, DropBlock regularization, and CIoU loss. These features are combined to achieve state-of-the-art results. - -A typical object detector is composed of several parts including the input, the backbone, the neck, and the head. The backbone of YOLOv4 is pre-trained on ImageNet and is used to predict classes and bounding boxes of objects. The backbone could be from several models including VGG, ResNet, ResNeXt, or DenseNet. The neck part of the detector is used to collect feature maps from different stages and usually includes several bottom-up paths and several top-down paths. The head part is what is used to make the final object detections and classifications. - -## Bag of Freebies - -YOLOv4 also makes use of methods known as "bag of freebies," which are techniques that improve the accuracy of the model during training without increasing the cost of inference. Data augmentation is a common bag of freebies technique used in object detection, which increases the variability of the input images to improve the robustness of the model. Some examples of data augmentation include photometric distortions (adjusting the brightness, contrast, hue, saturation, and noise of an image) and geometric distortions (adding random scaling, cropping, flipping, and rotating). These techniques help the model to generalize better to different types of images. - -## Features and Performance - -YOLOv4 is designed for optimal speed and accuracy in object detection. The architecture of YOLOv4 includes CSPDarknet53 as the backbone, PANet as the neck, and YOLOv3 as the detection head. This design allows YOLOv4 to perform object detection at an impressive speed, making it suitable for real-time applications. YOLOv4 also excels in accuracy, achieving state-of-the-art results in object detection benchmarks. - -## Usage Examples - -As of the time of writing, Ultralytics does not currently support YOLOv4 models. Therefore, any users interested in using YOLOv4 will need to refer directly to the YOLOv4 GitHub repository for installation and usage instructions. - -Here is a brief overview of the typical steps you might take to use YOLOv4: - -1. Visit the YOLOv4 GitHub repository: [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet). - -2. Follow the instructions provided in the README file for installation. This typically involves cloning the repository, installing necessary dependencies, and setting up any necessary environment variables. - -3. Once installation is complete, you can train and use the model as per the usage instructions provided in the repository. This usually involves preparing your dataset, configuring the model parameters, training the model, and then using the trained model to perform object detection. - -Please note that the specific steps may vary depending on your specific use case and the current state of the YOLOv4 repository. Therefore, it is strongly recommended to refer directly to the instructions provided in the YOLOv4 GitHub repository. - -We regret any inconvenience this may cause and will strive to update this document with usage examples for Ultralytics once support for YOLOv4 is implemented. - -## Conclusion - -YOLOv4 is a powerful and efficient object detection model that strikes a balance between speed and accuracy. Its use of unique features and bag of freebies techniques during training allows it to perform excellently in real-time object detection tasks. YOLOv4 can be trained and used by anyone with a conventional GPU, making it accessible and practical for a wide range of applications. - -## Citations and Acknowledgements - -We would like to acknowledge the YOLOv4 authors for their significant contributions in the field of real-time object detection: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{bochkovskiy2020yolov4, - title={YOLOv4: Optimal Speed and Accuracy of Object Detection}, - author={Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao}, - year={2020}, - eprint={2004.10934}, - archivePrefix={arXiv}, - primaryClass={cs.CV} - } - ``` - -The original YOLOv4 paper can be found on [arXiv](https://arxiv.org/abs/2004.10934). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/AlexeyAB/darknet). We appreciate their efforts in advancing the field and making their work accessible to the broader community. diff --git a/ultralytics-main/docs/en/models/yolov5.md b/ultralytics-main/docs/en/models/yolov5.md deleted file mode 100644 index af43d32..0000000 --- a/ultralytics-main/docs/en/models/yolov5.md +++ /dev/null @@ -1,114 +0,0 @@ ---- -comments: true -description: Discover YOLOv5u, a boosted version of the YOLOv5 model featuring an improved accuracy-speed tradeoff and numerous pre-trained models for various object detection tasks. -keywords: YOLOv5u, object detection, pre-trained models, Ultralytics, Inference, Validation, YOLOv5, YOLOv8, anchor-free, objectness-free, real-time applications, machine learning ---- - -# YOLOv5 - -## Overview - -YOLOv5u represents an advancement in object detection methodologies. Originating from the foundational architecture of the [YOLOv5](https://github.com/ultralytics/yolov5) model developed by Ultralytics, YOLOv5u integrates the anchor-free, objectness-free split head, a feature previously introduced in the [YOLOv8](yolov8.md) models. This adaptation refines the model's architecture, leading to an improved accuracy-speed tradeoff in object detection tasks. Given the empirical results and its derived features, YOLOv5u provides an efficient alternative for those seeking robust solutions in both research and practical applications. - -![Ultralytics YOLOv5](https://raw.githubusercontent.com/ultralytics/assets/main/yolov5/v70/splash.png) - -## Key Features - -- **Anchor-free Split Ultralytics Head:** Traditional object detection models rely on predefined anchor boxes to predict object locations. However, YOLOv5u modernizes this approach. By adopting an anchor-free split Ultralytics head, it ensures a more flexible and adaptive detection mechanism, consequently enhancing the performance in diverse scenarios. - -- **Optimized Accuracy-Speed Tradeoff:** Speed and accuracy often pull in opposite directions. But YOLOv5u challenges this tradeoff. It offers a calibrated balance, ensuring real-time detections without compromising on accuracy. This feature is particularly invaluable for applications that demand swift responses, such as autonomous vehicles, robotics, and real-time video analytics. - -- **Variety of Pre-trained Models:** Understanding that different tasks require different toolsets, YOLOv5u provides a plethora of pre-trained models. Whether you're focusing on Inference, Validation, or Training, there's a tailor-made model awaiting you. This variety ensures you're not just using a one-size-fits-all solution, but a model specifically fine-tuned for your unique challenge. - -## Supported Tasks and Modes - -The YOLOv5u models, with various pre-trained weights, excel in [Object Detection](../tasks/detect.md) tasks. They support a comprehensive range of modes, making them suitable for diverse applications, from development to deployment. - -| Model Type | Pre-trained Weights | Task | Inference | Validation | Training | Export | -|------------|-----------------------------------------------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLOv5u | `yolov5nu`, `yolov5su`, `yolov5mu`, `yolov5lu`, `yolov5xu`, `yolov5n6u`, `yolov5s6u`, `yolov5m6u`, `yolov5l6u`, `yolov5x6u` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | - -This table provides a detailed overview of the YOLOv5u model variants, highlighting their applicability in object detection tasks and support for various operational modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). This comprehensive support ensures that users can fully leverage the capabilities of YOLOv5u models in a wide range of object detection scenarios. - -## Performance Metrics - -!!! Performance - - === "Detection" - - See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/detect/coco/), which include 80 pre-trained classes. - - | Model | YAML | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - |---------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| - | [yolov5nu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5nu.pt) | [yolov5n.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | - | [yolov5su.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5su.pt) | [yolov5s.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | - | [yolov5mu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5mu.pt) | [yolov5m.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | - | [yolov5lu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5lu.pt) | [yolov5l.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | - | [yolov5xu.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5xu.pt) | [yolov5x.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5.yaml) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | - | | | | | | | | | - | [yolov5n6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5n6u.pt) | [yolov5n6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 42.1 | 211.0 | 1.83 | 4.3 | 7.8 | - | [yolov5s6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5s6u.pt) | [yolov5s6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 48.6 | 422.6 | 2.34 | 15.3 | 24.6 | - | [yolov5m6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5m6u.pt) | [yolov5m6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 53.6 | 810.9 | 4.36 | 41.2 | 65.7 | - | [yolov5l6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5l6u.pt) | [yolov5l6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 55.7 | 1470.9 | 5.47 | 86.1 | 137.4 | - | [yolov5x6u.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov5x6u.pt) | [yolov5x6.yaml](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v5/yolov5-p6.yaml) | 1280 | 56.8 | 2436.5 | 8.98 | 155.4 | 250.7 | - -## Usage Examples - -This example provides simple YOLOv5 training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: - - ```python - from ultralytics import YOLO - - # Load a COCO-pretrained YOLOv5n model - model = YOLO('yolov5n.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv5n model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Load a COCO-pretrained YOLOv5n model and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov5n.pt data=coco8.yaml epochs=100 imgsz=640 - - # Load a COCO-pretrained YOLOv5n model and run inference on the 'bus.jpg' image - yolo predict model=yolov5n.pt source=path/to/bus.jpg - ``` - -## Citations and Acknowledgements - -If you use YOLOv5 or YOLOv5u in your research, please cite the Ultralytics YOLOv5 repository as follows: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @software{yolov5, - title = {Ultralytics YOLOv5}, - author = {Glenn Jocher}, - year = {2020}, - version = {7.0}, - license = {AGPL-3.0}, - url = {https://github.com/ultralytics/yolov5}, - doi = {10.5281/zenodo.3908559}, - orcid = {0000-0001-5950-6979} - } - ``` - -Please note that YOLOv5 models are provided under [AGPL-3.0](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) and [Enterprise](https://ultralytics.com/license) licenses. diff --git a/ultralytics-main/docs/en/models/yolov6.md b/ultralytics-main/docs/en/models/yolov6.md deleted file mode 100644 index 3607917..0000000 --- a/ultralytics-main/docs/en/models/yolov6.md +++ /dev/null @@ -1,106 +0,0 @@ ---- -comments: true -description: Explore Meituan YOLOv6, a state-of-the-art object detection model striking a balance between speed and accuracy. Dive into features, pre-trained models, and Python usage. -keywords: Meituan YOLOv6, object detection, Ultralytics, YOLOv6 docs, Bi-directional Concatenation, Anchor-Aided Training, pretrained models, real-time applications ---- - -# Meituan YOLOv6 - -## Overview - -[Meituan](https://about.meituan.com/) YOLOv6 is a cutting-edge object detector that offers remarkable balance between speed and accuracy, making it a popular choice for real-time applications. This model introduces several notable enhancements on its architecture and training scheme, including the implementation of a Bi-directional Concatenation (BiC) module, an anchor-aided training (AAT) strategy, and an improved backbone and neck design for state-of-the-art accuracy on the COCO dataset. - -![Meituan YOLOv6](https://user-images.githubusercontent.com/26833433/240750495-4da954ce-8b3b-41c4-8afd-ddb74361d3c2.png) -![Model example image](https://user-images.githubusercontent.com/26833433/240750557-3e9ec4f0-0598-49a8-83ea-f33c91eb6d68.png) **Overview of YOLOv6.** Model architecture diagram showing the redesigned network components and training strategies that have led to significant performance improvements. (a) The neck of YOLOv6 (N and S are shown). Note for M/L, RepBlocks is replaced with CSPStackRep. (b) The structure of a BiC module. (c) A SimCSPSPPF block. ([source](https://arxiv.org/pdf/2301.05586.pdf)). - -### Key Features - -- **Bidirectional Concatenation (BiC) Module:** YOLOv6 introduces a BiC module in the neck of the detector, enhancing localization signals and delivering performance gains with negligible speed degradation. -- **Anchor-Aided Training (AAT) Strategy:** This model proposes AAT to enjoy the benefits of both anchor-based and anchor-free paradigms without compromising inference efficiency. -- **Enhanced Backbone and Neck Design:** By deepening YOLOv6 to include another stage in the backbone and neck, this model achieves state-of-the-art performance on the COCO dataset at high-resolution input. -- **Self-Distillation Strategy:** A new self-distillation strategy is implemented to boost the performance of smaller models of YOLOv6, enhancing the auxiliary regression branch during training and removing it at inference to avoid a marked speed decline. - -## Performance Metrics - -YOLOv6 provides various pre-trained models with different scales: - -- YOLOv6-N: 37.5% AP on COCO val2017 at 1187 FPS with NVIDIA Tesla T4 GPU. -- YOLOv6-S: 45.0% AP at 484 FPS. -- YOLOv6-M: 50.0% AP at 226 FPS. -- YOLOv6-L: 52.8% AP at 116 FPS. -- YOLOv6-L6: State-of-the-art accuracy in real-time. - -YOLOv6 also provides quantized models for different precisions and models optimized for mobile platforms. - -## Usage Examples - -This example provides simple YOLOv6 training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: - - ```python - from ultralytics import YOLO - - # Build a YOLOv6n model from scratch - model = YOLO('yolov6n.yaml') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv6n model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Build a YOLOv6n model from scratch and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov6n.yaml data=coco8.yaml epochs=100 imgsz=640 - - # Build a YOLOv6n model from scratch and run inference on the 'bus.jpg' image - yolo predict model=yolov6n.yaml source=path/to/bus.jpg - ``` - -## Supported Tasks and Modes - -The YOLOv6 series offers a range of models, each optimized for high-performance [Object Detection](../tasks/detect.md). These models cater to varying computational needs and accuracy requirements, making them versatile for a wide array of applications. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|---------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLOv6-N | `yolov6-n.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv6-S | `yolov6-s.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv6-M | `yolov6-m.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv6-L | `yolov6-l.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv6-L6 | `yolov6-l6.pt` | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | - -This table provides a detailed overview of the YOLOv6 model variants, highlighting their capabilities in object detection tasks and their compatibility with various operational modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). This comprehensive support ensures that users can fully leverage the capabilities of YOLOv6 models in a broad range of object detection scenarios. - -## Citations and Acknowledgements - -We would like to acknowledge the authors for their significant contributions in the field of real-time object detection: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @misc{li2023yolov6, - title={YOLOv6 v3.0: A Full-Scale Reloading}, - author={Chuyi Li and Lulu Li and Yifei Geng and Hongliang Jiang and Meng Cheng and Bo Zhang and Zaidan Ke and Xiaoming Xu and Xiangxiang Chu}, - year={2023}, - eprint={2301.05586}, - archivePrefix={arXiv}, - primaryClass={cs.CV} - } - ``` - -The original YOLOv6 paper can be found on [arXiv](https://arxiv.org/abs/2301.05586). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/meituan/YOLOv6). We appreciate their efforts in advancing the field and making their work accessible to the broader community. diff --git a/ultralytics-main/docs/en/models/yolov7.md b/ultralytics-main/docs/en/models/yolov7.md deleted file mode 100644 index f3d99d5..0000000 --- a/ultralytics-main/docs/en/models/yolov7.md +++ /dev/null @@ -1,65 +0,0 @@ ---- -comments: true -description: Explore the YOLOv7, a real-time object detector. Understand its superior speed, impressive accuracy, and unique trainable bag-of-freebies optimization focus. -keywords: YOLOv7, real-time object detector, state-of-the-art, Ultralytics, MS COCO dataset, model re-parameterization, dynamic label assignment, extended scaling, compound scaling ---- - -# YOLOv7: Trainable Bag-of-Freebies - -YOLOv7 is a state-of-the-art real-time object detector that surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS. It has the highest accuracy (56.8% AP) among all known real-time object detectors with 30 FPS or higher on GPU V100. Moreover, YOLOv7 outperforms other object detectors such as YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, and many others in speed and accuracy. The model is trained on the MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code for YOLOv7 is available on GitHub. - -![YOLOv7 comparison with SOTA object detectors](https://github.com/ultralytics/ultralytics/assets/26833433/5e1e0420-8122-4c79-b8d0-2860aa79af92) -**Comparison of state-of-the-art object detectors.** From the results in Table 2 we know that the proposed method has the best speed-accuracy trade-off comprehensively. If we compare YOLOv7-tiny-SiLU with YOLOv5-N (r6.1), our method is 127 fps faster and 10.7% more accurate on AP. In addition, YOLOv7 has 51.4% AP at frame rate of 161 fps, while PPYOLOE-L with the same AP has only 78 fps frame rate. In terms of parameter usage, YOLOv7 is 41% less than PPYOLOE-L. If we compare YOLOv7-X with 114 fps inference speed to YOLOv5-L (r6.1) with 99 fps inference speed, YOLOv7-X can improve AP by 3.9%. If YOLOv7-X is compared with YOLOv5-X (r6.1) of similar scale, the inference speed of YOLOv7-X is 31 fps faster. In addition, in terms the amount of parameters and computation, YOLOv7-X reduces 22% of parameters and 8% of computation compared to YOLOv5-X (r6.1), but improves AP by 2.2% ([Source](https://arxiv.org/pdf/2207.02696.pdf)). - -## Overview - -Real-time object detection is an important component in many computer vision systems, including multi-object tracking, autonomous driving, robotics, and medical image analysis. In recent years, real-time object detection development has focused on designing efficient architectures and improving the inference speed of various CPUs, GPUs, and neural processing units (NPUs). YOLOv7 supports both mobile GPU and GPU devices, from the edge to the cloud. - -Unlike traditional real-time object detectors that focus on architecture optimization, YOLOv7 introduces a focus on the optimization of the training process. This includes modules and optimization methods designed to improve the accuracy of object detection without increasing the inference cost, a concept known as the "trainable bag-of-freebies". - -## Key Features - -YOLOv7 introduces several key features: - -1. **Model Re-parameterization**: YOLOv7 proposes a planned re-parameterized model, which is a strategy applicable to layers in different networks with the concept of gradient propagation path. - -2. **Dynamic Label Assignment**: The training of the model with multiple output layers presents a new issue: "How to assign dynamic targets for the outputs of different branches?" To solve this problem, YOLOv7 introduces a new label assignment method called coarse-to-fine lead guided label assignment. - -3. **Extended and Compound Scaling**: YOLOv7 proposes "extend" and "compound scaling" methods for the real-time object detector that can effectively utilize parameters and computation. - -4. **Efficiency**: The method proposed by YOLOv7 can effectively reduce about 40% parameters and 50% computation of state-of-the-art real-time object detector, and has faster inference speed and higher detection accuracy. - -## Usage Examples - -As of the time of writing, Ultralytics does not currently support YOLOv7 models. Therefore, any users interested in using YOLOv7 will need to refer directly to the YOLOv7 GitHub repository for installation and usage instructions. - -Here is a brief overview of the typical steps you might take to use YOLOv7: - -1. Visit the YOLOv7 GitHub repository: [https://github.com/WongKinYiu/yolov7](https://github.com/WongKinYiu/yolov7). - -2. Follow the instructions provided in the README file for installation. This typically involves cloning the repository, installing necessary dependencies, and setting up any necessary environment variables. - -3. Once installation is complete, you can train and use the model as per the usage instructions provided in the repository. This usually involves preparing your dataset, configuring the model parameters, training the model, and then using the trained model to perform object detection. - -Please note that the specific steps may vary depending on your specific use case and the current state of the YOLOv7 repository. Therefore, it is strongly recommended to refer directly to the instructions provided in the YOLOv7 GitHub repository. - -We regret any inconvenience this may cause and will strive to update this document with usage examples for Ultralytics once support for YOLOv7 is implemented. - -## Citations and Acknowledgements - -We would like to acknowledge the YOLOv7 authors for their significant contributions in the field of real-time object detection: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{wang2022yolov7, - title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors}, - author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark}, - journal={arXiv preprint arXiv:2207.02696}, - year={2022} - } - ``` - -The original YOLOv7 paper can be found on [arXiv](https://arxiv.org/pdf/2207.02696.pdf). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/WongKinYiu/yolov7). We appreciate their efforts in advancing the field and making their work accessible to the broader community. diff --git a/ultralytics-main/docs/en/models/yolov8.md b/ultralytics-main/docs/en/models/yolov8.md deleted file mode 100644 index e793677..0000000 --- a/ultralytics-main/docs/en/models/yolov8.md +++ /dev/null @@ -1,186 +0,0 @@ ---- -comments: true -description: Explore the thrilling features of YOLOv8, the latest version of our real-time object detector! Learn how advanced architectures, pre-trained models and optimal balance between accuracy & speed make YOLOv8 the perfect choice for your object detection tasks. -keywords: YOLOv8, Ultralytics, real-time object detector, pre-trained models, documentation, object detection, YOLO series, advanced architectures, accuracy, speed ---- - -# YOLOv8 - -## Overview - -YOLOv8 is the latest iteration in the YOLO series of real-time object detectors, offering cutting-edge performance in terms of accuracy and speed. Building upon the advancements of previous YOLO versions, YOLOv8 introduces new features and optimizations that make it an ideal choice for various object detection tasks in a wide range of applications. - -![Ultralytics YOLOv8](https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/yolo-comparison-plots.png) - -

-
- -
- Watch: Ultralytics YOLOv8 Model Overview -

- -## Key Features - -- **Advanced Backbone and Neck Architectures:** YOLOv8 employs state-of-the-art backbone and neck architectures, resulting in improved feature extraction and object detection performance. -- **Anchor-free Split Ultralytics Head:** YOLOv8 adopts an anchor-free split Ultralytics head, which contributes to better accuracy and a more efficient detection process compared to anchor-based approaches. -- **Optimized Accuracy-Speed Tradeoff:** With a focus on maintaining an optimal balance between accuracy and speed, YOLOv8 is suitable for real-time object detection tasks in diverse application areas. -- **Variety of Pre-trained Models:** YOLOv8 offers a range of pre-trained models to cater to various tasks and performance requirements, making it easier to find the right model for your specific use case. - -## Supported Tasks and Modes - -The YOLOv8 series offers a diverse range of models, each specialized for specific tasks in computer vision. These models are designed to cater to various requirements, from object detection to more complex tasks like instance segmentation, pose/keypoints detection, oriented object detection, and classification. - -Each variant of the YOLOv8 series is optimized for its respective task, ensuring high performance and accuracy. Additionally, these models are compatible with various operational modes including [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md), facilitating their use in different stages of deployment and development. - -| Model | Filenames | Task | Inference | Validation | Training | Export | -|-------------|----------------------------------------------------------------------------------------------------------------|----------------------------------------------|-----------|------------|----------|--------| -| YOLOv8 | `yolov8n.pt` `yolov8s.pt` `yolov8m.pt` `yolov8l.pt` `yolov8x.pt` | [Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv8-seg | `yolov8n-seg.pt` `yolov8s-seg.pt` `yolov8m-seg.pt` `yolov8l-seg.pt` `yolov8x-seg.pt` | [Instance Segmentation](../tasks/segment.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv8-pose | `yolov8n-pose.pt` `yolov8s-pose.pt` `yolov8m-pose.pt` `yolov8l-pose.pt` `yolov8x-pose.pt` `yolov8x-pose-p6.pt` | [Pose/Keypoints](../tasks/pose.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv8-obb | `yolov8n-obb.pt` `yolov8s-obb.pt` `yolov8m-obb.pt` `yolov8l-obb.pt` `yolov8x-obb.pt` | [Oriented Detection](../tasks/obb.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv8-cls | `yolov8n-cls.pt` `yolov8s-cls.pt` `yolov8m-cls.pt` `yolov8l-cls.pt` `yolov8x-cls.pt` | [Classification](../tasks/classify.md) | ✅ | ✅ | ✅ | ✅ | - -This table provides an overview of the YOLOv8 model variants, highlighting their applicability in specific tasks and their compatibility with various operational modes such as Inference, Validation, Training, and Export. It showcases the versatility and robustness of the YOLOv8 series, making them suitable for a variety of applications in computer vision. - -## Performance Metrics - -!!! Performance - - === "Detection (COCO)" - - See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/detect/coco/), which include 80 pre-trained classes. - - | Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | - | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | - | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | - | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | - | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | - | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | - - === "Detection (Open Images V7)" - - See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examples with these models trained on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/), which include 600 pre-trained classes. - - | Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | - | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 | - | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 | - | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 | - | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 | - | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 | - - === "Segmentation (COCO)" - - See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/segment/coco/), which include 80 pre-trained classes. - - | Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | - | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | - | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | - | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | - | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | - | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | - - === "Classification (ImageNet)" - - See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usage examples with these models trained on [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet/), which include 1000 pre-trained classes. - - | Model | size
(pixels) | acc
top1 | acc
top5 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) at 640 | - | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | - | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | - | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | - | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | - | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | - | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | - - === "Pose (COCO)" - - See [Pose Estimation Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples with these models trained on [COCO](https://docs.ultralytics.com/datasets/pose/coco/), which include 1 pre-trained class, 'person'. - - | Model | size
(pixels) | mAPpose
50-95 | mAPpose
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | - | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | - | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | - | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | - | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | - | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | - | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | - - === "OBB (DOTAv1)" - - See [Oriented Detection Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with these models trained on [DOTAv1](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10/), which include 15 pre-trained classes. - - | Model | size
(pixels) | mAPtest
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | - |----------------------------------------------------------------------------------------------|-----------------------| -------------------- | -------------------------------- | ------------------------------------- | -------------------- | ----------------- | - | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 | - | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 | - | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | - | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | - | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | - -## Usage Examples - -This example provides simple YOLOv8 training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -Note the below example is for YOLOv8 [Detect](../tasks/detect.md) models for object detection. For additional supported tasks see the [Segment](../tasks/segment.md), [Classify](../tasks/classify.md), [OBB](../tasks/obb.md) docs and [Pose](../tasks/pose.md) docs. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: - - ```python - from ultralytics import YOLO - - # Load a COCO-pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv8n model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Load a COCO-pretrained YOLOv8n model and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov8n.pt data=coco8.yaml epochs=100 imgsz=640 - - # Load a COCO-pretrained YOLOv8n model and run inference on the 'bus.jpg' image - yolo predict model=yolov8n.pt source=path/to/bus.jpg - ``` - -## Citations and Acknowledgements - -If you use the YOLOv8 model or any other software from this repository in your work, please cite it using the following format: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @software{yolov8_ultralytics, - author = {Glenn Jocher and Ayush Chaurasia and Jing Qiu}, - title = {Ultralytics YOLOv8}, - version = {8.0.0}, - year = {2023}, - url = {https://github.com/ultralytics/ultralytics}, - orcid = {0000-0001-5950-6979, 0000-0002-7603-6750, 0000-0003-3783-7069}, - license = {AGPL-3.0} - } - ``` - -Please note that the DOI is pending and will be added to the citation once it is available. YOLOv8 models are provided under [AGPL-3.0](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) and [Enterprise](https://ultralytics.com/license) licenses. diff --git a/ultralytics-main/docs/en/models/yolov9.md b/ultralytics-main/docs/en/models/yolov9.md deleted file mode 100644 index 51ddfff..0000000 --- a/ultralytics-main/docs/en/models/yolov9.md +++ /dev/null @@ -1,152 +0,0 @@ ---- -comments: true -description: Discover YOLOv9, the latest addition to the real-time object detection arsenal, leveraging Programmable Gradient Information and GELAN architecture for unparalleled performance. -keywords: YOLOv9, real-time object detection, Programmable Gradient Information, GELAN architecture, Ultralytics, MS COCO dataset, open-source, lightweight model, computer vision, AI ---- - -# YOLOv9: A Leap Forward in Object Detection Technology - -YOLOv9 marks a significant advancement in real-time object detection, introducing groundbreaking techniques such as Programmable Gradient Information (PGI) and the Generalized Efficient Layer Aggregation Network (GELAN). This model demonstrates remarkable improvements in efficiency, accuracy, and adaptability, setting new benchmarks on the MS COCO dataset. The YOLOv9 project, while developed by a separate open-source team, builds upon the robust codebase provided by [Ultralytics](https://ultralytics.com) [YOLOv5](yolov5.md), showcasing the collaborative spirit of the AI research community. - -![YOLOv9 performance comparison](https://github.com/ultralytics/ultralytics/assets/26833433/9f41ef7b-6008-43eb-8ba1-0a9b89600100) - -## Introduction to YOLOv9 - -In the quest for optimal real-time object detection, YOLOv9 stands out with its innovative approach to overcoming information loss challenges inherent in deep neural networks. By integrating PGI and the versatile GELAN architecture, YOLOv9 not only enhances the model's learning capacity but also ensures the retention of crucial information throughout the detection process, thereby achieving exceptional accuracy and performance. - -## Core Innovations of YOLOv9 - -YOLOv9's advancements are deeply rooted in addressing the challenges posed by information loss in deep neural networks. The Information Bottleneck Principle and the innovative use of Reversible Functions are central to its design, ensuring YOLOv9 maintains high efficiency and accuracy. - -### Information Bottleneck Principle - -The Information Bottleneck Principle reveals a fundamental challenge in deep learning: as data passes through successive layers of a network, the potential for information loss increases. This phenomenon is mathematically represented as: - -```python -I(X, X) >= I(X, f_theta(X)) >= I(X, g_phi(f_theta(X))) -``` - -where `I` denotes mutual information, and `f` and `g` represent transformation functions with parameters `theta` and `phi`, respectively. YOLOv9 counters this challenge by implementing Programmable Gradient Information (PGI), which aids in preserving essential data across the network's depth, ensuring more reliable gradient generation and, consequently, better model convergence and performance. - -### Reversible Functions - -The concept of Reversible Functions is another cornerstone of YOLOv9's design. A function is deemed reversible if it can be inverted without any loss of information, as expressed by: - -```python -X = v_zeta(r_psi(X)) -``` - -with `psi` and `zeta` as parameters for the reversible and its inverse function, respectively. This property is crucial for deep learning architectures, as it allows the network to retain a complete information flow, thereby enabling more accurate updates to the model's parameters. YOLOv9 incorporates reversible functions within its architecture to mitigate the risk of information degradation, especially in deeper layers, ensuring the preservation of critical data for object detection tasks. - -### Impact on Lightweight Models - -Addressing information loss is particularly vital for lightweight models, which are often under-parameterized and prone to losing significant information during the feedforward process. YOLOv9's architecture, through the use of PGI and reversible functions, ensures that even with a streamlined model, the essential information required for accurate object detection is retained and effectively utilized. - -### Programmable Gradient Information (PGI) - -PGI is a novel concept introduced in YOLOv9 to combat the information bottleneck problem, ensuring the preservation of essential data across deep network layers. This allows for the generation of reliable gradients, facilitating accurate model updates and improving the overall detection performance. - -### Generalized Efficient Layer Aggregation Network (GELAN) - -GELAN represents a strategic architectural advancement, enabling YOLOv9 to achieve superior parameter utilization and computational efficiency. Its design allows for flexible integration of various computational blocks, making YOLOv9 adaptable to a wide range of applications without sacrificing speed or accuracy. - -![YOLOv9 architecture comparison](https://github.com/ultralytics/ultralytics/assets/26833433/286a3971-677b-45e6-a90b-4b6bd565a7af) - -## Performance on MS COCO Dataset - -The performance of YOLOv9 on the [COCO dataset](../datasets/detect/coco.md) exemplifies its significant advancements in real-time object detection, setting new benchmarks across various model sizes. Table 1 presents a comprehensive comparison of state-of-the-art real-time object detectors, illustrating YOLOv9's superior efficiency and accuracy. - -**Table 1. Comparison of State-of-the-Art Real-Time Object Detectors** - -| Model | size
(pixels) | APval
50-95 | APval
50 | APval
75 | params
(M) | FLOPs
(B) | -|---------------------------------------------------------------------------------------|-----------------------|---------------------|------------------|------------------|--------------------|-------------------| -| YOLOv9-S | 640 | 46.8 | 63.4 | 50.7 | 7.2 | 26.7 | -| YOLOv9-M | 640 | 51.4 | 68.1 | 56.1 | 20.1 | 76.8 | -| [YOLOv9-C](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov9c.pt) | 640 | 53.0 | 70.2 | 57.8 | 25.5 | 102.8 | -| [YOLOv9-E](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov9e.pt) | 640 | 55.6 | 72.8 | 60.6 | 58.1 | 192.5 | - -YOLOv9's iterations, ranging from the smaller S variant to the extensive E model, demonstrate improvements not only in accuracy (AP metrics) but also in efficiency with a reduced number of parameters and computational needs (FLOPs). This table underscores YOLOv9's ability to deliver high precision while maintaining or reducing the computational overhead compared to prior versions and competing models. - -Comparatively, YOLOv9 exhibits remarkable gains: - -- **Lightweight Models**: YOLOv9-S surpasses the YOLO MS-S in parameter efficiency and computational load while achieving an improvement of 0.4∼0.6% in AP. -- **Medium to Large Models**: YOLOv9-M and YOLOv9-E show notable advancements in balancing the trade-off between model complexity and detection performance, offering significant reductions in parameters and computations against the backdrop of improved accuracy. - -The YOLOv9-C model, in particular, highlights the effectiveness of the architecture's optimizations. It operates with 42% fewer parameters and 21% less computational demand than YOLOv7 AF, yet it achieves comparable accuracy, demonstrating YOLOv9's significant efficiency improvements. Furthermore, the YOLOv9-E model sets a new standard for large models, with 15% fewer parameters and 25% less computational need than [YOLOv8x](yolov8.md), alongside a substantial 1.7% improvement in AP. - -These results showcase YOLOv9's strategic advancements in model design, emphasizing its enhanced efficiency without compromising on the precision essential for real-time object detection tasks. The model not only pushes the boundaries of performance metrics but also emphasizes the importance of computational efficiency, making it a pivotal development in the field of computer vision. - -## Conclusion - -YOLOv9 represents a pivotal development in real-time object detection, offering significant improvements in terms of efficiency, accuracy, and adaptability. By addressing critical challenges through innovative solutions like PGI and GELAN, YOLOv9 sets a new precedent for future research and application in the field. As the AI community continues to evolve, YOLOv9 stands as a testament to the power of collaboration and innovation in driving technological progress. - -## Usage Examples - -This example provides simple YOLOv9 training and inference examples. For full documentation on these and other [modes](../modes/index.md) see the [Predict](../modes/predict.md), [Train](../modes/train.md), [Val](../modes/val.md) and [Export](../modes/export.md) docs pages. - -!!! Example - - === "Python" - - PyTorch pretrained `*.pt` models as well as configuration `*.yaml` files can be passed to the `YOLO()` class to create a model instance in python: - - ```python - from ultralytics import YOLO - - # Build a YOLOv9c model from scratch - model = YOLO('yolov9c.yaml') - - # Build a YOLOv9c model from pretrained weight - model = YOLO('yolov9c.pt') - - # Display model information (optional) - model.info() - - # Train the model on the COCO8 example dataset for 100 epochs - results = model.train(data='coco8.yaml', epochs=100, imgsz=640) - - # Run inference with the YOLOv9c model on the 'bus.jpg' image - results = model('path/to/bus.jpg') - ``` - - === "CLI" - - CLI commands are available to directly run the models: - - ```bash - # Build a YOLOv9c model from scratch and train it on the COCO8 example dataset for 100 epochs - yolo train model=yolov9c.yaml data=coco8.yaml epochs=100 imgsz=640 - - # Build a YOLOv9c model from scratch and run inference on the 'bus.jpg' image - yolo predict model=yolov9c.yaml source=path/to/bus.jpg - ``` - -## Supported Tasks and Modes - -The YOLOv9 series offers a range of models, each optimized for high-performance [Object Detection](../tasks/detect.md). These models cater to varying computational needs and accuracy requirements, making them versatile for a wide array of applications. - -| Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | -|------------|-----------------------------------------------------------------------------------------|----------------------------------------|-----------|------------|----------|--------| -| YOLOv9-C | [yolov9c.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov9c.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | -| YOLOv9-E | [yolov9e.pt](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov9e.pt) | [Object Detection](../tasks/detect.md) | ✅ | ✅ | ✅ | ✅ | - -This table provides a detailed overview of the YOLOv9 model variants, highlighting their capabilities in object detection tasks and their compatibility with various operational modes such as [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). This comprehensive support ensures that users can fully leverage the capabilities of YOLOv9 models in a broad range of object detection scenarios. - -## Citations and Acknowledgements - -We would like to acknowledge the YOLOv9 authors for their significant contributions in the field of real-time object detection: - -!!! Quote "" - - === "BibTeX" - - ```bibtex - @article{wang2024yolov9, - title={{YOLOv9}: Learning What You Want to Learn Using Programmable Gradient Information}, - author={Wang, Chien-Yao and Liao, Hong-Yuan Mark}, - booktitle={arXiv preprint arXiv:2402.13616}, - year={2024} - } - ``` - -The original YOLOv9 paper can be found on [arXiv](https://arxiv.org/pdf/2402.13616.pdf). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/WongKinYiu/yolov9). We appreciate their efforts in advancing the field and making their work accessible to the broader community. diff --git a/ultralytics-main/docs/en/modes/benchmark.md b/ultralytics-main/docs/en/modes/benchmark.md deleted file mode 100644 index 7f8e457..0000000 --- a/ultralytics-main/docs/en/modes/benchmark.md +++ /dev/null @@ -1,106 +0,0 @@ ---- -comments: true -description: Learn how to profile speed and accuracy of YOLOv8 across various export formats; get insights on mAP50-95, accuracy_top5 metrics, and more. -keywords: Ultralytics, YOLOv8, benchmarking, speed profiling, accuracy profiling, mAP50-95, accuracy_top5, ONNX, OpenVINO, TensorRT, YOLO export formats ---- - -# Model Benchmarking with Ultralytics YOLO - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -Once your model is trained and validated, the next logical step is to evaluate its performance in various real-world scenarios. Benchmark mode in Ultralytics YOLOv8 serves this purpose by providing a robust framework for assessing the speed and accuracy of your model across a range of export formats. - -

-
- -
- Watch: Ultralytics Modes Tutorial: Benchmark -

- -## Why Is Benchmarking Crucial? - -- **Informed Decisions:** Gain insights into the trade-offs between speed and accuracy. -- **Resource Allocation:** Understand how different export formats perform on different hardware. -- **Optimization:** Learn which export format offers the best performance for your specific use case. -- **Cost Efficiency:** Make more efficient use of hardware resources based on benchmark results. - -### Key Metrics in Benchmark Mode - -- **mAP50-95:** For object detection, segmentation, and pose estimation. -- **accuracy_top5:** For image classification. -- **Inference Time:** Time taken for each image in milliseconds. - -### Supported Export Formats - -- **ONNX:** For optimal CPU performance -- **TensorRT:** For maximal GPU efficiency -- **OpenVINO:** For Intel hardware optimization -- **CoreML, TensorFlow SavedModel, and More:** For diverse deployment needs. - -!!! Tip "Tip" - - * Export to ONNX or OpenVINO for up to 3x CPU speedup. - * Export to TensorRT for up to 5x GPU speedup. - -## Usage Examples - -Run YOLOv8n benchmarks on all supported export formats including ONNX, TensorRT etc. See Arguments section below for a full list of export arguments. - -!!! Example - - === "Python" - - ```python - from ultralytics.utils.benchmarks import benchmark - - # Benchmark on GPU - benchmark(model='yolov8n.pt', data='coco8.yaml', imgsz=640, half=False, device=0) - ``` - - === "CLI" - - ```bash - yolo benchmark model=yolov8n.pt data='coco8.yaml' imgsz=640 half=False device=0 - ``` - -## Arguments - -Arguments such as `model`, `data`, `imgsz`, `half`, `device`, and `verbose` provide users with the flexibility to fine-tune the benchmarks to their specific needs and compare the performance of different export formats with ease. - -| Key | Default Value | Description | -|-----------|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------| -| `model` | `None` | Specifies the path to the model file. Accepts both `.pt` and `.yaml` formats, e.g., `"yolov8n.pt"` for pre-trained models or configuration files. | -| `data` | `None` | Path to a YAML file defining the dataset for benchmarking, typically including paths and settings for validation data. Example: `"coco128.yaml"`. | -| `imgsz` | `640` | The input image size for the model. Can be a single integer for square images or a tuple `(width, height)` for non-square, e.g., `(640, 480)`. | -| `half` | `False` | Enables FP16 (half-precision) inference, reducing memory usage and possibly increasing speed on compatible hardware. Use `half=True` to enable. | -| `int8` | `False` | Activates INT8 quantization for further optimized performance on supported devices, especially useful for edge devices. Set `int8=True` to use. | -| `device` | `None` | Defines the computation device(s) for benchmarking, such as `"cpu"`, `"cuda:0"`, or a list of devices like `"cuda:0,1"` for multi-GPU setups. | -| `verbose` | `False` | Controls the level of detail in logging output. A boolean value; set `verbose=True` for detailed logs or a float for thresholding errors. | - -## Export Formats - -Benchmarks will attempt to run automatically on all possible export formats below. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/modes/export.md b/ultralytics-main/docs/en/modes/export.md deleted file mode 100644 index 5859b18..0000000 --- a/ultralytics-main/docs/en/modes/export.md +++ /dev/null @@ -1,111 +0,0 @@ ---- -comments: true -description: Step-by-step guide on exporting your YOLOv8 models to various format like ONNX, TensorRT, CoreML and more for deployment. Explore now!. -keywords: YOLO, YOLOv8, Ultralytics, Model export, ONNX, TensorRT, CoreML, TensorFlow SavedModel, OpenVINO, PyTorch, export model ---- - -# Model Export with Ultralytics YOLO - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -The ultimate goal of training a model is to deploy it for real-world applications. Export mode in Ultralytics YOLOv8 offers a versatile range of options for exporting your trained model to different formats, making it deployable across various platforms and devices. This comprehensive guide aims to walk you through the nuances of model exporting, showcasing how to achieve maximum compatibility and performance. - -

-
- -
- Watch: How To Export Custom Trained Ultralytics YOLOv8 Model and Run Live Inference on Webcam. -

- -## Why Choose YOLOv8's Export Mode? - -- **Versatility:** Export to multiple formats including ONNX, TensorRT, CoreML, and more. -- **Performance:** Gain up to 5x GPU speedup with TensorRT and 3x CPU speedup with ONNX or OpenVINO. -- **Compatibility:** Make your model universally deployable across numerous hardware and software environments. -- **Ease of Use:** Simple CLI and Python API for quick and straightforward model exporting. - -### Key Features of Export Mode - -Here are some of the standout functionalities: - -- **One-Click Export:** Simple commands for exporting to different formats. -- **Batch Export:** Export batched-inference capable models. -- **Optimized Inference:** Exported models are optimized for quicker inference times. -- **Tutorial Videos:** In-depth guides and tutorials for a smooth exporting experience. - -!!! Tip "Tip" - - * Export to ONNX or OpenVINO for up to 3x CPU speedup. - * Export to TensorRT for up to 5x GPU speedup. - -## Usage Examples - -Export a YOLOv8n model to a different format like ONNX or TensorRT. See Arguments section below for a full list of export arguments. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - - === "CLI" - - ```bash - yolo export model=yolov8n.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -## Arguments - -This table details the configurations and options available for exporting YOLO models to different formats. These settings are critical for optimizing the exported model's performance, size, and compatibility across various platforms and environments. Proper configuration ensures that the model is ready for deployment in the intended application with optimal efficiency. - -| Argument | Type | Default | Description | -|-------------|------------------|-----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `format` | `str` | `'torchscript'` | Target format for the exported model, such as `'onnx'`, `'torchscript'`, `'tensorflow'`, or others, defining compatibility with various deployment environments. | -| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. | -| `keras` | `bool` | `False` | Enables export to Keras format for TensorFlow SavedModel, providing compatibility with TensorFlow serving and APIs. | -| `optimize` | `bool` | `False` | Applies optimization for mobile devices when exporting to TorchScript, potentially reducing model size and improving performance. | -| `half` | `bool` | `False` | Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. | -| `int8` | `bool` | `False` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal accuracy loss, primarily for edge devices. | -| `dynamic` | `bool` | `False` | Allows dynamic input sizes for ONNX and TensorRT exports, enhancing flexibility in handling varying image dimensions. | -| `simplify` | `bool` | `False` | Simplifies the model graph for ONNX exports, potentially improving performance and compatibility. | -| `opset` | `int` | `None` | Specifies the ONNX opset version for compatibility with different ONNX parsers and runtimes. If not set, uses the latest supported version. | -| `workspace` | `float` | `4.0` | Sets the maximum workspace size in GB for TensorRT optimizations, balancing memory usage and performance. | -| `nms` | `bool` | `False` | Adds Non-Maximum Suppression (NMS) to the CoreML export, essential for accurate and efficient detection post-processing. | - -Adjusting these parameters allows for customization of the export process to fit specific requirements, such as deployment environment, hardware constraints, and performance targets. Selecting the appropriate format and settings is essential for achieving the best balance between model size, speed, and accuracy. - -## Export Formats - -Available YOLOv8 export formats are in the table below. You can export to any format using the `format` argument, i.e. `format='onnx'` or `format='engine'`. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | diff --git a/ultralytics-main/docs/en/modes/index.md b/ultralytics-main/docs/en/modes/index.md deleted file mode 100644 index c04aa40..0000000 --- a/ultralytics-main/docs/en/modes/index.md +++ /dev/null @@ -1,73 +0,0 @@ ---- -comments: true -description: From training to tracking, make the most of YOLOv8 with Ultralytics. Get insights and examples for each supported mode including validation, export, and benchmarking. -keywords: Ultralytics, YOLOv8, Machine Learning, Object Detection, Training, Validation, Prediction, Export, Tracking, Benchmarking ---- - -# Ultralytics YOLOv8 Modes - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -Ultralytics YOLOv8 is not just another object detection model; it's a versatile framework designed to cover the entire lifecycle of machine learning models—from data ingestion and model training to validation, deployment, and real-world tracking. Each mode serves a specific purpose and is engineered to offer you the flexibility and efficiency required for different tasks and use-cases. - -

-
- -
- Watch: Ultralytics Modes Tutorial: Train, Validate, Predict, Export & Benchmark. -

- -### Modes at a Glance - -Understanding the different **modes** that Ultralytics YOLOv8 supports is critical to getting the most out of your models: - -- **Train** mode: Fine-tune your model on custom or preloaded datasets. -- **Val** mode: A post-training checkpoint to validate model performance. -- **Predict** mode: Unleash the predictive power of your model on real-world data. -- **Export** mode: Make your model deployment-ready in various formats. -- **Track** mode: Extend your object detection model into real-time tracking applications. -- **Benchmark** mode: Analyze the speed and accuracy of your model in diverse deployment environments. - -This comprehensive guide aims to give you an overview and practical insights into each mode, helping you harness the full potential of YOLOv8. - -## [Train](train.md) - -Train mode is used for training a YOLOv8 model on a custom dataset. In this mode, the model is trained using the specified dataset and hyperparameters. The training process involves optimizing the model's parameters so that it can accurately predict the classes and locations of objects in an image. - -[Train Examples](train.md){ .md-button } - -## [Val](val.md) - -Val mode is used for validating a YOLOv8 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its accuracy and generalization performance. This mode can be used to tune the hyperparameters of the model to improve its performance. - -[Val Examples](val.md){ .md-button } - -## [Predict](predict.md) - -Predict mode is used for making predictions using a trained YOLOv8 model on new images or videos. In this mode, the model is loaded from a checkpoint file, and the user can provide images or videos to perform inference. The model predicts the classes and locations of objects in the input images or videos. - -[Predict Examples](predict.md){ .md-button } - -## [Export](export.md) - -Export mode is used for exporting a YOLOv8 model to a format that can be used for deployment. In this mode, the model is converted to a format that can be used by other software applications or hardware devices. This mode is useful when deploying the model to production environments. - -[Export Examples](export.md){ .md-button } - -## [Track](track.md) - -Track mode is used for tracking objects in real-time using a YOLOv8 model. In this mode, the model is loaded from a checkpoint file, and the user can provide a live video stream to perform real-time object tracking. This mode is useful for applications such as surveillance systems or self-driving cars. - -[Track Examples](track.md){ .md-button } - -## [Benchmark](benchmark.md) - -Benchmark mode is used to profile the speed and accuracy of various export formats for YOLOv8. The benchmarks provide information on the size of the exported format, its `mAP50-95` metrics (for object detection, segmentation and pose) or `accuracy_top5` metrics (for classification), and the inference time in milliseconds per image across various export formats like ONNX, OpenVINO, TensorRT and others. This information can help users choose the optimal export format for their specific use case based on their requirements for speed and accuracy. - -[Benchmark Examples](benchmark.md){ .md-button } diff --git a/ultralytics-main/docs/en/modes/predict.md b/ultralytics-main/docs/en/modes/predict.md deleted file mode 100644 index d3a9d47..0000000 --- a/ultralytics-main/docs/en/modes/predict.md +++ /dev/null @@ -1,795 +0,0 @@ ---- -comments: true -description: Discover how to use YOLOv8 predict mode for various tasks. Learn about different inference sources like images, videos, and data formats. -keywords: Ultralytics, YOLOv8, predict mode, inference sources, prediction tasks, streaming mode, image processing, video processing, machine learning, AI ---- - -# Model Prediction with Ultralytics YOLO - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -In the world of machine learning and computer vision, the process of making sense out of visual data is called 'inference' or 'prediction'. Ultralytics YOLOv8 offers a powerful feature known as **predict mode** that is tailored for high-performance, real-time inference on a wide range of data sources. - -

-
- -
- Watch: How to Extract the Outputs from Ultralytics YOLOv8 Model for Custom Projects. -

- -## Real-world Applications - -| Manufacturing | Sports | Safety | -|:-------------------------------------------------:|:----------------------------------------------------:|:-------------------------------------------:| -| ![Vehicle Spare Parts Detection][car spare parts] | ![Football Player Detection][football player detect] | ![People Fall Detection][human fall detect] | -| Vehicle Spare Parts Detection | Football Player Detection | People Fall Detection | - -## Why Use Ultralytics YOLO for Inference? - -Here's why you should consider YOLOv8's predict mode for your various inference needs: - -- **Versatility:** Capable of making inferences on images, videos, and even live streams. -- **Performance:** Engineered for real-time, high-speed processing without sacrificing accuracy. -- **Ease of Use:** Intuitive Python and CLI interfaces for rapid deployment and testing. -- **Highly Customizable:** Various settings and parameters to tune the model's inference behavior according to your specific requirements. - -### Key Features of Predict Mode - -YOLOv8's predict mode is designed to be robust and versatile, featuring: - -- **Multiple Data Source Compatibility:** Whether your data is in the form of individual images, a collection of images, video files, or real-time video streams, predict mode has you covered. -- **Streaming Mode:** Use the streaming feature to generate a memory-efficient generator of `Results` objects. Enable this by setting `stream=True` in the predictor's call method. -- **Batch Processing:** The ability to process multiple images or video frames in a single batch, further speeding up inference time. -- **Integration Friendly:** Easily integrate with existing data pipelines and other software components, thanks to its flexible API. - -Ultralytics YOLO models return either a Python list of `Results` objects, or a memory-efficient Python generator of `Results` objects when `stream=True` is passed to the model during inference: - -!!! Example "Predict" - - === "Return a list with `stream=False`" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # pretrained YOLOv8n model - - # Run batched inference on a list of images - results = model(['im1.jpg', 'im2.jpg']) # return a list of Results objects - - # Process results list - for result in results: - boxes = result.boxes # Boxes object for bounding box outputs - masks = result.masks # Masks object for segmentation masks outputs - keypoints = result.keypoints # Keypoints object for pose outputs - probs = result.probs # Probs object for classification outputs - result.show() # display to screen - result.save(filename='result.jpg') # save to disk - ``` - - === "Return a generator with `stream=True`" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # pretrained YOLOv8n model - - # Run batched inference on a list of images - results = model(['im1.jpg', 'im2.jpg'], stream=True) # return a generator of Results objects - - # Process results generator - for result in results: - boxes = result.boxes # Boxes object for bounding box outputs - masks = result.masks # Masks object for segmentation masks outputs - keypoints = result.keypoints # Keypoints object for pose outputs - probs = result.probs # Probs object for classification outputs - result.show() # display to screen - result.save(filename='result.jpg') # save to disk - ``` - -## Inference Sources - -YOLOv8 can process different types of input sources for inference, as shown in the table below. The sources include static images, video streams, and various data formats. The table also indicates whether each source can be used in streaming mode with the argument `stream=True` ✅. Streaming mode is beneficial for processing videos or live streams as it creates a generator of results instead of loading all frames into memory. - -!!! Tip "Tip" - - Use `stream=True` for processing long videos or large datasets to efficiently manage memory. When `stream=False`, the results for all frames or data points are stored in memory, which can quickly add up and cause out-of-memory errors for large inputs. In contrast, `stream=True` utilizes a generator, which only keeps the results of the current frame or data point in memory, significantly reducing memory consumption and preventing out-of-memory issues. - -| Source | Argument | Type | Notes | -|----------------|--------------------------------------------|-----------------|---------------------------------------------------------------------------------------------| -| image | `'image.jpg'` | `str` or `Path` | Single image file. | -| URL | `'https://ultralytics.com/images/bus.jpg'` | `str` | URL to an image. | -| screenshot | `'screen'` | `str` | Capture a screenshot. | -| PIL | `Image.open('im.jpg')` | `PIL.Image` | HWC format with RGB channels. | -| OpenCV | `cv2.imread('im.jpg')` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | -| numpy | `np.zeros((640,1280,3))` | `np.ndarray` | HWC format with BGR channels `uint8 (0-255)`. | -| torch | `torch.zeros(16,3,320,640)` | `torch.Tensor` | BCHW format with RGB channels `float32 (0.0-1.0)`. | -| CSV | `'sources.csv'` | `str` or `Path` | CSV file containing paths to images, videos, or directories. | -| video ✅ | `'video.mp4'` | `str` or `Path` | Video file in formats like MP4, AVI, etc. | -| directory ✅ | `'path/'` | `str` or `Path` | Path to a directory containing images or videos. | -| glob ✅ | `'path/*.jpg'` | `str` | Glob pattern to match multiple files. Use the `*` character as a wildcard. | -| YouTube ✅ | `'https://youtu.be/LNwODJXcvt4'` | `str` | URL to a YouTube video. | -| stream ✅ | `'rtsp://example.com/media.mp4'` | `str` | URL for streaming protocols such as RTSP, RTMP, TCP, or an IP address. | -| multi-stream ✅ | `'list.streams'` | `str` or `Path` | `*.streams` text file with one stream URL per row, i.e. 8 streams will run at batch-size 8. | - -Below are code examples for using each source type: - -!!! Example "Prediction sources" - - === "image" - - Run inference on an image file. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define path to the image file - source = 'path/to/image.jpg' - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "screenshot" - - Run inference on the current screen content as a screenshot. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define current screenshot as source - source = 'screen' - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "URL" - - Run inference on an image or video hosted remotely via URL. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define remote image or video URL - source = 'https://ultralytics.com/images/bus.jpg' - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "PIL" - - Run inference on an image opened with Python Imaging Library (PIL). - ```python - from PIL import Image - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Open an image using PIL - source = Image.open('path/to/image.jpg') - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "OpenCV" - - Run inference on an image read with OpenCV. - ```python - import cv2 - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Read an image using OpenCV - source = cv2.imread('path/to/image.jpg') - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "numpy" - - Run inference on an image represented as a numpy array. - ```python - import numpy as np - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Create a random numpy array of HWC shape (640, 640, 3) with values in range [0, 255] and type uint8 - source = np.random.randint(low=0, high=255, size=(640, 640, 3), dtype='uint8') - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "torch" - - Run inference on an image represented as a PyTorch tensor. - ```python - import torch - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Create a random torch tensor of BCHW shape (1, 3, 640, 640) with values in range [0, 1] and type float32 - source = torch.rand(1, 3, 640, 640, dtype=torch.float32) - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "CSV" - - Run inference on a collection of images, URLs, videos and directories listed in a CSV file. - ```python - import torch - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define a path to a CSV file with images, URLs, videos and directories - source = 'path/to/file.csv' - - # Run inference on the source - results = model(source) # list of Results objects - ``` - - === "video" - - Run inference on a video file. By using `stream=True`, you can create a generator of Results objects to reduce memory usage. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define path to video file - source = 'path/to/video.mp4' - - # Run inference on the source - results = model(source, stream=True) # generator of Results objects - ``` - - === "directory" - - Run inference on all images and videos in a directory. To also capture images and videos in subdirectories use a glob pattern, i.e. `path/to/dir/**/*`. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define path to directory containing images and videos for inference - source = 'path/to/dir' - - # Run inference on the source - results = model(source, stream=True) # generator of Results objects - ``` - - === "glob" - - Run inference on all images and videos that match a glob expression with `*` characters. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define a glob search for all JPG files in a directory - source = 'path/to/dir/*.jpg' - - # OR define a recursive glob search for all JPG files including subdirectories - source = 'path/to/dir/**/*.jpg' - - # Run inference on the source - results = model(source, stream=True) # generator of Results objects - ``` - - === "YouTube" - - Run inference on a YouTube video. By using `stream=True`, you can create a generator of Results objects to reduce memory usage for long videos. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Define source as YouTube video URL - source = 'https://youtu.be/LNwODJXcvt4' - - # Run inference on the source - results = model(source, stream=True) # generator of Results objects - ``` - - === "Streams" - - Run inference on remote streaming sources using RTSP, RTMP, TCP and IP address protocols. If multiple streams are provided in a `*.streams` text file then batched inference will run, i.e. 8 streams will run at batch-size 8, otherwise single streams will run at batch-size 1. - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Single stream with batch-size 1 inference - source = 'rtsp://example.com/media.mp4' # RTSP, RTMP, TCP or IP streaming address - - # Multiple streams with batched inference (i.e. batch-size 8 for 8 streams) - source = 'path/to/list.streams' # *.streams text file with one streaming address per row - - # Run inference on the source - results = model(source, stream=True) # generator of Results objects - ``` - -## Inference Arguments - -`model.predict()` accepts multiple arguments that can be passed at inference time to override defaults: - -!!! Example - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Run inference on 'bus.jpg' with arguments - model.predict('bus.jpg', save=True, imgsz=320, conf=0.5) - ``` - -Inference arguments: - -| Argument | Type | Default | Description | -|-----------------|----------------|------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `source` | `str` | `'ultralytics/assets'` | Specifies the data source for inference. Can be an image path, video file, directory, URL, or device ID for live feeds. Supports a wide range of formats and sources, enabling flexible application across different types of input. | -| `conf` | `float` | `0.25` | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. | -| `iou` | `float` | `0.7` | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Higher values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. | -| `imgsz` | `int or tuple` | `640` | Defines the image size for inference. Can be a single integer `640` for square resizing or a (height, width) tuple. Proper sizing can improve detection accuracy and processing speed. | -| `half` | `bool` | `False` | Enables half-precision (FP16) inference, which can speed up model inference on supported GPUs with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for inference (e.g., `cpu`, `cuda:0` or `0`). Allows users to select between CPU, a specific GPU, or other compute devices for model execution. | -| `max_det` | `int` | `300` | Maximum number of detections allowed per image. Limits the total number of objects the model can detect in a single inference, preventing excessive outputs in dense scenes. | -| `vid_stride` | `int` | `1` | Frame stride for video inputs. Allows skipping frames in videos to speed up processing at the cost of temporal resolution. A value of 1 processes every frame, higher values skip frames. | -| `stream_buffer` | `bool` | `False` | Determines if all frames should be buffered when processing video streams (`True`), or if the model should return the most recent frame (`False`). Useful for real-time applications. | -| `visualize` | `bool` | `False` | Activates visualization of model features during inference, providing insights into what the model is "seeing". Useful for debugging and model interpretation. | -| `augment` | `bool` | `False` | Enables test-time augmentation (TTA) for predictions, potentially improving detection robustness at the cost of inference speed. | -| `agnostic_nms` | `bool` | `False` | Enables class-agnostic Non-Maximum Suppression (NMS), which merges overlapping boxes of different classes. Useful in multi-class detection scenarios where class overlap is common. | -| `classes` | `list[int]` | `None` | Filters predictions to a set of class IDs. Only detections belonging to the specified classes will be returned. Useful for focusing on relevant objects in multi-class detection tasks. | -| `retina_masks` | `bool` | `False` | Uses high-resolution segmentation masks if available in the model. This can enhance mask quality for segmentation tasks, providing finer detail. | -| `embed` | `list[int]` | `None` | Specifies the layers from which to extract feature vectors or embeddings. Useful for downstream tasks like clustering or similarity search. | - -Visualization arguments: - -| Argument | Type | Default | Description | -|---------------|---------------|---------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `show` | `bool` | `False` | If `True`, displays the annotated images or videos in a window. Useful for immediate visual feedback during development or testing. | -| `save` | `bool` | `False` | Enables saving of the annotated images or videos to file. Useful for documentation, further analysis, or sharing results. | -| `save_frames` | `bool` | `False` | When processing videos, saves individual frames as images. Useful for extracting specific frames or for detailed frame-by-frame analysis. | -| `save_txt` | `bool` | `False` | Saves detection results in a text file, following the format `[class] [x_center] [y_center] [width] [height] [confidence]`. Useful for integration with other analysis tools. | -| `save_conf` | `bool` | `False` | Includes confidence scores in the saved text files. Enhances the detail available for post-processing and analysis. | -| `save_crop` | `bool` | `False` | Saves cropped images of detections. Useful for dataset augmentation, analysis, or creating focused datasets for specific objects. | -| `show_labels` | `bool` | `True` | Displays labels for each detection in the visual output. Provides immediate understanding of detected objects. | -| `show_conf` | `bool` | `True` | Displays the confidence score for each detection alongside the label. Gives insight into the model's certainty for each detection. | -| `show_boxes` | `bool` | `True` | Draws bounding boxes around detected objects. Essential for visual identification and location of objects in images or video frames. | -| `line_width` | `None or int` | `None` | Specifies the line width of bounding boxes. If `None`, the line width is automatically adjusted based on the image size. Provides visual customization for clarity. | - -## Image and Video Formats - -YOLOv8 supports various image and video formats, as specified in [ultralytics/data/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/utils.py). See the tables below for the valid suffixes and example predict commands. - -### Images - -The below table contains valid Ultralytics image formats. - -| Image Suffixes | Example Predict Command | Reference | -|----------------|----------------------------------|-------------------------------------------------------------------------------| -| `.bmp` | `yolo predict source=image.bmp` | [Microsoft BMP File Format](https://en.wikipedia.org/wiki/BMP_file_format) | -| `.dng` | `yolo predict source=image.dng` | [Adobe DNG](https://www.adobe.com/products/photoshop/extend.displayTab2.html) | -| `.jpeg` | `yolo predict source=image.jpeg` | [JPEG](https://en.wikipedia.org/wiki/JPEG) | -| `.jpg` | `yolo predict source=image.jpg` | [JPEG](https://en.wikipedia.org/wiki/JPEG) | -| `.mpo` | `yolo predict source=image.mpo` | [Multi Picture Object](https://fileinfo.com/extension/mpo) | -| `.png` | `yolo predict source=image.png` | [Portable Network Graphics](https://en.wikipedia.org/wiki/PNG) | -| `.tif` | `yolo predict source=image.tif` | [Tag Image File Format](https://en.wikipedia.org/wiki/TIFF) | -| `.tiff` | `yolo predict source=image.tiff` | [Tag Image File Format](https://en.wikipedia.org/wiki/TIFF) | -| `.webp` | `yolo predict source=image.webp` | [WebP](https://en.wikipedia.org/wiki/WebP) | -| `.pfm` | `yolo predict source=image.pfm` | [Portable FloatMap](https://en.wikipedia.org/wiki/Netpbm#File_formats) | - -### Videos - -The below table contains valid Ultralytics video formats. - -| Video Suffixes | Example Predict Command | Reference | -|----------------|----------------------------------|----------------------------------------------------------------------------------| -| `.asf` | `yolo predict source=video.asf` | [Advanced Systems Format](https://en.wikipedia.org/wiki/Advanced_Systems_Format) | -| `.avi` | `yolo predict source=video.avi` | [Audio Video Interleave](https://en.wikipedia.org/wiki/Audio_Video_Interleave) | -| `.gif` | `yolo predict source=video.gif` | [Graphics Interchange Format](https://en.wikipedia.org/wiki/GIF) | -| `.m4v` | `yolo predict source=video.m4v` | [MPEG-4 Part 14](https://en.wikipedia.org/wiki/M4V) | -| `.mkv` | `yolo predict source=video.mkv` | [Matroska](https://en.wikipedia.org/wiki/Matroska) | -| `.mov` | `yolo predict source=video.mov` | [QuickTime File Format](https://en.wikipedia.org/wiki/QuickTime_File_Format) | -| `.mp4` | `yolo predict source=video.mp4` | [MPEG-4 Part 14 - Wikipedia](https://en.wikipedia.org/wiki/MPEG-4_Part_14) | -| `.mpeg` | `yolo predict source=video.mpeg` | [MPEG-1 Part 2](https://en.wikipedia.org/wiki/MPEG-1) | -| `.mpg` | `yolo predict source=video.mpg` | [MPEG-1 Part 2](https://en.wikipedia.org/wiki/MPEG-1) | -| `.ts` | `yolo predict source=video.ts` | [MPEG Transport Stream](https://en.wikipedia.org/wiki/MPEG_transport_stream) | -| `.wmv` | `yolo predict source=video.wmv` | [Windows Media Video](https://en.wikipedia.org/wiki/Windows_Media_Video) | -| `.webm` | `yolo predict source=video.webm` | [WebM Project](https://en.wikipedia.org/wiki/WebM) | - -## Working with Results - -All Ultralytics `predict()` calls will return a list of `Results` objects: - -!!! Example "Results" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Run inference on an image - results = model('bus.jpg') # list of 1 Results object - results = model(['bus.jpg', 'zidane.jpg']) # list of 2 Results objects - ``` - -`Results` objects have the following attributes: - -| Attribute | Type | Description | -|--------------|-----------------------|------------------------------------------------------------------------------------------| -| `orig_img` | `numpy.ndarray` | The original image as a numpy array. | -| `orig_shape` | `tuple` | The original image shape in (height, width) format. | -| `boxes` | `Boxes, optional` | A Boxes object containing the detection bounding boxes. | -| `masks` | `Masks, optional` | A Masks object containing the detection masks. | -| `probs` | `Probs, optional` | A Probs object containing probabilities of each class for classification task. | -| `keypoints` | `Keypoints, optional` | A Keypoints object containing detected keypoints for each object. | -| `obb` | `OBB, optional` | An OBB object containing oriented bounding boxes. | -| `speed` | `dict` | A dictionary of preprocess, inference, and postprocess speeds in milliseconds per image. | -| `names` | `dict` | A dictionary of class names. | -| `path` | `str` | The path to the image file. | - -`Results` objects have the following methods: - -| Method | Return Type | Description | -|---------------|-----------------|-------------------------------------------------------------------------------------| -| `update()` | `None` | Update the boxes, masks, and probs attributes of the Results object. | -| `cpu()` | `Results` | Return a copy of the Results object with all tensors on CPU memory. | -| `numpy()` | `Results` | Return a copy of the Results object with all tensors as numpy arrays. | -| `cuda()` | `Results` | Return a copy of the Results object with all tensors on GPU memory. | -| `to()` | `Results` | Return a copy of the Results object with tensors on the specified device and dtype. | -| `new()` | `Results` | Return a new Results object with the same image, path, and names. | -| `plot()` | `numpy.ndarray` | Plots the detection results. Returns a numpy array of the annotated image. | -| `show()` | `None` | Show annotated results to screen. | -| `save()` | `None` | Save annotated results to file. | -| `verbose()` | `str` | Return log string for each task. | -| `save_txt()` | `None` | Save predictions into a txt file. | -| `save_crop()` | `None` | Save cropped predictions to `save_dir/cls/file_name.jpg`. | -| `tojson()` | `str` | Convert the object to JSON format. | - -For more details see the [`Results` class documentation](../reference/engine/results.md). - -### Boxes - -`Boxes` object can be used to index, manipulate, and convert bounding boxes to different formats. - -!!! Example "Boxes" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Run inference on an image - results = model('bus.jpg') # results list - - # View results - for r in results: - print(r.boxes) # print the Boxes object containing the detection bounding boxes - ``` - -Here is a table for the `Boxes` class methods and properties, including their name, type, and description: - -| Name | Type | Description | -|-----------|---------------------------|--------------------------------------------------------------------| -| `cpu()` | Method | Move the object to CPU memory. | -| `numpy()` | Method | Convert the object to a numpy array. | -| `cuda()` | Method | Move the object to CUDA memory. | -| `to()` | Method | Move the object to the specified device. | -| `xyxy` | Property (`torch.Tensor`) | Return the boxes in xyxy format. | -| `conf` | Property (`torch.Tensor`) | Return the confidence values of the boxes. | -| `cls` | Property (`torch.Tensor`) | Return the class values of the boxes. | -| `id` | Property (`torch.Tensor`) | Return the track IDs of the boxes (if available). | -| `xywh` | Property (`torch.Tensor`) | Return the boxes in xywh format. | -| `xyxyn` | Property (`torch.Tensor`) | Return the boxes in xyxy format normalized by original image size. | -| `xywhn` | Property (`torch.Tensor`) | Return the boxes in xywh format normalized by original image size. | - -For more details see the [`Boxes` class documentation](../reference/engine/results.md#ultralytics.engine.results.Boxes). - -### Masks - -`Masks` object can be used index, manipulate and convert masks to segments. - -!!! Example "Masks" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n-seg Segment model - model = YOLO('yolov8n-seg.pt') - - # Run inference on an image - results = model('bus.jpg') # results list - - # View results - for r in results: - print(r.masks) # print the Masks object containing the detected instance masks - ``` - -Here is a table for the `Masks` class methods and properties, including their name, type, and description: - -| Name | Type | Description | -|-----------|---------------------------|-----------------------------------------------------------------| -| `cpu()` | Method | Returns the masks tensor on CPU memory. | -| `numpy()` | Method | Returns the masks tensor as a numpy array. | -| `cuda()` | Method | Returns the masks tensor on GPU memory. | -| `to()` | Method | Returns the masks tensor with the specified device and dtype. | -| `xyn` | Property (`torch.Tensor`) | A list of normalized segments represented as tensors. | -| `xy` | Property (`torch.Tensor`) | A list of segments in pixel coordinates represented as tensors. | - -For more details see the [`Masks` class documentation](../reference/engine/results.md#ultralytics.engine.results.Masks). - -### Keypoints - -`Keypoints` object can be used index, manipulate and normalize coordinates. - -!!! Example "Keypoints" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n-pose Pose model - model = YOLO('yolov8n-pose.pt') - - # Run inference on an image - results = model('bus.jpg') # results list - - # View results - for r in results: - print(r.keypoints) # print the Keypoints object containing the detected keypoints - ``` - -Here is a table for the `Keypoints` class methods and properties, including their name, type, and description: - -| Name | Type | Description | -|-----------|---------------------------|-------------------------------------------------------------------| -| `cpu()` | Method | Returns the keypoints tensor on CPU memory. | -| `numpy()` | Method | Returns the keypoints tensor as a numpy array. | -| `cuda()` | Method | Returns the keypoints tensor on GPU memory. | -| `to()` | Method | Returns the keypoints tensor with the specified device and dtype. | -| `xyn` | Property (`torch.Tensor`) | A list of normalized keypoints represented as tensors. | -| `xy` | Property (`torch.Tensor`) | A list of keypoints in pixel coordinates represented as tensors. | -| `conf` | Property (`torch.Tensor`) | Returns confidence values of keypoints if available, else None. | - -For more details see the [`Keypoints` class documentation](../reference/engine/results.md#ultralytics.engine.results.Keypoints). - -### Probs - -`Probs` object can be used index, get `top1` and `top5` indices and scores of classification. - -!!! Example "Probs" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n-cls Classify model - model = YOLO('yolov8n-cls.pt') - - # Run inference on an image - results = model('bus.jpg') # results list - - # View results - for r in results: - print(r.probs) # print the Probs object containing the detected class probabilities - ``` - -Here's a table summarizing the methods and properties for the `Probs` class: - -| Name | Type | Description | -|------------|---------------------------|-------------------------------------------------------------------------| -| `cpu()` | Method | Returns a copy of the probs tensor on CPU memory. | -| `numpy()` | Method | Returns a copy of the probs tensor as a numpy array. | -| `cuda()` | Method | Returns a copy of the probs tensor on GPU memory. | -| `to()` | Method | Returns a copy of the probs tensor with the specified device and dtype. | -| `top1` | Property (`int`) | Index of the top 1 class. | -| `top5` | Property (`list[int]`) | Indices of the top 5 classes. | -| `top1conf` | Property (`torch.Tensor`) | Confidence of the top 1 class. | -| `top5conf` | Property (`torch.Tensor`) | Confidences of the top 5 classes. | - -For more details see the [`Probs` class documentation](../reference/engine/results.md#ultralytics.engine.results.Probs). - -### OBB - -`OBB` object can be used to index, manipulate, and convert oriented bounding boxes to different formats. - -!!! Example "OBB" - - ```python - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n-obb.pt') - - # Run inference on an image - results = model('bus.jpg') # results list - - # View results - for r in results: - print(r.obb) # print the OBB object containing the oriented detection bounding boxes - ``` - -Here is a table for the `OBB` class methods and properties, including their name, type, and description: - -| Name | Type | Description | -|-------------|---------------------------|-----------------------------------------------------------------------| -| `cpu()` | Method | Move the object to CPU memory. | -| `numpy()` | Method | Convert the object to a numpy array. | -| `cuda()` | Method | Move the object to CUDA memory. | -| `to()` | Method | Move the object to the specified device. | -| `conf` | Property (`torch.Tensor`) | Return the confidence values of the boxes. | -| `cls` | Property (`torch.Tensor`) | Return the class values of the boxes. | -| `id` | Property (`torch.Tensor`) | Return the track IDs of the boxes (if available). | -| `xyxy` | Property (`torch.Tensor`) | Return the horizontal boxes in xyxy format. | -| `xywhr` | Property (`torch.Tensor`) | Return the rotated boxes in xywhr format. | -| `xyxyxyxy` | Property (`torch.Tensor`) | Return the rotated boxes in xyxyxyxy format. | -| `xyxyxyxyn` | Property (`torch.Tensor`) | Return the rotated boxes in xyxyxyxy format normalized by image size. | - -For more details see the [`OBB` class documentation](../reference/engine/results.md#ultralytics.engine.results.OBB). - -## Plotting Results - -The `plot()` method in `Results` objects facilitates visualization of predictions by overlaying detected objects (such as bounding boxes, masks, keypoints, and probabilities) onto the original image. This method returns the annotated image as a NumPy array, allowing for easy display or saving. - -!!! Example "Plotting" - - ```python - from PIL import Image - from ultralytics import YOLO - - # Load a pretrained YOLOv8n model - model = YOLO('yolov8n.pt') - - # Run inference on 'bus.jpg' - results = model(['bus.jpg', 'zidane.jpg']) # results list - - # Visualize the results - for i, r in enumerate(results): - # Plot results image - im_bgr = r.plot() # BGR-order numpy array - im_rgb = Image.fromarray(im_bgr[..., ::-1]) # RGB-order PIL image - - # Show results to screen (in supported environments) - r.show() - - # Save results to disk - r.save(filename=f'results{i}.jpg') - ``` - -### `plot()` Method Parameters - -The `plot()` method supports various arguments to customize the output: - -| Argument | Type | Description | Default | -|--------------|-----------------|----------------------------------------------------------------------------|---------------| -| `conf` | `bool` | Include detection confidence scores. | `True` | -| `line_width` | `float` | Line width of bounding boxes. Scales with image size if `None`. | `None` | -| `font_size` | `float` | Text font size. Scales with image size if `None`. | `None` | -| `font` | `str` | Font name for text annotations. | `'Arial.ttf'` | -| `pil` | `bool` | Return image as a PIL Image object. | `False` | -| `img` | `numpy.ndarray` | Alternative image for plotting. Uses the original image if `None`. | `None` | -| `im_gpu` | `torch.Tensor` | GPU-accelerated image for faster mask plotting. Shape: (1, 3, 640, 640). | `None` | -| `kpt_radius` | `int` | Radius for drawn keypoints. | `5` | -| `kpt_line` | `bool` | Connect keypoints with lines. | `True` | -| `labels` | `bool` | Include class labels in annotations. | `True` | -| `boxes` | `bool` | Overlay bounding boxes on the image. | `True` | -| `masks` | `bool` | Overlay masks on the image. | `True` | -| `probs` | `bool` | Include classification probabilities. | `True` | -| `show` | `bool` | Display the annotated image directly using the default image viewer. | `False` | -| `save` | `bool` | Save the annotated image to a file specified by `filename`. | `False` | -| `filename` | `str` | Path and name of the file to save the annotated image if `save` is `True`. | `None` | - -## Thread-Safe Inference - -Ensuring thread safety during inference is crucial when you are running multiple YOLO models in parallel across different threads. Thread-safe inference guarantees that each thread's predictions are isolated and do not interfere with one another, avoiding race conditions and ensuring consistent and reliable outputs. - -When using YOLO models in a multi-threaded application, it's important to instantiate separate model objects for each thread or employ thread-local storage to prevent conflicts: - -!!! Example "Thread-Safe Inference" - - Instantiate a single model inside each thread for thread-safe inference: - ```python - from ultralytics import YOLO - from threading import Thread - - def thread_safe_predict(image_path): - # Instantiate a new model inside the thread - local_model = YOLO("yolov8n.pt") - results = local_model.predict(image_path) - # Process results - - - # Starting threads that each have their own model instance - Thread(target=thread_safe_predict, args=("image1.jpg",)).start() - Thread(target=thread_safe_predict, args=("image2.jpg",)).start() - ``` - -For an in-depth look at thread-safe inference with YOLO models and step-by-step instructions, please refer to our [YOLO Thread-Safe Inference Guide](../guides/yolo-thread-safe-inference.md). This guide will provide you with all the necessary information to avoid common pitfalls and ensure that your multi-threaded inference runs smoothly. - -## Streaming Source `for`-loop - -Here's a Python script using OpenCV (`cv2`) and YOLOv8 to run inference on video frames. This script assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`). - -!!! Example "Streaming for-loop" - - ```python - import cv2 - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Open the video file - video_path = "path/to/your/video/file.mp4" - cap = cv2.VideoCapture(video_path) - - # Loop through the video frames - while cap.isOpened(): - # Read a frame from the video - success, frame = cap.read() - - if success: - # Run YOLOv8 inference on the frame - results = model(frame) - - # Visualize the results on the frame - annotated_frame = results[0].plot() - - # Display the annotated frame - cv2.imshow("YOLOv8 Inference", annotated_frame) - - # Break the loop if 'q' is pressed - if cv2.waitKey(1) & 0xFF == ord("q"): - break - else: - # Break the loop if the end of the video is reached - break - - # Release the video capture object and close the display window - cap.release() - cv2.destroyAllWindows() - ``` - -This script will run predictions on each frame of the video, visualize the results, and display them in a window. The loop can be exited by pressing 'q'. - -[car spare parts]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/a0f802a8-0776-44cf-8f17-93974a4a28a1 - -[football player detect]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/7d320e1f-fc57-4d7f-a691-78ee579c3442 - -[human fall detect]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/86437c4a-3227-4eee-90ef-9efb697bdb43 diff --git a/ultralytics-main/docs/en/modes/track.md b/ultralytics-main/docs/en/modes/track.md deleted file mode 100644 index 22e9c0a..0000000 --- a/ultralytics-main/docs/en/modes/track.md +++ /dev/null @@ -1,360 +0,0 @@ ---- -comments: true -description: Learn how to use Ultralytics YOLO for object tracking in video streams. Guides to use different trackers and customise tracker configurations. -keywords: Ultralytics, YOLO, object tracking, video streams, BoT-SORT, ByteTrack, Python guide, CLI guide ---- - -# Multi-Object Tracking with Ultralytics YOLO - -Multi-object tracking examples - -Object tracking in the realm of video analytics is a critical task that not only identifies the location and class of objects within the frame but also maintains a unique ID for each detected object as the video progresses. The applications are limitless—ranging from surveillance and security to real-time sports analytics. - -## Why Choose Ultralytics YOLO for Object Tracking? - -The output from Ultralytics trackers is consistent with standard object detection but has the added value of object IDs. This makes it easy to track objects in video streams and perform subsequent analytics. Here's why you should consider using Ultralytics YOLO for your object tracking needs: - -- **Efficiency:** Process video streams in real-time without compromising accuracy. -- **Flexibility:** Supports multiple tracking algorithms and configurations. -- **Ease of Use:** Simple Python API and CLI options for quick integration and deployment. -- **Customizability:** Easy to use with custom trained YOLO models, allowing integration into domain-specific applications. - -

-
- -
- Watch: Object Detection and Tracking with Ultralytics YOLOv8. -

- -## Real-world Applications - -| Transportation | Retail | Aquaculture | -|:----------------------------------:|:--------------------------------:|:----------------------------:| -| ![Vehicle Tracking][vehicle track] | ![People Tracking][people track] | ![Fish Tracking][fish track] | -| Vehicle Tracking | People Tracking | Fish Tracking | - -## Features at a Glance - -Ultralytics YOLO extends its object detection features to provide robust and versatile object tracking: - -- **Real-Time Tracking:** Seamlessly track objects in high-frame-rate videos. -- **Multiple Tracker Support:** Choose from a variety of established tracking algorithms. -- **Customizable Tracker Configurations:** Tailor the tracking algorithm to meet specific requirements by adjusting various parameters. - -## Available Trackers - -Ultralytics YOLO supports the following tracking algorithms. They can be enabled by passing the relevant YAML configuration file such as `tracker=tracker_type.yaml`: - -- [BoT-SORT](https://github.com/NirAharon/BoT-SORT) - Use `botsort.yaml` to enable this tracker. -- [ByteTrack](https://github.com/ifzhang/ByteTrack) - Use `bytetrack.yaml` to enable this tracker. - -The default tracker is BoT-SORT. - -## Tracking - -To run the tracker on video streams, use a trained Detect, Segment or Pose model such as YOLOv8n, YOLOv8n-seg and YOLOv8n-pose. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load an official or custom model - model = YOLO('yolov8n.pt') # Load an official Detect model - model = YOLO('yolov8n-seg.pt') # Load an official Segment model - model = YOLO('yolov8n-pose.pt') # Load an official Pose model - model = YOLO('path/to/best.pt') # Load a custom trained model - - # Perform tracking with the model - results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True) # Tracking with default tracker - results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml") # Tracking with ByteTrack tracker - ``` - - === "CLI" - - ```bash - # Perform tracking with various models using the command line interface - yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" # Official Detect model - yolo track model=yolov8n-seg.pt source="https://youtu.be/LNwODJXcvt4" # Official Segment model - yolo track model=yolov8n-pose.pt source="https://youtu.be/LNwODJXcvt4" # Official Pose model - yolo track model=path/to/best.pt source="https://youtu.be/LNwODJXcvt4" # Custom trained model - - # Track using ByteTrack tracker - yolo track model=path/to/best.pt tracker="bytetrack.yaml" - ``` - -As can be seen in the above usage, tracking is available for all Detect, Segment and Pose models run on videos or streaming sources. - -## Configuration - -### Tracking Arguments - -Tracking configuration shares properties with Predict mode, such as `conf`, `iou`, and `show`. For further configurations, refer to the [Predict](../modes/predict.md#inference-arguments) model page. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Configure the tracking parameters and run the tracker - model = YOLO('yolov8n.pt') - results = model.track(source="https://youtu.be/LNwODJXcvt4", conf=0.3, iou=0.5, show=True) - ``` - - === "CLI" - - ```bash - # Configure tracking parameters and run the tracker using the command line interface - yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" conf=0.3, iou=0.5 show - ``` - -### Tracker Selection - -Ultralytics also allows you to use a modified tracker configuration file. To do this, simply make a copy of a tracker config file (for example, `custom_tracker.yaml`) from [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) and modify any configurations (except the `tracker_type`) as per your needs. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load the model and run the tracker with a custom configuration file - model = YOLO('yolov8n.pt') - results = model.track(source="https://youtu.be/LNwODJXcvt4", tracker='custom_tracker.yaml') - ``` - - === "CLI" - - ```bash - # Load the model and run the tracker with a custom configuration file using the command line interface - yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" tracker='custom_tracker.yaml' - ``` - -For a comprehensive list of tracking arguments, refer to the [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) page. - -## Python Examples - -### Persisting Tracks Loop - -Here is a Python script using OpenCV (`cv2`) and YOLOv8 to run object tracking on video frames. This script still assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`). The `persist=True` argument tells the tracker that the current image or frame is the next in a sequence and to expect tracks from the previous image in the current image. - -!!! Example "Streaming for-loop with tracking" - - ```python - import cv2 - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Open the video file - video_path = "path/to/video.mp4" - cap = cv2.VideoCapture(video_path) - - # Loop through the video frames - while cap.isOpened(): - # Read a frame from the video - success, frame = cap.read() - - if success: - # Run YOLOv8 tracking on the frame, persisting tracks between frames - results = model.track(frame, persist=True) - - # Visualize the results on the frame - annotated_frame = results[0].plot() - - # Display the annotated frame - cv2.imshow("YOLOv8 Tracking", annotated_frame) - - # Break the loop if 'q' is pressed - if cv2.waitKey(1) & 0xFF == ord("q"): - break - else: - # Break the loop if the end of the video is reached - break - - # Release the video capture object and close the display window - cap.release() - cv2.destroyAllWindows() - ``` - -Please note the change from `model(frame)` to `model.track(frame)`, which enables object tracking instead of simple detection. This modified script will run the tracker on each frame of the video, visualize the results, and display them in a window. The loop can be exited by pressing 'q'. - -### Plotting Tracks Over Time - -Visualizing object tracks over consecutive frames can provide valuable insights into the movement patterns and behavior of detected objects within a video. With Ultralytics YOLOv8, plotting these tracks is a seamless and efficient process. - -In the following example, we demonstrate how to utilize YOLOv8's tracking capabilities to plot the movement of detected objects across multiple video frames. This script involves opening a video file, reading it frame by frame, and utilizing the YOLO model to identify and track various objects. By retaining the center points of the detected bounding boxes and connecting them, we can draw lines that represent the paths followed by the tracked objects. - -!!! Example "Plotting tracks over multiple video frames" - - ```python - from collections import defaultdict - - import cv2 - import numpy as np - - from ultralytics import YOLO - - # Load the YOLOv8 model - model = YOLO('yolov8n.pt') - - # Open the video file - video_path = "path/to/video.mp4" - cap = cv2.VideoCapture(video_path) - - # Store the track history - track_history = defaultdict(lambda: []) - - # Loop through the video frames - while cap.isOpened(): - # Read a frame from the video - success, frame = cap.read() - - if success: - # Run YOLOv8 tracking on the frame, persisting tracks between frames - results = model.track(frame, persist=True) - - # Get the boxes and track IDs - boxes = results[0].boxes.xywh.cpu() - track_ids = results[0].boxes.id.int().cpu().tolist() - - # Visualize the results on the frame - annotated_frame = results[0].plot() - - # Plot the tracks - for box, track_id in zip(boxes, track_ids): - x, y, w, h = box - track = track_history[track_id] - track.append((float(x), float(y))) # x, y center point - if len(track) > 30: # retain 90 tracks for 90 frames - track.pop(0) - - # Draw the tracking lines - points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10) - - # Display the annotated frame - cv2.imshow("YOLOv8 Tracking", annotated_frame) - - # Break the loop if 'q' is pressed - if cv2.waitKey(1) & 0xFF == ord("q"): - break - else: - # Break the loop if the end of the video is reached - break - - # Release the video capture object and close the display window - cap.release() - cv2.destroyAllWindows() - ``` - -### Multithreaded Tracking - -Multithreaded tracking provides the capability to run object tracking on multiple video streams simultaneously. This is particularly useful when handling multiple video inputs, such as from multiple surveillance cameras, where concurrent processing can greatly enhance efficiency and performance. - -In the provided Python script, we make use of Python's `threading` module to run multiple instances of the tracker concurrently. Each thread is responsible for running the tracker on one video file, and all the threads run simultaneously in the background. - -To ensure that each thread receives the correct parameters (the video file, the model to use and the file index), we define a function `run_tracker_in_thread` that accepts these parameters and contains the main tracking loop. This function reads the video frame by frame, runs the tracker, and displays the results. - -Two different models are used in this example: `yolov8n.pt` and `yolov8n-seg.pt`, each tracking objects in a different video file. The video files are specified in `video_file1` and `video_file2`. - -The `daemon=True` parameter in `threading.Thread` means that these threads will be closed as soon as the main program finishes. We then start the threads with `start()` and use `join()` to make the main thread wait until both tracker threads have finished. - -Finally, after all threads have completed their task, the windows displaying the results are closed using `cv2.destroyAllWindows()`. - -!!! Example "Streaming for-loop with tracking" - - ```python - import threading - import cv2 - from ultralytics import YOLO - - - def run_tracker_in_thread(filename, model, file_index): - """ - Runs a video file or webcam stream concurrently with the YOLOv8 model using threading. - - This function captures video frames from a given file or camera source and utilizes the YOLOv8 model for object - tracking. The function runs in its own thread for concurrent processing. - - Args: - filename (str): The path to the video file or the identifier for the webcam/external camera source. - model (obj): The YOLOv8 model object. - file_index (int): An index to uniquely identify the file being processed, used for display purposes. - - Note: - Press 'q' to quit the video display window. - """ - video = cv2.VideoCapture(filename) # Read the video file - - while True: - ret, frame = video.read() # Read the video frames - - # Exit the loop if no more frames in either video - if not ret: - break - - # Track objects in frames if available - results = model.track(frame, persist=True) - res_plotted = results[0].plot() - cv2.imshow(f"Tracking_Stream_{file_index}", res_plotted) - - key = cv2.waitKey(1) - if key == ord('q'): - break - - # Release video sources - video.release() - - - # Load the models - model1 = YOLO('yolov8n.pt') - model2 = YOLO('yolov8n-seg.pt') - - # Define the video files for the trackers - video_file1 = "path/to/video1.mp4" # Path to video file, 0 for webcam - video_file2 = 0 # Path to video file, 0 for webcam, 1 for external camera - - # Create the tracker threads - tracker_thread1 = threading.Thread(target=run_tracker_in_thread, args=(video_file1, model1, 1), daemon=True) - tracker_thread2 = threading.Thread(target=run_tracker_in_thread, args=(video_file2, model2, 2), daemon=True) - - # Start the tracker threads - tracker_thread1.start() - tracker_thread2.start() - - # Wait for the tracker threads to finish - tracker_thread1.join() - tracker_thread2.join() - - # Clean up and close windows - cv2.destroyAllWindows() - ``` - -This example can easily be extended to handle more video files and models by creating more threads and applying the same methodology. - -## Contribute New Trackers - -Are you proficient in multi-object tracking and have successfully implemented or adapted a tracking algorithm with Ultralytics YOLO? We invite you to contribute to our Trackers section in [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers)! Your real-world applications and solutions could be invaluable for users working on tracking tasks. - -By contributing to this section, you help expand the scope of tracking solutions available within the Ultralytics YOLO framework, adding another layer of functionality and utility for the community. - -To initiate your contribution, please refer to our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for comprehensive instructions on submitting a Pull Request (PR) 🛠️. We are excited to see what you bring to the table! - -Together, let's enhance the tracking capabilities of the Ultralytics YOLO ecosystem 🙏! - -[fish track]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/a5146d0f-bfa8-4e0a-b7df-3c1446cd8142 - -[people track]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/93bb4ee2-77a0-4e4e-8eb6-eb8f527f0527 - -[vehicle track]: https://github.com/RizwanMunawar/ultralytics/assets/62513924/ee6e6038-383b-4f21-ac29-b2a1c7d386ab diff --git a/ultralytics-main/docs/en/modes/train.md b/ultralytics-main/docs/en/modes/train.md deleted file mode 100644 index 820ff4b..0000000 --- a/ultralytics-main/docs/en/modes/train.md +++ /dev/null @@ -1,328 +0,0 @@ ---- -comments: true -description: Step-by-step guide to train YOLOv8 models with Ultralytics YOLO including examples of single-GPU and multi-GPU training -keywords: Ultralytics, YOLOv8, YOLO, object detection, train mode, custom dataset, GPU training, multi-GPU, hyperparameters, CLI examples, Python examples ---- - -# Model Training with Ultralytics YOLO - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -Training a deep learning model involves feeding it data and adjusting its parameters so that it can make accurate predictions. Train mode in Ultralytics YOLOv8 is engineered for effective and efficient training of object detection models, fully utilizing modern hardware capabilities. This guide aims to cover all the details you need to get started with training your own models using YOLOv8's robust set of features. - -

-
- -
- Watch: How to Train a YOLOv8 model on Your Custom Dataset in Google Colab. -

- -## Why Choose Ultralytics YOLO for Training? - -Here are some compelling reasons to opt for YOLOv8's Train mode: - -- **Efficiency:** Make the most out of your hardware, whether you're on a single-GPU setup or scaling across multiple GPUs. -- **Versatility:** Train on custom datasets in addition to readily available ones like COCO, VOC, and ImageNet. -- **User-Friendly:** Simple yet powerful CLI and Python interfaces for a straightforward training experience. -- **Hyperparameter Flexibility:** A broad range of customizable hyperparameters to fine-tune model performance. - -### Key Features of Train Mode - -The following are some notable features of YOLOv8's Train mode: - -- **Automatic Dataset Download:** Standard datasets like COCO, VOC, and ImageNet are downloaded automatically on first use. -- **Multi-GPU Support:** Scale your training efforts seamlessly across multiple GPUs to expedite the process. -- **Hyperparameter Configuration:** The option to modify hyperparameters through YAML configuration files or CLI arguments. -- **Visualization and Monitoring:** Real-time tracking of training metrics and visualization of the learning process for better insights. - -!!! Tip "Tip" - - * YOLOv8 datasets like COCO, VOC, ImageNet and many others automatically download on first use, i.e. `yolo train data=coco.yaml` - -## Usage Examples - -Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. The training device can be specified using the `device` argument. If no argument is passed GPU `device=0` will be used if available, otherwise `device=cpu` will be used. See Arguments section below for a full list of training arguments. - -!!! Example "Single-GPU and CPU Training Example" - - Device is determined automatically. If a GPU is available then it will be used, otherwise training will start on CPU. - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.yaml') # build a new model from YAML - model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='coco128.yaml', epochs=100, imgsz=640) - ``` - - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo detect train data=coco128.yaml model=yolov8n.yaml epochs=100 imgsz=640 - - # Start training from a pretrained *.pt model - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo detect train data=coco128.yaml model=yolov8n.yaml pretrained=yolov8n.pt epochs=100 imgsz=640 - ``` - -### Multi-GPU Training - -Multi-GPU training allows for more efficient utilization of available hardware resources by distributing the training load across multiple GPUs. This feature is available through both the Python API and the command-line interface. To enable multi-GPU training, specify the GPU device IDs you wish to use. - -!!! Example "Multi-GPU Training Example" - - To train with 2 GPUs, CUDA devices 0 and 1 use the following commands. Expand to additional GPUs as required. - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training) - - # Train the model with 2 GPUs - results = model.train(data='coco128.yaml', epochs=100, imgsz=640, device=[0, 1]) - ``` - - === "CLI" - - ```bash - # Start training from a pretrained *.pt model using GPUs 0 and 1 - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640 device=0,1 - ``` - -### Apple M1 and M2 MPS Training - -With the support for Apple M1 and M2 chips integrated in the Ultralytics YOLO models, it's now possible to train your models on devices utilizing the powerful Metal Performance Shaders (MPS) framework. The MPS offers a high-performance way of executing computation and image processing tasks on Apple's custom silicon. - -To enable training on Apple M1 and M2 chips, you should specify 'mps' as your device when initiating the training process. Below is an example of how you could do this in Python and via the command line: - -!!! Example "MPS Training Example" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training) - - # Train the model with 2 GPUs - results = model.train(data='coco128.yaml', epochs=100, imgsz=640, device='mps') - ``` - - === "CLI" - - ```bash - # Start training from a pretrained *.pt model using GPUs 0 and 1 - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640 device=mps - ``` - -While leveraging the computational power of the M1/M2 chips, this enables more efficient processing of the training tasks. For more detailed guidance and advanced configuration options, please refer to the [PyTorch MPS documentation](https://pytorch.org/docs/stable/notes/mps.html). - -### Resuming Interrupted Trainings - -Resuming training from a previously saved state is a crucial feature when working with deep learning models. This can come in handy in various scenarios, like when the training process has been unexpectedly interrupted, or when you wish to continue training a model with new data or for more epochs. - -When training is resumed, Ultralytics YOLO loads the weights from the last saved model and also restores the optimizer state, learning rate scheduler, and the epoch number. This allows you to continue the training process seamlessly from where it was left off. - -You can easily resume training in Ultralytics YOLO by setting the `resume` argument to `True` when calling the `train` method, and specifying the path to the `.pt` file containing the partially trained model weights. - -Below is an example of how to resume an interrupted training using Python and via the command line: - -!!! Example "Resume Training Example" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('path/to/last.pt') # load a partially trained model - - # Resume training - results = model.train(resume=True) - ``` - - === "CLI" - - ```bash - # Resume an interrupted training - yolo train resume model=path/to/last.pt - ``` - -By setting `resume=True`, the `train` function will continue training from where it left off, using the state stored in the 'path/to/last.pt' file. If the `resume` argument is omitted or set to `False`, the `train` function will start a new training session. - -Remember that checkpoints are saved at the end of every epoch by default, or at fixed interval using the `save_period` argument, so you must complete at least 1 epoch to resume a training run. - -## Train Settings - -The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and accuracy. Key training settings include batch size, learning rate, momentum, and weight decay. Additionally, the choice of optimizer, loss function, and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. - -| Argument | Default | Description | -|-------------------|----------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `model` | `None` | Specifies the model file for training. Accepts a path to either a `.pt` pretrained model or a `.yaml` configuration file. Essential for defining the model structure or initializing weights. | -| `data` | `None` | Path to the dataset configuration file (e.g., `coco128.yaml`). This file contains dataset-specific parameters, including paths to training and validation data, class names, and number of classes. | -| `epochs` | `100` | Total number of training epochs. Each epoch represents a full pass over the entire dataset. Adjusting this value can affect training duration and model performance. | -| `time` | `None` | Maximum training time in hours. If set, this overrides the `epochs` argument, allowing training to automatically stop after the specified duration. Useful for time-constrained training scenarios. | -| `patience` | `100` | Number of epochs to wait without improvement in validation metrics before early stopping the training. Helps prevent overfitting by stopping training when performance plateaus. | -| `batch` | `16` | Batch size for training, indicating how many images are processed before the model's internal parameters are updated. AutoBatch (`batch=-1`) dynamically adjusts the batch size based on GPU memory availability. | -| `imgsz` | `640` | Target image size for training. All images are resized to this dimension before being fed into the model. Affects model accuracy and computational complexity. | -| `save` | `True` | Enables saving of training checkpoints and final model weights. Useful for resuming training or model deployment. | -| `save_period` | `-1` | Frequency of saving model checkpoints, specified in epochs. A value of -1 disables this feature. Useful for saving interim models during long training sessions. | -| `cache` | `False` | Enables caching of dataset images in memory (`True`/`ram`), on disk (`disk`), or disables it (`False`). Improves training speed by reducing disk I/O at the cost of increased memory usage. | -| `device` | `None` | Specifies the computational device(s) for training: a single GPU (`device=0`), multiple GPUs (`device=0,1`), CPU (`device=cpu`), or MPS for Apple silicon (`device=mps`). | -| `workers` | `8` | Number of worker threads for data loading (per `RANK` if Multi-GPU training). Influences the speed of data preprocessing and feeding into the model, especially useful in multi-GPU setups. | -| `project` | `None` | Name of the project directory where training outputs are saved. Allows for organized storage of different experiments. | -| `name` | `None` | Name of the training run. Used for creating a subdirectory within the project folder, where training logs and outputs are stored. | -| `exist_ok` | `False` | If True, allows overwriting of an existing project/name directory. Useful for iterative experimentation without needing to manually clear previous outputs. | -| `pretrained` | `True` | Determines whether to start training from a pretrained model. Can be a boolean value or a string path to a specific model from which to load weights. Enhances training efficiency and model performance. | -| `optimizer` | `'auto'` | Choice of optimizer for training. Options include `SGD`, `Adam`, `AdamW`, `NAdam`, `RAdam`, `RMSProp` etc., or `auto` for automatic selection based on model configuration. Affects convergence speed and stability. | -| `verbose` | `False` | Enables verbose output during training, providing detailed logs and progress updates. Useful for debugging and closely monitoring the training process. | -| `seed` | `0` | Sets the random seed for training, ensuring reproducibility of results across runs with the same configurations. | -| `deterministic` | `True` | Forces deterministic algorithm use, ensuring reproducibility but may affect performance and speed due to the restriction on non-deterministic algorithms. | -| `single_cls` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. | -| `rect` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. | -| `cos_lr` | `False` | Utilizes a cosine learning rate scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. | -| `close_mosaic` | `10` | Disables mosaic data augmentation in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. | -| `resume` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. | -| `amp` | `True` | Enables Automatic Mixed Precision (AMP) training, reducing memory usage and possibly speeding up training with minimal impact on accuracy. | -| `fraction` | `1.0` | Specifies the fraction of the dataset to use for training. Allows for training on a subset of the full dataset, useful for experiments or when resources are limited. | -| `profile` | `False` | Enables profiling of ONNX and TensorRT speeds during training, useful for optimizing model deployment. | -| `freeze` | `None` | Freezes the first N layers of the model or specified layers by index, reducing the number of trainable parameters. Useful for fine-tuning or transfer learning. | -| `lr0` | `0.01` | Initial learning rate (i.e. `SGD=1E-2`, `Adam=1E-3`) . Adjusting this value is crucial for the optimization process, influencing how rapidly model weights are updated. | -| `lrf` | `0.01` | Final learning rate as a fraction of the initial rate = (`lr0 * lrf`), used in conjunction with schedulers to adjust the learning rate over time. | -| `momentum` | `0.937` | Momentum factor for SGD or beta1 for Adam optimizers, influencing the incorporation of past gradients in the current update. | -| `weight_decay` | `0.0005` | L2 regularization term, penalizing large weights to prevent overfitting. | -| `warmup_epochs` | `3.0` | Number of epochs for learning rate warmup, gradually increasing the learning rate from a low value to the initial learning rate to stabilize training early on. | -| `warmup_momentum` | `0.8` | Initial momentum for warmup phase, gradually adjusting to the set momentum over the warmup period. | -| `warmup_bias_lr` | `0.1` | Learning rate for bias parameters during the warmup phase, helping stabilize model training in the initial epochs. | -| `box` | `7.5` | Weight of the box loss component in the loss function, influencing how much emphasis is placed on accurately predicting bounding box coordinates. | -| `cls` | `0.5` | Weight of the classification loss in the total loss function, affecting the importance of correct class prediction relative to other components. | -| `dfl` | `1.5` | Weight of the distribution focal loss, used in certain YOLO versions for fine-grained classification. | -| `pose` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. | -| `kobj` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. | -| `label_smoothing` | `0.0` | Applies label smoothing, softening hard labels to a mix of the target label and a uniform distribution over labels, can improve generalization. | -| `nbs` | `64` | Nominal batch size for normalization of loss. | -| `overlap_mask` | `True` | Determines whether segmentation masks should overlap during training, applicable in instance segmentation tasks. | -| `mask_ratio` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. | -| `dropout` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. | -| `val` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. | -| `plots` | `False` | Generates and saves plots of training and validation metrics, as well as prediction examples, providing visual insights into model performance and learning progression. | - -## Augmentation Settings and Hyperparameters - -Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the training data, helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: - -| Argument | Type | Default | Range | Description | -|----------------|---------|---------------|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `hsv_h` | `float` | `0.015` | `0.0 - 1.0` | Adjusts the hue of the image by a fraction of the color wheel, introducing color variability. Helps the model generalize across different lighting conditions. | -| `hsv_s` | `float` | `0.7` | `0.0 - 1.0` | Alters the saturation of the image by a fraction, affecting the intensity of colors. Useful for simulating different environmental conditions. | -| `hsv_v` | `float` | `0.4` | `0.0 - 1.0` | Modifies the value (brightness) of the image by a fraction, helping the model to perform well under various lighting conditions. | -| `degrees` | `float` | `0.0` | `-180 - +180` | Rotates the image randomly within the specified degree range, improving the model's ability to recognize objects at various orientations. | -| `translate` | `float` | `0.1` | `0.0 - 1.0` | Translates the image horizontally and vertically by a fraction of the image size, aiding in learning to detect partially visible objects. | -| `scale` | `float` | `0.5` | `>=0.0` | Scales the image by a gain factor, simulating objects at different distances from the camera. | -| `shear` | `float` | `0.0` | `-180 - +180` | Shears the image by a specified degree, mimicking the effect of objects being viewed from different angles. | -| `perspective` | `float` | `0.0` | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space. | -| `flipud` | `float` | `0.0` | `0.0 - 1.0` | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics. | -| `fliplr` | `float` | `0.5` | `0.0 - 1.0` | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity. | -| `mosaic` | `float` | `1.0` | `0.0 - 1.0` | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding. | -| `mixup` | `float` | `0.0` | `0.0 - 1.0` | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability. | -| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies objects from one image and pastes them onto another, useful for increasing object instances and learning object occlusion. | -| `auto_augment` | `str` | `randaugment` | - | Automatically applies a predefined augmentation policy (`randaugment`, `autoaugment`, `augmix`), optimizing for classification tasks by diversifying the visual features. | -| `erasing` | `float` | `0.4` | `0.0 - 1.0` | Randomly erases a portion of the image during classification training, encouraging the model to focus on less obvious features for recognition. | - -These settings can be adjusted to meet the specific requirements of the dataset and task at hand. Experimenting with different values can help find the optimal augmentation strategy that leads to the best model performance. - -!!! info - - For more information about training augmentation operations, see the [reference section](../reference/data/augment.md). - -## Logging - -In training a YOLOv8 model, you might find it valuable to keep track of the model's performance over time. This is where logging comes into play. Ultralytics' YOLO provides support for three types of loggers - Comet, ClearML, and TensorBoard. - -To use a logger, select it from the dropdown menu in the code snippet above and run it. The chosen logger will be installed and initialized. - -### Comet - -[Comet](../integrations/comet.md) is a platform that allows data scientists and developers to track, compare, explain and optimize experiments and models. It provides functionalities such as real-time metrics, code diffs, and hyperparameters tracking. - -To use Comet: - -!!! Example - - === "Python" - - ```python - # pip install comet_ml - import comet_ml - - comet_ml.init() - ``` - -Remember to sign in to your Comet account on their website and get your API key. You will need to add this to your environment variables or your script to log your experiments. - -### ClearML - -[ClearML](https://www.clear.ml/) is an open-source platform that automates tracking of experiments and helps with efficient sharing of resources. It is designed to help teams manage, execute, and reproduce their ML work more efficiently. - -To use ClearML: - -!!! Example - - === "Python" - - ```python - # pip install clearml - import clearml - - clearml.browser_login() - ``` - -After running this script, you will need to sign in to your ClearML account on the browser and authenticate your session. - -### TensorBoard - -[TensorBoard](https://www.tensorflow.org/tensorboard) is a visualization toolkit for TensorFlow. It allows you to visualize your TensorFlow graph, plot quantitative metrics about the execution of your graph, and show additional data like images that pass through it. - -To use TensorBoard in [Google Colab](https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb): - -!!! Example - - === "CLI" - - ```bash - load_ext tensorboard - tensorboard --logdir ultralytics/runs # replace with 'runs' directory - ``` - -To use TensorBoard locally run the below command and view results at http://localhost:6006/. - -!!! Example - - === "CLI" - - ```bash - tensorboard --logdir ultralytics/runs # replace with 'runs' directory - ``` - -This will load TensorBoard and direct it to the directory where your training logs are saved. - -After setting up your logger, you can then proceed with your model training. All training metrics will be automatically logged in your chosen platform, and you can access these logs to monitor your model's performance over time, compare different models, and identify areas for improvement. diff --git a/ultralytics-main/docs/en/modes/val.md b/ultralytics-main/docs/en/modes/val.md deleted file mode 100644 index 0c77425..0000000 --- a/ultralytics-main/docs/en/modes/val.md +++ /dev/null @@ -1,128 +0,0 @@ ---- -comments: true -description: Guide for Validating YOLOv8 Models. Learn how to evaluate the performance of your YOLO models using validation settings and metrics with Python and CLI examples. -keywords: Ultralytics, YOLO Docs, YOLOv8, validation, model evaluation, hyperparameters, accuracy, metrics, Python, CLI ---- - -# Model Validation with Ultralytics YOLO - -Ultralytics YOLO ecosystem and integrations - -## Introduction - -Validation is a critical step in the machine learning pipeline, allowing you to assess the quality of your trained models. Val mode in Ultralytics YOLOv8 provides a robust suite of tools and metrics for evaluating the performance of your object detection models. This guide serves as a complete resource for understanding how to effectively use the Val mode to ensure that your models are both accurate and reliable. - -

-
- -
- Watch: Ultralytics Modes Tutorial: Validation -

- -## Why Validate with Ultralytics YOLO? - -Here's why using YOLOv8's Val mode is advantageous: - -- **Precision:** Get accurate metrics like mAP50, mAP75, and mAP50-95 to comprehensively evaluate your model. -- **Convenience:** Utilize built-in features that remember training settings, simplifying the validation process. -- **Flexibility:** Validate your model with the same or different datasets and image sizes. -- **Hyperparameter Tuning:** Use validation metrics to fine-tune your model for better performance. - -### Key Features of Val Mode - -These are the notable functionalities offered by YOLOv8's Val mode: - -- **Automated Settings:** Models remember their training configurations for straightforward validation. -- **Multi-Metric Support:** Evaluate your model based on a range of accuracy metrics. -- **CLI and Python API:** Choose from command-line interface or Python API based on your preference for validation. -- **Data Compatibility:** Works seamlessly with datasets used during the training phase as well as custom datasets. - -!!! Tip "Tip" - - * YOLOv8 models automatically remember their training settings, so you can validate a model at the same image size and on the original dataset easily with just `yolo val model=yolov8n.pt` or `model('yolov8n.pt').val()` - -## Usage Examples - -Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. See Arguments section below for a full list of export arguments. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val() # no arguments needed, dataset and settings remembered - metrics.box.map # map50-95 - metrics.box.map50 # map50 - metrics.box.map75 # map75 - metrics.box.maps # a list contains map50-95 of each category - ``` - - === "CLI" - - ```bash - yolo detect val model=yolov8n.pt # val official model - yolo detect val model=path/to/best.pt # val custom model - ``` - -## Arguments for YOLO Model Validation - -When validating YOLO models, several arguments can be fine-tuned to optimize the evaluation process. These arguments control aspects such as input image size, batch processing, and performance thresholds. Below is a detailed breakdown of each argument to help you customize your validation settings effectively. - -| Argument | Type | Default | Description | -|---------------|---------|---------|---------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco128.yaml`). This file includes paths to validation data, class names, and number of classes. | -| `imgsz` | `int` | `640` | Defines the size of input images. All images are resized to this dimension before processing. | -| `batch` | `int` | `16` | Sets the number of images per batch. Use `-1` for AutoBatch, which automatically adjusts based on GPU memory availability. | -| `save_json` | `bool` | `False` | If `True`, saves the results to a JSON file for further analysis or integration with other tools. | -| `save_hybrid` | `bool` | `False` | If `True`, saves a hybrid version of labels that combines original annotations with additional model predictions. | -| `conf` | `float` | `0.001` | Sets the minimum confidence threshold for detections. Detections with confidence below this threshold are discarded. | -| `iou` | `float` | `0.6` | Sets the Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Helps in reducing duplicate detections. | -| `max_det` | `int` | `300` | Limits the maximum number of detections per image. Useful in dense scenes to prevent excessive detections. | -| `half` | `bool` | `True` | Enables half-precision (FP16) computation, reducing memory usage and potentially increasing speed with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for validation (`cpu`, `cuda:0`, etc.). Allows flexibility in utilizing CPU or GPU resources. | -| `dnn` | `bool` | `False` | If `True`, uses the OpenCV DNN module for ONNX model inference, offering an alternative to PyTorch inference methods. | -| `plots` | `bool` | `False` | When set to `True`, generates and saves plots of predictions versus ground truth for visual evaluation of the model's performance. | -| `rect` | `bool` | `False` | If `True`, uses rectangular inference for batching, reducing padding and potentially increasing speed and efficiency. | -| `split` | `str` | `val` | Determines the dataset split to use for validation (`val`, `test`, or `train`). Allows flexibility in choosing the data segment for performance evaluation. | - -Each of these settings plays a vital role in the validation process, allowing for a customizable and efficient evaluation of YOLO models. Adjusting these parameters according to your specific needs and resources can help achieve the best balance between accuracy and performance. - -### Example Validation with Arguments - -The below examples showcase YOLO model validation with custom arguments in Python and CLI. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') - - # Customize validation settings - validation_results = model.val(data='coco8.yaml', - imgsz=640, - batch=16, - conf=0.25, - iou=0.6, - device='0') - ``` - - === "CLI" - - ```bash - yolo val model=yolov8n.pt data=coco8.yaml imgsz=640 batch=16 conf=0.25 iou=0.6 device=0 - ``` diff --git a/ultralytics-main/docs/en/quickstart.md b/ultralytics-main/docs/en/quickstart.md deleted file mode 100644 index cf54217..0000000 --- a/ultralytics-main/docs/en/quickstart.md +++ /dev/null @@ -1,328 +0,0 @@ ---- -comments: true -description: Explore various methods to install Ultralytics using pip, conda, git and Docker. Learn how to use Ultralytics with command line interface or within your Python projects. -keywords: Ultralytics installation, pip install Ultralytics, Docker install Ultralytics, Ultralytics command line interface, Ultralytics Python interface ---- - -## Install Ultralytics - -Ultralytics provides various installation methods including pip, conda, and Docker. Install YOLOv8 via the `ultralytics` pip package for the latest stable release or by cloning the [Ultralytics GitHub repository](https://github.com/ultralytics/ultralytics) for the most up-to-date version. Docker can be used to execute the package in an isolated container, avoiding local installation. - -

-
- -
- Watch: Ultralytics YOLO Quick Start Guide -

- -!!! Example "Install" - - === "Pip install (recommended)" - - Install the `ultralytics` package using pip, or update an existing installation by running `pip install -U ultralytics`. Visit the Python Package Index (PyPI) for more details on the `ultralytics` package: [https://pypi.org/project/ultralytics/](https://pypi.org/project/ultralytics/). - - [![PyPI version](https://badge.fury.io/py/ultralytics.svg)](https://badge.fury.io/py/ultralytics) [![Downloads](https://static.pepy.tech/badge/ultralytics)](https://pepy.tech/project/ultralytics) - - ```bash - # Install the ultralytics package from PyPI - pip install ultralytics - ``` - - You can also install the `ultralytics` package directly from the GitHub [repository](https://github.com/ultralytics/ultralytics). This might be useful if you want the latest development version. Make sure to have the Git command-line tool installed on your system. The `@main` command installs the `main` branch and may be modified to another branch, i.e. `@my-branch`, or removed entirely to default to `main` branch. - - ```bash - # Install the ultralytics package from GitHub - pip install git+https://github.com/ultralytics/ultralytics.git@main - ``` - - === "Conda install" - - Conda is an alternative package manager to pip which may also be used for installation. Visit Anaconda for more details at [https://anaconda.org/conda-forge/ultralytics](https://anaconda.org/conda-forge/ultralytics). Ultralytics feedstock repository for updating the conda package is at [https://github.com/conda-forge/ultralytics-feedstock/](https://github.com/conda-forge/ultralytics-feedstock/). - - - [![Conda Recipe](https://img.shields.io/badge/recipe-ultralytics-green.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Version](https://img.shields.io/conda/vn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) [![Conda Platforms](https://img.shields.io/conda/pn/conda-forge/ultralytics.svg)](https://anaconda.org/conda-forge/ultralytics) - - ```bash - # Install the ultralytics package using conda - conda install -c conda-forge ultralytics - ``` - - !!! Note - - If you are installing in a CUDA environment best practice is to install `ultralytics`, `pytorch` and `pytorch-cuda` in the same command to allow the conda package manager to resolve any conflicts, or else to install `pytorch-cuda` last to allow it override the CPU-specific `pytorch` package if necessary. - ```bash - # Install all packages together using conda - conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=11.8 ultralytics - ``` - - ### Conda Docker Image - - Ultralytics Conda Docker images are also available from [DockerHub](https://hub.docker.com/r/ultralytics/ultralytics). These images are based on [Miniconda3](https://docs.conda.io/projects/miniconda/en/latest/) and are an simple way to start using `ultralytics` in a Conda environment. - - ```bash - # Set image name as a variable - t=ultralytics/ultralytics:latest-conda - - # Pull the latest ultralytics image from Docker Hub - sudo docker pull $t - - # Run the ultralytics image in a container with GPU support - sudo docker run -it --ipc=host --gpus all $t # all GPUs - sudo docker run -it --ipc=host --gpus '"device=2,3"' $t # specify GPUs - ``` - - === "Git clone" - Clone the `ultralytics` repository if you are interested in contributing to the development or wish to experiment with the latest source code. After cloning, navigate into the directory and install the package in editable mode `-e` using pip. - ```bash - # Clone the ultralytics repository - git clone https://github.com/ultralytics/ultralytics - - # Navigate to the cloned directory - cd ultralytics - - # Install the package in editable mode for development - pip install -e . - ``` - - === "Docker" - - Utilize Docker to effortlessly execute the `ultralytics` package in an isolated container, ensuring consistent and smooth performance across various environments. By choosing one of the official `ultralytics` images from [Docker Hub](https://hub.docker.com/r/ultralytics/ultralytics), you not only avoid the complexity of local installation but also benefit from access to a verified working environment. Ultralytics offers 5 main supported Docker images, each designed to provide high compatibility and efficiency for different platforms and use cases: - - Docker Pulls - - - **Dockerfile:** GPU image recommended for training. - - **Dockerfile-arm64:** Optimized for ARM64 architecture, allowing deployment on devices like Raspberry Pi and other ARM64-based platforms. - - **Dockerfile-cpu:** Ubuntu-based CPU-only version suitable for inference and environments without GPUs. - - **Dockerfile-jetson:** Tailored for NVIDIA Jetson devices, integrating GPU support optimized for these platforms. - - **Dockerfile-python:** Minimal image with just Python and necessary dependencies, ideal for lightweight applications and development. - - **Dockerfile-conda:** Based on Miniconda3 with conda installation of ultralytics package. - - Below are the commands to get the latest image and execute it: - - ```bash - # Set image name as a variable - t=ultralytics/ultralytics:latest - - # Pull the latest ultralytics image from Docker Hub - sudo docker pull $t - - # Run the ultralytics image in a container with GPU support - sudo docker run -it --ipc=host --gpus all $t # all GPUs - sudo docker run -it --ipc=host --gpus '"device=2,3"' $t # specify GPUs - ``` - - The above command initializes a Docker container with the latest `ultralytics` image. The `-it` flag assigns a pseudo-TTY and maintains stdin open, enabling you to interact with the container. The `--ipc=host` flag sets the IPC (Inter-Process Communication) namespace to the host, which is essential for sharing memory between processes. The `--gpus all` flag enables access to all available GPUs inside the container, which is crucial for tasks that require GPU computation. - - Note: To work with files on your local machine within the container, use Docker volumes for mounting a local directory into the container: - - ```bash - # Mount local directory to a directory inside the container - sudo docker run -it --ipc=host --gpus all -v /path/on/host:/path/in/container $t - ``` - - Alter `/path/on/host` with the directory path on your local machine, and `/path/in/container` with the desired path inside the Docker container for accessibility. - - For advanced Docker usage, feel free to explore the [Ultralytics Docker Guide](https://docs.ultralytics.com/guides/docker-quickstart/). - -See the `ultralytics` [requirements.txt](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) file for a list of dependencies. Note that all examples above install all required dependencies. - -!!! Tip "Tip" - - PyTorch requirements vary by operating system and CUDA requirements, so it's recommended to install PyTorch first following instructions at [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally). - - - PyTorch Installation Instructions - - -## Use Ultralytics with CLI - -The Ultralytics command line interface (CLI) allows for simple single-line commands without the need for a Python environment. CLI requires no customization or Python code. You can simply run all tasks from the terminal with the `yolo` command. Check out the [CLI Guide](usage/cli.md) to learn more about using YOLOv8 from the command line. - -!!! Example - - === "Syntax" - - Ultralytics `yolo` commands use the following syntax: - ```bash - yolo TASK MODE ARGS - ``` - - - `TASK` (optional) is one of ([detect](tasks/detect.md), [segment](tasks/segment.md), [classify](tasks/classify.md), [pose](tasks/pose.md)) - - `MODE` (required) is one of ([train](modes/train.md), [val](modes/val.md), [predict](modes/predict.md), [export](modes/export.md), [track](modes/track.md)) - - `ARGS` (optional) are `arg=value` pairs like `imgsz=640` that override defaults. - - See all `ARGS` in the full [Configuration Guide](usage/cfg.md) or with the `yolo cfg` CLI command. - - === "Train" - - Train a detection model for 10 epochs with an initial learning_rate of 0.01 - ```bash - yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 - ``` - - === "Predict" - - Predict a YouTube video using a pretrained segmentation model at image size 320: - ```bash - yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 - ``` - - === "Val" - - Val a pretrained detection model at batch-size 1 and image size 640: - ```bash - yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 - ``` - - === "Export" - - Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required) - ```bash - yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128 - ``` - - === "Special" - - Run special commands to see version, view settings, run checks and more: - ```bash - yolo help - yolo checks - yolo version - yolo settings - yolo copy-cfg - yolo cfg - ``` - -!!! Warning "Warning" - - Arguments must be passed as `arg=val` pairs, split by an equals `=` sign and delimited by spaces between pairs. Do not use `--` argument prefixes or commas `,` between arguments. - - - `yolo predict model=yolov8n.pt imgsz=640 conf=0.25` ✅ - - `yolo predict model yolov8n.pt imgsz 640 conf 0.25` ❌ (missing `=`) - - `yolo predict model=yolov8n.pt, imgsz=640, conf=0.25` ❌ (do not use `,`) - - `yolo predict --model yolov8n.pt --imgsz 640 --conf 0.25` ❌ (do not use `--`) - -[CLI Guide](usage/cli.md){ .md-button } - -## Use Ultralytics with Python - -YOLOv8's Python interface allows for seamless integration into your Python projects, making it easy to load, run, and process the model's output. Designed with simplicity and ease of use in mind, the Python interface enables users to quickly implement object detection, segmentation, and classification in their projects. This makes YOLOv8's Python interface an invaluable tool for anyone looking to incorporate these functionalities into their Python projects. - -For example, users can load a model, train it, evaluate its performance on a validation set, and even export it to ONNX format with just a few lines of code. Check out the [Python Guide](usage/python.md) to learn more about using YOLOv8 within your Python projects. - -!!! Example - - ```python - from ultralytics import YOLO - - # Create a new YOLO model from scratch - model = YOLO('yolov8n.yaml') - - # Load a pretrained YOLO model (recommended for training) - model = YOLO('yolov8n.pt') - - # Train the model using the 'coco128.yaml' dataset for 3 epochs - results = model.train(data='coco128.yaml', epochs=3) - - # Evaluate the model's performance on the validation set - results = model.val() - - # Perform object detection on an image using the model - results = model('https://ultralytics.com/images/bus.jpg') - - # Export the model to ONNX format - success = model.export(format='onnx') - ``` - -[Python Guide](usage/python.md){.md-button .md-button--primary} - -## Ultralytics Settings - -The Ultralytics library provides a powerful settings management system to enable fine-grained control over your experiments. By making use of the `SettingsManager` housed within the `ultralytics.utils` module, users can readily access and alter their settings. These are stored in a YAML file and can be viewed or modified either directly within the Python environment or via the Command-Line Interface (CLI). - -### Inspecting Settings - -To gain insight into the current configuration of your settings, you can view them directly: - -!!! Example "View settings" - - === "Python" - You can use Python to view your settings. Start by importing the `settings` object from the `ultralytics` module. Print and return settings using the following commands: - ```python - from ultralytics import settings - - # View all settings - print(settings) - - # Return a specific setting - value = settings['runs_dir'] - ``` - - === "CLI" - Alternatively, the command-line interface allows you to check your settings with a simple command: - ```bash - yolo settings - ``` - -### Modifying Settings - -Ultralytics allows users to easily modify their settings. Changes can be performed in the following ways: - -!!! Example "Update settings" - - === "Python" - Within the Python environment, call the `update` method on the `settings` object to change your settings: - ```python - from ultralytics import settings - - # Update a setting - settings.update({'runs_dir': '/path/to/runs'}) - - # Update multiple settings - settings.update({'runs_dir': '/path/to/runs', 'tensorboard': False}) - - # Reset settings to default values - settings.reset() - ``` - - === "CLI" - If you prefer using the command-line interface, the following commands will allow you to modify your settings: - ```bash - # Update a setting - yolo settings runs_dir='/path/to/runs' - - # Update multiple settings - yolo settings runs_dir='/path/to/runs' tensorboard=False - - # Reset settings to default values - yolo settings reset - ``` - -### Understanding Settings - -The table below provides an overview of the settings available for adjustment within Ultralytics. Each setting is outlined along with an example value, the data type, and a brief description. - -| Name | Example Value | Data Type | Description | -|--------------------|-----------------------|-----------|------------------------------------------------------------------------------------------------------------------| -| `settings_version` | `'0.0.4'` | `str` | Ultralytics _settings_ version (different from Ultralytics [pip](https://pypi.org/project/ultralytics/) version) | -| `datasets_dir` | `'/path/to/datasets'` | `str` | The directory where the datasets are stored | -| `weights_dir` | `'/path/to/weights'` | `str` | The directory where the model weights are stored | -| `runs_dir` | `'/path/to/runs'` | `str` | The directory where the experiment runs are stored | -| `uuid` | `'a1b2c3d4'` | `str` | The unique identifier for the current settings | -| `sync` | `True` | `bool` | Whether to sync analytics and crashes to HUB | -| `api_key` | `''` | `str` | Ultralytics HUB [API Key](https://hub.ultralytics.com/settings?tab=api+keys) | -| `clearml` | `True` | `bool` | Whether to use ClearML logging | -| `comet` | `True` | `bool` | Whether to use [Comet ML](https://bit.ly/yolov8-readme-comet) for experiment tracking and visualization | -| `dvc` | `True` | `bool` | Whether to use [DVC for experiment tracking](https://dvc.org/doc/dvclive/ml-frameworks/yolo) and version control | -| `hub` | `True` | `bool` | Whether to use [Ultralytics HUB](https://hub.ultralytics.com) integration | -| `mlflow` | `True` | `bool` | Whether to use MLFlow for experiment tracking | -| `neptune` | `True` | `bool` | Whether to use Neptune for experiment tracking | -| `raytune` | `True` | `bool` | Whether to use Ray Tune for hyperparameter tuning | -| `tensorboard` | `True` | `bool` | Whether to use TensorBoard for visualization | -| `wandb` | `True` | `bool` | Whether to use Weights & Biases logging | - -As you navigate through your projects or experiments, be sure to revisit these settings to ensure that they are optimally configured for your needs. diff --git a/ultralytics-main/docs/en/reference/cfg/__init__.md b/ultralytics-main/docs/en/reference/cfg/__init__.md deleted file mode 100644 index b8db12c..0000000 --- a/ultralytics-main/docs/en/reference/cfg/__init__.md +++ /dev/null @@ -1,64 +0,0 @@ ---- -description: Explore Ultralytics cfg functions like cfg2dict, handle_deprecation, merge_equal_args & more to handle YOLO settings and configurations efficiently. -keywords: Ultralytics, YOLO, Configuration, cfg2dict, handle_deprecation, merge_equals_args, handle_yolo_settings, copy_default_cfg, Image Detection ---- - -# Reference for `ultralytics/cfg/__init__.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/__init__.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/__init__.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/cfg/__init__.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.cfg.cfg2dict - -

- -## ::: ultralytics.cfg.get_cfg - -

- -## ::: ultralytics.cfg.get_save_dir - -

- -## ::: ultralytics.cfg._handle_deprecation - -

- -## ::: ultralytics.cfg.check_dict_alignment - -

- -## ::: ultralytics.cfg.merge_equals_args - -

- -## ::: ultralytics.cfg.handle_yolo_hub - -

- -## ::: ultralytics.cfg.handle_yolo_settings - -

- -## ::: ultralytics.cfg.handle_explorer - -

- -## ::: ultralytics.cfg.parse_key_value_pair - -

- -## ::: ultralytics.cfg.smart_value - -

- -## ::: ultralytics.cfg.entrypoint - -

- -## ::: ultralytics.cfg.copy_default_cfg - -

diff --git a/ultralytics-main/docs/en/reference/data/annotator.md b/ultralytics-main/docs/en/reference/data/annotator.md deleted file mode 100644 index ab685b2..0000000 --- a/ultralytics-main/docs/en/reference/data/annotator.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Enhance your machine learning model with Ultralytics’ auto_annotate function. Simplify data annotation for improved model training. -keywords: Ultralytics, Auto-Annotate, Machine Learning, AI, Annotation, Data Processing, Model Training ---- - -# Reference for `ultralytics/data/annotator.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/annotator.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/annotator.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/annotator.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.annotator.auto_annotate - -

diff --git a/ultralytics-main/docs/en/reference/data/augment.md b/ultralytics-main/docs/en/reference/data/augment.md deleted file mode 100644 index 1d4099f..0000000 --- a/ultralytics-main/docs/en/reference/data/augment.md +++ /dev/null @@ -1,84 +0,0 @@ ---- -description: Detailed exploration into Ultralytics data augmentation methods including BaseTransform, MixUp, LetterBox, ToTensor, and more for enhancing model performance. -keywords: Ultralytics, Data Augmentation, BaseTransform, MixUp, RandomHSV, LetterBox, Albumentations, classify_transforms, classify_albumentations ---- - -# Reference for `ultralytics/data/augment.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/augment.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/augment.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/augment.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.augment.BaseTransform - -

- -## ::: ultralytics.data.augment.Compose - -

- -## ::: ultralytics.data.augment.BaseMixTransform - -

- -## ::: ultralytics.data.augment.Mosaic - -

- -## ::: ultralytics.data.augment.MixUp - -

- -## ::: ultralytics.data.augment.RandomPerspective - -

- -## ::: ultralytics.data.augment.RandomHSV - -

- -## ::: ultralytics.data.augment.RandomFlip - -

- -## ::: ultralytics.data.augment.LetterBox - -

- -## ::: ultralytics.data.augment.CopyPaste - -

- -## ::: ultralytics.data.augment.Albumentations - -

- -## ::: ultralytics.data.augment.Format - -

- -## ::: ultralytics.data.augment.ClassifyLetterBox - -

- -## ::: ultralytics.data.augment.CenterCrop - -

- -## ::: ultralytics.data.augment.ToTensor - -

- -## ::: ultralytics.data.augment.v8_transforms - -

- -## ::: ultralytics.data.augment.classify_transforms - -

- -## ::: ultralytics.data.augment.classify_augmentations - -

diff --git a/ultralytics-main/docs/en/reference/data/base.md b/ultralytics-main/docs/en/reference/data/base.md deleted file mode 100644 index c98a7c3..0000000 --- a/ultralytics-main/docs/en/reference/data/base.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore BaseDataset in Ultralytics docs. Learn how this implementation simplifies dataset creation and manipulation. -keywords: Ultralytics, docs, BaseDataset, data manipulation, dataset creation ---- - -# Reference for `ultralytics/data/base.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/base.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/base.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/base.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.base.BaseDataset - -

diff --git a/ultralytics-main/docs/en/reference/data/build.md b/ultralytics-main/docs/en/reference/data/build.md deleted file mode 100644 index 811c11d..0000000 --- a/ultralytics-main/docs/en/reference/data/build.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Explore the Ultralytics YOLO v3 data build procedures, including the InfiniteDataLoader, seed_worker, build_dataloader, and load_inference_source. -keywords: Ultralytics, YOLO v3, Data build, DataLoader, InfiniteDataLoader, seed_worker, build_dataloader, load_inference_source ---- - -# Reference for `ultralytics/data/build.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/build.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/build.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/build.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.build.InfiniteDataLoader - -

- -## ::: ultralytics.data.build._RepeatSampler - -

- -## ::: ultralytics.data.build.seed_worker - -

- -## ::: ultralytics.data.build.build_yolo_dataset - -

- -## ::: ultralytics.data.build.build_dataloader - -

- -## ::: ultralytics.data.build.check_source - -

- -## ::: ultralytics.data.build.load_inference_source - -

diff --git a/ultralytics-main/docs/en/reference/data/converter.md b/ultralytics-main/docs/en/reference/data/converter.md deleted file mode 100644 index 1d456b3..0000000 --- a/ultralytics-main/docs/en/reference/data/converter.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Explore Ultralytics data converter functions like coco91_to_coco80_class, merge_multi_segment, rle2polygon for efficient data handling. -keywords: Ultralytics, Data Converter, coco91_to_coco80_class, merge_multi_segment, rle2polygon ---- - -# Reference for `ultralytics/data/converter.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/converter.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/converter.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/converter.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.converter.coco91_to_coco80_class - -

- -## ::: ultralytics.data.converter.coco80_to_coco91_class - -

- -## ::: ultralytics.data.converter.convert_coco - -

- -## ::: ultralytics.data.converter.convert_dota_to_yolo_obb - -

- -## ::: ultralytics.data.converter.min_index - -

- -## ::: ultralytics.data.converter.merge_multi_segment - -

- -## ::: ultralytics.data.converter.yolo_bbox2segment - -

diff --git a/ultralytics-main/docs/en/reference/data/dataset.md b/ultralytics-main/docs/en/reference/data/dataset.md deleted file mode 100644 index 242a054..0000000 --- a/ultralytics-main/docs/en/reference/data/dataset.md +++ /dev/null @@ -1,32 +0,0 @@ ---- -description: Explore the YOLODataset and SemanticDataset classes in YOLO data. Learn how to efficiently handle and manipulate your data with Ultralytics. -keywords: Ultralytics, YOLO, YOLODataset, SemanticDataset, data handling, data manipulation ---- - -# Reference for `ultralytics/data/dataset.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/dataset.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/dataset.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/dataset.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.dataset.YOLODataset - -

- -## ::: ultralytics.data.dataset.ClassificationDataset - -

- -## ::: ultralytics.data.dataset.SemanticDataset - -

- -## ::: ultralytics.data.dataset.load_dataset_cache_file - -

- -## ::: ultralytics.data.dataset.save_dataset_cache_file - -

diff --git a/ultralytics-main/docs/en/reference/data/explorer/explorer.md b/ultralytics-main/docs/en/reference/data/explorer/explorer.md deleted file mode 100644 index d860863..0000000 --- a/ultralytics-main/docs/en/reference/data/explorer/explorer.md +++ /dev/null @@ -1,21 +0,0 @@ ---- -comments: true -description: Comprehensive reference for the Explorer API. Get a brief description of all the main classes utilised for creating and handling the data in the Ultralytics data explorer project. -keywords: Ultralytics, explorer.py, data explorer, Semantic search, vector similarity search, class reference, documentation, ExplorerDataset, Explorer, data handling ---- - -# Reference for `ultralytics/data/explorer/explorer.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/explorer.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/explorer.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/explorer/explorer.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.explorer.explorer.ExplorerDataset - -

- -## ::: ultralytics.data.explorer.explorer.Explorer - -

diff --git a/ultralytics-main/docs/en/reference/data/explorer/gui/dash.md b/ultralytics-main/docs/en/reference/data/explorer/gui/dash.md deleted file mode 100644 index fd241d9..0000000 --- a/ultralytics-main/docs/en/reference/data/explorer/gui/dash.md +++ /dev/null @@ -1,57 +0,0 @@ ---- -comments: true -description: Detailed reference for the Explorer GUI. Includes brief descriptions for all the major functions used in the dashboard demo of Explorer API. -keywords: Ultralytics, data explorer, gui, function reference, documentation, AI queries, image similarity, SQL queries, streamlit, semantic search ---- - -# Reference for `ultralytics/data/explorer/gui/dash.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/gui/dash.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/gui/dash.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/explorer/gui/dash.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.explorer.gui.dash._get_explorer - -

- -## ::: ultralytics.data.explorer.gui.dash.init_explorer_form - -

- -## ::: ultralytics.data.explorer.gui.dash.query_form - -

- -## ::: ultralytics.data.explorer.gui.dash.ai_query_form - -

- -## ::: ultralytics.data.explorer.gui.dash.find_similar_imgs - -

- -## ::: ultralytics.data.explorer.gui.dash.similarity_form - -

- -## ::: ultralytics.data.explorer.gui.dash.run_sql_query - -

- -## ::: ultralytics.data.explorer.gui.dash.run_ai_query - -

- -## ::: ultralytics.data.explorer.gui.dash.reset_explorer - -

- -## ::: ultralytics.data.explorer.gui.dash.utralytics_explorer_docs_callback - -

- -## ::: ultralytics.data.explorer.gui.dash.layout - -

diff --git a/ultralytics-main/docs/en/reference/data/explorer/utils.md b/ultralytics-main/docs/en/reference/data/explorer/utils.md deleted file mode 100644 index d1769c5..0000000 --- a/ultralytics-main/docs/en/reference/data/explorer/utils.md +++ /dev/null @@ -1,33 +0,0 @@ ---- -comments: true -description: Detailed reference for the Explorer utils. Provides descriptions and details on important utility functions for managing and interacting with data in the Ultralytics explorer project. -keywords: Ultralytics, data explorer, function reference, documentation, get table schema, get sim index schema, sanitize batch, plot query result, prompt SQL query ---- - -# Reference for `ultralytics/data/explorer/utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/explorer/utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/explorer/utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.explorer.utils.get_table_schema - -

- -## ::: ultralytics.data.explorer.utils.get_sim_index_schema - -

- -## ::: ultralytics.data.explorer.utils.sanitize_batch - -

- -## ::: ultralytics.data.explorer.utils.plot_query_result - -

- -## ::: ultralytics.data.explorer.utils.prompt_sql_query - -

diff --git a/ultralytics-main/docs/en/reference/data/loaders.md b/ultralytics-main/docs/en/reference/data/loaders.md deleted file mode 100644 index 99d7749..0000000 --- a/ultralytics-main/docs/en/reference/data/loaders.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -description: Find detailed guides on Ultralytics YOLO data loaders, including LoadStreams, LoadImages and LoadTensor. Learn how to get the best YouTube URLs. -keywords: Ultralytics, data loaders, LoadStreams, LoadImages, LoadTensor, YOLO, YouTube URLs ---- - -# Reference for `ultralytics/data/loaders.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/loaders.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/loaders.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/loaders.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.loaders.SourceTypes - -

- -## ::: ultralytics.data.loaders.LoadStreams - -

- -## ::: ultralytics.data.loaders.LoadScreenshots - -

- -## ::: ultralytics.data.loaders.LoadImagesAndVideos - -

- -## ::: ultralytics.data.loaders.LoadPilAndNumpy - -

- -## ::: ultralytics.data.loaders.LoadTensor - -

- -## ::: ultralytics.data.loaders.autocast_list - -

- -## ::: ultralytics.data.loaders.get_best_youtube_url - -

diff --git a/ultralytics-main/docs/en/reference/data/split_dota.md b/ultralytics-main/docs/en/reference/data/split_dota.md deleted file mode 100644 index ae3dfaa..0000000 --- a/ultralytics-main/docs/en/reference/data/split_dota.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -description: Detailed guide on using YOLO with DOTA dataset for object detection, including dataset preparation, image splitting, and label handling. -keywords: Ultralytics, YOLO, DOTA dataset, object detection, image processing, python, dataset preparation, image splitting, label handling, YOLO with DOTA, computer vision, AI, machine learning ---- - -# Reference for `ultralytics/data/split_dota.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/split_dota.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/split_dota.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/split_dota.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.split_dota.bbox_iof - -

- -## ::: ultralytics.data.split_dota.load_yolo_dota - -

- -## ::: ultralytics.data.split_dota.get_windows - -

- -## ::: ultralytics.data.split_dota.get_window_obj - -

- -## ::: ultralytics.data.split_dota.crop_and_save - -

- -## ::: ultralytics.data.split_dota.split_images_and_labels - -

- -## ::: ultralytics.data.split_dota.split_trainval - -

- -## ::: ultralytics.data.split_dota.split_test - -

diff --git a/ultralytics-main/docs/en/reference/data/utils.md b/ultralytics-main/docs/en/reference/data/utils.md deleted file mode 100644 index af06ce8..0000000 --- a/ultralytics-main/docs/en/reference/data/utils.md +++ /dev/null @@ -1,68 +0,0 @@ ---- -description: Uncover a detailed guide to Ultralytics data utilities. Learn functions from img2label_paths to autosplit, all boosting your YOLO model’s efficiency. -keywords: Ultralytics, data utils, YOLO, img2label_paths, exif_size, polygon2mask, polygons2masks_overlap, check_cls_dataset, delete_dsstore, autosplit ---- - -# Reference for `ultralytics/data/utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/data/utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/data/utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.data.utils.HUBDatasetStats - -

- -## ::: ultralytics.data.utils.img2label_paths - -

- -## ::: ultralytics.data.utils.get_hash - -

- -## ::: ultralytics.data.utils.exif_size - -

- -## ::: ultralytics.data.utils.verify_image - -

- -## ::: ultralytics.data.utils.verify_image_label - -

- -## ::: ultralytics.data.utils.polygon2mask - -

- -## ::: ultralytics.data.utils.polygons2masks - -

- -## ::: ultralytics.data.utils.polygons2masks_overlap - -

- -## ::: ultralytics.data.utils.find_dataset_yaml - -

- -## ::: ultralytics.data.utils.check_det_dataset - -

- -## ::: ultralytics.data.utils.check_cls_dataset - -

- -## ::: ultralytics.data.utils.compress_one_image - -

- -## ::: ultralytics.data.utils.autosplit - -

diff --git a/ultralytics-main/docs/en/reference/engine/exporter.md b/ultralytics-main/docs/en/reference/engine/exporter.md deleted file mode 100644 index e8daeac..0000000 --- a/ultralytics-main/docs/en/reference/engine/exporter.md +++ /dev/null @@ -1,32 +0,0 @@ ---- -description: Explore the exporter functionality of Ultralytics. Learn about exporting formats, IOSDetectModel, and try exporting with examples. -keywords: Ultralytics, Exporter, IOSDetectModel, Export Formats, Try export ---- - -# Reference for `ultralytics/engine/exporter.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/exporter.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/exporter.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/exporter.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.exporter.Exporter - -

- -## ::: ultralytics.engine.exporter.IOSDetectModel - -

- -## ::: ultralytics.engine.exporter.export_formats - -

- -## ::: ultralytics.engine.exporter.gd_outputs - -

- -## ::: ultralytics.engine.exporter.try_export - -

diff --git a/ultralytics-main/docs/en/reference/engine/model.md b/ultralytics-main/docs/en/reference/engine/model.md deleted file mode 100644 index 5579d75..0000000 --- a/ultralytics-main/docs/en/reference/engine/model.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the detailed guide on using the Ultralytics YOLO Engine Model. Learn better ways to implement, train and evaluate YOLO models. -keywords: Ultralytics, YOLO, engine model, documentation, guide, implementation, training, evaluation ---- - -# Reference for `ultralytics/engine/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.model.Model - -

diff --git a/ultralytics-main/docs/en/reference/engine/predictor.md b/ultralytics-main/docs/en/reference/engine/predictor.md deleted file mode 100644 index ad50352..0000000 --- a/ultralytics-main/docs/en/reference/engine/predictor.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about Ultralytics BasePredictor, an essential component of our engine that serves as the foundation for all prediction operations. -keywords: Ultralytics, BasePredictor, YOLO, prediction, engine ---- - -# Reference for `ultralytics/engine/predictor.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/predictor.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/predictor.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/predictor.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.predictor.BasePredictor - -

diff --git a/ultralytics-main/docs/en/reference/engine/results.md b/ultralytics-main/docs/en/reference/engine/results.md deleted file mode 100644 index 9b389ee..0000000 --- a/ultralytics-main/docs/en/reference/engine/results.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Master Ultralytics engine results including base tensors, boxes, and keypoints with our thorough documentation. -keywords: Ultralytics, engine, results, base tensor, boxes, keypoints ---- - -# Reference for `ultralytics/engine/results.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/results.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/results.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/results.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.results.BaseTensor - -

- -## ::: ultralytics.engine.results.Results - -

- -## ::: ultralytics.engine.results.Boxes - -

- -## ::: ultralytics.engine.results.Masks - -

- -## ::: ultralytics.engine.results.Keypoints - -

- -## ::: ultralytics.engine.results.Probs - -

- -## ::: ultralytics.engine.results.OBB - -

diff --git a/ultralytics-main/docs/en/reference/engine/trainer.md b/ultralytics-main/docs/en/reference/engine/trainer.md deleted file mode 100644 index 7c74b04..0000000 --- a/ultralytics-main/docs/en/reference/engine/trainer.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about the BaseTrainer class in the Ultralytics library. From training control, customization to advanced usage. -keywords: Ultralytics, BaseTrainer, Machine Learning, Training Control, Python library ---- - -# Reference for `ultralytics/engine/trainer.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/trainer.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/trainer.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/trainer.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.trainer.BaseTrainer - -

diff --git a/ultralytics-main/docs/en/reference/engine/tuner.md b/ultralytics-main/docs/en/reference/engine/tuner.md deleted file mode 100644 index 7882b8c..0000000 --- a/ultralytics-main/docs/en/reference/engine/tuner.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the Ultralytics Tuner, a powerful tool designed for hyperparameter tuning of YOLO models to optimize performance across various tasks like object detection, image classification, and more. -keywords: Ultralytics, Tuner, YOLO, hyperparameter tuning, optimization, object detection, image classification, instance segmentation, pose estimation, multi-object tracking ---- - -# Reference for `ultralytics/engine/tuner.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/tuner.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/tuner.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/tuner.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.tuner.Tuner - -

diff --git a/ultralytics-main/docs/en/reference/engine/validator.md b/ultralytics-main/docs/en/reference/engine/validator.md deleted file mode 100644 index 5c0f4cd..0000000 --- a/ultralytics-main/docs/en/reference/engine/validator.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about the Ultralytics BaseValidator module. Understand its principles, uses, and how it interacts with other components. -keywords: Ultralytics, BaseValidator, Ultralytics engine, module, components ---- - -# Reference for `ultralytics/engine/validator.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/validator.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/validator.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/engine/validator.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.engine.validator.BaseValidator - -

diff --git a/ultralytics-main/docs/en/reference/hub/__init__.md b/ultralytics-main/docs/en/reference/hub/__init__.md deleted file mode 100644 index 912de06..0000000 --- a/ultralytics-main/docs/en/reference/hub/__init__.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Explore Ultralytics hub functions for model resetting, checking datasets, model exporting and more. Easy-to-follow instructions provided. -keywords: Ultralytics, hub functions, model export, dataset check, reset model, YOLO Docs ---- - -# Reference for `ultralytics/hub/__init__.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/__init__.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/__init__.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/hub/__init__.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.hub.login - -

- -## ::: ultralytics.hub.logout - -

- -## ::: ultralytics.hub.reset_model - -

- -## ::: ultralytics.hub.export_fmts_hub - -

- -## ::: ultralytics.hub.export_model - -

- -## ::: ultralytics.hub.get_export - -

- -## ::: ultralytics.hub.check_dataset - -

diff --git a/ultralytics-main/docs/en/reference/hub/auth.md b/ultralytics-main/docs/en/reference/hub/auth.md deleted file mode 100644 index 964dc73..0000000 --- a/ultralytics-main/docs/en/reference/hub/auth.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Dive into the Ultralytics Auth API documentation & learn how to manage authentication in your AI & ML projects easily and effectively. -keywords: Ultralytics, Auth, API documentation, User Authentication, AI, Machine Learning ---- - -# Reference for `ultralytics/hub/auth.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/auth.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/auth.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/hub/auth.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.hub.auth.Auth - -

diff --git a/ultralytics-main/docs/en/reference/hub/session.md b/ultralytics-main/docs/en/reference/hub/session.md deleted file mode 100644 index fb30715..0000000 --- a/ultralytics-main/docs/en/reference/hub/session.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore details about the HUBTrainingSession in Ultralytics framework. Learn to utilize this functionality for effective model training. -keywords: Ultralytics, HUBTrainingSession, Documentation, Model Training, AI, Machine Learning, YOLO ---- - -# Reference for `ultralytics/hub/session.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/session.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/session.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/hub/session.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.hub.session.HUBTrainingSession - -

diff --git a/ultralytics-main/docs/en/reference/hub/utils.md b/ultralytics-main/docs/en/reference/hub/utils.md deleted file mode 100644 index e310a01..0000000 --- a/ultralytics-main/docs/en/reference/hub/utils.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Explore Ultralytics docs for various Events, including "request_with_credentials" and "requests_with_progress". Also, understand the use of the "smart_request". -keywords: Ultralytics, Events, request_with_credentials, smart_request, Ultralytics hub utils, requests_with_progress ---- - -# Reference for `ultralytics/hub/utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/hub/utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/hub/utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.hub.utils.Events - -

- -## ::: ultralytics.hub.utils.request_with_credentials - -

- -## ::: ultralytics.hub.utils.requests_with_progress - -

- -## ::: ultralytics.hub.utils.smart_request - -

diff --git a/ultralytics-main/docs/en/reference/models/fastsam/model.md b/ultralytics-main/docs/en/reference/models/fastsam/model.md deleted file mode 100644 index 0e99a8c..0000000 --- a/ultralytics-main/docs/en/reference/models/fastsam/model.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn all about Ultralytics FastSAM model. Dive into our comprehensive guide for seamless integration and efficient model training. -keywords: Ultralytics, FastSAM model, Model documentation, Efficient model training ---- - -# Reference for `ultralytics/models/fastsam/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/fastsam/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.fastsam.model.FastSAM - -

diff --git a/ultralytics-main/docs/en/reference/models/fastsam/predict.md b/ultralytics-main/docs/en/reference/models/fastsam/predict.md deleted file mode 100644 index 7c7196e..0000000 --- a/ultralytics-main/docs/en/reference/models/fastsam/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Get detailed insights about Ultralytics FastSAMPredictor. Learn to predict and optimize your AI models with our properly documented guidelines. -keywords: Ultralytics, FastSAMPredictor, predictive modeling, AI optimization, machine learning, deep learning, Ultralytics documentation ---- - -# Reference for `ultralytics/models/fastsam/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/fastsam/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.fastsam.predict.FastSAMPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/fastsam/prompt.md b/ultralytics-main/docs/en/reference/models/fastsam/prompt.md deleted file mode 100644 index 0a37023..0000000 --- a/ultralytics-main/docs/en/reference/models/fastsam/prompt.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn to effectively utilize FastSAMPrompt model from Ultralytics. Detailed guide to help you get the most out of your machine learning models. -keywords: Ultralytics, FastSAMPrompt, machine learning, model, guide, documentation ---- - -# Reference for `ultralytics/models/fastsam/prompt.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/prompt.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/prompt.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/fastsam/prompt.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.fastsam.prompt.FastSAMPrompt - -

diff --git a/ultralytics-main/docs/en/reference/models/fastsam/utils.md b/ultralytics-main/docs/en/reference/models/fastsam/utils.md deleted file mode 100644 index 0ba33ab..0000000 --- a/ultralytics-main/docs/en/reference/models/fastsam/utils.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Learn how to adjust bounding boxes to image borders in Ultralytics models using the bbox_iou utility. Enhance your object detection performance. -keywords: Ultralytics, bounding boxes, Bboxes, image borders, object detection, bbox_iou, model utilities ---- - -# Reference for `ultralytics/models/fastsam/utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/fastsam/utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.fastsam.utils.adjust_bboxes_to_image_border - -

- -## ::: ultralytics.models.fastsam.utils.bbox_iou - -

diff --git a/ultralytics-main/docs/en/reference/models/fastsam/val.md b/ultralytics-main/docs/en/reference/models/fastsam/val.md deleted file mode 100644 index 4064f05..0000000 --- a/ultralytics-main/docs/en/reference/models/fastsam/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about FastSAMValidator in Ultralytics models. Comprehensive guide to enhancing AI capabilities with Ultralytics. -keywords: Ultralytics, FastSAMValidator, model, synthetic, AI, machine learning, validation ---- - -# Reference for `ultralytics/models/fastsam/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/fastsam/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/fastsam/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.fastsam.val.FastSAMValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/nas/model.md b/ultralytics-main/docs/en/reference/models/nas/model.md deleted file mode 100644 index 9536e54..0000000 --- a/ultralytics-main/docs/en/reference/models/nas/model.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn how our NAS model operates in Ultralytics. Comprehensive guide with detailed examples. Master the nuances of Ultralytics NAS model. -keywords: Ultralytics, NAS model, NAS guide, machine learning, model documentation ---- - -# Reference for `ultralytics/models/nas/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/nas/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.nas.model.NAS - -

diff --git a/ultralytics-main/docs/en/reference/models/nas/predict.md b/ultralytics-main/docs/en/reference/models/nas/predict.md deleted file mode 100644 index 3dcc0fd..0000000 --- a/ultralytics-main/docs/en/reference/models/nas/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore Ultralytics NASPredictor. Understand high-level architecture of the model for effective implementation and efficient predictions. -keywords: NASPredictor, Ultralytics, Ultralytics model, model architecture, efficient predictions ---- - -# Reference for `ultralytics/models/nas/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/nas/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.nas.predict.NASPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/nas/val.md b/ultralytics-main/docs/en/reference/models/nas/val.md deleted file mode 100644 index 5d0adf6..0000000 --- a/ultralytics-main/docs/en/reference/models/nas/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the utilities and functions of the Ultralytics NASValidator. Find out how it benefits allocation and optimization in AI models. -keywords: Ultralytics, NASValidator, models.nas.val.NASValidator, AI models, allocation, optimization ---- - -# Reference for `ultralytics/models/nas/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/nas/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.nas.val.NASValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/rtdetr/model.md b/ultralytics-main/docs/en/reference/models/rtdetr/model.md deleted file mode 100644 index a4578b2..0000000 --- a/ultralytics-main/docs/en/reference/models/rtdetr/model.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the specifics of using the RTDETR model in Ultralytics. Detailed documentation layered with explanations and examples. -keywords: Ultralytics, RTDETR model, Ultralytics models, object detection, Ultralytics documentation ---- - -# Reference for `ultralytics/models/rtdetr/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/rtdetr/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.rtdetr.model.RTDETR - -

diff --git a/ultralytics-main/docs/en/reference/models/rtdetr/predict.md b/ultralytics-main/docs/en/reference/models/rtdetr/predict.md deleted file mode 100644 index 4763381..0000000 --- a/ultralytics-main/docs/en/reference/models/rtdetr/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn how to use the RTDETRPredictor model of the Ultralytics package. Detailed documentation, usage instructions, and advice. -keywords: Ultralytics, RTDETRPredictor, model documentation, guide, real-time object detection ---- - -# Reference for `ultralytics/models/rtdetr/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/rtdetr/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.rtdetr.predict.RTDETRPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/rtdetr/train.md b/ultralytics-main/docs/en/reference/models/rtdetr/train.md deleted file mode 100644 index 4f9faaa..0000000 --- a/ultralytics-main/docs/en/reference/models/rtdetr/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Get insights into RTDETRTrainer, a crucial component of Ultralytics for effective model training. Explore detailed documentation at Ultralytics. -keywords: Ultralytics, RTDETRTrainer, model training, Ultralytics models, PyTorch models, neural networks, machine learning, deep learning ---- - -# Reference for `ultralytics/models/rtdetr/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/rtdetr/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.rtdetr.train.RTDETRTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/rtdetr/val.md b/ultralytics-main/docs/en/reference/models/rtdetr/val.md deleted file mode 100644 index d31bc86..0000000 --- a/ultralytics-main/docs/en/reference/models/rtdetr/val.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Explore RTDETRDataset in Ultralytics Models. Learn about the RTDETRValidator function, understand its usage in real-time object detection. -keywords: Ultralytics, RTDETRDataset, RTDETRValidator, real-time object detection, models documentation ---- - -# Reference for `ultralytics/models/rtdetr/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/rtdetr/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.rtdetr.val.RTDETRDataset - -

- -## ::: ultralytics.models.rtdetr.val.RTDETRValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/amg.md b/ultralytics-main/docs/en/reference/models/sam/amg.md deleted file mode 100644 index dea35e4..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/amg.md +++ /dev/null @@ -1,56 +0,0 @@ ---- -description: Explore Ultralytics methods for mask data processing, transformation and encoding. Deepen your understanding of RLE encoding, image cropping and more. -keywords: Ultralytics, Mask Data, Transformation, Encoding, RLE encoding, Image cropping, Pytorch, SAM, AMG, Ultralytics model ---- - -# Reference for `ultralytics/models/sam/amg.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/amg.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/amg.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/amg.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.amg.is_box_near_crop_edge - -

- -## ::: ultralytics.models.sam.amg.batch_iterator - -

- -## ::: ultralytics.models.sam.amg.calculate_stability_score - -

- -## ::: ultralytics.models.sam.amg.build_point_grid - -

- -## ::: ultralytics.models.sam.amg.build_all_layer_point_grids - -

- -## ::: ultralytics.models.sam.amg.generate_crop_boxes - -

- -## ::: ultralytics.models.sam.amg.uncrop_boxes_xyxy - -

- -## ::: ultralytics.models.sam.amg.uncrop_points - -

- -## ::: ultralytics.models.sam.amg.uncrop_masks - -

- -## ::: ultralytics.models.sam.amg.remove_small_regions - -

- -## ::: ultralytics.models.sam.amg.batched_mask_to_box - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/build.md b/ultralytics-main/docs/en/reference/models/sam/build.md deleted file mode 100644 index 9adeeb4..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/build.md +++ /dev/null @@ -1,36 +0,0 @@ ---- -description: Master building SAM ViT models with Ultralytics. Discover steps to leverage the power of SAM and Vision Transformer sessions. -keywords: Ultralytics, SAM, build sam, vision transformer, vits, build_sam_vit_l, build_sam_vit_b, build_sam ---- - -# Reference for `ultralytics/models/sam/build.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/build.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/build.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/build.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.build.build_sam_vit_h - -

- -## ::: ultralytics.models.sam.build.build_sam_vit_l - -

- -## ::: ultralytics.models.sam.build.build_sam_vit_b - -

- -## ::: ultralytics.models.sam.build.build_mobile_sam - -

- -## ::: ultralytics.models.sam.build._build_sam - -

- -## ::: ultralytics.models.sam.build.build_sam - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/model.md b/ultralytics-main/docs/en/reference/models/sam/model.md deleted file mode 100644 index 32444bc..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/model.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Dive into the SAM model details in the Ultralytics YOLO documentation. Understand, implement, and optimize your model use. -keywords: Ultralytics, YOLO, SAM Model, Documentations, Machine Learning, AI, Convolutional neural network ---- - -# Reference for `ultralytics/models/sam/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.model.SAM - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/modules/decoders.md b/ultralytics-main/docs/en/reference/models/sam/modules/decoders.md deleted file mode 100644 index 215b832..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/modules/decoders.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Explore MaskDecoder, a part of the Ultralytics models. Gain insights on how to utilize it effectively in the SAM modules decoders MLP. -keywords: Ultralytics, MaskDecoder, SAM modules, decoders, MLP, YOLO, machine learning, image recognition ---- - -# Reference for `ultralytics/models/sam/modules/decoders.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/decoders.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/decoders.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/modules/decoders.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.modules.decoders.MaskDecoder - -

- -## ::: ultralytics.models.sam.modules.decoders.MLP - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/modules/encoders.md b/ultralytics-main/docs/en/reference/models/sam/modules/encoders.md deleted file mode 100644 index ffcbf44..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/modules/encoders.md +++ /dev/null @@ -1,52 +0,0 @@ ---- -description: Discover detailed information on ImageEncoderViT, PositionEmbeddingRandom, Attention, window_partition, get_rel_pos and more in Ultralytics models encoders documentation. -keywords: Ultralytics, Encoders, Modules, Documentation, ImageEncoderViT, PositionEmbeddingRandom, Attention, window_partition, get_rel_pos ---- - -# Reference for `ultralytics/models/sam/modules/encoders.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/encoders.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/encoders.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/modules/encoders.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.modules.encoders.ImageEncoderViT - -

- -## ::: ultralytics.models.sam.modules.encoders.PromptEncoder - -

- -## ::: ultralytics.models.sam.modules.encoders.PositionEmbeddingRandom - -

- -## ::: ultralytics.models.sam.modules.encoders.Block - -

- -## ::: ultralytics.models.sam.modules.encoders.Attention - -

- -## ::: ultralytics.models.sam.modules.encoders.PatchEmbed - -

- -## ::: ultralytics.models.sam.modules.encoders.window_partition - -

- -## ::: ultralytics.models.sam.modules.encoders.window_unpartition - -

- -## ::: ultralytics.models.sam.modules.encoders.get_rel_pos - -

- -## ::: ultralytics.models.sam.modules.encoders.add_decomposed_rel_pos - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/modules/sam.md b/ultralytics-main/docs/en/reference/models/sam/modules/sam.md deleted file mode 100644 index d309e24..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/modules/sam.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the Sam module of Ultralytics. Discover detailed methods, classes, and information for efficient deep-learning model training!. -keywords: Ultralytics, Sam module, deep learning, model training, Ultralytics documentation ---- - -# Reference for `ultralytics/models/sam/modules/sam.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/sam.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/sam.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/modules/sam.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.modules.sam.Sam - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/modules/tiny_encoder.md b/ultralytics-main/docs/en/reference/models/sam/modules/tiny_encoder.md deleted file mode 100644 index 1d945be..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/modules/tiny_encoder.md +++ /dev/null @@ -1,56 +0,0 @@ ---- -description: Get in-depth insights about Ultralytics Tiny Encoder Modules such as Conv2d_BN, MBConv, ConvLayer, Attention, BasicLayer, and TinyViT. Improve your understanding of machine learning model components. -keywords: Ultralytics, Tiny Encoder, Conv2d_BN, MBConv, ConvLayer, Attention, BasicLayer, TinyViT, Machine learning modules, Ultralytics models ---- - -# Reference for `ultralytics/models/sam/modules/tiny_encoder.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/tiny_encoder.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/tiny_encoder.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/modules/tiny_encoder.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.Conv2d_BN - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.PatchEmbed - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.MBConv - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.PatchMerging - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.ConvLayer - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.Mlp - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.Attention - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.TinyViTBlock - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.BasicLayer - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.LayerNorm2d - -

- -## ::: ultralytics.models.sam.modules.tiny_encoder.TinyViT - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/modules/transformer.md b/ultralytics-main/docs/en/reference/models/sam/modules/transformer.md deleted file mode 100644 index d36a31e..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/modules/transformer.md +++ /dev/null @@ -1,24 +0,0 @@ ---- -description: Learn about TwoWayTransformer and Attention modules in Ultralytics. Leverage these tools to enhance your AI models. -keywords: Ultralytics, TwoWayTransformer, Attention, AI models, transformers ---- - -# Reference for `ultralytics/models/sam/modules/transformer.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/transformer.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/modules/transformer.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/modules/transformer.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.modules.transformer.TwoWayTransformer - -

- -## ::: ultralytics.models.sam.modules.transformer.TwoWayAttentionBlock - -

- -## ::: ultralytics.models.sam.modules.transformer.Attention - -

diff --git a/ultralytics-main/docs/en/reference/models/sam/predict.md b/ultralytics-main/docs/en/reference/models/sam/predict.md deleted file mode 100644 index ae4c788..0000000 --- a/ultralytics-main/docs/en/reference/models/sam/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Master the ultralytics.models.sam.predict.Predictor class with our comprehensive guide. Discover techniques to enhance your model predictions. -keywords: Ultralytics, predictor, models, sam.predict.Predictor, AI, machine learning, predictive models ---- - -# Reference for `ultralytics/models/sam/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/sam/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/sam/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.sam.predict.Predictor - -

diff --git a/ultralytics-main/docs/en/reference/models/utils/loss.md b/ultralytics-main/docs/en/reference/models/utils/loss.md deleted file mode 100644 index 567308e..0000000 --- a/ultralytics-main/docs/en/reference/models/utils/loss.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Learn to use the DETRLoss function provided by Ultralytics YOLO. Understand how to utilize loss in RTDETR detection models to improve accuracy. -keywords: Ultralytics, YOLO, Documentation, DETRLoss, Detection Loss, Loss function, DETR, RTDETR Detection Models ---- - -# Reference for `ultralytics/models/utils/loss.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/utils/loss.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/utils/loss.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/utils/loss.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.utils.loss.DETRLoss - -

- -## ::: ultralytics.models.utils.loss.RTDETRDetectionLoss - -

diff --git a/ultralytics-main/docs/en/reference/models/utils/ops.md b/ultralytics-main/docs/en/reference/models/utils/ops.md deleted file mode 100644 index 4ca7614..0000000 --- a/ultralytics-main/docs/en/reference/models/utils/ops.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Discover details for "HungarianMatcher" & "inverse_sigmoid" functions in Ultralytics YOLO, advanced tools supporting detection models. -keywords: Ultralytics, YOLO, HungarianMatcher, inverse_sigmoid, detection models, model utilities, ops ---- - -# Reference for `ultralytics/models/utils/ops.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/utils/ops.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/utils/ops.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/utils/ops.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.utils.ops.HungarianMatcher - -

- -## ::: ultralytics.models.utils.ops.get_cdn_group - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/classify/predict.md b/ultralytics-main/docs/en/reference/models/yolo/classify/predict.md deleted file mode 100644 index 581107b..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/classify/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the Ultralytics ClassificationPredictor guide for model prediction and visualization. Build powerful AI models with YOLO. -keywords: Ultralytics, classification predictor, predict, YOLO, AI models, model visualization ---- - -# Reference for `ultralytics/models/yolo/classify/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/classify/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.classify.predict.ClassificationPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/classify/train.md b/ultralytics-main/docs/en/reference/models/yolo/classify/train.md deleted file mode 100644 index e4b9ea8..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/classify/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Delve into Classification Trainer at Ultralytics YOLO docs and optimize your model's training process with insights from the masters!. -keywords: Ultralytics, YOLO, Classification Trainer, deep learning, training process, AI models, documentation ---- - -# Reference for `ultralytics/models/yolo/classify/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/classify/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.classify.train.ClassificationTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/classify/val.md b/ultralytics-main/docs/en/reference/models/yolo/classify/val.md deleted file mode 100644 index 27f64ff..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/classify/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore YOLO ClassificationValidator, a key element of Ultralytics YOLO models. Learn how it validates and fine-tunes model outputs. -keywords: Ultralytics, YOLO, ClassificationValidator, model validation, model fine-tuning, deep learning, computer vision ---- - -# Reference for `ultralytics/models/yolo/classify/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/classify/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.classify.val.ClassificationValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/detect/predict.md b/ultralytics-main/docs/en/reference/models/yolo/detect/predict.md deleted file mode 100644 index 4b6cafd..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/detect/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the guide to using the DetectionPredictor in Ultralytics YOLO. Learn how to predict, detect and analyze objects accurately. -keywords: Ultralytics, YOLO, DetectionPredictor, detect, predict, object detection, analysis ---- - -# Reference for `ultralytics/models/yolo/detect/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/detect/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.detect.predict.DetectionPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/detect/train.md b/ultralytics-main/docs/en/reference/models/yolo/detect/train.md deleted file mode 100644 index bca6faf..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/detect/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Maximize your model's potential with Ultralytics YOLO Detection Trainer. Learn advanced techniques, tips, and tricks for training. -keywords: Ultralytics YOLO, YOLO, Detection Trainer, Model Training, Machine Learning, Deep Learning, Computer Vision ---- - -# Reference for `ultralytics/models/yolo/detect/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/detect/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.detect.train.DetectionTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/detect/val.md b/ultralytics-main/docs/en/reference/models/yolo/detect/val.md deleted file mode 100644 index c5333d0..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/detect/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Discover function valuation of your YOLO models with the Ultralytics Detection Validator. Enhance precision and recall rates today. -keywords: Ultralytics, YOLO, Detection Validator, model valuation, precision, recall ---- - -# Reference for `ultralytics/models/yolo/detect/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/detect/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/detect/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.detect.val.DetectionValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/model.md b/ultralytics-main/docs/en/reference/models/yolo/model.md deleted file mode 100644 index 6df6b73..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/model.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Discover the Ultralytics YOLO model class. Learn advanced techniques, tips, and tricks for training. -keywords: Ultralytics YOLO, YOLO, YOLO model, Model Training, Machine Learning, Deep Learning, Computer Vision ---- - -# Reference for `ultralytics/models/yolo/model.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/model.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/model.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/model.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.model.YOLO - -

- -## ::: ultralytics.models.yolo.model.YOLOWorld - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/obb/predict.md b/ultralytics-main/docs/en/reference/models/yolo/obb/predict.md deleted file mode 100644 index 159f59a..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/obb/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Discover OBBPredictor for YOLO, specializing in Oriented Bounding Box predictions. Essential for advanced object detection with Ultralytics YOLO. -keywords: Ultralytics, OBBPredictor, YOLO, Oriented Bounding Box, object detection, advanced object detection, YOLO model, deep learning, AI, machine learning, computer vision, OBB detection ---- - -# Reference for `ultralytics/models/yolo/obb/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/obb/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.obb.predict.OBBPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/obb/train.md b/ultralytics-main/docs/en/reference/models/yolo/obb/train.md deleted file mode 100644 index 1a9c8ec..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/obb/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Master the Ultralytics YOLO OBB Trainer: A specialized tool for training YOLO models using Oriented Bounding Boxes. Features detailed usage, model initialization, and training processes. -keywords: Ultralytics, YOLO OBB Trainer, Oriented Bounding Box, OBB model training, YOLO model training, computer vision, deep learning, machine learning, YOLO object detection, model initialization, YOLO training process ---- - -# Reference for `ultralytics/models/yolo/obb/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/obb/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.obb.train.OBBTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/obb/val.md b/ultralytics-main/docs/en/reference/models/yolo/obb/val.md deleted file mode 100644 index b18db7e..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/obb/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about Ultralytics' advanced OBBValidator, an extension of YOLO object detection for oriented bounding box validation. -keywords: Ultralytics, YOLO, OBBValidator, object detection, oriented bounding box, OBB, machine learning, AI, deep learning, Python, YOLO model, image processing, computer vision, YOLO object detection ---- - -# Reference for `ultralytics/models/yolo/obb/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/obb/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/obb/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.obb.val.OBBValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/pose/predict.md b/ultralytics-main/docs/en/reference/models/yolo/pose/predict.md deleted file mode 100644 index 9eb4af4..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/pose/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Discover how to use PosePredictor in the Ultralytics YOLO model. Includes detailed guides, code examples, and explanations. -keywords: Ultralytics, YOLO, PosePredictor, machine learning, AI, predictive models ---- - -# Reference for `ultralytics/models/yolo/pose/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/pose/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.pose.predict.PosePredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/pose/train.md b/ultralytics-main/docs/en/reference/models/yolo/pose/train.md deleted file mode 100644 index 1d02bf2..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/pose/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore Ultralytics PoseTrainer for YOLO models. Get a step-by-step guide on how to train on custom pose data for more accurate AI modeling. -keywords: Ultralytics, YOLO, PoseTrainer, pose training, AI modeling, custom data training ---- - -# Reference for `ultralytics/models/yolo/pose/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/pose/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.pose.train.PoseTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/pose/val.md b/ultralytics-main/docs/en/reference/models/yolo/pose/val.md deleted file mode 100644 index 77207be..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/pose/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the PoseValidator—review how Ultralytics YOLO validates poses for object detection. Improve your understanding of YOLO. -keywords: PoseValidator, Ultralytics, YOLO, Object detection, Pose validation ---- - -# Reference for `ultralytics/models/yolo/pose/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/pose/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.pose.val.PoseValidator - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/segment/predict.md b/ultralytics-main/docs/en/reference/models/yolo/segment/predict.md deleted file mode 100644 index a92b6f6..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/segment/predict.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Discover how to utilize the YOLO Segmentation Predictor in Ultralytics. Enhance your objects detection skills with us. -keywords: YOLO, Ultralytics, object detection, segmentation predictor ---- - -# Reference for `ultralytics/models/yolo/segment/predict.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/predict.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/predict.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/segment/predict.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.segment.predict.SegmentationPredictor - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/segment/train.md b/ultralytics-main/docs/en/reference/models/yolo/segment/train.md deleted file mode 100644 index 1b5c3d5..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/segment/train.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Maximize your YOLO model's performance with our SegmentationTrainer. Explore comprehensive guides and tutorials on ultralytics.com. -keywords: Ultralytics, YOLO, SegmentationTrainer, image segmentation, object detection, model training, YOLO model ---- - -# Reference for `ultralytics/models/yolo/segment/train.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/train.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/train.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/segment/train.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.segment.train.SegmentationTrainer - -

diff --git a/ultralytics-main/docs/en/reference/models/yolo/segment/val.md b/ultralytics-main/docs/en/reference/models/yolo/segment/val.md deleted file mode 100644 index 745b22c..0000000 --- a/ultralytics-main/docs/en/reference/models/yolo/segment/val.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Get practical insights about our SegmentationValidator in YOLO Ultralytics models. Discover functionality details, methods, inputs, and outputs. -keywords: Ultralytics, YOLO, SegmentationValidator, model segmentation, image classification, object detection ---- - -# Reference for `ultralytics/models/yolo/segment/val.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/val.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/segment/val.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/models/yolo/segment/val.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.models.yolo.segment.val.SegmentationValidator - -

diff --git a/ultralytics-main/docs/en/reference/nn/autobackend.md b/ultralytics-main/docs/en/reference/nn/autobackend.md deleted file mode 100644 index 3e8c2f7..0000000 --- a/ultralytics-main/docs/en/reference/nn/autobackend.md +++ /dev/null @@ -1,24 +0,0 @@ ---- -description: Get to know more about Ultralytics nn.autobackend.check_class_names functionality. Optimize your YOLO models seamlessly. -keywords: Ultralytics, AutoBackend, check_class_names, YOLO, YOLO models, optimization ---- - -# Reference for `ultralytics/nn/autobackend.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/autobackend.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/autobackend.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/autobackend.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.autobackend.AutoBackend - -

- -## ::: ultralytics.nn.autobackend.check_class_names - -

- -## ::: ultralytics.nn.autobackend.default_class_names - -

diff --git a/ultralytics-main/docs/en/reference/nn/modules/block.md b/ultralytics-main/docs/en/reference/nn/modules/block.md deleted file mode 100644 index e94da5a..0000000 --- a/ultralytics-main/docs/en/reference/nn/modules/block.md +++ /dev/null @@ -1,140 +0,0 @@ ---- -description: Explore Ultralytics YOLO neural network modules, Proto to BottleneckCSP. Detailed explanation of each module with easy-to-follow code examples. -keywords: YOLO, Ultralytics, neural network, nn.modules.block, Proto, HGBlock, SPPF, C2, C3, RepC3, C3Ghost, Bottleneck, BottleneckCSP ---- - -# Reference for `ultralytics/nn/modules/block.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/block.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/block.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/modules/block.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.modules.block.DFL - -

- -## ::: ultralytics.nn.modules.block.Proto - -

- -## ::: ultralytics.nn.modules.block.HGStem - -

- -## ::: ultralytics.nn.modules.block.HGBlock - -

- -## ::: ultralytics.nn.modules.block.SPP - -

- -## ::: ultralytics.nn.modules.block.SPPF - -

- -## ::: ultralytics.nn.modules.block.C1 - -

- -## ::: ultralytics.nn.modules.block.C2 - -

- -## ::: ultralytics.nn.modules.block.C2f - -

- -## ::: ultralytics.nn.modules.block.C3 - -

- -## ::: ultralytics.nn.modules.block.C3x - -

- -## ::: ultralytics.nn.modules.block.RepC3 - -

- -## ::: ultralytics.nn.modules.block.C3TR - -

- -## ::: ultralytics.nn.modules.block.C3Ghost - -

- -## ::: ultralytics.nn.modules.block.GhostBottleneck - -

- -## ::: ultralytics.nn.modules.block.Bottleneck - -

- -## ::: ultralytics.nn.modules.block.BottleneckCSP - -

- -## ::: ultralytics.nn.modules.block.ResNetBlock - -

- -## ::: ultralytics.nn.modules.block.ResNetLayer - -

- -## ::: ultralytics.nn.modules.block.MaxSigmoidAttnBlock - -

- -## ::: ultralytics.nn.modules.block.C2fAttn - -

- -## ::: ultralytics.nn.modules.block.ImagePoolingAttn - -

- -## ::: ultralytics.nn.modules.block.ContrastiveHead - -

- -## ::: ultralytics.nn.modules.block.BNContrastiveHead - -

- -## ::: ultralytics.nn.modules.block.RepBottleneck - -

- -## ::: ultralytics.nn.modules.block.RepCSP - -

- -## ::: ultralytics.nn.modules.block.RepNCSPELAN4 - -

- -## ::: ultralytics.nn.modules.block.ADown - -

- -## ::: ultralytics.nn.modules.block.SPPELAN - -

- -## ::: ultralytics.nn.modules.block.Silence - -

- -## ::: ultralytics.nn.modules.block.CBLinear - -

- -## ::: ultralytics.nn.modules.block.CBFuse - -

diff --git a/ultralytics-main/docs/en/reference/nn/modules/conv.md b/ultralytics-main/docs/en/reference/nn/modules/conv.md deleted file mode 100644 index 6c9fb35..0000000 --- a/ultralytics-main/docs/en/reference/nn/modules/conv.md +++ /dev/null @@ -1,68 +0,0 @@ ---- -description: Explore various Ultralytics convolution modules including Conv2, DWConv, ConvTranspose, GhostConv, Channel Attention and more. -keywords: Ultralytics, Convolution Modules, Conv2, DWConv, ConvTranspose, GhostConv, ChannelAttention, CBAM, autopad ---- - -# Reference for `ultralytics/nn/modules/conv.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/conv.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/conv.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/modules/conv.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.modules.conv.Conv - -

- -## ::: ultralytics.nn.modules.conv.Conv2 - -

- -## ::: ultralytics.nn.modules.conv.LightConv - -

- -## ::: ultralytics.nn.modules.conv.DWConv - -

- -## ::: ultralytics.nn.modules.conv.DWConvTranspose2d - -

- -## ::: ultralytics.nn.modules.conv.ConvTranspose - -

- -## ::: ultralytics.nn.modules.conv.Focus - -

- -## ::: ultralytics.nn.modules.conv.GhostConv - -

- -## ::: ultralytics.nn.modules.conv.RepConv - -

- -## ::: ultralytics.nn.modules.conv.ChannelAttention - -

- -## ::: ultralytics.nn.modules.conv.SpatialAttention - -

- -## ::: ultralytics.nn.modules.conv.CBAM - -

- -## ::: ultralytics.nn.modules.conv.Concat - -

- -## ::: ultralytics.nn.modules.conv.autopad - -

diff --git a/ultralytics-main/docs/en/reference/nn/modules/head.md b/ultralytics-main/docs/en/reference/nn/modules/head.md deleted file mode 100644 index 6dc3e44..0000000 --- a/ultralytics-main/docs/en/reference/nn/modules/head.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Explore docs covering Ultralytics YOLO detection, pose & RTDETRDecoder. Comprehensive guides to help you understand Ultralytics nn modules. -keywords: Ultralytics, YOLO, Detection, Pose, RTDETRDecoder, nn modules, guides ---- - -# Reference for `ultralytics/nn/modules/head.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/head.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/head.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/modules/head.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.modules.head.Detect - -

- -## ::: ultralytics.nn.modules.head.Segment - -

- -## ::: ultralytics.nn.modules.head.OBB - -

- -## ::: ultralytics.nn.modules.head.Pose - -

- -## ::: ultralytics.nn.modules.head.Classify - -

- -## ::: ultralytics.nn.modules.head.WorldDetect - -

- -## ::: ultralytics.nn.modules.head.RTDETRDecoder - -

diff --git a/ultralytics-main/docs/en/reference/nn/modules/transformer.md b/ultralytics-main/docs/en/reference/nn/modules/transformer.md deleted file mode 100644 index 91904be..0000000 --- a/ultralytics-main/docs/en/reference/nn/modules/transformer.md +++ /dev/null @@ -1,52 +0,0 @@ ---- -description: Learn about Ultralytics transformer encoder, layer, MLP block, LayerNorm2d and the deformable transformer decoder layer. Expand your understanding of these crucial AI modules. -keywords: Ultralytics, Ultralytics documentation, TransformerEncoderLayer, TransformerLayer, MLPBlock, LayerNorm2d, DeformableTransformerDecoderLayer ---- - -# Reference for `ultralytics/nn/modules/transformer.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/transformer.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/transformer.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/modules/transformer.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.modules.transformer.TransformerEncoderLayer - -

- -## ::: ultralytics.nn.modules.transformer.AIFI - -

- -## ::: ultralytics.nn.modules.transformer.TransformerLayer - -

- -## ::: ultralytics.nn.modules.transformer.TransformerBlock - -

- -## ::: ultralytics.nn.modules.transformer.MLPBlock - -

- -## ::: ultralytics.nn.modules.transformer.MLP - -

- -## ::: ultralytics.nn.modules.transformer.LayerNorm2d - -

- -## ::: ultralytics.nn.modules.transformer.MSDeformAttn - -

- -## ::: ultralytics.nn.modules.transformer.DeformableTransformerDecoderLayer - -

- -## ::: ultralytics.nn.modules.transformer.DeformableTransformerDecoder - -

diff --git a/ultralytics-main/docs/en/reference/nn/modules/utils.md b/ultralytics-main/docs/en/reference/nn/modules/utils.md deleted file mode 100644 index 22b813e..0000000 --- a/ultralytics-main/docs/en/reference/nn/modules/utils.md +++ /dev/null @@ -1,32 +0,0 @@ ---- -description: Explore Ultralytics neural network utils, such as bias_init_with_prob, inverse_sigmoid and multi_scale_deformable_attn_pytorch functions. -keywords: Ultralytics, neural network, nn.modules.utils, bias_init_with_prob, inverse_sigmoid, multi_scale_deformable_attn_pytorch ---- - -# Reference for `ultralytics/nn/modules/utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/modules/utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.modules.utils._get_clones - -

- -## ::: ultralytics.nn.modules.utils.bias_init_with_prob - -

- -## ::: ultralytics.nn.modules.utils.linear_init - -

- -## ::: ultralytics.nn.modules.utils.inverse_sigmoid - -

- -## ::: ultralytics.nn.modules.utils.multi_scale_deformable_attn_pytorch - -

diff --git a/ultralytics-main/docs/en/reference/nn/tasks.md b/ultralytics-main/docs/en/reference/nn/tasks.md deleted file mode 100644 index 66d2e0e..0000000 --- a/ultralytics-main/docs/en/reference/nn/tasks.md +++ /dev/null @@ -1,80 +0,0 @@ ---- -description: Dive into the intricacies of YOLO tasks.py. Learn about DetectionModel, PoseModel and more for powerful AI development. -keywords: Ultralytics, YOLO, nn tasks, DetectionModel, PoseModel, RTDETRDetectionModel, model weights, parse model, AI development ---- - -# Reference for `ultralytics/nn/tasks.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/tasks.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/tasks.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/nn/tasks.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.nn.tasks.BaseModel - -

- -## ::: ultralytics.nn.tasks.DetectionModel - -

- -## ::: ultralytics.nn.tasks.OBBModel - -

- -## ::: ultralytics.nn.tasks.SegmentationModel - -

- -## ::: ultralytics.nn.tasks.PoseModel - -

- -## ::: ultralytics.nn.tasks.ClassificationModel - -

- -## ::: ultralytics.nn.tasks.RTDETRDetectionModel - -

- -## ::: ultralytics.nn.tasks.WorldModel - -

- -## ::: ultralytics.nn.tasks.Ensemble - -

- -## ::: ultralytics.nn.tasks.temporary_modules - -

- -## ::: ultralytics.nn.tasks.torch_safe_load - -

- -## ::: ultralytics.nn.tasks.attempt_load_weights - -

- -## ::: ultralytics.nn.tasks.attempt_load_one_weight - -

- -## ::: ultralytics.nn.tasks.parse_model - -

- -## ::: ultralytics.nn.tasks.yaml_model_load - -

- -## ::: ultralytics.nn.tasks.guess_model_scale - -

- -## ::: ultralytics.nn.tasks.guess_model_task - -

diff --git a/ultralytics-main/docs/en/reference/solutions/ai_gym.md b/ultralytics-main/docs/en/reference/solutions/ai_gym.md deleted file mode 100644 index eb3e634..0000000 --- a/ultralytics-main/docs/en/reference/solutions/ai_gym.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore Ultralytics YOLO's advanced AI Gym feature for real-time pose estimation and gym exercise tracking using cutting-edge machine learning technology. -keywords: Ultralytics, YOLO, AI Gym, pose estimation, real-time tracking, machine learning, exercise counting, AI fitness, computer vision, gym workout analysis, YOLOv8, artificial intelligence, fitness technology ---- - -# Reference for `ultralytics/solutions/ai_gym.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/ai_gym.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/ai_gym.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/ai_gym.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.solutions.ai_gym.AIGym - -

diff --git a/ultralytics-main/docs/en/reference/solutions/distance_calculation.md b/ultralytics-main/docs/en/reference/solutions/distance_calculation.md deleted file mode 100644 index 4361885..0000000 --- a/ultralytics-main/docs/en/reference/solutions/distance_calculation.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore Ultralytics YOLO's distance calculation feature designed for advance analytics, providing an immediate, impactful way to interpret computer vision data. -keywords: Ultralytics, YOLO, distance calculation, object tracking, data visualization, real-time tracking, machine learning, object counting, computer vision, vehicle analytics, YOLOv8, artificial intelligence ---- - -# Reference for `ultralytics/solutions/distance_calculation.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/distance_calculation.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.solutions.distance_calculation.DistanceCalculation - -

diff --git a/ultralytics-main/docs/en/reference/solutions/heatmap.md b/ultralytics-main/docs/en/reference/solutions/heatmap.md deleted file mode 100644 index 133125c..0000000 --- a/ultralytics-main/docs/en/reference/solutions/heatmap.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore Ultralytics YOLO's advanced Heatmaps feature designed to highlight areas of interest, providing an immediate, impactful way to interpret spatial information. -keywords: Ultralytics, YOLO, heatmaps, object tracking, data visualization, real-time tracking, machine learning, object counting, computer vision, retail analytics, YOLOv8, artificial intelligence ---- - -# Reference for `ultralytics/solutions/heatmap.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/heatmap.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/heatmap.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/heatmap.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.solutions.heatmap.Heatmap - -

diff --git a/ultralytics-main/docs/en/reference/solutions/object_counter.md b/ultralytics-main/docs/en/reference/solutions/object_counter.md deleted file mode 100644 index 6cd3e00..0000000 --- a/ultralytics-main/docs/en/reference/solutions/object_counter.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Transform object tracking with Ultralytics YOLO Object Counter featuring cutting-edge technology for precise real-time counting in video streams. -keywords: Ultralytics YOLO, object tracking software, real-time counting solutions, video stream analysis, YOLOv8 object detection, AI surveillance, smart counting technology, computer vision, AI-powered tracking, object counting accuracy, video analytics tools, automated monitoring. ---- - -# Reference for `ultralytics/solutions/object_counter.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/object_counter.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/object_counter.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/object_counter.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.solutions.object_counter.ObjectCounter - -

diff --git a/ultralytics-main/docs/en/reference/solutions/speed_estimation.md b/ultralytics-main/docs/en/reference/solutions/speed_estimation.md deleted file mode 100644 index 93cc87e..0000000 --- a/ultralytics-main/docs/en/reference/solutions/speed_estimation.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Transform speed estimation with Ultralytics YOLO speed estimation featuring cutting-edge technology for precise real-time counting in video streams. -keywords: Ultralytics YOLO, speed estimation software, real-time vehicle tracking solutions, video stream analysis, YOLOv8 object detection, smart counting technology, computer vision, AI-powered tracking, video analytics tools, automated monitoring. ---- - -# Reference for `ultralytics/solutions/speed_estimation.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/speed_estimation.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.solutions.speed_estimation.SpeedEstimator - -

diff --git a/ultralytics-main/docs/en/reference/trackers/basetrack.md b/ultralytics-main/docs/en/reference/trackers/basetrack.md deleted file mode 100644 index 97f5c4a..0000000 --- a/ultralytics-main/docs/en/reference/trackers/basetrack.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Get familiar with TrackState in Ultralytics. Learn how it is used in the BaseTrack of the Ultralytics tracker for enhanced functionality. -keywords: Ultralytics, TrackState, BaseTrack, Ultralytics tracker, Ultralytics documentation ---- - -# Reference for `ultralytics/trackers/basetrack.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/basetrack.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/basetrack.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/basetrack.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.basetrack.TrackState - -

- -## ::: ultralytics.trackers.basetrack.BaseTrack - -

diff --git a/ultralytics-main/docs/en/reference/trackers/bot_sort.md b/ultralytics-main/docs/en/reference/trackers/bot_sort.md deleted file mode 100644 index 85dfeee..0000000 --- a/ultralytics-main/docs/en/reference/trackers/bot_sort.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Master the use of Ultralytics BOTrack, a key component of the powerful Ultralytics tracking system. Learn to integrate and use BOTSORT in your projects. -keywords: Ultralytics, BOTSORT, BOTrack, tracking system, official documentation, machine learning, AI tracking ---- - -# Reference for `ultralytics/trackers/bot_sort.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/bot_sort.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/bot_sort.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/bot_sort.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.bot_sort.BOTrack - -

- -## ::: ultralytics.trackers.bot_sort.BOTSORT - -

diff --git a/ultralytics-main/docs/en/reference/trackers/byte_tracker.md b/ultralytics-main/docs/en/reference/trackers/byte_tracker.md deleted file mode 100644 index e240d44..0000000 --- a/ultralytics-main/docs/en/reference/trackers/byte_tracker.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Step-in to explore in-depth the functionalities of Ultralytics BYTETracker under STrack. Gain advanced feature insights to streamline your operations. -keywords: STrack, Ultralytics, BYTETracker, documentation, Ultralytics tracker, object tracking, YOLO ---- - -# Reference for `ultralytics/trackers/byte_tracker.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/byte_tracker.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/byte_tracker.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/byte_tracker.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.byte_tracker.STrack - -

- -## ::: ultralytics.trackers.byte_tracker.BYTETracker - -

diff --git a/ultralytics-main/docs/en/reference/trackers/track.md b/ultralytics-main/docs/en/reference/trackers/track.md deleted file mode 100644 index 7f15130..0000000 --- a/ultralytics-main/docs/en/reference/trackers/track.md +++ /dev/null @@ -1,24 +0,0 @@ ---- -description: Explore Ultralytics documentation on prediction function starters & register trackers. Understand our code & its applications better. -keywords: Ultralytics, YOLO, on predict start, register tracker, prediction functions, documentation ---- - -# Reference for `ultralytics/trackers/track.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/track.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/track.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/track.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.track.on_predict_start - -

- -## ::: ultralytics.trackers.track.on_predict_postprocess_end - -

- -## ::: ultralytics.trackers.track.register_tracker - -

diff --git a/ultralytics-main/docs/en/reference/trackers/utils/gmc.md b/ultralytics-main/docs/en/reference/trackers/utils/gmc.md deleted file mode 100644 index fa51e8e..0000000 --- a/ultralytics-main/docs/en/reference/trackers/utils/gmc.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Explore the Ultralytics GMC tool in our comprehensive documentation. Learn how it works, best practices, and implementation advice. -keywords: Ultralytics, GMC utility, Ultralytics documentation, Ultralytics tracker, machine learning tools ---- - -# Reference for `ultralytics/trackers/utils/gmc.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/gmc.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/gmc.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/utils/gmc.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.utils.gmc.GMC - -

diff --git a/ultralytics-main/docs/en/reference/trackers/utils/kalman_filter.md b/ultralytics-main/docs/en/reference/trackers/utils/kalman_filter.md deleted file mode 100644 index 11063ef..0000000 --- a/ultralytics-main/docs/en/reference/trackers/utils/kalman_filter.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Explore KalmanFilterXYAH, a key component of Ultralytics trackers. Understand its utilities and learn to leverage it in your own projects. -keywords: Ultralytics, KalmanFilterXYAH, tracker, documentation, guide ---- - -# Reference for `ultralytics/trackers/utils/kalman_filter.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/kalman_filter.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/kalman_filter.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/utils/kalman_filter.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.utils.kalman_filter.KalmanFilterXYAH - -

- -## ::: ultralytics.trackers.utils.kalman_filter.KalmanFilterXYWH - -

diff --git a/ultralytics-main/docs/en/reference/trackers/utils/matching.md b/ultralytics-main/docs/en/reference/trackers/utils/matching.md deleted file mode 100644 index fb7d326..0000000 --- a/ultralytics-main/docs/en/reference/trackers/utils/matching.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Explore in-depth guidance for using Ultralytics trackers utils matching, including merge_matches, linear_assignment, iou_distance, embedding_distance, fuse_motion, and fuse_score. -keywords: Ultralytics, Trackers Utils, Matching, merge_matches, linear_assignment, iou_distance, embedding_distance, fuse_motion, fuse_score, documentation ---- - -# Reference for `ultralytics/trackers/utils/matching.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/matching.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/trackers/utils/matching.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/trackers/utils/matching.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.trackers.utils.matching.linear_assignment - -

- -## ::: ultralytics.trackers.utils.matching.iou_distance - -

- -## ::: ultralytics.trackers.utils.matching.embedding_distance - -

- -## ::: ultralytics.trackers.utils.matching.fuse_score - -

diff --git a/ultralytics-main/docs/en/reference/utils/__init__.md b/ultralytics-main/docs/en/reference/utils/__init__.md deleted file mode 100644 index fc4c9a7..0000000 --- a/ultralytics-main/docs/en/reference/utils/__init__.md +++ /dev/null @@ -1,160 +0,0 @@ ---- -description: Explore the Ultralytics Utils package, with handy functions like colorstr, yaml_save, set_logging & more, designed to enhance your coding experience. -keywords: Ultralytics, Utils, utilitarian functions, colorstr, yaml_save, set_logging, is_kaggle, is_docker, clean_url ---- - -# Reference for `ultralytics/utils/__init__.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/__init__.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/__init__.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/__init__.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.TQDM - -

- -## ::: ultralytics.utils.SimpleClass - -

- -## ::: ultralytics.utils.IterableSimpleNamespace - -

- -## ::: ultralytics.utils.ThreadingLocked - -

- -## ::: ultralytics.utils.TryExcept - -

- -## ::: ultralytics.utils.Retry - -

- -## ::: ultralytics.utils.SettingsManager - -

- -## ::: ultralytics.utils.plt_settings - -

- -## ::: ultralytics.utils.set_logging - -

- -## ::: ultralytics.utils.emojis - -

- -## ::: ultralytics.utils.yaml_save - -

- -## ::: ultralytics.utils.yaml_load - -

- -## ::: ultralytics.utils.yaml_print - -

- -## ::: ultralytics.utils.is_ubuntu - -

- -## ::: ultralytics.utils.is_colab - -

- -## ::: ultralytics.utils.is_kaggle - -

- -## ::: ultralytics.utils.is_jupyter - -

- -## ::: ultralytics.utils.is_docker - -

- -## ::: ultralytics.utils.is_online - -

- -## ::: ultralytics.utils.is_pip_package - -

- -## ::: ultralytics.utils.is_dir_writeable - -

- -## ::: ultralytics.utils.is_pytest_running - -

- -## ::: ultralytics.utils.is_github_action_running - -

- -## ::: ultralytics.utils.is_git_dir - -

- -## ::: ultralytics.utils.get_git_dir - -

- -## ::: ultralytics.utils.get_git_origin_url - -

- -## ::: ultralytics.utils.get_git_branch - -

- -## ::: ultralytics.utils.get_default_args - -

- -## ::: ultralytics.utils.get_ubuntu_version - -

- -## ::: ultralytics.utils.get_user_config_dir - -

- -## ::: ultralytics.utils.colorstr - -

- -## ::: ultralytics.utils.remove_colorstr - -

- -## ::: ultralytics.utils.threaded - -

- -## ::: ultralytics.utils.set_sentry - -

- -## ::: ultralytics.utils.deprecation_warn - -

- -## ::: ultralytics.utils.clean_url - -

- -## ::: ultralytics.utils.url2file - -

diff --git a/ultralytics-main/docs/en/reference/utils/autobatch.md b/ultralytics-main/docs/en/reference/utils/autobatch.md deleted file mode 100644 index 4dc132b..0000000 --- a/ultralytics-main/docs/en/reference/utils/autobatch.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Explore Ultralytics documentation for check_train_batch_size utility in the autobatch module. Understand how it could improve your machine learning process. -keywords: Ultralytics, check_train_batch_size, autobatch, utility, machine learning, documentation ---- - -# Reference for `ultralytics/utils/autobatch.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/autobatch.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/autobatch.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/autobatch.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.autobatch.check_train_batch_size - -

- -## ::: ultralytics.utils.autobatch.autobatch - -

diff --git a/ultralytics-main/docs/en/reference/utils/benchmarks.md b/ultralytics-main/docs/en/reference/utils/benchmarks.md deleted file mode 100644 index 76d4885..0000000 --- a/ultralytics-main/docs/en/reference/utils/benchmarks.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -description: Discover how to profile your models using Ultralytics utilities. Enhance performance, optimize your benchmarks, and learn best practices. -keywords: Ultralytics, ProfileModels, benchmarks, model profiling, performance optimization ---- - -# Reference for `ultralytics/utils/benchmarks.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/benchmarks.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/benchmarks.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/benchmarks.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.benchmarks.ProfileModels - -

- -## ::: ultralytics.utils.benchmarks.benchmark - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/base.md b/ultralytics-main/docs/en/reference/utils/callbacks/base.md deleted file mode 100644 index 609e34b..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/base.md +++ /dev/null @@ -1,120 +0,0 @@ ---- -description: Explore how to use the on-train, on-validation, on-pretrain, and on-predict callbacks in Ultralytics. Learn to update params, save models, and add integration callbacks. -keywords: Ultralytics, Callbacks, On-train, On-validation, On-pretrain, On-predict, Parameters update, Model saving, Integration callbacks ---- - -# Reference for `ultralytics/utils/callbacks/base.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/base.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/base.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/base.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.base.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.base.on_pretrain_routine_end - -

- -## ::: ultralytics.utils.callbacks.base.on_train_start - -

- -## ::: ultralytics.utils.callbacks.base.on_train_epoch_start - -

- -## ::: ultralytics.utils.callbacks.base.on_train_batch_start - -

- -## ::: ultralytics.utils.callbacks.base.optimizer_step - -

- -## ::: ultralytics.utils.callbacks.base.on_before_zero_grad - -

- -## ::: ultralytics.utils.callbacks.base.on_train_batch_end - -

- -## ::: ultralytics.utils.callbacks.base.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.base.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.base.on_model_save - -

- -## ::: ultralytics.utils.callbacks.base.on_train_end - -

- -## ::: ultralytics.utils.callbacks.base.on_params_update - -

- -## ::: ultralytics.utils.callbacks.base.teardown - -

- -## ::: ultralytics.utils.callbacks.base.on_val_start - -

- -## ::: ultralytics.utils.callbacks.base.on_val_batch_start - -

- -## ::: ultralytics.utils.callbacks.base.on_val_batch_end - -

- -## ::: ultralytics.utils.callbacks.base.on_val_end - -

- -## ::: ultralytics.utils.callbacks.base.on_predict_start - -

- -## ::: ultralytics.utils.callbacks.base.on_predict_batch_start - -

- -## ::: ultralytics.utils.callbacks.base.on_predict_batch_end - -

- -## ::: ultralytics.utils.callbacks.base.on_predict_postprocess_end - -

- -## ::: ultralytics.utils.callbacks.base.on_predict_end - -

- -## ::: ultralytics.utils.callbacks.base.on_export_start - -

- -## ::: ultralytics.utils.callbacks.base.on_export_end - -

- -## ::: ultralytics.utils.callbacks.base.get_default_callbacks - -

- -## ::: ultralytics.utils.callbacks.base.add_integration_callbacks - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/clearml.md b/ultralytics-main/docs/en/reference/utils/callbacks/clearml.md deleted file mode 100644 index a05b08c..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/clearml.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Uncover the specifics of Ultralytics ClearML callbacks, from pretrain routine start to training end. Boost your ML model performance. -keywords: Ultralytics, clearML, callbacks, pretrain routine start, validation end, train epoch end, training end ---- - -# Reference for `ultralytics/utils/callbacks/clearml.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/clearml.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/clearml.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/clearml.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.clearml._log_debug_samples - -

- -## ::: ultralytics.utils.callbacks.clearml._log_plot - -

- -## ::: ultralytics.utils.callbacks.clearml.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.clearml.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.clearml.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.clearml.on_val_end - -

- -## ::: ultralytics.utils.callbacks.clearml.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/comet.md b/ultralytics-main/docs/en/reference/utils/callbacks/comet.md deleted file mode 100644 index 2ba62fa..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/comet.md +++ /dev/null @@ -1,108 +0,0 @@ ---- -description: Explore comprehensive documentation for utilising Comet Callbacks in Ultralytics. Learn to optimise training, logging, and experiment workflows. -keywords: Ultralytics, Comet Callbacks, Training optimisation, Logging, Experiment Workflows ---- - -# Reference for `ultralytics/utils/callbacks/comet.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/comet.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/comet.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/comet.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.comet._get_comet_mode - -

- -## ::: ultralytics.utils.callbacks.comet._get_comet_model_name - -

- -## ::: ultralytics.utils.callbacks.comet._get_eval_batch_logging_interval - -

- -## ::: ultralytics.utils.callbacks.comet._get_max_image_predictions_to_log - -

- -## ::: ultralytics.utils.callbacks.comet._scale_confidence_score - -

- -## ::: ultralytics.utils.callbacks.comet._should_log_confusion_matrix - -

- -## ::: ultralytics.utils.callbacks.comet._should_log_image_predictions - -

- -## ::: ultralytics.utils.callbacks.comet._get_experiment_type - -

- -## ::: ultralytics.utils.callbacks.comet._create_experiment - -

- -## ::: ultralytics.utils.callbacks.comet._fetch_trainer_metadata - -

- -## ::: ultralytics.utils.callbacks.comet._scale_bounding_box_to_original_image_shape - -

- -## ::: ultralytics.utils.callbacks.comet._format_ground_truth_annotations_for_detection - -

- -## ::: ultralytics.utils.callbacks.comet._format_prediction_annotations_for_detection - -

- -## ::: ultralytics.utils.callbacks.comet._fetch_annotations - -

- -## ::: ultralytics.utils.callbacks.comet._create_prediction_metadata_map - -

- -## ::: ultralytics.utils.callbacks.comet._log_confusion_matrix - -

- -## ::: ultralytics.utils.callbacks.comet._log_images - -

- -## ::: ultralytics.utils.callbacks.comet._log_image_predictions - -

- -## ::: ultralytics.utils.callbacks.comet._log_plots - -

- -## ::: ultralytics.utils.callbacks.comet._log_model - -

- -## ::: ultralytics.utils.callbacks.comet.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.comet.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.comet.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.comet.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/dvc.md b/ultralytics-main/docs/en/reference/utils/callbacks/dvc.md deleted file mode 100644 index a325989..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/dvc.md +++ /dev/null @@ -1,48 +0,0 @@ ---- -description: Browse through Ultralytics YOLO docs to learn about important logging and callback functions used in training and pretraining models. -keywords: Ultralytics, YOLO, callbacks, logger, training, pretraining, machine learning, models ---- - -# Reference for `ultralytics/utils/callbacks/dvc.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/dvc.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/dvc.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/dvc.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.dvc._log_images - -

- -## ::: ultralytics.utils.callbacks.dvc._log_plots - -

- -## ::: ultralytics.utils.callbacks.dvc._log_confusion_matrix - -

- -## ::: ultralytics.utils.callbacks.dvc.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.dvc.on_pretrain_routine_end - -

- -## ::: ultralytics.utils.callbacks.dvc.on_train_start - -

- -## ::: ultralytics.utils.callbacks.dvc.on_train_epoch_start - -

- -## ::: ultralytics.utils.callbacks.dvc.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.dvc.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/hub.md b/ultralytics-main/docs/en/reference/utils/callbacks/hub.md deleted file mode 100644 index 3735e90..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/hub.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -description: Explore the detailed information on key Ultralytics callbacks such as on_pretrain_routine_end, on_model_save, on_train_start, and on_predict_start. -keywords: Ultralytics, callbacks, on_pretrain_routine_end, on_model_save, on_train_start, on_predict_start, hub, training ---- - -# Reference for `ultralytics/utils/callbacks/hub.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/hub.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/hub.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/hub.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.hub.on_pretrain_routine_end - -

- -## ::: ultralytics.utils.callbacks.hub.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.hub.on_model_save - -

- -## ::: ultralytics.utils.callbacks.hub.on_train_end - -

- -## ::: ultralytics.utils.callbacks.hub.on_train_start - -

- -## ::: ultralytics.utils.callbacks.hub.on_val_start - -

- -## ::: ultralytics.utils.callbacks.hub.on_predict_start - -

- -## ::: ultralytics.utils.callbacks.hub.on_export_start - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/mlflow.md b/ultralytics-main/docs/en/reference/utils/callbacks/mlflow.md deleted file mode 100644 index e3fab6c..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/mlflow.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Understand routines at the end of pre-training and training in Ultralytics. Elevate your MLflow callbacks expertise. -keywords: Ultralytics, MLflow, Callbacks, on_pretrain_routine_end, on_train_end, Machine Learning, Training ---- - -# Reference for `ultralytics/utils/callbacks/mlflow.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/mlflow.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/mlflow.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/mlflow.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.mlflow.on_pretrain_routine_end - -

- -## ::: ultralytics.utils.callbacks.mlflow.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.mlflow.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.mlflow.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/neptune.md b/ultralytics-main/docs/en/reference/utils/callbacks/neptune.md deleted file mode 100644 index 82906ac..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/neptune.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -description: Explore exhaustive details about Ultralytics callbacks in Neptune, with specifics about scalar logging, routine start, and more. -keywords: Ultralytics, Neptune callbacks, on_train_epoch_end, on_val_end, _log_plot, _log_images, on_pretrain_routine_start, on_fit_epoch_end, on_train_end ---- - -# Reference for `ultralytics/utils/callbacks/neptune.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/neptune.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/neptune.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/neptune.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.neptune._log_scalars - -

- -## ::: ultralytics.utils.callbacks.neptune._log_images - -

- -## ::: ultralytics.utils.callbacks.neptune._log_plot - -

- -## ::: ultralytics.utils.callbacks.neptune.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.neptune.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.neptune.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.neptune.on_val_end - -

- -## ::: ultralytics.utils.callbacks.neptune.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/raytune.md b/ultralytics-main/docs/en/reference/utils/callbacks/raytune.md deleted file mode 100644 index 2ed6191..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/raytune.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Discover the functionality of the on_fit_epoch_end callback in the Ultralytics YOLO framework. Learn how to end an epoch in your deep learning projects. -keywords: Ultralytics, YOLO, on_fit_epoch_end, callbacks, documentation, deep learning, YOLO framework ---- - -# Reference for `ultralytics/utils/callbacks/raytune.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/raytune.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/raytune.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/raytune.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.raytune.on_fit_epoch_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/tensorboard.md b/ultralytics-main/docs/en/reference/utils/callbacks/tensorboard.md deleted file mode 100644 index 74fb3b1..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/tensorboard.md +++ /dev/null @@ -1,36 +0,0 @@ ---- -description: Explore Ultralytics YOLO Docs for a deep understanding of log_scalars, on_batch_end & other callback utilities embedded in the tensorboard module. -keywords: Ultralytics, YOLO, documentation, callback utilities, log_scalars, on_batch_end, tensorboard ---- - -# Reference for `ultralytics/utils/callbacks/tensorboard.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/tensorboard.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/tensorboard.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/tensorboard.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.tensorboard._log_scalars - -

- -## ::: ultralytics.utils.callbacks.tensorboard._log_tensorboard_graph - -

- -## ::: ultralytics.utils.callbacks.tensorboard.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.tensorboard.on_train_start - -

- -## ::: ultralytics.utils.callbacks.tensorboard.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.tensorboard.on_fit_epoch_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/callbacks/wb.md b/ultralytics-main/docs/en/reference/utils/callbacks/wb.md deleted file mode 100644 index 59a2088..0000000 --- a/ultralytics-main/docs/en/reference/utils/callbacks/wb.md +++ /dev/null @@ -1,40 +0,0 @@ ---- -description: Deep dive into Ultralytics callbacks. Learn how to use the _log_plots, on_fit_epoch_end, and on_train_end functions effectively. -keywords: Ultralytics, callbacks, _log_plots, on_fit_epoch_end, on_train_end ---- - -# Reference for `ultralytics/utils/callbacks/wb.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/wb.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/wb.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/callbacks/wb.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.callbacks.wb._custom_table - -

- -## ::: ultralytics.utils.callbacks.wb._plot_curve - -

- -## ::: ultralytics.utils.callbacks.wb._log_plots - -

- -## ::: ultralytics.utils.callbacks.wb.on_pretrain_routine_start - -

- -## ::: ultralytics.utils.callbacks.wb.on_fit_epoch_end - -

- -## ::: ultralytics.utils.callbacks.wb.on_train_epoch_end - -

- -## ::: ultralytics.utils.callbacks.wb.on_train_end - -

diff --git a/ultralytics-main/docs/en/reference/utils/checks.md b/ultralytics-main/docs/en/reference/utils/checks.md deleted file mode 100644 index f2e4ed9..0000000 --- a/ultralytics-main/docs/en/reference/utils/checks.md +++ /dev/null @@ -1,112 +0,0 @@ ---- -description: Learn about our routine checks that safeguard Ultralytics operations including ASCII, font, YOLO file, YAML, Python and torchvision checks. -keywords: Ultralytics, utility checks, ASCII, check_version, pip_update, check_python, check_torchvision, check_yaml, YOLO filename ---- - -# Reference for `ultralytics/utils/checks.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/checks.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/checks.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/checks.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.checks.parse_requirements - -

- -## ::: ultralytics.utils.checks.parse_version - -

- -## ::: ultralytics.utils.checks.is_ascii - -

- -## ::: ultralytics.utils.checks.check_imgsz - -

- -## ::: ultralytics.utils.checks.check_version - -

- -## ::: ultralytics.utils.checks.check_latest_pypi_version - -

- -## ::: ultralytics.utils.checks.check_pip_update_available - -

- -## ::: ultralytics.utils.checks.check_font - -

- -## ::: ultralytics.utils.checks.check_python - -

- -## ::: ultralytics.utils.checks.check_requirements - -

- -## ::: ultralytics.utils.checks.check_torchvision - -

- -## ::: ultralytics.utils.checks.check_suffix - -

- -## ::: ultralytics.utils.checks.check_yolov5u_filename - -

- -## ::: ultralytics.utils.checks.check_model_file_from_stem - -

- -## ::: ultralytics.utils.checks.check_file - -

- -## ::: ultralytics.utils.checks.check_yaml - -

- -## ::: ultralytics.utils.checks.check_is_path_safe - -

- -## ::: ultralytics.utils.checks.check_imshow - -

- -## ::: ultralytics.utils.checks.check_yolo - -

- -## ::: ultralytics.utils.checks.collect_system_info - -

- -## ::: ultralytics.utils.checks.check_amp - -

- -## ::: ultralytics.utils.checks.git_describe - -

- -## ::: ultralytics.utils.checks.print_args - -

- -## ::: ultralytics.utils.checks.cuda_device_count - -

- -## ::: ultralytics.utils.checks.cuda_is_available - -

diff --git a/ultralytics-main/docs/en/reference/utils/dist.md b/ultralytics-main/docs/en/reference/utils/dist.md deleted file mode 100644 index 1ca18e3..0000000 --- a/ultralytics-main/docs/en/reference/utils/dist.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Discover the role of dist.find_free_network_port & dist.generate_ddp_command in Ultralytics DDP utilities. Use our guide for efficient deployment. -keywords: Ultralytics, DDP, DDP utility functions, Distributed Data Processing, find free network port, generate DDP command ---- - -# Reference for `ultralytics/utils/dist.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/dist.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/dist.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/dist.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.dist.find_free_network_port - -

- -## ::: ultralytics.utils.dist.generate_ddp_file - -

- -## ::: ultralytics.utils.dist.generate_ddp_command - -

- -## ::: ultralytics.utils.dist.ddp_cleanup - -

diff --git a/ultralytics-main/docs/en/reference/utils/downloads.md b/ultralytics-main/docs/en/reference/utils/downloads.md deleted file mode 100644 index aeef4c9..0000000 --- a/ultralytics-main/docs/en/reference/utils/downloads.md +++ /dev/null @@ -1,52 +0,0 @@ ---- -description: Learn about the download utilities in Ultralytics YOLO, featuring functions like is_url, check_disk_space, get_github_assets, and download. -keywords: Ultralytics, YOLO, download utilities, is_url, check_disk_space, get_github_assets, download, documentation ---- - -# Reference for `ultralytics/utils/downloads.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/downloads.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/downloads.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/downloads.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.downloads.is_url - -

- -## ::: ultralytics.utils.downloads.delete_dsstore - -

- -## ::: ultralytics.utils.downloads.zip_directory - -

- -## ::: ultralytics.utils.downloads.unzip_file - -

- -## ::: ultralytics.utils.downloads.check_disk_space - -

- -## ::: ultralytics.utils.downloads.get_google_drive_file_info - -

- -## ::: ultralytics.utils.downloads.safe_download - -

- -## ::: ultralytics.utils.downloads.get_github_assets - -

- -## ::: ultralytics.utils.downloads.attempt_download_asset - -

- -## ::: ultralytics.utils.downloads.download - -

diff --git a/ultralytics-main/docs/en/reference/utils/errors.md b/ultralytics-main/docs/en/reference/utils/errors.md deleted file mode 100644 index 816328a..0000000 --- a/ultralytics-main/docs/en/reference/utils/errors.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn about the HUBModelError in Ultralytics. Enhance your understanding, troubleshoot errors and optimize your machine learning projects. -keywords: Ultralytics, HUBModelError, Machine Learning, Error troubleshooting, Ultralytics documentation ---- - -# Reference for `ultralytics/utils/errors.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/errors.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/errors.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/errors.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.errors.HUBModelError - -

diff --git a/ultralytics-main/docs/en/reference/utils/files.md b/ultralytics-main/docs/en/reference/utils/files.md deleted file mode 100644 index e9bd16d..0000000 --- a/ultralytics-main/docs/en/reference/utils/files.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -description: Discover how to use Ultralytics utility functions for file-related operations including incrementing paths, finding file age, checking file size and creating directories. -keywords: Ultralytics, utility functions, file operations, working directory, file age, file size, create directories ---- - -# Reference for `ultralytics/utils/files.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/files.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/files.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/files.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.files.WorkingDirectory - -

- -## ::: ultralytics.utils.files.spaces_in_path - -

- -## ::: ultralytics.utils.files.increment_path - -

- -## ::: ultralytics.utils.files.file_age - -

- -## ::: ultralytics.utils.files.file_date - -

- -## ::: ultralytics.utils.files.file_size - -

- -## ::: ultralytics.utils.files.get_latest_run - -

- -## ::: ultralytics.utils.files.update_models - -

diff --git a/ultralytics-main/docs/en/reference/utils/instance.md b/ultralytics-main/docs/en/reference/utils/instance.md deleted file mode 100644 index 6771cd8..0000000 --- a/ultralytics-main/docs/en/reference/utils/instance.md +++ /dev/null @@ -1,24 +0,0 @@ ---- -description: Dive into Ultralytics detailed utility guide. Learn about Bboxes, _ntuple and more from Ultralytics utils.instance module. -keywords: Ultralytics, Bboxes, _ntuple, utility, ultralytics utils.instance ---- - -# Reference for `ultralytics/utils/instance.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/instance.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/instance.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/instance.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.instance.Bboxes - -

- -## ::: ultralytics.utils.instance.Instances - -

- -## ::: ultralytics.utils.instance._ntuple - -

diff --git a/ultralytics-main/docs/en/reference/utils/loss.md b/ultralytics-main/docs/en/reference/utils/loss.md deleted file mode 100644 index 94ae791..0000000 --- a/ultralytics-main/docs/en/reference/utils/loss.md +++ /dev/null @@ -1,52 +0,0 @@ ---- -description: Explore Ultralytics' versatile loss functions - VarifocalLoss, BboxLoss, v8DetectionLoss, v8PoseLoss. Improve your accuracy on YOLO implementations. -keywords: Ultralytics, Loss functions, VarifocalLoss, BboxLoss, v8DetectionLoss, v8PoseLoss, YOLO, Ultralytics Documentation ---- - -# Reference for `ultralytics/utils/loss.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/loss.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/loss.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/loss.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.loss.VarifocalLoss - -

- -## ::: ultralytics.utils.loss.FocalLoss - -

- -## ::: ultralytics.utils.loss.BboxLoss - -

- -## ::: ultralytics.utils.loss.RotatedBboxLoss - -

- -## ::: ultralytics.utils.loss.KeypointLoss - -

- -## ::: ultralytics.utils.loss.v8DetectionLoss - -

- -## ::: ultralytics.utils.loss.v8SegmentationLoss - -

- -## ::: ultralytics.utils.loss.v8PoseLoss - -

- -## ::: ultralytics.utils.loss.v8ClassificationLoss - -

- -## ::: ultralytics.utils.loss.v8OBBLoss - -

diff --git a/ultralytics-main/docs/en/reference/utils/metrics.md b/ultralytics-main/docs/en/reference/utils/metrics.md deleted file mode 100644 index 21c8506..0000000 --- a/ultralytics-main/docs/en/reference/utils/metrics.md +++ /dev/null @@ -1,96 +0,0 @@ ---- -description: Explore Ultralytics YOLO metrics tools - from confusion matrix, detection metrics, pose metrics to box IoU. Learn how to compute and plot precision-recall curves. -keywords: Ultralytics, YOLO, YOLOv3, YOLOv4, metrics, confusion matrix, detection metrics, pose metrics, box IoU, mask IoU, plot precision-recall curves, compute average precision ---- - -# Reference for `ultralytics/utils/metrics.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/metrics.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/metrics.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/metrics.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.metrics.ConfusionMatrix - -

- -## ::: ultralytics.utils.metrics.Metric - -

- -## ::: ultralytics.utils.metrics.DetMetrics - -

- -## ::: ultralytics.utils.metrics.SegmentMetrics - -

- -## ::: ultralytics.utils.metrics.PoseMetrics - -

- -## ::: ultralytics.utils.metrics.ClassifyMetrics - -

- -## ::: ultralytics.utils.metrics.OBBMetrics - -

- -## ::: ultralytics.utils.metrics.bbox_ioa - -

- -## ::: ultralytics.utils.metrics.box_iou - -

- -## ::: ultralytics.utils.metrics.bbox_iou - -

- -## ::: ultralytics.utils.metrics.mask_iou - -

- -## ::: ultralytics.utils.metrics.kpt_iou - -

- -## ::: ultralytics.utils.metrics._get_covariance_matrix - -

- -## ::: ultralytics.utils.metrics.probiou - -

- -## ::: ultralytics.utils.metrics.batch_probiou - -

- -## ::: ultralytics.utils.metrics.smooth_BCE - -

- -## ::: ultralytics.utils.metrics.smooth - -

- -## ::: ultralytics.utils.metrics.plot_pr_curve - -

- -## ::: ultralytics.utils.metrics.plot_mc_curve - -

- -## ::: ultralytics.utils.metrics.compute_ap - -

- -## ::: ultralytics.utils.metrics.ap_per_class - -

diff --git a/ultralytics-main/docs/en/reference/utils/ops.md b/ultralytics-main/docs/en/reference/utils/ops.md deleted file mode 100644 index 4cd9d5f..0000000 --- a/ultralytics-main/docs/en/reference/utils/ops.md +++ /dev/null @@ -1,136 +0,0 @@ ---- -description: Explore detailed documentation for Ultralytics utility operations. Learn about methods like segment2box, make_divisible, clip_boxes, and many more. -keywords: Ultralytics YOLO, Utility Operations, segment2box, make_divisible, clip_boxes, scale_image, xywh2xyxy, xyxy2xywhn, xywh2ltwh, ltwh2xywh, segments2boxes, crop_mask, process_mask, scale_masks, masks2segments ---- - -# Reference for `ultralytics/utils/ops.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/ops.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/ops.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/ops.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.ops.Profile - -

- -## ::: ultralytics.utils.ops.segment2box - -

- -## ::: ultralytics.utils.ops.scale_boxes - -

- -## ::: ultralytics.utils.ops.make_divisible - -

- -## ::: ultralytics.utils.ops.nms_rotated - -

- -## ::: ultralytics.utils.ops.non_max_suppression - -

- -## ::: ultralytics.utils.ops.clip_boxes - -

- -## ::: ultralytics.utils.ops.clip_coords - -

- -## ::: ultralytics.utils.ops.scale_image - -

- -## ::: ultralytics.utils.ops.xyxy2xywh - -

- -## ::: ultralytics.utils.ops.xywh2xyxy - -

- -## ::: ultralytics.utils.ops.xywhn2xyxy - -

- -## ::: ultralytics.utils.ops.xyxy2xywhn - -

- -## ::: ultralytics.utils.ops.xywh2ltwh - -

- -## ::: ultralytics.utils.ops.xyxy2ltwh - -

- -## ::: ultralytics.utils.ops.ltwh2xywh - -

- -## ::: ultralytics.utils.ops.xyxyxyxy2xywhr - -

- -## ::: ultralytics.utils.ops.xywhr2xyxyxyxy - -

- -## ::: ultralytics.utils.ops.ltwh2xyxy - -

- -## ::: ultralytics.utils.ops.segments2boxes - -

- -## ::: ultralytics.utils.ops.resample_segments - -

- -## ::: ultralytics.utils.ops.crop_mask - -

- -## ::: ultralytics.utils.ops.process_mask_upsample - -

- -## ::: ultralytics.utils.ops.process_mask - -

- -## ::: ultralytics.utils.ops.process_mask_native - -

- -## ::: ultralytics.utils.ops.scale_masks - -

- -## ::: ultralytics.utils.ops.scale_coords - -

- -## ::: ultralytics.utils.ops.regularize_rboxes - -

- -## ::: ultralytics.utils.ops.masks2segments - -

- -## ::: ultralytics.utils.ops.convert_torch2numpy_batch - -

- -## ::: ultralytics.utils.ops.clean_str - -

diff --git a/ultralytics-main/docs/en/reference/utils/patches.md b/ultralytics-main/docs/en/reference/utils/patches.md deleted file mode 100644 index fdcf394..0000000 --- a/ultralytics-main/docs/en/reference/utils/patches.md +++ /dev/null @@ -1,28 +0,0 @@ ---- -description: Learn about Ultralytics utils patches including imread, imshow and torch_save. Enhance your image processing skills. -keywords: Ultralytics, Utils, Patches, imread, imshow, torch_save, image processing ---- - -# Reference for `ultralytics/utils/patches.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/patches.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/patches.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/patches.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.patches.imread - -

- -## ::: ultralytics.utils.patches.imwrite - -

- -## ::: ultralytics.utils.patches.imshow - -

- -## ::: ultralytics.utils.patches.torch_save - -

diff --git a/ultralytics-main/docs/en/reference/utils/plotting.md b/ultralytics-main/docs/en/reference/utils/plotting.md deleted file mode 100644 index bf00d2f..0000000 --- a/ultralytics-main/docs/en/reference/utils/plotting.md +++ /dev/null @@ -1,56 +0,0 @@ ---- -description: Master advanced plotting utils from Ultralytics including color annotations, label and image plotting, and feature visualization. -keywords: Ultralytics, plotting, utils, color annotation, label plotting, image plotting, feature visualization ---- - -# Reference for `ultralytics/utils/plotting.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/plotting.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/plotting.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/plotting.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.plotting.Colors - -

- -## ::: ultralytics.utils.plotting.Annotator - -

- -## ::: ultralytics.utils.plotting.plot_labels - -

- -## ::: ultralytics.utils.plotting.save_one_box - -

- -## ::: ultralytics.utils.plotting.plot_images - -

- -## ::: ultralytics.utils.plotting.plot_results - -

- -## ::: ultralytics.utils.plotting.plt_color_scatter - -

- -## ::: ultralytics.utils.plotting.plot_tune_results - -

- -## ::: ultralytics.utils.plotting.output_to_target - -

- -## ::: ultralytics.utils.plotting.output_to_rotated_target - -

- -## ::: ultralytics.utils.plotting.feature_visualization - -

diff --git a/ultralytics-main/docs/en/reference/utils/tal.md b/ultralytics-main/docs/en/reference/utils/tal.md deleted file mode 100644 index 9f832aa..0000000 --- a/ultralytics-main/docs/en/reference/utils/tal.md +++ /dev/null @@ -1,36 +0,0 @@ ---- -description: Explore Ultralytics utilities for optimized task assignment, bounding box creation, and distance calculation. Learn more about algorithm implementations. -keywords: Ultralytics, task aligned assigner, select highest overlaps, make anchors, dist2bbox, bbox2dist, utilities, algorithm ---- - -# Reference for `ultralytics/utils/tal.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/tal.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/tal.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/tal.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.tal.TaskAlignedAssigner - -

- -## ::: ultralytics.utils.tal.RotatedTaskAlignedAssigner - -

- -## ::: ultralytics.utils.tal.make_anchors - -

- -## ::: ultralytics.utils.tal.dist2bbox - -

- -## ::: ultralytics.utils.tal.bbox2dist - -

- -## ::: ultralytics.utils.tal.dist2rbox - -

diff --git a/ultralytics-main/docs/en/reference/utils/torch_utils.md b/ultralytics-main/docs/en/reference/utils/torch_utils.md deleted file mode 100644 index 5c88f29..0000000 --- a/ultralytics-main/docs/en/reference/utils/torch_utils.md +++ /dev/null @@ -1,120 +0,0 @@ ---- -description: Explore Ultralytics-tailored torch utility features like Model EMA, early stopping, smart inference, image scaling, get_flops, and many more. -keywords: Ultralytics, Torch Utils, Model EMA, Early Stopping, Smart Inference, Get CPU Info, Time Sync, Fuse Deconv and bn, Get num params, Get FLOPs, Scale img, Copy attr, Intersect dicts, De_parallel, Init seeds, Profile ---- - -# Reference for `ultralytics/utils/torch_utils.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/torch_utils.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/torch_utils.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/torch_utils.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.torch_utils.ModelEMA - -

- -## ::: ultralytics.utils.torch_utils.EarlyStopping - -

- -## ::: ultralytics.utils.torch_utils.torch_distributed_zero_first - -

- -## ::: ultralytics.utils.torch_utils.smart_inference_mode - -

- -## ::: ultralytics.utils.torch_utils.get_cpu_info - -

- -## ::: ultralytics.utils.torch_utils.select_device - -

- -## ::: ultralytics.utils.torch_utils.time_sync - -

- -## ::: ultralytics.utils.torch_utils.fuse_conv_and_bn - -

- -## ::: ultralytics.utils.torch_utils.fuse_deconv_and_bn - -

- -## ::: ultralytics.utils.torch_utils.model_info - -

- -## ::: ultralytics.utils.torch_utils.get_num_params - -

- -## ::: ultralytics.utils.torch_utils.get_num_gradients - -

- -## ::: ultralytics.utils.torch_utils.model_info_for_loggers - -

- -## ::: ultralytics.utils.torch_utils.get_flops - -

- -## ::: ultralytics.utils.torch_utils.get_flops_with_torch_profiler - -

- -## ::: ultralytics.utils.torch_utils.initialize_weights - -

- -## ::: ultralytics.utils.torch_utils.scale_img - -

- -## ::: ultralytics.utils.torch_utils.make_divisible - -

- -## ::: ultralytics.utils.torch_utils.copy_attr - -

- -## ::: ultralytics.utils.torch_utils.get_latest_opset - -

- -## ::: ultralytics.utils.torch_utils.intersect_dicts - -

- -## ::: ultralytics.utils.torch_utils.is_parallel - -

- -## ::: ultralytics.utils.torch_utils.de_parallel - -

- -## ::: ultralytics.utils.torch_utils.one_cycle - -

- -## ::: ultralytics.utils.torch_utils.init_seeds - -

- -## ::: ultralytics.utils.torch_utils.strip_optimizer - -

- -## ::: ultralytics.utils.torch_utils.profile - -

diff --git a/ultralytics-main/docs/en/reference/utils/triton.md b/ultralytics-main/docs/en/reference/utils/triton.md deleted file mode 100644 index 6a86de6..0000000 --- a/ultralytics-main/docs/en/reference/utils/triton.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Deploy ML models effortlessly with Ultralytics TritonRemoteModel. Simplify serving with our comprehensive utils guide. -keywords: Ultralytics, YOLO, TritonRemoteModel, machine learning, model serving, deployment, utils, documentation ---- - -# Reference for `ultralytics/utils/triton.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/triton.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/triton.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/triton.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.triton.TritonRemoteModel - -

diff --git a/ultralytics-main/docs/en/reference/utils/tuner.md b/ultralytics-main/docs/en/reference/utils/tuner.md deleted file mode 100644 index d05f83d..0000000 --- a/ultralytics-main/docs/en/reference/utils/tuner.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -description: Learn to utilize the run_ray_tune function with Ultralytics. Make your machine learning tuning process easier and more efficient. -keywords: Ultralytics, run_ray_tune, machine learning tuning, machine learning efficiency ---- - -# Reference for `ultralytics/utils/tuner.py` - -!!! Note - - This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/tuner.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/tuner.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/utils/tuner.py) 🛠️. Thank you 🙏! - -

- -## ::: ultralytics.utils.tuner.run_ray_tune - -

diff --git a/ultralytics-main/docs/en/robots.txt b/ultralytics-main/docs/en/robots.txt deleted file mode 100644 index 9436a7a..0000000 --- a/ultralytics-main/docs/en/robots.txt +++ /dev/null @@ -1,16 +0,0 @@ -User-agent: * -Sitemap: https://docs.ultralytics.com/sitemap.xml -Sitemap: https://docs.ultralytics.com/ar/sitemap.xml -Sitemap: https://docs.ultralytics.com/de/sitemap.xml -Sitemap: https://docs.ultralytics.com/es/sitemap.xml -Sitemap: https://docs.ultralytics.com/fr/sitemap.xml -Sitemap: https://docs.ultralytics.com/hi/sitemap.xml -Sitemap: https://docs.ultralytics.com/it/sitemap.xml -Sitemap: https://docs.ultralytics.com/ja/sitemap.xml -Sitemap: https://docs.ultralytics.com/ko/sitemap.xml -Sitemap: https://docs.ultralytics.com/nl/sitemap.xml -Sitemap: https://docs.ultralytics.com/pt/sitemap.xml -Sitemap: https://docs.ultralytics.com/ru/sitemap.xml -Sitemap: https://docs.ultralytics.com/tr/sitemap.xml -Sitemap: https://docs.ultralytics.com/vi/sitemap.xml -Sitemap: https://docs.ultralytics.com/zh/sitemap.xml diff --git a/ultralytics-main/docs/en/tasks/classify.md b/ultralytics-main/docs/en/tasks/classify.md deleted file mode 100644 index 4a54750..0000000 --- a/ultralytics-main/docs/en/tasks/classify.md +++ /dev/null @@ -1,181 +0,0 @@ ---- -comments: true -description: Learn about YOLOv8 Classify models for image classification. Get detailed information on List of Pretrained Models & how to Train, Validate, Predict & Export models. -keywords: Ultralytics, YOLOv8, Image Classification, Pretrained Models, YOLOv8n-cls, Training, Validation, Prediction, Model Export ---- - -# Image Classification - -Image classification examples - -Image classification is the simplest of the three tasks and involves classifying an entire image into one of a set of predefined classes. - -The output of an image classifier is a single class label and a confidence score. Image classification is useful when you need to know only what class an image belongs to and don't need to know where objects of that class are located or what their exact shape is. - -

-
- -
- Watch: Explore Ultralytics YOLO Tasks: Image Classification using Ultralytics HUB -

- -!!! Tip "Tip" - - YOLOv8 Classify models use the `-cls` suffix, i.e. `yolov8n-cls.pt` and are pretrained on [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/ImageNet.yaml). - -## [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/v8) - -YOLOv8 pretrained Classify models are shown here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/ImageNet.yaml) dataset. - -[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. - -| Model | size
(pixels) | acc
top1 | acc
top5 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) at 640 | -|----------------------------------------------------------------------------------------------|-----------------------|------------------|------------------|--------------------------------|-------------------------------------|--------------------|--------------------------| -| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 | -| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 | -| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 | -| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 | -| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 | - -- **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set.
Reproduce by `yolo val classify data=path/to/ImageNet device=0` -- **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu` - -## Train - -Train YOLOv8n-cls on the MNIST160 dataset for 100 epochs at image size 64. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-cls.yaml') # build a new model from YAML - model = YOLO('yolov8n-cls.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n-cls.yaml').load('yolov8n-cls.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='mnist160', epochs=100, imgsz=64) - ``` - - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo classify train data=mnist160 model=yolov8n-cls.yaml epochs=100 imgsz=64 - - # Start training from a pretrained *.pt model - yolo classify train data=mnist160 model=yolov8n-cls.pt epochs=100 imgsz=64 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo classify train data=mnist160 model=yolov8n-cls.yaml pretrained=yolov8n-cls.pt epochs=100 imgsz=64 - ``` - -### Dataset format - -YOLO classification dataset format can be found in detail in the [Dataset Guide](../datasets/classify/index.md). - -## Val - -Validate trained YOLOv8n-cls model accuracy on the MNIST160 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-cls.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val() # no arguments needed, dataset and settings remembered - metrics.top1 # top1 accuracy - metrics.top5 # top5 accuracy - ``` - === "CLI" - - ```bash - yolo classify val model=yolov8n-cls.pt # val official model - yolo classify val model=path/to/best.pt # val custom model - ``` - -## Predict - -Use a trained YOLOv8n-cls model to run predictions on images. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-cls.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Predict with the model - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - ``` - === "CLI" - - ```bash - yolo classify predict model=yolov8n-cls.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model - yolo classify predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model - ``` - -See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page. - -## Export - -Export a YOLOv8n-cls model to a different format like ONNX, CoreML, etc. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-cls.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - === "CLI" - - ```bash - yolo export model=yolov8n-cls.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -Available YOLOv8-cls export formats are in the table below. You can predict or validate directly on exported models, i.e. `yolo predict model=yolov8n-cls.onnx`. Usage examples are shown for your model after export completes. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|-------------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n-cls.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-cls.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-cls.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n-cls_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-cls.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-cls.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-cls_saved_model/` | ✅ | `imgsz`, `keras` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-cls.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-cls.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-cls_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-cls_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/tasks/detect.md b/ultralytics-main/docs/en/tasks/detect.md deleted file mode 100644 index b5d2700..0000000 --- a/ultralytics-main/docs/en/tasks/detect.md +++ /dev/null @@ -1,182 +0,0 @@ ---- -comments: true -description: Official documentation for YOLOv8 by Ultralytics. Learn how to train, validate, predict and export models in various formats. Including detailed performance stats. -keywords: YOLOv8, Ultralytics, object detection, pretrained models, training, validation, prediction, export models, COCO, ImageNet, PyTorch, ONNX, CoreML ---- - -# Object Detection - -Object detection examples - -Object detection is a task that involves identifying the location and class of objects in an image or video stream. - -The output of an object detector is a set of bounding boxes that enclose the objects in the image, along with class labels and confidence scores for each box. Object detection is a good choice when you need to identify objects of interest in a scene, but don't need to know exactly where the object is or its exact shape. - -

-
- -
- Watch: Object Detection with Pre-trained Ultralytics YOLOv8 Model. -

- -!!! Tip "Tip" - - YOLOv8 Detect models are the default YOLOv8 models, i.e. `yolov8n.pt` and are pretrained on [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml). - -## [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/v8) - -YOLOv8 pretrained Detect models are shown here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/ImageNet.yaml) dataset. - -[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. - -| Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -|--------------------------------------------------------------------------------------|-----------------------|----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | - -- **mAPval** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset.
Reproduce by `yolo val detect data=coco.yaml device=0` -- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val detect data=coco128.yaml batch=1 device=0|cpu` - -## Train - -Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.yaml') # build a new model from YAML - model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='coco128.yaml', epochs=100, imgsz=640) - ``` - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo detect train data=coco128.yaml model=yolov8n.yaml epochs=100 imgsz=640 - - # Start training from a pretrained *.pt model - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo detect train data=coco128.yaml model=yolov8n.yaml pretrained=yolov8n.pt epochs=100 imgsz=640 - ``` - -### Dataset format - -YOLO detection dataset format can be found in detail in the [Dataset Guide](../datasets/detect/index.md). To convert your existing dataset from other formats (like COCO etc.) to YOLO format, please use [JSON2YOLO](https://github.com/ultralytics/JSON2YOLO) tool by Ultralytics. - -## Val - -Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val() # no arguments needed, dataset and settings remembered - metrics.box.map # map50-95 - metrics.box.map50 # map50 - metrics.box.map75 # map75 - metrics.box.maps # a list contains map50-95 of each category - ``` - === "CLI" - - ```bash - yolo detect val model=yolov8n.pt # val official model - yolo detect val model=path/to/best.pt # val custom model - ``` - -## Predict - -Use a trained YOLOv8n model to run predictions on images. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Predict with the model - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - ``` - === "CLI" - - ```bash - yolo detect predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model - yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model - ``` - -See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page. - -## Export - -Export a YOLOv8n model to a different format like ONNX, CoreML, etc. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - === "CLI" - - ```bash - yolo export model=yolov8n.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -Available YOLOv8 export formats are in the table below. You can predict or validate directly on exported models, i.e. `yolo predict model=yolov8n.onnx`. Usage examples are shown for your model after export completes. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/tasks/index.md b/ultralytics-main/docs/en/tasks/index.md deleted file mode 100644 index 2cf4696..0000000 --- a/ultralytics-main/docs/en/tasks/index.md +++ /dev/null @@ -1,57 +0,0 @@ ---- -comments: true -description: Learn about the cornerstone computer vision tasks YOLOv8 can perform including detection, segmentation, classification, and pose estimation. Understand their uses in your AI projects. -keywords: Ultralytics, YOLOv8, Detection, Segmentation, Classification, Pose Estimation, Oriented Object Detection, AI Framework, Computer Vision Tasks ---- - -# Ultralytics YOLOv8 Tasks - -
-Ultralytics YOLO supported tasks - -YOLOv8 is an AI framework that supports multiple computer vision **tasks**. The framework can be used to perform [detection](detect.md), [segmentation](segment.md), [obb](obb.md), [classification](classify.md), and [pose](pose.md) estimation. Each of these tasks has a different objective and use case. - -

-
- -
- Watch: Explore Ultralytics YOLO Tasks: Object Detection, Segmentation, OBB, Tracking, and Pose Estimation. -

- -## [Detection](detect.md) - -Detection is the primary task supported by YOLOv8. It involves detecting objects in an image or video frame and drawing bounding boxes around them. The detected objects are classified into different categories based on their features. YOLOv8 can detect multiple objects in a single image or video frame with high accuracy and speed. - -[Detection Examples](detect.md){ .md-button } - -## [Segmentation](segment.md) - -Segmentation is a task that involves segmenting an image into different regions based on the content of the image. Each region is assigned a label based on its content. This task is useful in applications such as image segmentation and medical imaging. YOLOv8 uses a variant of the U-Net architecture to perform segmentation. - -[Segmentation Examples](segment.md){ .md-button } - -## [Classification](classify.md) - -Classification is a task that involves classifying an image into different categories. YOLOv8 can be used to classify images based on their content. It uses a variant of the EfficientNet architecture to perform classification. - -[Classification Examples](classify.md){ .md-button } - -## [Pose](pose.md) - -Pose/keypoint detection is a task that involves detecting specific points in an image or video frame. These points are referred to as keypoints and are used to track movement or pose estimation. YOLOv8 can detect keypoints in an image or video frame with high accuracy and speed. - -[Pose Examples](pose.md){ .md-button } - -## [OBB](obb.md) - -Oriented object detection goes a step further than regular object detection with introducing an extra angle to locate objects more accurate in an image. YOLOv8 can detect rotated objects in an image or video frame with high accuracy and speed. - -[Oriented Detection](obb.md){ .md-button } - -## Conclusion - -YOLOv8 supports multiple tasks, including detection, segmentation, classification, oriented object detection and keypoints detection. Each of these tasks has different objectives and use cases. By understanding the differences between these tasks, you can choose the appropriate task for your computer vision application. diff --git a/ultralytics-main/docs/en/tasks/obb.md b/ultralytics-main/docs/en/tasks/obb.md deleted file mode 100644 index aa75d51..0000000 --- a/ultralytics-main/docs/en/tasks/obb.md +++ /dev/null @@ -1,191 +0,0 @@ ---- -comments: true -description: Learn how to use oriented object detection models with Ultralytics YOLO. Instructions on training, validation, image prediction, and model export. -keywords: yolov8, oriented object detection, Ultralytics, DOTA dataset, rotated object detection, object detection, model training, model validation, image prediction, model export ---- - -# Oriented Bounding Boxes Object Detection - - - -Oriented object detection goes a step further than object detection and introduce an extra angle to locate objects more accurate in an image. - -The output of an oriented object detector is a set of rotated bounding boxes that exactly enclose the objects in the image, along with class labels and confidence scores for each box. Object detection is a good choice when you need to identify objects of interest in a scene, but don't need to know exactly where the object is or its exact shape. - - - -!!! Tip "Tip" - - YOLOv8 OBB models use the `-obb` suffix, i.e. `yolov8n-obb.pt` and are pretrained on [DOTAv1](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/DOTAv1.yaml). - -

-
- -
- Watch: Object Detection using Ultralytics YOLOv8 Oriented Bounding Boxes (YOLOv8-OBB) -

- -## Visual Samples - -| Ships Detection using OBB | Vehicle Detection using OBB | -|:-------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------:| -| ![Ships Detection using OBB](https://github.com/RizwanMunawar/ultralytics/assets/62513924/5051d324-416f-4b58-ab62-f1bf9d7134b0) | ![Vehicle Detection using OBB](https://github.com/RizwanMunawar/ultralytics/assets/62513924/9a366262-910a-403b-a5e2-9c68b75700d3) | - -## [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/v8) - -YOLOv8 pretrained OBB models are shown here, which are pretrained on the [DOTAv1](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/DOTAv1.yaml) dataset. - -[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. - -| Model | size
(pixels) | mAPtest
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -|----------------------------------------------------------------------------------------------|-----------------------|--------------------|--------------------------------|-------------------------------------|--------------------|-------------------| -| [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 | -| [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 | -| [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 | -| [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 | -| [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 | - -- **mAPtest** values are for single-model multiscale on [DOTAv1 test](https://captain-whu.github.io/DOTA/index.html) dataset.
Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html). -- **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu` - -## Train - -Train YOLOv8n-obb on the `dota8.yaml` dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-obb.yaml') # build a new model from YAML - model = YOLO('yolov8n-obb.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n-obb.yaml').load('yolov8n.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='dota8.yaml', epochs=100, imgsz=640) - ``` - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo obb train data=dota8.yaml model=yolov8n-obb.yaml epochs=100 imgsz=640 - - # Start training from a pretrained *.pt model - yolo obb train data=dota8.yaml model=yolov8n-obb.pt epochs=100 imgsz=640 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo obb train data=dota8.yaml model=yolov8n-obb.yaml pretrained=yolov8n-obb.pt epochs=100 imgsz=640 - ``` - -### Dataset format - -OBB dataset format can be found in detail in the [Dataset Guide](../datasets/obb/index.md). - -## Val - -Validate trained YOLOv8n-obb model accuracy on the DOTA8 dataset. No argument need to passed as the `model` -retains it's training `data` and arguments as model attributes. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-obb.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val(data='dota8.yaml') # no arguments needed, dataset and settings remembered - metrics.box.map # map50-95(B) - metrics.box.map50 # map50(B) - metrics.box.map75 # map75(B) - metrics.box.maps # a list contains map50-95(B) of each category - ``` - === "CLI" - - ```bash - yolo obb val model=yolov8n-obb.pt data=dota8.yaml # val official model - yolo obb val model=path/to/best.pt data=path/to/data.yaml # val custom model - ``` - -## Predict - -Use a trained YOLOv8n-obb model to run predictions on images. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-obb.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Predict with the model - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - ``` - === "CLI" - - ```bash - yolo obb predict model=yolov8n-obb.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model - yolo obb predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model - ``` - -See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page. - -## Export - -Export a YOLOv8n-obb model to a different format like ONNX, CoreML, etc. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-obb.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - === "CLI" - - ```bash - yolo export model=yolov8n-obb.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -Available YOLOv8-obb export formats are in the table below. You can predict or validate directly on exported models, i.e. `yolo predict model=yolov8n-obb.onnx`. Usage examples are shown for your model after export completes. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|-------------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n-obb.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-obb.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-obb.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n-obb_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-obb.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-obb.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-obb_saved_model/` | ✅ | `imgsz`, `keras` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-obb.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-obb.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-obb_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-obb_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-obb_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-obb_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/tasks/pose.md b/ultralytics-main/docs/en/tasks/pose.md deleted file mode 100644 index 431164b..0000000 --- a/ultralytics-main/docs/en/tasks/pose.md +++ /dev/null @@ -1,185 +0,0 @@ ---- -comments: true -description: Learn how to use Ultralytics YOLOv8 for pose estimation tasks. Find pretrained models, learn how to train, validate, predict, and export your own. -keywords: Ultralytics, YOLO, YOLOv8, pose estimation, keypoints detection, object detection, pre-trained models, machine learning, artificial intelligence ---- - -# Pose Estimation - -Pose estimation examples - -Pose estimation is a task that involves identifying the location of specific points in an image, usually referred to as keypoints. The keypoints can represent various parts of the object such as joints, landmarks, or other distinctive features. The locations of the keypoints are usually represented as a set of 2D `[x, y]` or 3D `[x, y, visible]` coordinates. - -The output of a pose estimation model is a set of points that represent the keypoints on an object in the image, usually along with the confidence scores for each point. Pose estimation is a good choice when you need to identify specific parts of an object in a scene, and their location in relation to each other. - -

-
- -
- Watch: Pose Estimation with Ultralytics YOLOv8. -

- -!!! Tip "Tip" - - YOLOv8 _pose_ models use the `-pose` suffix, i.e. `yolov8n-pose.pt`. These models are trained on the [COCO keypoints](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco-pose.yaml) dataset and are suitable for a variety of pose estimation tasks. - -## [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/v8) - -YOLOv8 pretrained Pose models are shown here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/ImageNet.yaml) dataset. - -[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. - -| Model | size
(pixels) | mAPpose
50-95 | mAPpose
50 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -|------------------------------------------------------------------------------------------------------|-----------------------|-----------------------|--------------------|--------------------------------|-------------------------------------|--------------------|-------------------| -| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 | -| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 | -| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 | -| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 | -| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 | -| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 | - -- **mAPval** values are for single-model single-scale on [COCO Keypoints val2017](https://cocodataset.org) dataset.
Reproduce by `yolo val pose data=coco-pose.yaml device=0` -- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu` - -## Train - -Train a YOLOv8-pose model on the COCO128-pose dataset. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-pose.yaml') # build a new model from YAML - model = YOLO('yolov8n-pose.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n-pose.yaml').load('yolov8n-pose.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='coco8-pose.yaml', epochs=100, imgsz=640) - ``` - - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo pose train data=coco8-pose.yaml model=yolov8n-pose.yaml epochs=100 imgsz=640 - - # Start training from a pretrained *.pt model - yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo pose train data=coco8-pose.yaml model=yolov8n-pose.yaml pretrained=yolov8n-pose.pt epochs=100 imgsz=640 - ``` - -### Dataset format - -YOLO pose dataset format can be found in detail in the [Dataset Guide](../datasets/pose/index.md). To convert your existing dataset from other formats (like COCO etc.) to YOLO format, please use [JSON2YOLO](https://github.com/ultralytics/JSON2YOLO) tool by Ultralytics. - -## Val - -Validate trained YOLOv8n-pose model accuracy on the COCO128-pose dataset. No argument need to passed as the `model` -retains it's training `data` and arguments as model attributes. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-pose.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val() # no arguments needed, dataset and settings remembered - metrics.box.map # map50-95 - metrics.box.map50 # map50 - metrics.box.map75 # map75 - metrics.box.maps # a list contains map50-95 of each category - ``` - === "CLI" - - ```bash - yolo pose val model=yolov8n-pose.pt # val official model - yolo pose val model=path/to/best.pt # val custom model - ``` - -## Predict - -Use a trained YOLOv8n-pose model to run predictions on images. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-pose.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Predict with the model - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - ``` - === "CLI" - - ```bash - yolo pose predict model=yolov8n-pose.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model - yolo pose predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model - ``` - -See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page. - -## Export - -Export a YOLOv8n Pose model to a different format like ONNX, CoreML, etc. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-pose.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - === "CLI" - - ```bash - yolo export model=yolov8n-pose.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -Available YOLOv8-pose export formats are in the table below. You can predict or validate directly on exported models, i.e. `yolo predict model=yolov8n-pose.onnx`. Usage examples are shown for your model after export completes. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|--------------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n-pose.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-pose.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-pose.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n-pose_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-pose.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-pose.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-pose_saved_model/` | ✅ | `imgsz`, `keras` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-pose.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-pose.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-pose_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-pose_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-pose_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-pose_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/tasks/segment.md b/ultralytics-main/docs/en/tasks/segment.md deleted file mode 100644 index 921378a..0000000 --- a/ultralytics-main/docs/en/tasks/segment.md +++ /dev/null @@ -1,187 +0,0 @@ ---- -comments: true -description: Learn how to use instance segmentation models with Ultralytics YOLO. Instructions on training, validation, image prediction, and model export. -keywords: yolov8, instance segmentation, Ultralytics, COCO dataset, image segmentation, object detection, model training, model validation, image prediction, model export ---- - -# Instance Segmentation - -Instance segmentation examples - -Instance segmentation goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image. - -The output of an instance segmentation model is a set of masks or contours that outline each object in the image, along with class labels and confidence scores for each object. Instance segmentation is useful when you need to know not only where objects are in an image, but also what their exact shape is. - -

-
- -
- Watch: Run Segmentation with Pre-Trained Ultralytics YOLOv8 Model in Python. -

- -!!! Tip "Tip" - - YOLOv8 Segment models use the `-seg` suffix, i.e. `yolov8n-seg.pt` and are pretrained on [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml). - -## [Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models/v8) - -YOLOv8 pretrained Segment models are shown here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/ImageNet.yaml) dataset. - -[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/models) download automatically from the latest Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use. - -| Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -|----------------------------------------------------------------------------------------------|-----------------------|----------------------|-----------------------|--------------------------------|-------------------------------------|--------------------|-------------------| -| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | -| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | -| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | -| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | -| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | - -- **mAPval** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset.
Reproduce by `yolo val segment data=coco.yaml device=0` -- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance.
Reproduce by `yolo val segment data=coco128-seg.yaml batch=1 device=0|cpu` - -## Train - -Train YOLOv8n-seg on the COCO128-seg dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](../usage/cfg.md) page. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-seg.yaml') # build a new model from YAML - model = YOLO('yolov8n-seg.pt') # load a pretrained model (recommended for training) - model = YOLO('yolov8n-seg.yaml').load('yolov8n.pt') # build from YAML and transfer weights - - # Train the model - results = model.train(data='coco128-seg.yaml', epochs=100, imgsz=640) - ``` - === "CLI" - - ```bash - # Build a new model from YAML and start training from scratch - yolo segment train data=coco128-seg.yaml model=yolov8n-seg.yaml epochs=100 imgsz=640 - - # Start training from a pretrained *.pt model - yolo segment train data=coco128-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 - - # Build a new model from YAML, transfer pretrained weights to it and start training - yolo segment train data=coco128-seg.yaml model=yolov8n-seg.yaml pretrained=yolov8n-seg.pt epochs=100 imgsz=640 - ``` - -### Dataset format - -YOLO segmentation dataset format can be found in detail in the [Dataset Guide](../datasets/segment/index.md). To convert your existing dataset from other formats (like COCO etc.) to YOLO format, please use [JSON2YOLO](https://github.com/ultralytics/JSON2YOLO) tool by Ultralytics. - -## Val - -Validate trained YOLOv8n-seg model accuracy on the COCO128-seg dataset. No argument need to passed as the `model` -retains it's training `data` and arguments as model attributes. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-seg.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Validate the model - metrics = model.val() # no arguments needed, dataset and settings remembered - metrics.box.map # map50-95(B) - metrics.box.map50 # map50(B) - metrics.box.map75 # map75(B) - metrics.box.maps # a list contains map50-95(B) of each category - metrics.seg.map # map50-95(M) - metrics.seg.map50 # map50(M) - metrics.seg.map75 # map75(M) - metrics.seg.maps # a list contains map50-95(M) of each category - ``` - === "CLI" - - ```bash - yolo segment val model=yolov8n-seg.pt # val official model - yolo segment val model=path/to/best.pt # val custom model - ``` - -## Predict - -Use a trained YOLOv8n-seg model to run predictions on images. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-seg.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom model - - # Predict with the model - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - ``` - === "CLI" - - ```bash - yolo segment predict model=yolov8n-seg.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model - yolo segment predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model - ``` - -See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page. - -## Export - -Export a YOLOv8n-seg model to a different format like ONNX, CoreML, etc. - -!!! Example - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n-seg.pt') # load an official model - model = YOLO('path/to/best.pt') # load a custom trained model - - # Export the model - model.export(format='onnx') - ``` - === "CLI" - - ```bash - yolo export model=yolov8n-seg.pt format=onnx # export official model - yolo export model=path/to/best.pt format=onnx # export custom trained model - ``` - -Available YOLOv8-seg export formats are in the table below. You can predict or validate directly on exported models, i.e. `yolo predict model=yolov8n-seg.onnx`. Usage examples are shown for your model after export completes. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|-------------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n-seg.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-seg.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-seg.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n-seg_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-seg.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-seg.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-seg_saved_model/` | ✅ | `imgsz`, `keras` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-seg.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-seg.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-seg_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-seg_ncnn_model/` | ✅ | `imgsz`, `half` | - -See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. diff --git a/ultralytics-main/docs/en/usage/callbacks.md b/ultralytics-main/docs/en/usage/callbacks.md deleted file mode 100644 index 275492e..0000000 --- a/ultralytics-main/docs/en/usage/callbacks.md +++ /dev/null @@ -1,101 +0,0 @@ ---- -comments: true -description: Learn how to utilize callbacks in the Ultralytics framework during train, val, export, and predict modes for enhanced functionality. -keywords: Ultralytics, YOLO, callbacks guide, training callback, validation callback, export callback, prediction callback ---- - -## Callbacks - -Ultralytics framework supports callbacks as entry points in strategic stages of train, val, export, and predict modes. Each callback accepts a `Trainer`, `Validator`, or `Predictor` object depending on the operation type. All properties of these objects can be found in Reference section of the docs. - -

-
- -
- Watch: Mastering Ultralytics YOLOv8: Callbacks -

- -## Examples - -### Returning additional information with Prediction - -In this example, we want to return the original frame with each result object. Here's how we can do that - -```python -from ultralytics import YOLO - - -def on_predict_batch_end(predictor): - # Retrieve the batch data - _, image, _, _ = predictor.batch - - # Ensure that image is a list - image = image if isinstance(image, list) else [image] - - # Combine the prediction results with the corresponding frames - predictor.results = zip(predictor.results, image) - - -# Create a YOLO model instance -model = YOLO(f'yolov8n.pt') - -# Add the custom callback to the model -model.add_callback("on_predict_batch_end", on_predict_batch_end) - -# Iterate through the results and frames -for (result, frame) in model.predict(): # or model.track() - pass -``` - -## All callbacks - -Here are all supported callbacks. See callbacks [source code](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/callbacks/base.py) for additional details. - -### Trainer Callbacks - -| Callback | Description | -|-----------------------------|---------------------------------------------------------| -| `on_pretrain_routine_start` | Triggered at the beginning of pre-training routine | -| `on_pretrain_routine_end` | Triggered at the end of pre-training routine | -| `on_train_start` | Triggered when the training starts | -| `on_train_epoch_start` | Triggered at the start of each training epoch | -| `on_train_batch_start` | Triggered at the start of each training batch | -| `optimizer_step` | Triggered during the optimizer step | -| `on_before_zero_grad` | Triggered before gradients are zeroed | -| `on_train_batch_end` | Triggered at the end of each training batch | -| `on_train_epoch_end` | Triggered at the end of each training epoch | -| `on_fit_epoch_end` | Triggered at the end of each fit epoch | -| `on_model_save` | Triggered when the model is saved | -| `on_train_end` | Triggered when the training process ends | -| `on_params_update` | Triggered when model parameters are updated | -| `teardown` | Triggered when the training process is being cleaned up | - -### Validator Callbacks - -| Callback | Description | -|----------------------|-------------------------------------------------| -| `on_val_start` | Triggered when the validation starts | -| `on_val_batch_start` | Triggered at the start of each validation batch | -| `on_val_batch_end` | Triggered at the end of each validation batch | -| `on_val_end` | Triggered when the validation ends | - -### Predictor Callbacks - -| Callback | Description | -|------------------------------|---------------------------------------------------| -| `on_predict_start` | Triggered when the prediction process starts | -| `on_predict_batch_start` | Triggered at the start of each prediction batch | -| `on_predict_postprocess_end` | Triggered at the end of prediction postprocessing | -| `on_predict_batch_end` | Triggered at the end of each prediction batch | -| `on_predict_end` | Triggered when the prediction process ends | - -### Exporter Callbacks - -| Callback | Description | -|-------------------|------------------------------------------| -| `on_export_start` | Triggered when the export process starts | -| `on_export_end` | Triggered when the export process ends | diff --git a/ultralytics-main/docs/en/usage/cfg.md b/ultralytics-main/docs/en/usage/cfg.md deleted file mode 100644 index 4b8b291..0000000 --- a/ultralytics-main/docs/en/usage/cfg.md +++ /dev/null @@ -1,269 +0,0 @@ ---- -comments: true -description: Master YOLOv8 settings and hyperparameters for improved model performance. Learn to use YOLO CLI commands, adjust training settings, and optimize YOLO tasks & modes. -keywords: YOLOv8, settings, hyperparameters, YOLO CLI commands, YOLO tasks, YOLO modes, Ultralytics documentation, model optimization, YOLOv8 training ---- - -YOLO settings and hyperparameters play a critical role in the model's performance, speed, and accuracy. These settings and hyperparameters can affect the model's behavior at various stages of the model development process, including training, validation, and prediction. - -

-
- -
- Watch: Mastering Ultralytics YOLOv8: Configuration -

- -Ultralytics commands use the following syntax: - -!!! Example - - === "CLI" - - ```bash - yolo TASK MODE ARGS - ``` - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a YOLOv8 model from a pre-trained weights file - model = YOLO('yolov8n.pt') - - # Run MODE mode using the custom arguments ARGS (guess TASK) - model.MODE(ARGS) - ``` - -Where: - -- `TASK` (optional) is one of ([detect](../tasks/detect.md), [segment](../tasks/segment.md), [classify](../tasks/classify.md), [pose](../tasks/pose.md)) -- `MODE` (required) is one of ([train](../modes/train.md), [val](../modes/val.md), [predict](../modes/predict.md), [export](../modes/export.md), [track](../modes/track.md)) -- `ARGS` (optional) are `arg=value` pairs like `imgsz=640` that override defaults. - -Default `ARG` values are defined on this page from the `cfg/defaults.yaml` [file](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/default.yaml). - -#### Tasks - -YOLO models can be used for a variety of tasks, including detection, segmentation, classification and pose. These tasks differ in the type of output they produce and the specific problem they are designed to solve. - -- **Detect**: For identifying and localizing objects or regions of interest in an image or video. -- **Segment**: For dividing an image or video into regions or pixels that correspond to different objects or classes. -- **Classify**: For predicting the class label of an input image. -- **Pose**: For identifying objects and estimating their keypoints in an image or video. -- **OBB**: Oriented (i.e. rotated) bounding boxes suitable for satellite or medical imagery. - -| Argument | Default | Description | -|----------|------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `task` | `'detect'` | Specifies the YOLO task to be executed. Options include `detect` for object detection, `segment` for segmentation, `classify` for classification, `pose` for pose estimation and `OBB` for oriented bounding boxes. Each task is tailored to specific types of output and problems within image and video analysis. | - -[Tasks Guide](../tasks/index.md){ .md-button } - -#### Modes - -YOLO models can be used in different modes depending on the specific problem you are trying to solve. These modes include: - -- **Train**: For training a YOLOv8 model on a custom dataset. -- **Val**: For validating a YOLOv8 model after it has been trained. -- **Predict**: For making predictions using a trained YOLOv8 model on new images or videos. -- **Export**: For exporting a YOLOv8 model to a format that can be used for deployment. -- **Track**: For tracking objects in real-time using a YOLOv8 model. -- **Benchmark**: For benchmarking YOLOv8 exports (ONNX, TensorRT, etc.) speed and accuracy. - -| Argument | Default | Description | -|----------|-----------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `mode` | `'train'` | Specifies the mode in which the YOLO model operates. Options are `train` for model training, `val` for validation, `predict` for inference on new data, `export` for model conversion to deployment formats, `track` for object tracking, and `benchmark` for performance evaluation. Each mode is designed for different stages of the model lifecycle, from development through deployment. | - -[Modes Guide](../modes/index.md){ .md-button } - -## Train Settings - -The training settings for YOLO models encompass various hyperparameters and configurations used during the training process. These settings influence the model's performance, speed, and accuracy. Key training settings include batch size, learning rate, momentum, and weight decay. Additionally, the choice of optimizer, loss function, and training dataset composition can impact the training process. Careful tuning and experimentation with these settings are crucial for optimizing performance. - -| Argument | Default | Description | -|-------------------|----------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `model` | `None` | Specifies the model file for training. Accepts a path to either a `.pt` pretrained model or a `.yaml` configuration file. Essential for defining the model structure or initializing weights. | -| `data` | `None` | Path to the dataset configuration file (e.g., `coco128.yaml`). This file contains dataset-specific parameters, including paths to training and validation data, class names, and number of classes. | -| `epochs` | `100` | Total number of training epochs. Each epoch represents a full pass over the entire dataset. Adjusting this value can affect training duration and model performance. | -| `time` | `None` | Maximum training time in hours. If set, this overrides the `epochs` argument, allowing training to automatically stop after the specified duration. Useful for time-constrained training scenarios. | -| `patience` | `100` | Number of epochs to wait without improvement in validation metrics before early stopping the training. Helps prevent overfitting by stopping training when performance plateaus. | -| `batch` | `16` | Batch size for training, indicating how many images are processed before the model's internal parameters are updated. AutoBatch (`batch=-1`) dynamically adjusts the batch size based on GPU memory availability. | -| `imgsz` | `640` | Target image size for training. All images are resized to this dimension before being fed into the model. Affects model accuracy and computational complexity. | -| `save` | `True` | Enables saving of training checkpoints and final model weights. Useful for resuming training or model deployment. | -| `save_period` | `-1` | Frequency of saving model checkpoints, specified in epochs. A value of -1 disables this feature. Useful for saving interim models during long training sessions. | -| `cache` | `False` | Enables caching of dataset images in memory (`True`/`ram`), on disk (`disk`), or disables it (`False`). Improves training speed by reducing disk I/O at the cost of increased memory usage. | -| `device` | `None` | Specifies the computational device(s) for training: a single GPU (`device=0`), multiple GPUs (`device=0,1`), CPU (`device=cpu`), or MPS for Apple silicon (`device=mps`). | -| `workers` | `8` | Number of worker threads for data loading (per `RANK` if Multi-GPU training). Influences the speed of data preprocessing and feeding into the model, especially useful in multi-GPU setups. | -| `project` | `None` | Name of the project directory where training outputs are saved. Allows for organized storage of different experiments. | -| `name` | `None` | Name of the training run. Used for creating a subdirectory within the project folder, where training logs and outputs are stored. | -| `exist_ok` | `False` | If True, allows overwriting of an existing project/name directory. Useful for iterative experimentation without needing to manually clear previous outputs. | -| `pretrained` | `True` | Determines whether to start training from a pretrained model. Can be a boolean value or a string path to a specific model from which to load weights. Enhances training efficiency and model performance. | -| `optimizer` | `'auto'` | Choice of optimizer for training. Options include `SGD`, `Adam`, `AdamW`, `NAdam`, `RAdam`, `RMSProp` etc., or `auto` for automatic selection based on model configuration. Affects convergence speed and stability. | -| `verbose` | `False` | Enables verbose output during training, providing detailed logs and progress updates. Useful for debugging and closely monitoring the training process. | -| `seed` | `0` | Sets the random seed for training, ensuring reproducibility of results across runs with the same configurations. | -| `deterministic` | `True` | Forces deterministic algorithm use, ensuring reproducibility but may affect performance and speed due to the restriction on non-deterministic algorithms. | -| `single_cls` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. | -| `rect` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. | -| `cos_lr` | `False` | Utilizes a cosine learning rate scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. | -| `close_mosaic` | `10` | Disables mosaic data augmentation in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. | -| `resume` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. | -| `amp` | `True` | Enables Automatic Mixed Precision (AMP) training, reducing memory usage and possibly speeding up training with minimal impact on accuracy. | -| `fraction` | `1.0` | Specifies the fraction of the dataset to use for training. Allows for training on a subset of the full dataset, useful for experiments or when resources are limited. | -| `profile` | `False` | Enables profiling of ONNX and TensorRT speeds during training, useful for optimizing model deployment. | -| `freeze` | `None` | Freezes the first N layers of the model or specified layers by index, reducing the number of trainable parameters. Useful for fine-tuning or transfer learning. | -| `lr0` | `0.01` | Initial learning rate (i.e. `SGD=1E-2`, `Adam=1E-3`) . Adjusting this value is crucial for the optimization process, influencing how rapidly model weights are updated. | -| `lrf` | `0.01` | Final learning rate as a fraction of the initial rate = (`lr0 * lrf`), used in conjunction with schedulers to adjust the learning rate over time. | -| `momentum` | `0.937` | Momentum factor for SGD or beta1 for Adam optimizers, influencing the incorporation of past gradients in the current update. | -| `weight_decay` | `0.0005` | L2 regularization term, penalizing large weights to prevent overfitting. | -| `warmup_epochs` | `3.0` | Number of epochs for learning rate warmup, gradually increasing the learning rate from a low value to the initial learning rate to stabilize training early on. | -| `warmup_momentum` | `0.8` | Initial momentum for warmup phase, gradually adjusting to the set momentum over the warmup period. | -| `warmup_bias_lr` | `0.1` | Learning rate for bias parameters during the warmup phase, helping stabilize model training in the initial epochs. | -| `box` | `7.5` | Weight of the box loss component in the loss function, influencing how much emphasis is placed on accurately predicting bounding box coordinates. | -| `cls` | `0.5` | Weight of the classification loss in the total loss function, affecting the importance of correct class prediction relative to other components. | -| `dfl` | `1.5` | Weight of the distribution focal loss, used in certain YOLO versions for fine-grained classification. | -| `pose` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. | -| `kobj` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. | -| `label_smoothing` | `0.0` | Applies label smoothing, softening hard labels to a mix of the target label and a uniform distribution over labels, can improve generalization. | -| `nbs` | `64` | Nominal batch size for normalization of loss. | -| `overlap_mask` | `True` | Determines whether segmentation masks should overlap during training, applicable in instance segmentation tasks. | -| `mask_ratio` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. | -| `dropout` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. | -| `val` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. | -| `plots` | `False` | Generates and saves plots of training and validation metrics, as well as prediction examples, providing visual insights into model performance and learning progression. | - -[Train Guide](../modes/train.md){ .md-button } - -## Predict Settings - -The prediction settings for YOLO models encompass a range of hyperparameters and configurations that influence the model's performance, speed, and accuracy during inference on new data. Careful tuning and experimentation with these settings are essential to achieve optimal performance for a specific task. Key settings include the confidence threshold, Non-Maximum Suppression (NMS) threshold, and the number of classes considered. Additional factors affecting the prediction process are input data size and format, the presence of supplementary features such as masks or multiple labels per box, and the particular task the model is employed for. - -Inference arguments: - -| Argument | Type | Default | Description | -|-----------------|----------------|------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `source` | `str` | `'ultralytics/assets'` | Specifies the data source for inference. Can be an image path, video file, directory, URL, or device ID for live feeds. Supports a wide range of formats and sources, enabling flexible application across different types of input. | -| `conf` | `float` | `0.25` | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. | -| `iou` | `float` | `0.7` | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Higher values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. | -| `imgsz` | `int or tuple` | `640` | Defines the image size for inference. Can be a single integer `640` for square resizing or a (height, width) tuple. Proper sizing can improve detection accuracy and processing speed. | -| `half` | `bool` | `False` | Enables half-precision (FP16) inference, which can speed up model inference on supported GPUs with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for inference (e.g., `cpu`, `cuda:0` or `0`). Allows users to select between CPU, a specific GPU, or other compute devices for model execution. | -| `max_det` | `int` | `300` | Maximum number of detections allowed per image. Limits the total number of objects the model can detect in a single inference, preventing excessive outputs in dense scenes. | -| `vid_stride` | `int` | `1` | Frame stride for video inputs. Allows skipping frames in videos to speed up processing at the cost of temporal resolution. A value of 1 processes every frame, higher values skip frames. | -| `stream_buffer` | `bool` | `False` | Determines if all frames should be buffered when processing video streams (`True`), or if the model should return the most recent frame (`False`). Useful for real-time applications. | -| `visualize` | `bool` | `False` | Activates visualization of model features during inference, providing insights into what the model is "seeing". Useful for debugging and model interpretation. | -| `augment` | `bool` | `False` | Enables test-time augmentation (TTA) for predictions, potentially improving detection robustness at the cost of inference speed. | -| `agnostic_nms` | `bool` | `False` | Enables class-agnostic Non-Maximum Suppression (NMS), which merges overlapping boxes of different classes. Useful in multi-class detection scenarios where class overlap is common. | -| `classes` | `list[int]` | `None` | Filters predictions to a set of class IDs. Only detections belonging to the specified classes will be returned. Useful for focusing on relevant objects in multi-class detection tasks. | -| `retina_masks` | `bool` | `False` | Uses high-resolution segmentation masks if available in the model. This can enhance mask quality for segmentation tasks, providing finer detail. | -| `embed` | `list[int]` | `None` | Specifies the layers from which to extract feature vectors or embeddings. Useful for downstream tasks like clustering or similarity search. | - -Visualization arguments: - -| Argument | Type | Default | Description | -|---------------|---------------|---------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `show` | `bool` | `False` | If `True`, displays the annotated images or videos in a window. Useful for immediate visual feedback during development or testing. | -| `save` | `bool` | `False` | Enables saving of the annotated images or videos to file. Useful for documentation, further analysis, or sharing results. | -| `save_frames` | `bool` | `False` | When processing videos, saves individual frames as images. Useful for extracting specific frames or for detailed frame-by-frame analysis. | -| `save_txt` | `bool` | `False` | Saves detection results in a text file, following the format `[class] [x_center] [y_center] [width] [height] [confidence]`. Useful for integration with other analysis tools. | -| `save_conf` | `bool` | `False` | Includes confidence scores in the saved text files. Enhances the detail available for post-processing and analysis. | -| `save_crop` | `bool` | `False` | Saves cropped images of detections. Useful for dataset augmentation, analysis, or creating focused datasets for specific objects. | -| `show_labels` | `bool` | `True` | Displays labels for each detection in the visual output. Provides immediate understanding of detected objects. | -| `show_conf` | `bool` | `True` | Displays the confidence score for each detection alongside the label. Gives insight into the model's certainty for each detection. | -| `show_boxes` | `bool` | `True` | Draws bounding boxes around detected objects. Essential for visual identification and location of objects in images or video frames. | -| `line_width` | `None or int` | `None` | Specifies the line width of bounding boxes. If `None`, the line width is automatically adjusted based on the image size. Provides visual customization for clarity. | - -[Predict Guide](../modes/predict.md){ .md-button } - -## Validation Settings - -The val (validation) settings for YOLO models involve various hyperparameters and configurations used to evaluate the model's performance on a validation dataset. These settings influence the model's performance, speed, and accuracy. Common YOLO validation settings include batch size, validation frequency during training, and performance evaluation metrics. Other factors affecting the validation process include the validation dataset's size and composition, as well as the specific task the model is employed for. - -| Argument | Type | Default | Description | -|---------------|---------|---------|---------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `data` | `str` | `None` | Specifies the path to the dataset configuration file (e.g., `coco128.yaml`). This file includes paths to validation data, class names, and number of classes. | -| `imgsz` | `int` | `640` | Defines the size of input images. All images are resized to this dimension before processing. | -| `batch` | `int` | `16` | Sets the number of images per batch. Use `-1` for AutoBatch, which automatically adjusts based on GPU memory availability. | -| `save_json` | `bool` | `False` | If `True`, saves the results to a JSON file for further analysis or integration with other tools. | -| `save_hybrid` | `bool` | `False` | If `True`, saves a hybrid version of labels that combines original annotations with additional model predictions. | -| `conf` | `float` | `0.001` | Sets the minimum confidence threshold for detections. Detections with confidence below this threshold are discarded. | -| `iou` | `float` | `0.6` | Sets the Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Helps in reducing duplicate detections. | -| `max_det` | `int` | `300` | Limits the maximum number of detections per image. Useful in dense scenes to prevent excessive detections. | -| `half` | `bool` | `True` | Enables half-precision (FP16) computation, reducing memory usage and potentially increasing speed with minimal impact on accuracy. | -| `device` | `str` | `None` | Specifies the device for validation (`cpu`, `cuda:0`, etc.). Allows flexibility in utilizing CPU or GPU resources. | -| `dnn` | `bool` | `False` | If `True`, uses the OpenCV DNN module for ONNX model inference, offering an alternative to PyTorch inference methods. | -| `plots` | `bool` | `False` | When set to `True`, generates and saves plots of predictions versus ground truth for visual evaluation of the model's performance. | -| `rect` | `bool` | `False` | If `True`, uses rectangular inference for batching, reducing padding and potentially increasing speed and efficiency. | -| `split` | `str` | `val` | Determines the dataset split to use for validation (`val`, `test`, or `train`). Allows flexibility in choosing the data segment for performance evaluation. | - -Careful tuning and experimentation with these settings are crucial to ensure optimal performance on the validation dataset and detect and prevent overfitting. - -[Val Guide](../modes/val.md){ .md-button } - -## Export Settings - -Export settings for YOLO models encompass configurations and options related to saving or exporting the model for use in different environments or platforms. These settings can impact the model's performance, size, and compatibility with various systems. Key export settings include the exported model file format (e.g., ONNX, TensorFlow SavedModel), the target device (e.g., CPU, GPU), and additional features such as masks or multiple labels per box. The export process may also be affected by the model's specific task and the requirements or constraints of the destination environment or platform. - -| Argument | Type | Default | Description | -|-------------|------------------|-----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `format` | `str` | `'torchscript'` | Target format for the exported model, such as `'onnx'`, `'torchscript'`, `'tensorflow'`, or others, defining compatibility with various deployment environments. | -| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. | -| `keras` | `bool` | `False` | Enables export to Keras format for TensorFlow SavedModel, providing compatibility with TensorFlow serving and APIs. | -| `optimize` | `bool` | `False` | Applies optimization for mobile devices when exporting to TorchScript, potentially reducing model size and improving performance. | -| `half` | `bool` | `False` | Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. | -| `int8` | `bool` | `False` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal accuracy loss, primarily for edge devices. | -| `dynamic` | `bool` | `False` | Allows dynamic input sizes for ONNX and TensorRT exports, enhancing flexibility in handling varying image dimensions. | -| `simplify` | `bool` | `False` | Simplifies the model graph for ONNX exports, potentially improving performance and compatibility. | -| `opset` | `int` | `None` | Specifies the ONNX opset version for compatibility with different ONNX parsers and runtimes. If not set, uses the latest supported version. | -| `workspace` | `float` | `4.0` | Sets the maximum workspace size in GB for TensorRT optimizations, balancing memory usage and performance. | -| `nms` | `bool` | `False` | Adds Non-Maximum Suppression (NMS) to the CoreML export, essential for accurate and efficient detection post-processing. | - -It is crucial to thoughtfully configure these settings to ensure the exported model is optimized for the intended use case and functions effectively in the target environment. - -[Export Guide](../modes/export.md){ .md-button } - -## Augmentation Settings - -Augmentation techniques are essential for improving the robustness and performance of YOLO models by introducing variability into the training data, helping the model generalize better to unseen data. The following table outlines the purpose and effect of each augmentation argument: - -| Argument | Type | Default | Range | Description | -|----------------|---------|---------------|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `hsv_h` | `float` | `0.015` | `0.0 - 1.0` | Adjusts the hue of the image by a fraction of the color wheel, introducing color variability. Helps the model generalize across different lighting conditions. | -| `hsv_s` | `float` | `0.7` | `0.0 - 1.0` | Alters the saturation of the image by a fraction, affecting the intensity of colors. Useful for simulating different environmental conditions. | -| `hsv_v` | `float` | `0.4` | `0.0 - 1.0` | Modifies the value (brightness) of the image by a fraction, helping the model to perform well under various lighting conditions. | -| `degrees` | `float` | `0.0` | `-180 - +180` | Rotates the image randomly within the specified degree range, improving the model's ability to recognize objects at various orientations. | -| `translate` | `float` | `0.1` | `0.0 - 1.0` | Translates the image horizontally and vertically by a fraction of the image size, aiding in learning to detect partially visible objects. | -| `scale` | `float` | `0.5` | `>=0.0` | Scales the image by a gain factor, simulating objects at different distances from the camera. | -| `shear` | `float` | `0.0` | `-180 - +180` | Shears the image by a specified degree, mimicking the effect of objects being viewed from different angles. | -| `perspective` | `float` | `0.0` | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space. | -| `flipud` | `float` | `0.0` | `0.0 - 1.0` | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics. | -| `fliplr` | `float` | `0.5` | `0.0 - 1.0` | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity. | -| `mosaic` | `float` | `1.0` | `0.0 - 1.0` | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding. | -| `mixup` | `float` | `0.0` | `0.0 - 1.0` | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability. | -| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies objects from one image and pastes them onto another, useful for increasing object instances and learning object occlusion. | -| `auto_augment` | `str` | `randaugment` | - | Automatically applies a predefined augmentation policy (`randaugment`, `autoaugment`, `augmix`), optimizing for classification tasks by diversifying the visual features. | -| `erasing` | `float` | `0.4` | `0.0 - 1.0` | Randomly erases a portion of the image during classification training, encouraging the model to focus on less obvious features for recognition. | - -These settings can be adjusted to meet the specific requirements of the dataset and task at hand. Experimenting with different values can help find the optimal augmentation strategy that leads to the best model performance. - -## Logging, Checkpoints and Plotting Settings - -Logging, checkpoints, plotting, and file management are important considerations when training a YOLO model. - -- Logging: It is often helpful to log various metrics and statistics during training to track the model's progress and diagnose any issues that may arise. This can be done using a logging library such as TensorBoard or by writing log messages to a file. -- Checkpoints: It is a good practice to save checkpoints of the model at regular intervals during training. This allows you to resume training from a previous point if the training process is interrupted or if you want to experiment with different training configurations. -- Plotting: Visualizing the model's performance and training progress can be helpful for understanding how the model is behaving and identifying potential issues. This can be done using a plotting library such as matplotlib or by generating plots using a logging library such as TensorBoard. -- File management: Managing the various files generated during the training process, such as model checkpoints, log files, and plots, can be challenging. It is important to have a clear and organized file structure to keep track of these files and make it easy to access and analyze them as needed. - -Effective logging, checkpointing, plotting, and file management can help you keep track of the model's progress and make it easier to debug and optimize the training process. - -| Argument | Default | Description | -|------------|----------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `project` | `'runs'` | Specifies the root directory for saving training runs. Each run will be saved in a separate subdirectory within this directory. | -| `name` | `'exp'` | Defines the name of the experiment. If not specified, YOLO automatically increments this name for each run, e.g., `exp`, `exp2`, etc., to avoid overwriting previous experiments. | -| `exist_ok` | `False` | Determines whether to overwrite an existing experiment directory if one with the same name already exists. Setting this to `True` allows overwriting, while `False` prevents it. | -| `plots` | `False` | Controls the generation and saving of training and validation plots. Set to `True` to create plots such as loss curves, precision-recall curves, and sample predictions. Useful for visually tracking model performance over time. | -| `save` | `False` | Enables the saving of training checkpoints and final model weights. Set to `True` to periodically save model states, allowing training to be resumed from these checkpoints or models to be deployed. | diff --git a/ultralytics-main/docs/en/usage/cli.md b/ultralytics-main/docs/en/usage/cli.md deleted file mode 100644 index c71d7d0..0000000 --- a/ultralytics-main/docs/en/usage/cli.md +++ /dev/null @@ -1,231 +0,0 @@ ---- -comments: true -description: Learn how to use Ultralytics YOLO through Command Line, train models, run predictions and exports models to different formats easily using terminal commands. -keywords: Ultralytics, YOLO, CLI, train, validation, prediction, command line interface, YOLO CLI, YOLO terminal, model training, prediction, exporting ---- - -# Command Line Interface Usage - -The YOLO command line interface (CLI) allows for simple single-line commands without the need for a Python environment. CLI requires no customization or Python code. You can simply run all tasks from the terminal with the `yolo` command. - -

-
- -
- Watch: Mastering Ultralytics YOLOv8: CLI -

- -!!! Example - - === "Syntax" - - Ultralytics `yolo` commands use the following syntax: - ```bash - yolo TASK MODE ARGS - - Where TASK (optional) is one of [detect, segment, classify] - MODE (required) is one of [train, val, predict, export, track] - ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults. - ``` - See all ARGS in the full [Configuration Guide](cfg.md) or with `yolo cfg` - - === "Train" - - Train a detection model for 10 epochs with an initial learning_rate of 0.01 - ```bash - yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 - ``` - - === "Predict" - - Predict a YouTube video using a pretrained segmentation model at image size 320: - ```bash - yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 - ``` - - === "Val" - - Val a pretrained detection model at batch-size 1 and image size 640: - ```bash - yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 - ``` - - === "Export" - - Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required) - ```bash - yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128 - ``` - - === "Special" - - Run special commands to see version, view settings, run checks and more: - ```bash - yolo help - yolo checks - yolo version - yolo settings - yolo copy-cfg - yolo cfg - ``` - -Where: - -- `TASK` (optional) is one of `[detect, segment, classify]`. If it is not passed explicitly YOLOv8 will try to guess the `TASK` from the model type. -- `MODE` (required) is one of `[train, val, predict, export, track]` -- `ARGS` (optional) are any number of custom `arg=value` pairs like `imgsz=320` that override defaults. For a full list of available `ARGS` see the [Configuration](cfg.md) page and `defaults.yaml` - GitHub [source](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/default.yaml). - -!!! Warning "Warning" - - Arguments must be passed as `arg=val` pairs, split by an equals `=` sign and delimited by spaces ` ` between pairs. Do not use `--` argument prefixes or commas `,` between arguments. - - - `yolo predict model=yolov8n.pt imgsz=640 conf=0.25`   ✅ - - `yolo predict model yolov8n.pt imgsz 640 conf 0.25`   ❌ - - `yolo predict --model yolov8n.pt --imgsz 640 --conf 0.25`   ❌ - -## Train - -Train YOLOv8n on the COCO128 dataset for 100 epochs at image size 640. For a full list of available arguments see the [Configuration](cfg.md) page. - -!!! Example "Example" - - === "Train" - - Start training YOLOv8n on COCO128 for 100 epochs at image-size 640. - ```bash - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640 - ``` - - === "Resume" - - Resume an interrupted training. - ```bash - yolo detect train resume model=last.pt - ``` - -## Val - -Validate trained YOLOv8n model accuracy on the COCO128 dataset. No argument need to passed as the `model` retains it's training `data` and arguments as model attributes. - -!!! Example "Example" - - === "Official" - - Validate an official YOLOv8n model. - ```bash - yolo detect val model=yolov8n.pt - ``` - - === "Custom" - - Validate a custom-trained model. - ```bash - yolo detect val model=path/to/best.pt - ``` - -## Predict - -Use a trained YOLOv8n model to run predictions on images. - -!!! Example "Example" - - === "Official" - - Predict with an official YOLOv8n model. - ```bash - yolo detect predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' - ``` - - === "Custom" - - Predict with a custom model. - ```bash - yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' - ``` - -## Export - -Export a YOLOv8n model to a different format like ONNX, CoreML, etc. - -!!! Example "Example" - - === "Official" - - Export an official YOLOv8n model to ONNX format. - ```bash - yolo export model=yolov8n.pt format=onnx - ``` - - === "Custom" - - Export a custom-trained model to ONNX format. - ```bash - yolo export model=path/to/best.pt format=onnx - ``` - -Available YOLOv8 export formats are in the table below. You can export to any format using the `format` argument, i.e. `format='onnx'` or `format='engine'`. - -| Format | `format` Argument | Model | Metadata | Arguments | -|--------------------------------------------------------------------|-------------------|---------------------------|----------|-----------------------------------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | - | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | `imgsz`, `optimize` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `opset` | -| [OpenVINO](../integrations/openvino.md) | `openvino` | `yolov8n_openvino_model/` | ✅ | `imgsz`, `half`, `int8` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | `imgsz`, `half`, `dynamic`, `simplify`, `workspace` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlpackage` | ✅ | `imgsz`, `half`, `int8`, `nms` | -| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | `imgsz`, `keras`, `int8` | -| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | `imgsz` | -| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | `imgsz`, `half`, `int8` | -| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | -| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | -| [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | - -## Overriding default arguments - -Default arguments can be overridden by simply passing them as arguments in the CLI in `arg=value` pairs. - -!!! Tip "" - - === "Train" - - Train a detection model for `10 epochs` with `learning_rate` of `0.01` - ```bash - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 - ``` - - === "Predict" - - Predict a YouTube video using a pretrained segmentation model at image size 320: - ```bash - yolo segment predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 - ``` - - === "Val" - - Validate a pretrained detection model at batch-size 1 and image size 640: - ```bash - yolo detect val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 - ``` - -## Overriding default config file - -You can override the `default.yaml` config file entirely by passing a new file with the `cfg` arguments, i.e. `cfg=custom.yaml`. - -To do this first create a copy of `default.yaml` in your current working dir with the `yolo copy-cfg` command. - -This will create `default_copy.yaml`, which you can then pass as `cfg=default_copy.yaml` along with any additional args, like `imgsz=320` in this example: - -!!! Example - - === "CLI" - - ```bash - yolo copy-cfg - yolo cfg=default_copy.yaml imgsz=320 - ``` diff --git a/ultralytics-main/docs/en/usage/engine.md b/ultralytics-main/docs/en/usage/engine.md deleted file mode 100644 index 7d6964e..0000000 --- a/ultralytics-main/docs/en/usage/engine.md +++ /dev/null @@ -1,91 +0,0 @@ ---- -comments: true -description: Discover how to customize and extend base Ultralytics YOLO Trainer engines. Support your custom model and dataloader by overriding built-in functions. -keywords: Ultralytics, YOLO, trainer engines, BaseTrainer, DetectionTrainer, customizing trainers, extending trainers, custom model, custom dataloader ---- - -Both the Ultralytics YOLO command-line and Python interfaces are simply a high-level abstraction on the base engine executors. Let's take a look at the Trainer engine. - -

-
- -
- Watch: Mastering Ultralytics YOLOv8: Advanced Customization -

- -## BaseTrainer - -BaseTrainer contains the generic boilerplate training routine. It can be customized for any task based over overriding the required functions or operations as long the as correct formats are followed. For example, you can support your own custom model and dataloader by just overriding these functions: - -- `get_model(cfg, weights)` - The function that builds the model to be trained -- `get_dataloader()` - The function that builds the dataloader More details and source code can be found in [`BaseTrainer` Reference](../reference/engine/trainer.md) - -## DetectionTrainer - -Here's how you can use the YOLOv8 `DetectionTrainer` and customize it. - -```python -from ultralytics.models.yolo.detect import DetectionTrainer - -trainer = DetectionTrainer(overrides={...}) -trainer.train() -trained_model = trainer.best # get best model -``` - -### Customizing the DetectionTrainer - -Let's customize the trainer **to train a custom detection model** that is not supported directly. You can do this by simply overloading the existing the `get_model` functionality: - -```python -from ultralytics.models.yolo.detect import DetectionTrainer - - -class CustomTrainer(DetectionTrainer): - def get_model(self, cfg, weights): - ... - - -trainer = CustomTrainer(overrides={...}) -trainer.train() -``` - -You now realize that you need to customize the trainer further to: - -- Customize the `loss function`. -- Add `callback` that uploads model to your Google Drive after every 10 `epochs` Here's how you can do it: - -```python -from ultralytics.models.yolo.detect import DetectionTrainer -from ultralytics.nn.tasks import DetectionModel - - -class MyCustomModel(DetectionModel): - def init_criterion(self): - ... - - -class CustomTrainer(DetectionTrainer): - def get_model(self, cfg, weights): - return MyCustomModel(...) - - -# callback to upload model weights -def log_model(trainer): - last_weight_path = trainer.last - print(last_weight_path) - - -trainer = CustomTrainer(overrides={...}) -trainer.add_callback("on_train_epoch_end", log_model) # Adds to existing callback -trainer.train() -``` - -To know more about Callback triggering events and entry point, checkout our [Callbacks Guide](callbacks.md) - -## Other engine components - -There are other components that can be customized similarly like `Validators` and `Predictors`. See Reference section for more information on these. diff --git a/ultralytics-main/docs/en/usage/python.md b/ultralytics-main/docs/en/usage/python.md deleted file mode 100644 index db4fd2e..0000000 --- a/ultralytics-main/docs/en/usage/python.md +++ /dev/null @@ -1,325 +0,0 @@ ---- -comments: true -description: Boost your Python projects with object detection, segmentation and classification using YOLOv8. Explore how to load, train, validate, predict, export, track and benchmark models with ease. -keywords: YOLOv8, Ultralytics, Python, object detection, segmentation, classification, model training, validation, prediction, model export, benchmark, real-time tracking ---- - -# Python Usage - -Welcome to the YOLOv8 Python Usage documentation! This guide is designed to help you seamlessly integrate YOLOv8 into your Python projects for object detection, segmentation, and classification. Here, you'll learn how to load and use pretrained models, train new models, and perform predictions on images. The easy-to-use Python interface is a valuable resource for anyone looking to incorporate YOLOv8 into their Python projects, allowing you to quickly implement advanced object detection capabilities. Let's get started! - -

-
- -
- Watch: Mastering Ultralytics YOLOv8: Python -

- -For example, users can load a model, train it, evaluate its performance on a validation set, and even export it to ONNX format with just a few lines of code. - -!!! Example "Python" - - ```python - from ultralytics import YOLO - - # Create a new YOLO model from scratch - model = YOLO('yolov8n.yaml') - - # Load a pretrained YOLO model (recommended for training) - model = YOLO('yolov8n.pt') - - # Train the model using the 'coco128.yaml' dataset for 3 epochs - results = model.train(data='coco128.yaml', epochs=3) - - # Evaluate the model's performance on the validation set - results = model.val() - - # Perform object detection on an image using the model - results = model('https://ultralytics.com/images/bus.jpg') - - # Export the model to ONNX format - success = model.export(format='onnx') - ``` - -## [Train](../modes/train.md) - -Train mode is used for training a YOLOv8 model on a custom dataset. In this mode, the model is trained using the specified dataset and hyperparameters. The training process involves optimizing the model's parameters so that it can accurately predict the classes and locations of objects in an image. - -!!! Example "Train" - - === "From pretrained(recommended)" - - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') # pass any model type - results = model.train(epochs=5) - ``` - - === "From scratch" - - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.yaml') - results = model.train(data='coco128.yaml', epochs=5) - ``` - - === "Resume" - - ```python - model = YOLO("last.pt") - results = model.train(resume=True) - ``` - -[Train Examples](../modes/train.md){ .md-button } - -## [Val](../modes/val.md) - -Val mode is used for validating a YOLOv8 model after it has been trained. In this mode, the model is evaluated on a validation set to measure its accuracy and generalization performance. This mode can be used to tune the hyperparameters of the model to improve its performance. - -!!! Example "Val" - - === "Val after training" - - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.yaml') - model.train(data='coco128.yaml', epochs=5) - model.val() # It'll automatically evaluate the data you trained. - ``` - - === "Val independently" - - ```python - from ultralytics import YOLO - - model = YOLO("model.pt") - # It'll use the data YAML file in model.pt if you don't set data. - model.val() - # or you can set the data you want to val - model.val(data='coco128.yaml') - ``` - -[Val Examples](../modes/val.md){ .md-button } - -## [Predict](../modes/predict.md) - -Predict mode is used for making predictions using a trained YOLOv8 model on new images or videos. In this mode, the model is loaded from a checkpoint file, and the user can provide images or videos to perform inference. The model predicts the classes and locations of objects in the input images or videos. - -!!! Example "Predict" - - === "From source" - - ```python - from ultralytics import YOLO - from PIL import Image - import cv2 - - model = YOLO("model.pt") - # accepts all formats - image/dir/Path/URL/video/PIL/ndarray. 0 for webcam - results = model.predict(source="0") - results = model.predict(source="folder", show=True) # Display preds. Accepts all YOLO predict arguments - - # from PIL - im1 = Image.open("bus.jpg") - results = model.predict(source=im1, save=True) # save plotted images - - # from ndarray - im2 = cv2.imread("bus.jpg") - results = model.predict(source=im2, save=True, save_txt=True) # save predictions as labels - - # from list of PIL/ndarray - results = model.predict(source=[im1, im2]) - ``` - - === "Results usage" - - ```python - # results would be a list of Results object including all the predictions by default - # but be careful as it could occupy a lot memory when there're many images, - # especially the task is segmentation. - # 1. return as a list - results = model.predict(source="folder") - - # results would be a generator which is more friendly to memory by setting stream=True - # 2. return as a generator - results = model.predict(source=0, stream=True) - - for result in results: - # Detection - result.boxes.xyxy # box with xyxy format, (N, 4) - result.boxes.xywh # box with xywh format, (N, 4) - result.boxes.xyxyn # box with xyxy format but normalized, (N, 4) - result.boxes.xywhn # box with xywh format but normalized, (N, 4) - result.boxes.conf # confidence score, (N, 1) - result.boxes.cls # cls, (N, 1) - - # Segmentation - result.masks.data # masks, (N, H, W) - result.masks.xy # x,y segments (pixels), List[segment] * N - result.masks.xyn # x,y segments (normalized), List[segment] * N - - # Classification - result.probs # cls prob, (num_class, ) - - # Each result is composed of torch.Tensor by default, - # in which you can easily use following functionality: - result = result.cuda() - result = result.cpu() - result = result.to("cpu") - result = result.numpy() - ``` - -[Predict Examples](../modes/predict.md){ .md-button } - -## [Export](../modes/export.md) - -Export mode is used for exporting a YOLOv8 model to a format that can be used for deployment. In this mode, the model is converted to a format that can be used by other software applications or hardware devices. This mode is useful when deploying the model to production environments. - -!!! Example "Export" - - === "Export to ONNX" - - Export an official YOLOv8n model to ONNX with dynamic batch-size and image-size. - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - model.export(format='onnx', dynamic=True) - ``` - - === "Export to TensorRT" - - Export an official YOLOv8n model to TensorRT on `device=0` for acceleration on CUDA devices. - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - model.export(format='onnx', device=0) - ``` - -[Export Examples](../modes/export.md){ .md-button } - -## [Track](../modes/track.md) - -Track mode is used for tracking objects in real-time using a YOLOv8 model. In this mode, the model is loaded from a checkpoint file, and the user can provide a live video stream to perform real-time object tracking. This mode is useful for applications such as surveillance systems or self-driving cars. - -!!! Example "Track" - - === "Python" - - ```python - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.pt') # load an official detection model - model = YOLO('yolov8n-seg.pt') # load an official segmentation model - model = YOLO('path/to/best.pt') # load a custom model - - # Track with the model - results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True) - results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml") - ``` - -[Track Examples](../modes/track.md){ .md-button } - -## [Benchmark](../modes/benchmark.md) - -Benchmark mode is used to profile the speed and accuracy of various export formats for YOLOv8. The benchmarks provide information on the size of the exported format, its `mAP50-95` metrics (for object detection and segmentation) or `accuracy_top5` metrics (for classification), and the inference time in milliseconds per image across various export formats like ONNX, OpenVINO, TensorRT and others. This information can help users choose the optimal export format for their specific use case based on their requirements for speed and accuracy. - -!!! Example "Benchmark" - - === "Python" - - Benchmark an official YOLOv8n model across all export formats. - ```python - from ultralytics.utils.benchmarks import benchmark - - # Benchmark - benchmark(model='yolov8n.pt', data='coco8.yaml', imgsz=640, half=False, device=0) - ``` - -[Benchmark Examples](../modes/benchmark.md){ .md-button } - -## Explorer - -Explorer API can be used to explore datasets with advanced semantic, vector-similarity and SQL search among other features. It also enabled searching for images based on their content using natural language by utilizing the power of LLMs. The Explorer API allows you to write your own dataset exploration notebooks or scripts to get insights into your datasets. - -!!! Example "Semantic Search Using Explorer" - - === "Using Images" - - ```python - from ultralytics import Explorer - - # create an Explorer object - exp = Explorer(data='coco128.yaml', model='yolov8n.pt') - exp.create_embeddings_table() - - similar = exp.get_similar(img='https://ultralytics.com/images/bus.jpg', limit=10) - print(similar.head()) - - # Search using multiple indices - similar = exp.get_similar( - img=['https://ultralytics.com/images/bus.jpg', - 'https://ultralytics.com/images/bus.jpg'], - limit=10 - ) - print(similar.head()) - ``` - - === "Using Dataset Indices" - - ```python - from ultralytics import Explorer - - # create an Explorer object - exp = Explorer(data='coco128.yaml', model='yolov8n.pt') - exp.create_embeddings_table() - - similar = exp.get_similar(idx=1, limit=10) - print(similar.head()) - - # Search using multiple indices - similar = exp.get_similar(idx=[1,10], limit=10) - print(similar.head()) - ``` - -[Explorer](../datasets/explorer/index.md){ .md-button } - -## Using Trainers - -`YOLO` model class is a high-level wrapper on the Trainer classes. Each YOLO task has its own trainer that inherits from `BaseTrainer`. - -!!! Tip "Detection Trainer Example" - - ```python - from ultralytics.models.yolo import DetectionTrainer, DetectionValidator, DetectionPredictor - - # trainer - trainer = DetectionTrainer(overrides={}) - trainer.train() - trained_model = trainer.best - - # Validator - val = DetectionValidator(args=...) - val(model=trained_model) - - # predictor - pred = DetectionPredictor(overrides={}) - pred(source=SOURCE, model=trained_model) - - # resume from last weight - overrides["resume"] = trainer.last - trainer = detect.DetectionTrainer(overrides=overrides) - ``` - -You can easily customize Trainers to support custom tasks or explore R&D ideas. Learn more about Customizing `Trainers`, `Validators` and `Predictors` to suit your project needs in the Customization Section. - -[Customization tutorials](engine.md){ .md-button } diff --git a/ultralytics-main/docs/en/usage/simple-utilities.md b/ultralytics-main/docs/en/usage/simple-utilities.md deleted file mode 100644 index c170f51..0000000 --- a/ultralytics-main/docs/en/usage/simple-utilities.md +++ /dev/null @@ -1,429 +0,0 @@ ---- -comments: true -description: Discover how to extend the utility of the Ultralytics package to support your development process. -keywords: Ultralytics, YOLO, custom, function, workflow, utility, support, ---- - -# Simple Utilities - -

- code with perspective -

- -The `ultralytics` package comes with a myriad of utilities that can support, enhance, and speed up your workflows. There are many more available, but here are some that will be useful for most developers. They're also a great reference point to use when learning to program. - -## Data - -### YOLO Data Explorer - -[YOLO Explorer](../datasets/explorer/index.md) was added in the `8.1.0` anniversary update and is a powerful tool you can use to better understand your dataset. One of the key functions that YOLO Explorer provides, is the ability to use text queries to find object instances in your dataset. - -### Auto Labeling / Annotations - -Dataset annotation is a very resource intensive and time-consuming process. If you have a YOLO object detection model trained on a reasonable amount of data, you can use it and [SAM](../models/sam.md) to auto-annotate additional data (segmentation format). - -```{ .py .annotate } -from ultralytics.data.annotator import auto_annotate - -auto_annotate(#(1)! - data='path/to/new/data', - det_model='yolov8n.pt', - sam_model='mobile_sam.pt', - device="cuda", - output_dir="path/to/save_labels", -) -``` - -1. Nothing returns from this function - -- [See the reference section for `annotator.auto_annotate`](../reference/data/annotator.md#ultralytics.data.annotator.auto_annotate) for more insight on how the function operates. - -- Use in combination with the [function `segments2boxes`](#convert-segments-to-bounding-boxes) to generate object detection bounding boxes as well - -### Convert COCO into YOLO Format - -Use to convert COCO JSON annotations into proper YOLO format. For object detection (bounding box) datasets, `use_segments` and `use_keypoints` should both be `False` - -```{ .py .annotate } -from ultralytics.data.converter import convert_coco - -convert_coco(#(1)! - '../datasets/coco/annotations/', - use_segments=False, - use_keypoints=False, - cls91to80=True, -) -``` - -1. Nothing returns from this function - -For additional information about the `convert_coco` function, [visit the reference page](../reference/data/converter.md#ultralytics.data.converter.convert_coco) - -### Convert Bounding Boxes to Segments - -With existing `x y w h` bounding box data, convert to segments using the `yolo_bbox2segment` function. The files for images and annotations need to be organized like this: - -``` -data -|__ images - ├─ 001.jpg - ├─ 002.jpg - ├─ .. - └─ NNN.jpg -|__ labels - ├─ 001.txt - ├─ 002.txt - ├─ .. - └─ NNN.txt -``` - -```{ .py .annotate } -from ultralytics.data.converter import yolo_bbox2segment - -yolo_bbox2segment(#(1)! - im_dir="path/to/images", - save_dir=None, # saved to "labels-segment" in images directory - sam_model="sam_b.pt" -) -``` - -1. Nothing returns from this function - -[Visit the `yolo_bbox2segment` reference page](../reference/data/converter.md#ultralytics.data.converter.yolo_bbox2segment) for more information regarding the function. - -### Convert Segments to Bounding Boxes - -If you have a dataset that uses the [segmentation dataset format](../datasets/segment/index.md) you can easily convert these into up-right (or horizontal) bounding boxes (`x y w h` format) with this function. - -```python -from ultralytics.utils.ops import segments2boxes - -segments = np.array( - [[805, 392, 797, 400, ..., 808, 714, 808, 392], - [115, 398, 113, 400, ..., 150, 400, 149, 298], - [267, 412, 265, 413, ..., 300, 413, 299, 412], - ] -) - -segments2boxes([s.reshape(-1,2) for s in segments]) ->>> array([[ 741.66, 631.12, 133.31, 479.25], - [ 146.81, 649.69, 185.62, 502.88], - [ 281.81, 636.19, 118.12, 448.88]], - dtype=float32) # xywh bounding boxes -``` - -To understand how this function works, visit the [reference page](../reference/utils/ops.md#ultralytics.utils.ops.segments2boxes) - -## Utilities - -### Image Compression - -Compresses a single image file to reduced size while preserving its aspect ratio and quality. If the input image is smaller than the maximum dimension, it will not be resized. - -```{ .py .annotate } -from pathlib import Path -from ultralytics.data.utils import compress_one_image - -for f in Path('path/to/dataset').rglob('*.jpg'): - compress_one_image(f)#(1)! -``` - -1. Nothing returns from this function - -### Auto-split Dataset - -Automatically split a dataset into `train`/`val`/`test` splits and save the resulting splits into `autosplit_*.txt` files. This function will use random sampling, which is not included when using [`fraction` argument for training](../modes/train.md#arguments). - -```{ .py .annotate } -from ultralytics.data.utils import autosplit - -autosplit( #(1)! - path="path/to/images", - weights=(0.9, 0.1, 0.0), # (train, validation, test) fractional splits - annotated_only=False # split only images with annotation file when True -) -``` - -1. Nothing returns from this function - -See the [Reference page](../reference/data/utils.md#ultralytics.data.utils.autosplit) for additional details on this function. - -### Segment-polygon to Binary Mask - -Convert a single polygon (as list) to a binary mask of the specified image size. Polygon in the form of `[N, 2]` with `N` as the number of `(x, y)` points defining the polygon contour. - -!!! warning - - `N` must always be even. - -```python -import numpy as np -from ultralytics.data.utils import polygon2mask - -imgsz = (1080, 810) -polygon = np.array( - [805, 392, 797, 400, ..., 808, 714, 808, 392], # (238, 2) -) - -mask = polygon2mask( - imgsz, # tuple - [polygon], # input as list - color=255, # 8-bit binary - downsample_ratio=1 -) -``` - -## Bounding Boxes - -### Bounding Box (horizontal) Instances - -To manage bounding box data, the `Bboxes` class will help to convert between box coordinate formatting, scale box dimensions, calculate areas, include offsets, and more! - -```python -from ultralytics.utils.instance import Bboxes - -boxes = Bboxes( - bboxes=np.array( - [[ 22.878, 231.27, 804.98, 756.83,], - [ 48.552, 398.56, 245.35, 902.71,], - [ 669.47, 392.19, 809.72, 877.04,], - [ 221.52, 405.8, 344.98, 857.54,], - [ 0, 550.53, 63.01, 873.44,], - [ 0.0584, 254.46, 32.561, 324.87,]] - ), - format="xyxy", -) - -boxes.areas() ->>> array([ 4.1104e+05, 99216, 68000, 55772, 20347, 2288.5]) -boxes.convert("xywh") -boxes.bboxes ->>> array( - [[ 413.93, 494.05, 782.1, 525.56], - [ 146.95, 650.63, 196.8, 504.15], - [ 739.6, 634.62, 140.25, 484.85], - [ 283.25, 631.67, 123.46, 451.74], - [ 31.505, 711.99, 63.01, 322.91], - [ 16.31, 289.67, 32.503, 70.41]] -) -``` - -See the [`Bboxes` reference section](../reference/utils/instance.md#ultralytics.utils.instance.Bboxes) for more attributes and methods available. - -!!! tip - Many of the following functions (and more) can be accessed using the [`Bboxes` class](#bounding-box-horizontal-instances) but if you prefer to work with the functions directly, see the next subsections on how to import these independently. - -### Scaling Boxes - -When scaling and image up or down, corresponding bounding box coordinates can be appropriately scaled to match using `ultralytics.utils.ops.scale_boxes`. - -```{ .py .annotate } -import cv2 as cv -import numpy as np -from ultralytics.utils.ops import scale_boxes - -image = cv.imread("ultralytics/assets/bus.jpg") -*(h, w), c = image.shape -resized = cv.resize(image, None, (), fx=1.2, fy=1.2) -*(new_h, new_w), _ = resized.shape - -xyxy_boxes = np.array( - [[ 22.878, 231.27, 804.98, 756.83,], - [ 48.552, 398.56, 245.35, 902.71,], - [ 669.47, 392.19, 809.72, 877.04,], - [ 221.52, 405.8, 344.98, 857.54,], - [ 0, 550.53, 63.01, 873.44,], - [ 0.0584, 254.46, 32.561, 324.87,]] -) - -new_boxes = scale_boxes( - img1_shape=(h, w), # original image dimensions - boxes=xyxy_boxes, # boxes from original image - img0_shape=(new_h, new_w), # resized image dimensions (scale to) - ratio_pad=None, - padding=False, - xywh=False, -) - -new_boxes#(1)! ->>> array( - [[ 27.454, 277.52, 965.98, 908.2], - [ 58.262, 478.27, 294.42, 1083.3], - [ 803.36, 470.63, 971.66, 1052.4], - [ 265.82, 486.96, 413.98, 1029], - [ 0, 660.64, 75.612, 1048.1], - [ 0.0701, 305.35, 39.073, 389.84]] -) -``` - -1. Bounding boxes scaled for the new image size - -### Bounding Box Format Conversions - -#### XYXY → XYWH - -Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner. - -```python -import numpy as np -from ultralytics.utils.ops import xyxy2xywh - -xyxy_boxes = np.array( - [[ 22.878, 231.27, 804.98, 756.83,], - [ 48.552, 398.56, 245.35, 902.71,], - [ 669.47, 392.19, 809.72, 877.04,], - [ 221.52, 405.8, 344.98, 857.54,], - [ 0, 550.53, 63.01, 873.44,], - [ 0.0584, 254.46, 32.561, 324.87,]] -) -xywh = xyxy2xywh(xyxy_boxes) - -xywh ->>> array( - [[ 413.93, 494.05, 782.1, 525.56], - [ 146.95, 650.63, 196.8, 504.15], - [ 739.6, 634.62, 140.25, 484.85], - [ 283.25, 631.67, 123.46, 451.74], - [ 31.505, 711.99, 63.01, 322.91], - [ 16.31, 289.67, 32.503, 70.41]] -) -``` - -### All Bounding Box Conversions - -```python -from ultralytics.utils.ops import xywh2xyxy -from ultralytics.utils.ops import xywhn2xyxy # normalized → pixel -from ultralytics.utils.ops import xyxy2xywhn # pixel → normalized -from ultralytics.utils.ops import xywh2ltwh # xywh → top-left corner, w, h -from ultralytics.utils.ops import xyxy2ltwh # xyxy → top-left corner, w, h -from ultralytics.utils.ops import ltwh2xywh -from ultralytics.utils.ops import ltwh2xyxy -``` - -See docstring for each function or visit the `ultralytics.utils.ops` [reference page](../reference/utils/ops.md) to read more about each function. - -## Plotting - -### Drawing Annotations - -Ultralytics includes an Annotator class that can be used to annotate any kind of data. It's easiest to use with [object detection bounding boxes](../modes/predict.md#boxes), [pose key points](../modes/predict.md#keypoints), and [oriented bounding boxes](../modes/predict.md#obb). - -#### Horizontal Bounding Boxes - -```{ .py .annotate } -import cv2 as cv -import numpy as np -from ultralytics.utils.plotting import Annotator, colors - -names { #(1)! - 0: "person", - 5: "bus", - 11: "stop sign", -} - -image = cv.imread("ultralytics/assets/bus.jpg") -ann = Annotator( - image, - line_width=None, # default auto-size - font_size=None, # default auto-size - font="Arial.ttf", # must be ImageFont compatible - pil=False, # use PIL, otherwise uses OpenCV -) - -xyxy_boxes = np.array( - [[ 5, 22.878, 231.27, 804.98, 756.83,], # class-idx x1 y1 x2 y2 - [ 0, 48.552, 398.56, 245.35, 902.71,], - [ 0, 669.47, 392.19, 809.72, 877.04,], - [ 0, 221.52, 405.8, 344.98, 857.54,], - [ 0, 0, 550.53, 63.01, 873.44,], - [11, 0.0584, 254.46, 32.561, 324.87,]] -) - -for nb, box in enumerate(xyxy_boxes): - c_idx, *box = box - label = f"{str(nb).zfill(2)}:{names.get(int(c_idx))}" - ann.box_label(box, label, color=colors(c_idx, bgr=True)) - -image_with_bboxes = ann.result() -``` - -1. Names can be used from `model.names` when [working with detection results](../modes/predict.md#working-with-results) - -#### Oriented Bounding Boxes (OBB) -```python -import cv2 as cv -import numpy as np -from ultralytics.utils.plotting import Annotator, colors - -obb_names = {10: "small vehicle"} -obb_image = cv.imread("datasets/dota8/images/train/P1142__1024__0___824.jpg") -obb_boxes = np.array( - [[ 0, 635, 560, 919, 719, 1087, 420, 803, 261,], # class-idx x1 y1 x2 y2 x3 y2 x4 y4 - [ 0, 331, 19, 493, 260, 776, 70, 613, -171,], - [ 9, 869, 161, 886, 147, 851, 101, 833, 115,] - ] -) -ann = Annotator( - obb_image, - line_width=None, # default auto-size - font_size=None, # default auto-size - font="Arial.ttf", # must be ImageFont compatible - pil=False, # use PIL, otherwise uses OpenCV -) -for obb in obb_boxes: - c_idx, *obb = obb - obb = np.array(obb).reshape(-1, 4, 2).squeeze() - label = f"{names.get(int(c_idx))}" - ann.box_label( - obb, - label, - color=colors(c_idx, True), - rotated=True, - ) - -image_with_obb = ann.result() -``` - -See the [`Annotator` Reference Page](../reference/utils/plotting.md#ultralytics.utils.plotting.Annotator) for additional insight. - -## Miscellaneous - -### Code Profiling - -Check duration for code to run/process either using `with` or as a decorator. - -```python -from ultralytics.utils.ops import Profile - -with Profile(device=device) as dt: - pass # operation to measure - -print(dt) ->>> "Elapsed time is 9.5367431640625e-07 s" -``` - -### Ultralytics Supported Formats - -Want or need to use the formats of [images or videos types supported](../modes/predict.md#image-and-video-formats) by Ultralytics programmatically? Use these constants if you need. - -```python -from ultralytics.data.utils import IMG_FORMATS -from ultralytics.data.utils import VID_FORMATS - -print(IMG_FORMATS) ->>> ('bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp', 'pfm') -``` - -### Make Divisible - -Calculates the nearest whole number to `x` to make evenly divisible when divided by `y`. - -```python -from ultralytics.utils.ops import make_divisible - -make_divisible(7, 3) ->>> 9 -make_divisible(7, 2) ->>> 8 -``` diff --git a/ultralytics-main/docs/en/yolov5/environments/aws_quickstart_tutorial.md b/ultralytics-main/docs/en/yolov5/environments/aws_quickstart_tutorial.md deleted file mode 100644 index 2bf3240..0000000 --- a/ultralytics-main/docs/en/yolov5/environments/aws_quickstart_tutorial.md +++ /dev/null @@ -1,95 +0,0 @@ ---- -comments: true -description: Follow this comprehensive guide to set up and operate YOLOv5 on an AWS Deep Learning instance for object detection tasks. Get started with model training and deployment. -keywords: YOLOv5, AWS Deep Learning AMIs, object detection, machine learning, AI, model training, instance setup, Ultralytics ---- - -# YOLOv5 🚀 on AWS Deep Learning Instance: Your Complete Guide - -Setting up a high-performance deep learning environment can be daunting for newcomers, but fear not! 🛠️ With this guide, we'll walk you through the process of getting YOLOv5 up and running on an AWS Deep Learning instance. By leveraging the power of Amazon Web Services (AWS), even those new to machine learning can get started quickly and cost-effectively. The AWS platform's scalability is perfect for both experimentation and production deployment. - -Other quickstart options for YOLOv5 include our [Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) Open In Colab Open In Kaggle, [GCP Deep Learning VM](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial), and our Docker image at [Docker Hub](https://hub.docker.com/r/ultralytics/yolov5) Docker Pulls. - -## Step 1: AWS Console Sign-In - -Start by creating an account or signing in to the AWS console at [https://aws.amazon.com/console/](https://aws.amazon.com/console/). Once logged in, select the **EC2** service to manage and set up your instances. - -![Console](https://user-images.githubusercontent.com/26833433/106323804-debddd00-622c-11eb-997f-b8217dc0e975.png) - -## Step 2: Launch Your Instance - -In the EC2 dashboard, you'll find the **Launch Instance** button which is your gateway to creating a new virtual server. - -![Launch](https://user-images.githubusercontent.com/26833433/106323950-204e8800-622d-11eb-915d-5c90406973ea.png) - -### Selecting the Right Amazon Machine Image (AMI) - -Here's where you choose the operating system and software stack for your instance. Type 'Deep Learning' into the search field and select the latest Ubuntu-based Deep Learning AMI, unless your needs dictate otherwise. Amazon's Deep Learning AMIs come pre-installed with popular frameworks and GPU drivers to streamline your setup process. - -![Choose AMI](https://user-images.githubusercontent.com/26833433/106326107-c9e34880-6230-11eb-97c9-3b5fc2f4e2ff.png) - -### Picking an Instance Type - -For deep learning tasks, selecting a GPU instance type is generally recommended as it can vastly accelerate model training. For instance size considerations, remember that the model's memory requirements should never exceed what your instance can provide. - -**Note:** The size of your model should be a factor in selecting an instance. If your model exceeds an instance's available RAM, select a different instance type with enough memory for your application. - -For a list of available GPU instance types, visit [EC2 Instance Types](https://aws.amazon.com/ec2/instance-types/), specifically under Accelerated Computing. - -![Choose Type](https://user-images.githubusercontent.com/26833433/106324624-52141e80-622e-11eb-9662-1a376d9c887d.png) - -For more information on GPU monitoring and optimization, see [GPU Monitoring and Optimization](https://docs.aws.amazon.com/dlami/latest/devguide/tutorial-gpu.html). For pricing, see [On-Demand Pricing](https://aws.amazon.com/ec2/pricing/on-demand/) and [Spot Pricing](https://aws.amazon.com/ec2/spot/pricing/). - -### Configuring Your Instance - -Amazon EC2 Spot Instances offer a cost-effective way to run applications as they allow you to bid for unused capacity at a fraction of the standard cost. For a persistent experience that retains data even when the Spot Instance goes down, opt for a persistent request. - -![Spot Request](https://user-images.githubusercontent.com/26833433/106324835-ac14e400-622e-11eb-8853-df5ec9b16dfc.png) - -Remember to adjust the rest of your instance settings and security configurations as needed in Steps 4-7 before launching. - -## Step 3: Connect to Your Instance - -Once your instance is running, select its checkbox and click Connect to access the SSH information. Use the displayed SSH command in your preferred terminal to establish a connection to your instance. - -![Connect](https://user-images.githubusercontent.com/26833433/106325530-cf8c5e80-622f-11eb-9f64-5b313a9d57a1.png) - -## Step 4: Running YOLOv5 - -Logged into your instance, you're now ready to clone the YOLOv5 repository and install dependencies within a Python 3.8 or later environment. YOLOv5's models and datasets will automatically download from the latest [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone repository -cd yolov5 -pip install -r requirements.txt # install dependencies -``` - -With your environment set up, you can begin training, validating, performing inference, and exporting your YOLOv5 models: - -```bash -# Train a model on your data -python train.py - -# Validate the trained model for Precision, Recall, and mAP -python val.py --weights yolov5s.pt - -# Run inference using the trained model on your images or videos -python detect.py --weights yolov5s.pt --source path/to/images - -# Export the trained model to other formats for deployment -python export.py --weights yolov5s.pt --include onnx coreml tflite -``` - -## Optional Extras - -To add more swap memory, which can be a savior for large datasets, run: - -```bash -sudo fallocate -l 64G /swapfile # allocate 64GB swap file -sudo chmod 600 /swapfile # modify permissions -sudo mkswap /swapfile # set up a Linux swap area -sudo swapon /swapfile # activate swap file -free -h # verify swap memory -``` - -And that's it! 🎉 You've successfully created an AWS Deep Learning instance and run YOLOv5. Whether you're just starting with object detection or scaling up for production, this setup can help you achieve your machine learning goals. Happy training, validating, and deploying! If you encounter any hiccups along the way, the robust AWS documentation and the active Ultralytics community are here to support you. diff --git a/ultralytics-main/docs/en/yolov5/environments/azureml_quickstart_tutorial.md b/ultralytics-main/docs/en/yolov5/environments/azureml_quickstart_tutorial.md deleted file mode 100644 index 9f87f59..0000000 --- a/ultralytics-main/docs/en/yolov5/environments/azureml_quickstart_tutorial.md +++ /dev/null @@ -1,94 +0,0 @@ ---- -comments: true -description: Azure Machine Learning YOLOv5 quickstart -keywords: Ultralytics, YOLO, Deep Learning, Object detection, quickstart, Azure, AzureML ---- - -# YOLOv5 🚀 on AzureML - -This guide provides a quickstart to use YOLOv5 from an AzureML compute instance. - -Note that this guide is a quickstart for quick trials. If you want to unlock the full power AzureML, you can find the documentation to: - -- [Create a data asset](https://learn.microsoft.com/azure/machine-learning/how-to-create-data-assets) -- [Create an AzureML job](https://learn.microsoft.com/azure/machine-learning/how-to-train-model) -- [Register a model](https://learn.microsoft.com/azure/machine-learning/how-to-manage-models) - -## Prerequisites - -You need an [AzureML workspace](https://learn.microsoft.com/azure/machine-learning/concept-workspace?view=azureml-api-2). - -## Create a compute instance - -From your AzureML workspace, select Compute > Compute instances > New, select the instance with the resources you need. - -create-compute-arrow - -## Open a Terminal - -Now from the Notebooks view, open a Terminal and select your compute. - -![open-terminal-arrow](https://github.com/ouphi/ultralytics/assets/17216799/c4697143-7234-4a04-89ea-9084ed9c6312) - -## Setup and run YOLOv5 - -Now you can, create a virtual environment: - -```bash -conda create --name yolov5env -y -conda activate yolov5env -conda install pip -y -``` - -Clone YOLOv5 repository with its submodules: - -```bash -git clone https://github.com/ultralytics/yolov5 -cd yolov5 -git submodule update --init --recursive # Note that you might have a message asking you to add your folder as a safe.directory just copy the recommended command -``` - -Install the required dependencies: - -```bash -pip install -r yolov5/requirements.txt -pip install onnx>=1.10.0 -``` - -Train the YOLOv5 model: - -```bash -python train.py -``` - -Validate the model for Precision, Recall, and mAP - -```bash -python val.py --weights yolov5s.pt -``` - -Run inference on images and videos: - -```bash -python detect.py --weights yolov5s.pt --source path/to/images -``` - -Export models to other formats: - -```bash -python detect.py --weights yolov5s.pt --source path/to/images -``` - -## Notes on using a notebook - -Note that if you want to run these commands from a Notebook, you need to [create a new Kernel](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-access-terminal?view=azureml-api-2#add-new-kernels) and select your new Kernel on the top of your Notebook. - -If you create Python cells it will automatically use your custom environment, but if you add bash cells, you will need to run `source activate ` on each of these cells to make sure it uses your custom environment. - -For example: - -```bash -%%bash -source activate newenv -python val.py --weights yolov5s.pt -``` diff --git a/ultralytics-main/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md b/ultralytics-main/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md deleted file mode 100644 index 2e2bd81..0000000 --- a/ultralytics-main/docs/en/yolov5/environments/docker_image_quickstart_tutorial.md +++ /dev/null @@ -1,71 +0,0 @@ ---- -comments: true -description: Learn how to set up and run YOLOv5 in a Docker container. This tutorial includes the prerequisites and step-by-step instructions. -keywords: YOLOv5, Docker, Ultralytics, Image Detection, YOLOv5 Docker Image, Docker Container, Machine Learning, AI ---- - -# Get Started with YOLOv5 🚀 in Docker - -This tutorial will guide you through the process of setting up and running YOLOv5 in a Docker container. - -You can also explore other quickstart options for YOLOv5, such as our [Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) Open In Colab Open In Kaggle, [GCP Deep Learning VM](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial), and [Amazon AWS](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial). - -## Prerequisites - -1. **Nvidia Driver**: Version 455.23 or higher. Download from [Nvidia's website](https://www.nvidia.com/Download/index.aspx). -2. **Nvidia-Docker**: Allows Docker to interact with your local GPU. Installation instructions are available on the [Nvidia-Docker GitHub repository](https://github.com/NVIDIA/nvidia-docker). -3. **Docker Engine - CE**: Version 19.03 or higher. Download and installation instructions can be found on the [Docker website](https://docs.docker.com/install/). - -## Step 1: Pull the YOLOv5 Docker Image - -The Ultralytics YOLOv5 DockerHub repository is available at [https://hub.docker.com/r/ultralytics/yolov5](https://hub.docker.com/r/ultralytics/yolov5). Docker Autobuild ensures that the `ultralytics/yolov5:latest` image is always in sync with the most recent repository commit. To pull the latest image, run the following command: - -```bash -sudo docker pull ultralytics/yolov5:latest -``` - -## Step 2: Run the Docker Container - -### Basic container: - -Run an interactive instance of the YOLOv5 Docker image (called a "container") using the `-it` flag: - -```bash -sudo docker run --ipc=host -it ultralytics/yolov5:latest -``` - -### Container with local file access: - -To run a container with access to local files (e.g., COCO training data in `/datasets`), use the `-v` flag: - -```bash -sudo docker run --ipc=host -it -v "$(pwd)"/datasets:/usr/src/datasets ultralytics/yolov5:latest -``` - -### Container with GPU access: - -To run a container with GPU access, use the `--gpus all` flag: - -```bash -sudo docker run --ipc=host -it --gpus all ultralytics/yolov5:latest -``` - -## Step 3: Use YOLOv5 🚀 within the Docker Container - -Now you can train, test, detect, and export YOLOv5 models within the running Docker container: - -```bash -# Train a model on your data -python train.py - -# Validate the trained model for Precision, Recall, and mAP -python val.py --weights yolov5s.pt - -# Run inference using the trained model on your images or videos -python detect.py --weights yolov5s.pt --source path/to/images - -# Export the trained model to other formats for deployment -python export.py --weights yolov5s.pt --include onnx coreml tflite -``` - -

GCP running Docker

diff --git a/ultralytics-main/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md b/ultralytics-main/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md deleted file mode 100644 index fd96e84..0000000 --- a/ultralytics-main/docs/en/yolov5/environments/google_cloud_quickstart_tutorial.md +++ /dev/null @@ -1,87 +0,0 @@ ---- -comments: true -description: Discover how to deploy YOLOv5 on a GCP Deep Learning VM for seamless object detection. Ideal for ML beginners and cloud learners. Get started with our easy-to-follow tutorial! -keywords: YOLOv5, Google Cloud Platform, GCP, Deep Learning VM, ML model training, object detection, AI tutorial, cloud-based AI, machine learning setup ---- - -# Mastering YOLOv5 🚀 Deployment on Google Cloud Platform (GCP) Deep Learning Virtual Machine (VM) ⭐ - -Embarking on the journey of artificial intelligence and machine learning can be exhilarating, especially when you leverage the power and flexibility of a cloud platform. Google Cloud Platform (GCP) offers robust tools tailored for machine learning enthusiasts and professionals alike. One such tool is the Deep Learning VM that is preconfigured for data science and ML tasks. In this tutorial, we will navigate through the process of setting up YOLOv5 on a GCP Deep Learning VM. Whether you’re taking your first steps in ML or you’re a seasoned practitioner, this guide is designed to provide you with a clear pathway to implementing object detection models powered by YOLOv5. - -🆓 Plus, if you're a fresh GCP user, you’re in luck with a [$300 free credit offer](https://cloud.google.com/free/docs/gcp-free-tier#free-trial) to kickstart your projects. - -In addition to GCP, explore other accessible quickstart options for YOLOv5, like our [Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) Open In Colab for a browser-based experience, or the scalability of [Amazon AWS](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial). Furthermore, container aficionados can utilize our official Docker image at [Docker Hub](https://hub.docker.com/r/ultralytics/yolov5) Docker Pulls for an encapsulated environment. - -## Step 1: Create and Configure Your Deep Learning VM - -Let’s begin by creating a virtual machine that’s tuned for deep learning: - -1. Head over to the [GCP marketplace](https://console.cloud.google.com/marketplace/details/click-to-deploy-images/deeplearning) and select the **Deep Learning VM**. -2. Opt for a **n1-standard-8** instance; it offers a balance of 8 vCPUs and 30 GB of memory, ideally suited for our needs. -3. Next, select a GPU. This depends on your workload; even a basic one like the Tesla T4 will markedly accelerate your model training. -4. Tick the box for 'Install NVIDIA GPU driver automatically on first startup?' for hassle-free setup. -5. Allocate a 300 GB SSD Persistent Disk to ensure you don't bottleneck on I/O operations. -6. Hit 'Deploy' and let GCP do its magic in provisioning your custom Deep Learning VM. - -This VM comes loaded with a treasure trove of preinstalled tools and frameworks, including the [Anaconda](https://www.anaconda.com/) Python distribution, which conveniently bundles all the necessary dependencies for YOLOv5. - -![GCP Marketplace illustration of setting up a Deep Learning VM](https://user-images.githubusercontent.com/26833433/105811495-95863880-5f61-11eb-841d-c2f2a5aa0ffe.png) - -## Step 2: Ready the VM for YOLOv5 - -Following the environment setup, let's get YOLOv5 up and running: - -```bash -# Clone the YOLOv5 repository -git clone https://github.com/ultralytics/yolov5 - -# Change the directory to the cloned repository -cd yolov5 - -# Install the necessary Python packages from requirements.txt -pip install -r requirements.txt -``` - -This setup process ensures you're working with a Python environment version 3.8.0 or newer and PyTorch 1.8 or above. Our scripts smoothly download [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) rending from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases), making it hassle-free to start model training. - -## Step 3: Train and Deploy Your YOLOv5 Models 🌐 - -With the setup complete, you're ready to delve into training and inference with YOLOv5 on your GCP VM: - -```bash -# Train a model on your data -python train.py - -# Validate the trained model for Precision, Recall, and mAP -python val.py --weights yolov5s.pt - -# Run inference using the trained model on your images or videos -python detect.py --weights yolov5s.pt --source path/to/images - -# Export the trained model to other formats for deployment -python export.py --weights yolov5s.pt --include onnx coreml tflite -``` - -With just a few commands, YOLOv5 allows you to train custom object detection models tailored to your specific needs or utilize pre-trained weights for quick results on a variety of tasks. - -![Terminal command image illustrating model training on a GCP Deep Learning VM](https://user-images.githubusercontent.com/26833433/142223900-275e5c9e-e2b5-43f7-a21c-35c4ca7de87c.png) - -## Allocate Swap Space (optional) - -For those dealing with hefty datasets, consider amplifying your GCP instance with an additional 64GB of swap memory: - -```bash -sudo fallocate -l 64G /swapfile -sudo chmod 600 /swapfile -sudo mkswap /swapfile -sudo swapon /swapfile -free -h # confirm the memory increment -``` - -### Concluding Thoughts - -Congratulations! You are now empowered to harness the capabilities of YOLOv5 with the computational prowess of Google Cloud Platform. This combination provides scalability, efficiency, and versatility for your object detection tasks. Whether for personal projects, academic research, or industrial applications, you have taken a pivotal step into the world of AI and machine learning on the cloud. - -Do remember to document your journey, share insights with the Ultralytics community, and leverage the collaborative arenas such as [GitHub discussions](https://github.com/ultralytics/yolov5/discussions) to grow further. Now, go forth and innovate with YOLOv5 and GCP! 🌟 - -Want to keep improving your ML skills and knowledge? Dive into our [documentation and tutorials](https://docs.ultralytics.com/) for more resources. Let your AI adventure continue! diff --git a/ultralytics-main/docs/en/yolov5/index.md b/ultralytics-main/docs/en/yolov5/index.md deleted file mode 100644 index 826df5b..0000000 --- a/ultralytics-main/docs/en/yolov5/index.md +++ /dev/null @@ -1,93 +0,0 @@ ---- -comments: true -description: Deep dive into Ultralytics' YOLOv5. Learn about object detection model - YOLOv5, how to train it on custom data, multi-GPU training and more. -keywords: YOLOv5, object detection, computer vision, CUDA, PyTorch tutorial, multi-GPU training, custom dataset, model export, deployment, CI tests ---- - -# Comprehensive Guide to Ultralytics YOLOv5 - -
-

- - Ultralytics YOLOv5 v7.0 banner -

- -YOLOv5 CI -YOLOv5 Citation -Docker Pulls -
-Run on Gradient -Open In Colab -Open In Kaggle -
-
- -Welcome to the Ultralytics' YOLOv5🚀 Documentation! YOLOv5, the fifth iteration of the revolutionary "You Only Look Once" object detection model, is designed to deliver high-speed, high-accuracy results in real-time. - -

- -Built on PyTorch, this powerful deep learning framework has garnered immense popularity for its versatility, ease of use, and high performance. Our documentation guides you through the installation process, explains the architectural nuances of the model, showcases various use-cases, and provides a series of detailed tutorials. These resources will help you harness the full potential of YOLOv5 for your computer vision projects. Let's get started! - -
- -## Explore and Learn - -Here's a compilation of comprehensive tutorials that will guide you through different aspects of YOLOv5. - -- [Train Custom Data](tutorials/train_custom_data.md) 🚀 RECOMMENDED: Learn how to train the YOLOv5 model on your custom dataset. -- [Tips for Best Training Results](tutorials/tips_for_best_training_results.md) ☘️: Uncover practical tips to optimize your model training process. -- [Multi-GPU Training](tutorials/multi_gpu_training.md): Understand how to leverage multiple GPUs to expedite your training. -- [PyTorch Hub](tutorials/pytorch_hub_model_loading.md) 🌟 NEW: Learn to load pre-trained models via PyTorch Hub. -- [TFLite, ONNX, CoreML, TensorRT Export](tutorials/model_export.md) 🚀: Understand how to export your model to different formats. -- [NVIDIA Jetson platform Deployment](tutorials/running_on_jetson_nano.md) 🌟 NEW: Learn how to deploy your YOLOv5 model on NVIDIA Jetson platform. -- [Test-Time Augmentation (TTA)](tutorials/test_time_augmentation.md): Explore how to use TTA to improve your model's prediction accuracy. -- [Model Ensembling](tutorials/model_ensembling.md): Learn the strategy of combining multiple models for improved performance. -- [Model Pruning/Sparsity](tutorials/model_pruning_and_sparsity.md): Understand pruning and sparsity concepts, and how to create a more efficient model. -- [Hyperparameter Evolution](tutorials/hyperparameter_evolution.md): Discover the process of automated hyperparameter tuning for better model performance. -- [Transfer Learning with Frozen Layers](tutorials/transfer_learning_with_frozen_layers.md): Learn how to implement transfer learning by freezing layers in YOLOv5. -- [Architecture Summary](tutorials/architecture_description.md) 🌟 Delve into the structural details of the YOLOv5 model. -- [Roboflow for Datasets](tutorials/roboflow_datasets_integration.md): Understand how to utilize Roboflow for dataset management, labeling, and active learning. -- [ClearML Logging](tutorials/clearml_logging_integration.md) 🌟 Learn how to integrate ClearML for efficient logging during your model training. -- [YOLOv5 with Neural Magic](tutorials/neural_magic_pruning_quantization.md) Discover how to use Neural Magic's Deepsparse to prune and quantize your YOLOv5 model. -- [Comet Logging](tutorials/comet_logging_integration.md) 🌟 NEW: Explore how to utilize Comet for improved model training logging. - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. - -
-
- Ultralytics GitHub - space - Ultralytics LinkedIn - space - Ultralytics Twitter - space - Ultralytics YouTube - space - Ultralytics TikTok - space - Ultralytics Instagram - space - Ultralytics Discord -
- -## Connect and Contribute - -Your journey with YOLOv5 doesn't have to be a solitary one. Join our vibrant community on [GitHub](https://github.com/ultralytics/yolov5), connect with professionals on [LinkedIn](https://www.linkedin.com/company/ultralytics/), share your results on [Twitter](https://twitter.com/ultralytics), and find educational resources on [YouTube](https://youtube.com/ultralytics). Follow us on [TikTok](https://www.tiktok.com/@ultralytics) and [Instagram](https://www.instagram.com/ultralytics/) for more engaging content. - -Interested in contributing? We welcome contributions of all forms; from code improvements and bug reports to documentation updates. Check out our [contributing guidelines](https://github.com/ultralytics/yolov5/blob/master/CONTRIBUTING.md) for more information. - -We're excited to see the innovative ways you'll use YOLOv5. Dive in, experiment, and revolutionize your computer vision projects! 🚀 diff --git a/ultralytics-main/docs/en/yolov5/quickstart_tutorial.md b/ultralytics-main/docs/en/yolov5/quickstart_tutorial.md deleted file mode 100644 index e5a379c..0000000 --- a/ultralytics-main/docs/en/yolov5/quickstart_tutorial.md +++ /dev/null @@ -1,72 +0,0 @@ ---- -comments: true -description: Dive into YOLOv5 for object detection with our easy-to-follow guide on setup, model training, and image inference using PyTorch. Get started now! -keywords: YOLOv5 Tutorial, Object Detection Guide, PyTorch Model Training, Inference with YOLOv5, Ultralytics YOLOv5 Setup ---- - -# YOLOv5 Quickstart 🚀 - -Embark on your journey into the dynamic realm of real-time object detection with YOLOv5! This guide is crafted to serve as a comprehensive starting point for AI enthusiasts and professionals aiming to master YOLOv5. From initial setup to advanced training techniques, we've got you covered. By the end of this guide, you'll have the knowledge to implement YOLOv5 into your projects confidently. Let's ignite the engines and soar into YOLOv5! - -## Install - -Prepare for launch by cloning the repository and establishing the environment. This ensures that all the necessary [requirements](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) are installed. Check that you have [**Python>=3.8.0**](https://www.python.org/) and [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/) ready for takeoff. - -```bash -git clone https://github.com/ultralytics/yolov5 # clone repository -cd yolov5 -pip install -r requirements.txt # install dependencies -``` - -## Inference with PyTorch Hub - -Experience the simplicity of YOLOv5 [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) inference, where [models](https://github.com/ultralytics/yolov5/tree/master/models) are seamlessly downloaded from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```python -import torch - -# Model loading -model = torch.hub.load("ultralytics/yolov5", "yolov5s") # Can be 'yolov5n' - 'yolov5x6', or 'custom' - -# Inference on images -img = "https://ultralytics.com/images/zidane.jpg" # Can be a file, Path, PIL, OpenCV, numpy, or list of images - -# Run inference -results = model(img) - -# Display results -results.print() # Other options: .show(), .save(), .crop(), .pandas(), etc. -``` - -## Inference with detect.py - -Harness `detect.py` for versatile inference on various sources. It automatically fetches [models](https://github.com/ultralytics/yolov5/tree/master/models) from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases) and saves results with ease. - -```bash -python detect.py --weights yolov5s.pt --source 0 # webcam - img.jpg # image - vid.mp4 # video - screen # screenshot - path/ # directory - list.txt # list of images - list.streams # list of streams - 'path/*.jpg' # glob - 'https://youtu.be/LNwODJXcvt4' # YouTube - 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream -``` - -## Training - -Replicate the YOLOv5 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) benchmarks with the instructions below. The necessary [models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) are pulled directly from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training YOLOv5n/s/m/l/x on a V100 GPU should typically take 1/2/4/6/8 days respectively (note that [Multi-GPU](https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training) setups work faster). Maximize performance by using the highest possible `--batch-size` or use `--batch-size -1` for the YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092) feature. The following batch sizes are ideal for V100-16GB GPUs. - -```bash -python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml --batch-size 128 - yolov5s 64 - yolov5m 40 - yolov5l 24 - yolov5x 16 -``` - -YOLO training curves - -To conclude, YOLOv5 is not only a state-of-the-art tool for object detection but also a testament to the power of machine learning in transforming the way we interact with the world through visual understanding. As you progress through this guide and begin applying YOLOv5 to your projects, remember that you are at the forefront of a technological revolution, capable of achieving remarkable feats. Should you need further insights or support from fellow visionaries, you're invited to our [GitHub repository](https://github.com/ultralytics/yolov5) home to a thriving community of developers and researchers. Keep exploring, keep innovating, and enjoy the marvels of YOLOv5. Happy detecting! 🌠🔍 diff --git a/ultralytics-main/docs/en/yolov5/tutorials/architecture_description.md b/ultralytics-main/docs/en/yolov5/tutorials/architecture_description.md deleted file mode 100644 index 59a6e40..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/architecture_description.md +++ /dev/null @@ -1,224 +0,0 @@ ---- -comments: true -description: Explore the architecture of YOLOv5, an object detection algorithm by Ultralytics. Understand the model structure, data augmentation methods, training strategies, and loss computation techniques. -keywords: Ultralytics, YOLOv5, Object Detection, Architecture, Model Structure, Data Augmentation, Training Strategies, Loss Computation ---- - -# Ultralytics YOLOv5 Architecture - -YOLOv5 (v6.0/6.1) is a powerful object detection algorithm developed by Ultralytics. This article dives deep into the YOLOv5 architecture, data augmentation strategies, training methodologies, and loss computation techniques. This comprehensive understanding will help improve your practical application of object detection in various fields, including surveillance, autonomous vehicles, and image recognition. - -## 1. Model Structure - -YOLOv5's architecture consists of three main parts: - -- **Backbone**: This is the main body of the network. For YOLOv5, the backbone is designed using the `New CSP-Darknet53` structure, a modification of the Darknet architecture used in previous versions. -- **Neck**: This part connects the backbone and the head. In YOLOv5, `SPPF` and `New CSP-PAN` structures are utilized. -- **Head**: This part is responsible for generating the final output. YOLOv5 uses the `YOLOv3 Head` for this purpose. - -The structure of the model is depicted in the image below. The model structure details can be found in `yolov5l.yaml`. - -![yolov5](https://user-images.githubusercontent.com/31005897/172404576-c260dcf9-76bb-4bc8-b6a9-f2d987792583.png) - -YOLOv5 introduces some minor changes compared to its predecessors: - -1. The `Focus` structure, found in earlier versions, is replaced with a `6x6 Conv2d` structure. This change boosts efficiency [#4825](https://github.com/ultralytics/yolov5/issues/4825). -2. The `SPP` structure is replaced with `SPPF`. This alteration more than doubles the speed of processing. - -To test the speed of `SPP` and `SPPF`, the following code can be used: - -
-SPP vs SPPF speed profiling example (click to open) - -```python -import time -import torch -import torch.nn as nn - - -class SPP(nn.Module): - def __init__(self): - super().__init__() - self.maxpool1 = nn.MaxPool2d(5, 1, padding=2) - self.maxpool2 = nn.MaxPool2d(9, 1, padding=4) - self.maxpool3 = nn.MaxPool2d(13, 1, padding=6) - - def forward(self, x): - o1 = self.maxpool1(x) - o2 = self.maxpool2(x) - o3 = self.maxpool3(x) - return torch.cat([x, o1, o2, o3], dim=1) - - -class SPPF(nn.Module): - def __init__(self): - super().__init__() - self.maxpool = nn.MaxPool2d(5, 1, padding=2) - - def forward(self, x): - o1 = self.maxpool(x) - o2 = self.maxpool(o1) - o3 = self.maxpool(o2) - return torch.cat([x, o1, o2, o3], dim=1) - - -def main(): - input_tensor = torch.rand(8, 32, 16, 16) - spp = SPP() - sppf = SPPF() - output1 = spp(input_tensor) - output2 = sppf(input_tensor) - - print(torch.equal(output1, output2)) - - t_start = time.time() - for _ in range(100): - spp(input_tensor) - print(f"SPP time: {time.time() - t_start}") - - t_start = time.time() - for _ in range(100): - sppf(input_tensor) - print(f"SPPF time: {time.time() - t_start}") - - -if __name__ == '__main__': - main() -``` - -result: - -``` -True -SPP time: 0.5373051166534424 -SPPF time: 0.20780706405639648 -``` - -
- -## 2. Data Augmentation Techniques - -YOLOv5 employs various data augmentation techniques to improve the model's ability to generalize and reduce overfitting. These techniques include: - -- **Mosaic Augmentation**: An image processing technique that combines four training images into one in ways that encourage object detection models to better handle various object scales and translations. - - ![mosaic](https://user-images.githubusercontent.com/31005897/159109235-c7aad8f2-1d4f-41f9-8d5f-b2fde6f2885e.png) - -- **Copy-Paste Augmentation**: An innovative data augmentation method that copies random patches from an image and pastes them onto another randomly chosen image, effectively generating a new training sample. - - ![copy-paste](https://user-images.githubusercontent.com/31005897/159116277-91b45033-6bec-4f82-afc4-41138866628e.png) - -- **Random Affine Transformations**: This includes random rotation, scaling, translation, and shearing of the images. - - ![random-affine](https://user-images.githubusercontent.com/31005897/159109326-45cd5acb-14fa-43e7-9235-0f21b0021c7d.png) - -- **MixUp Augmentation**: A method that creates composite images by taking a linear combination of two images and their associated labels. - - ![mixup](https://user-images.githubusercontent.com/31005897/159109361-3b24333b-f481-478b-ae00-df7838f0b5cd.png) - -- **Albumentations**: A powerful library for image augmenting that supports a wide variety of augmentation techniques. - -- **HSV Augmentation**: Random changes to the Hue, Saturation, and Value of the images. - - ![hsv](https://user-images.githubusercontent.com/31005897/159109407-83d100ba-1aba-4f4b-aa03-4f048f815981.png) - -- **Random Horizontal Flip**: An augmentation method that randomly flips images horizontally. - - ![horizontal-flip](https://user-images.githubusercontent.com/31005897/159109429-0d44619a-a76a-49eb-bfc0-6709860c043e.png) - -## 3. Training Strategies - -YOLOv5 applies several sophisticated training strategies to enhance the model's performance. They include: - -- **Multiscale Training**: The input images are randomly rescaled within a range of 0.5 to 1.5 times their original size during the training process. -- **AutoAnchor**: This strategy optimizes the prior anchor boxes to match the statistical characteristics of the ground truth boxes in your custom data. -- **Warmup and Cosine LR Scheduler**: A method to adjust the learning rate to enhance model performance. -- **Exponential Moving Average (EMA)**: A strategy that uses the average of parameters over past steps to stabilize the training process and reduce generalization error. -- **Mixed Precision Training**: A method to perform operations in half-precision format, reducing memory usage and enhancing computational speed. -- **Hyperparameter Evolution**: A strategy to automatically tune hyperparameters to achieve optimal performance. - -## 4. Additional Features - -### 4.1 Compute Losses - -The loss in YOLOv5 is computed as a combination of three individual loss components: - -- **Classes Loss (BCE Loss)**: Binary Cross-Entropy loss, measures the error for the classification task. -- **Objectness Loss (BCE Loss)**: Another Binary Cross-Entropy loss, calculates the error in detecting whether an object is present in a particular grid cell or not. -- **Location Loss (CIoU Loss)**: Complete IoU loss, measures the error in localizing the object within the grid cell. - -The overall loss function is depicted by: - -![loss](https://latex.codecogs.com/svg.image?Loss=\lambda_1L_{cls}+\lambda_2L_{obj}+\lambda_3L_{loc}) - -### 4.2 Balance Losses - -The objectness losses of the three prediction layers (`P3`, `P4`, `P5`) are weighted differently. The balance weights are `[4.0, 1.0, 0.4]` respectively. This approach ensures that the predictions at different scales contribute appropriately to the total loss. - -![obj_loss](https://latex.codecogs.com/svg.image?L_{obj}=4.0\cdot&space;L_{obj}^{small}+1.0\cdot&space;L_{obj}^{medium}+0.4\cdot&space;L_{obj}^{large}) - -### 4.3 Eliminate Grid Sensitivity - -The YOLOv5 architecture makes some important changes to the box prediction strategy compared to earlier versions of YOLO. In YOLOv2 and YOLOv3, the box coordinates were directly predicted using the activation of the last layer. - -![b_x]() -![b_y]() -![b_w](https://latex.codecogs.com/svg.image?b_w=p_w\cdot&space;e^{t_w}) -![b_h](https://latex.codecogs.com/svg.image?b_h=p_h\cdot&space;e^{t_h}) - -YOLOv5 grid computation - -However, in YOLOv5, the formula for predicting the box coordinates has been updated to reduce grid sensitivity and prevent the model from predicting unbounded box dimensions. - -The revised formulas for calculating the predicted bounding box are as follows: - -![bx]() -![by]() -![bw]() -![bh]() - -Compare the center point offset before and after scaling. The center point offset range is adjusted from (0, 1) to (-0.5, 1.5). Therefore, offset can easily get 0 or 1. - -YOLOv5 grid scaling - -Compare the height and width scaling ratio(relative to anchor) before and after adjustment. The original yolo/darknet box equations have a serious flaw. Width and Height are completely unbounded as they are simply out=exp(in), which is dangerous, as it can lead to runaway gradients, instabilities, NaN losses and ultimately a complete loss of training. [refer this issue](https://github.com/ultralytics/yolov5/issues/471#issuecomment-662009779) - -YOLOv5 unbounded scaling - -### 4.4 Build Targets - -The build target process in YOLOv5 is critical for training efficiency and model accuracy. It involves assigning ground truth boxes to the appropriate grid cells in the output map and matching them with the appropriate anchor boxes. - -This process follows these steps: - -- Calculate the ratio of the ground truth box dimensions and the dimensions of each anchor template. - -![rw](https://latex.codecogs.com/svg.image?r_w=w_{gt}/w_{at}) - -![rh](https://latex.codecogs.com/svg.image?r_h=h_{gt}/h_{at}) - -![rwmax]() - -![rhmax]() - -![rmax]() - -![match](https://latex.codecogs.com/svg.image?r^{max}<{\rm&space;anchor_t}) - -YOLOv5 IoU computation - -- If the calculated ratio is within the threshold, match the ground truth box with the corresponding anchor. - -YOLOv5 grid overlap - -- Assign the matched anchor to the appropriate cells, keeping in mind that due to the revised center point offset, a ground truth box can be assigned to more than one anchor. Because the center point offset range is adjusted from (0, 1) to (-0.5, 1.5). GT Box can be assigned to more anchors. - -YOLOv5 anchor selection - -This way, the build targets process ensures that each ground truth object is properly assigned and matched during the training process, allowing YOLOv5 to learn the task of object detection more effectively. - -## Conclusion - -In conclusion, YOLOv5 represents a significant step forward in the development of real-time object detection models. By incorporating various new features, enhancements, and training strategies, it surpasses previous versions of the YOLO family in performance and efficiency. - -The primary enhancements in YOLOv5 include the use of a dynamic architecture, an extensive range of data augmentation techniques, innovative training strategies, as well as important adjustments in computing losses and the process of building targets. All these innovations significantly improve the accuracy and efficiency of object detection while retaining a high degree of speed, which is the trademark of YOLO models. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/clearml_logging_integration.md b/ultralytics-main/docs/en/yolov5/tutorials/clearml_logging_integration.md deleted file mode 100644 index 48fce1e..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/clearml_logging_integration.md +++ /dev/null @@ -1,237 +0,0 @@ ---- -comments: true -description: Learn how ClearML can enhance your YOLOv5 pipeline – track your training runs, version your data, remotely monitor your models and optimize performance. -keywords: ClearML, YOLOv5, Ultralytics, AI toolbox, training data, remote training, hyperparameter optimization, YOLOv5 model ---- - -# ClearML Integration - -Clear|MLClear|ML - -## About ClearML - -[ClearML](https://clear.ml/) is an [open-source](https://github.com/allegroai/clearml) toolbox designed to save you time ⏱️. - -🔨 Track every YOLOv5 training run in the experiment manager - -🔧 Version and easily access your custom training data with the integrated ClearML Data Versioning Tool - -🔦 Remotely train and monitor your YOLOv5 training runs using ClearML Agent - -🔬 Get the very best mAP using ClearML Hyperparameter Optimization - -🔭 Turn your newly trained YOLOv5 model into an API with just a few commands using ClearML Serving - -
-And so much more. It's up to you how many of these tools you want to use, you can stick to the experiment manager, or chain them all together into an impressive pipeline! -
-
- -![ClearML scalars dashboard](https://github.com/thepycoder/clearml_screenshots/raw/main/experiment_manager_with_compare.gif) - -
-
- -## 🦾 Setting Things Up - -To keep track of your experiments and/or data, ClearML needs to communicate to a server. You have 2 options to get one: - -Either sign up for free to the [ClearML Hosted Service](https://clear.ml/) or you can set up your own server, see [here](https://clear.ml/docs/latest/docs/deploying_clearml/clearml_server). Even the server is open-source, so even if you're dealing with sensitive data, you should be good to go! - -- Install the `clearml` python package: - - ```bash - pip install clearml - ``` - -- Connect the ClearML SDK to the server by [creating credentials](https://app.clear.ml/settings/workspace-configuration) (go right top to Settings -> Workspace -> Create new credentials), then execute the command below and follow the instructions: - - ```bash - clearml-init - ``` - -That's it! You're done 😎 - -
- -## 🚀 Training YOLOv5 With ClearML - -To enable ClearML experiment tracking, simply install the ClearML pip package. - -```bash -pip install clearml>=1.2.0 -``` - -This will enable integration with the YOLOv5 training script. Every training run from now on, will be captured and stored by the ClearML experiment manager. - -If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`. PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name! - -```bash -python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache -``` - -or with custom project and task name: - -```bash -python train.py --project my_project --name my_training --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache -``` - -This will capture: - -- Source code + uncommitted changes -- Installed packages -- (Hyper)parameters -- Model files (use `--save-period n` to save a checkpoint every n epochs) -- Console output -- Scalars (mAP_0.5, mAP_0.5:0.95, precision, recall, losses, learning rates, ...) -- General info such as machine details, runtime, creation date etc. -- All produced plots such as label correlogram and confusion matrix -- Images with bounding boxes per epoch -- Mosaic per epoch -- Validation images per epoch - -That's a lot right? 🤯 Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple experiments and directly compare them! - -There even more we can do with all of this information, like hyperparameter optimization and remote execution, so keep reading if you want to see how that works! - -### 🔗 Dataset Version Management - -Versioning your data separately from your code is generally a good idea and makes it easy to acquire the latest version too. This repository supports supplying a dataset version ID, and it will make sure to get the data if it's not there yet. Next to that, this workflow also saves the used dataset ID as part of the task parameters, so you will always know for sure which data was used in which experiment! - -![ClearML Dataset Interface](https://github.com/thepycoder/clearml_screenshots/raw/main/clearml_data.gif) - -### Prepare Your Dataset - -The YOLOv5 repository supports a number of different datasets by using YAML files containing their information. By default datasets are downloaded to the `../datasets` folder in relation to the repository root folder. So if you downloaded the `coco128` dataset using the link in the YAML or with the scripts provided by yolov5, you get this folder structure: - -``` -.. -|_ yolov5 -|_ datasets - |_ coco128 - |_ images - |_ labels - |_ LICENSE - |_ README.txt -``` - -But this can be any dataset you wish. Feel free to use your own, as long as you keep to this folder structure. - -Next, ⚠️**copy the corresponding YAML file to the root of the dataset folder**⚠️. This YAML files contains the information ClearML will need to properly use the dataset. You can make this yourself too, of course, just follow the structure of the example YAMLs. - -Basically we need the following keys: `path`, `train`, `test`, `val`, `nc`, `names`. - -``` -.. -|_ yolov5 -|_ datasets - |_ coco128 - |_ images - |_ labels - |_ coco128.yaml # <---- HERE! - |_ LICENSE - |_ README.txt -``` - -### Upload Your Dataset - -To get this dataset into ClearML as a versioned dataset, go to the dataset root folder and run the following command: - -```bash -cd coco128 -clearml-data sync --project YOLOv5 --name coco128 --folder . -``` - -The command `clearml-data sync` is actually a shorthand command. You could also run these commands one after the other: - -```bash -# Optionally add --parent if you want to base -# this version on another dataset version, so no duplicate files are uploaded! -clearml-data create --name coco128 --project YOLOv5 -clearml-data add --files . -clearml-data close -``` - -### Run Training Using A ClearML Dataset - -Now that you have a ClearML dataset, you can very simply use it to train custom YOLOv5 🚀 models! - -```bash -python train.py --img 640 --batch 16 --epochs 3 --data clearml:// --weights yolov5s.pt --cache -``` - -
- -### 👀 Hyperparameter Optimization - -Now that we have our experiments and data versioned, it's time to take a look at what we can build on top! - -Using the code information, installed packages and environment details, the experiment itself is now **completely reproducible**. In fact, ClearML allows you to clone an experiment and even change its parameters. We can then just rerun it with these new parameters automatically, this is basically what HPO does! - -To **run hyperparameter optimization locally**, we've included a pre-made script for you. Just make sure a training task has been run at least once, so it is in the ClearML experiment manager, we will essentially clone it and change its hyperparameters. - -You'll need to fill in the ID of this `template task` in the script found at `utils/loggers/clearml/hpo.py` and then just run it :) You can change `task.execute_locally()` to `task.execute()` to put it in a ClearML queue and have a remote agent work on it instead. - -```bash -# To use optuna, install it first, otherwise you can change the optimizer to just be RandomSearch -pip install optuna -python utils/loggers/clearml/hpo.py -``` - -![HPO](https://github.com/thepycoder/clearml_screenshots/raw/main/hpo.png) - -## 🤯 Remote Execution (advanced) - -Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site, or you have some budget to use cloud GPUs. This is where the ClearML Agent comes into play. Check out what the agent can do here: - -- [YouTube video](https://youtu.be/MX3BrXnaULs) -- [Documentation](https://clear.ml/docs/latest/docs/clearml_agent) - -In short: every experiment tracked by the experiment manager contains enough information to reproduce it on a different machine (installed packages, uncommitted changes etc.). So a ClearML agent does just that: it listens to a queue for incoming tasks and when it finds one, it recreates the environment and runs it while still reporting scalars, plots etc. to the experiment manager. - -You can turn any machine (a cloud VM, a local GPU machine, your own laptop ... ) into a ClearML agent by simply running: - -```bash -clearml-agent daemon --queue [--docker] -``` - -### Cloning, Editing And Enqueuing - -With our agent running, we can give it some work. Remember from the HPO section that we can clone a task and edit the hyperparameters? We can do that from the interface too! - -🪄 Clone the experiment by right-clicking it - -🎯 Edit the hyperparameters to what you wish them to be - -⏳ Enqueue the task to any of the queues by right-clicking it - -![Enqueue a task from the UI](https://github.com/thepycoder/clearml_screenshots/raw/main/enqueue.gif) - -### Executing A Task Remotely - -Now you can clone a task like we explained above, or simply mark your current script by adding `task.execute_remotely()` and on execution it will be put into a queue, for the agent to start working on! - -To run the YOLOv5 training script remotely, all you have to do is add this line to the training.py script after the clearml logger has been instantiated: - -```python -# ... -# Loggers -data_dict = None -if RANK in {-1, 0}: - loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance - if loggers.clearml: - loggers.clearml.task.execute_remotely(queue="my_queue") # <------ ADD THIS LINE - # Data_dict is either None is user did not choose for ClearML dataset or is filled in by ClearML - data_dict = loggers.clearml.data_dict -# ... -``` - -When running the training script after this change, python will run the script up until that line, after which it will package the code and send it to the queue instead! - -### Autoscaling workers - -ClearML comes with autoscalers too! This tool will automatically spin up new remote machines in the cloud of your choice (AWS, GCP, Azure) and turn them into ClearML agents for you whenever there are experiments detected in the queue. Once the tasks are processed, the autoscaler will automatically shut down the remote machines, and you stop paying! - -Check out the autoscalers getting started video below. - -[![Watch the video](https://img.youtube.com/vi/j4XVMAaUt3E/0.jpg)](https://youtu.be/j4XVMAaUt3E) diff --git a/ultralytics-main/docs/en/yolov5/tutorials/comet_logging_integration.md b/ultralytics-main/docs/en/yolov5/tutorials/comet_logging_integration.md deleted file mode 100644 index ae88411..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/comet_logging_integration.md +++ /dev/null @@ -1,256 +0,0 @@ ---- -comments: true -description: Learn how to set up and use Comet to enhance your YOLOv5 model training, metrics tracking and visualization. Includes a step by step guide to integrate Comet with YOLOv5. -keywords: YOLOv5, Comet, Machine Learning, Ultralytics, Real time metrics tracking, Hyperparameters, Model checkpoints, Model predictions, YOLOv5 training, Comet Credentials ---- - -![Comet](https://cdn.comet.ml/img/notebook_logo.png) - -# YOLOv5 with Comet - -This guide will cover how to use YOLOv5 with [Comet](https://bit.ly/yolov5-readme-comet2) - -## About Comet - -Comet builds tools that help data scientists, engineers, and team leaders accelerate and optimize machine learning and deep learning models. - -Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://www.comet.com/docs/v2/guides/comet-dashboard/code-panels/about-panels/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes! - -## Getting Started - -### Install Comet - -```shell -pip install comet_ml -``` - -### Configure Comet Credentials - -There are two ways to configure Comet with YOLOv5. - -You can either set your credentials through environment variables - -**Environment Variables** - -```shell -export COMET_API_KEY= -export COMET_PROJECT_NAME= # This will default to 'yolov5' -``` - -Or create a `.comet.config` file in your working directory and set your credentials there. - -**Comet Configuration File** - -``` -[comet] -api_key= -project_name= # This will default to 'yolov5' -``` - -### Run the Training Script - -```shell -# Train YOLOv5s on COCO128 for 5 epochs -python train.py --img 640 --batch 16 --epochs 5 --data coco128.yaml --weights yolov5s.pt -``` - -That's it! Comet will automatically log your hyperparameters, command line arguments, training and validation metrics. You can visualize and analyze your runs in the Comet UI - -yolo-ui - -## Try out an Example! - -Check out an example of a [completed run here](https://www.comet.com/examples/comet-example-yolov5/a0e29e0e9b984e4a822db2a62d0cb357?experiment-tab=chart&showOutliers=true&smoothing=0&transformY=smoothing&xAxis=step&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) - -Or better yet, try it out yourself in this Colab Notebook - -[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing) - -## Log automatically - -By default, Comet will log the following items - -## Metrics - -- Box Loss, Object Loss, Classification Loss for the training and validation data -- mAP_0.5, mAP_0.5:0.95 metrics for the validation data. -- Precision and Recall for the validation data - -## Parameters - -- Model Hyperparameters -- All parameters passed through the command line options - -## Visualizations - -- Confusion Matrix of the model predictions on the validation data -- Plots for the PR and F1 curves across all classes -- Correlogram of the Class Labels - -## Configure Comet Logging - -Comet can be configured to log additional data either through command line flags passed to the training script or through environment variables. - -```shell -export COMET_MODE=online # Set whether to run Comet in 'online' or 'offline' mode. Defaults to online -export COMET_MODEL_NAME= #Set the name for the saved model. Defaults to yolov5 -export COMET_LOG_CONFUSION_MATRIX=false # Set to disable logging a Comet Confusion Matrix. Defaults to true -export COMET_MAX_IMAGE_UPLOADS= # Controls how many total image predictions to log to Comet. Defaults to 100. -export COMET_LOG_PER_CLASS_METRICS=true # Set to log evaluation metrics for each detected class at the end of training. Defaults to false -export COMET_DEFAULT_CHECKPOINT_FILENAME= # Set this if you would like to resume training from a different checkpoint. Defaults to 'last.pt' -export COMET_LOG_BATCH_LEVEL_METRICS=true # Set this if you would like to log training metrics at the batch level. Defaults to false. -export COMET_LOG_PREDICTIONS=true # Set this to false to disable logging model predictions -``` - -## Logging Checkpoints with Comet - -Logging Models to Comet is disabled by default. To enable it, pass the `save-period` argument to the training script. This will save the logged checkpoints to Comet based on the interval value provided by `save-period` - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---save-period 1 -``` - -## Logging Model Predictions - -By default, model predictions (images, ground truth labels and bounding boxes) will be logged to Comet. - -You can control the frequency of logged predictions and the associated images by passing the `bbox_interval` command line argument. Predictions can be visualized using Comet's Object Detection Custom Panel. This frequency corresponds to every Nth batch of data per epoch. In the example below, we are logging every 2nd batch of data for each epoch. - -**Note:** The YOLOv5 validation dataloader will default to a batch size of 32, so you will have to set the logging frequency accordingly. - -Here is an [example project using the Panel](https://www.comet.com/examples/comet-example-yolov5?shareable=YcwMiJaZSXfcEXpGOHDD12vA1&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---bbox_interval 2 -``` - -### Controlling the number of Prediction Images logged to Comet - -When logging predictions from YOLOv5, Comet will log the images associated with each set of predictions. By default a maximum of 100 validation images are logged. You can increase or decrease this number using the `COMET_MAX_IMAGE_UPLOADS` environment variable. - -```shell -env COMET_MAX_IMAGE_UPLOADS=200 python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---bbox_interval 1 -``` - -### Logging Class Level Metrics - -Use the `COMET_LOG_PER_CLASS_METRICS` environment variable to log mAP, precision, recall, f1 for each class. - -```shell -env COMET_LOG_PER_CLASS_METRICS=true python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt -``` - -## Uploading a Dataset to Comet Artifacts - -If you would like to store your data using [Comet Artifacts](https://www.comet.com/docs/v2/guides/data-management/using-artifacts/#learn-more?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github), you can do so using the `upload_dataset` flag. - -The dataset be organized in the way described in the [YOLOv5 documentation](train_custom_data.md). The dataset config `yaml` file must follow the same format as that of the `coco128.yaml` file. - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data coco128.yaml \ ---weights yolov5s.pt \ ---upload_dataset -``` - -You can find the uploaded dataset in the Artifacts tab in your Comet Workspace artifact-1 - -You can preview the data directly in the Comet UI. artifact-2 - -Artifacts are versioned and also support adding metadata about the dataset. Comet will automatically log the metadata from your dataset `yaml` file artifact-3 - -### Using a saved Artifact - -If you would like to use a dataset from Comet Artifacts, set the `path` variable in your dataset `yaml` file to point to the following Artifact resource URL. - -``` -# contents of artifact.yaml file -path: "comet:///:" -``` - -Then pass this file to your training script in the following way - -```shell -python train.py \ ---img 640 \ ---batch 16 \ ---epochs 5 \ ---data artifact.yaml \ ---weights yolov5s.pt -``` - -Artifacts also allow you to track the lineage of data as it flows through your Experimentation workflow. Here you can see a graph that shows you all the experiments that have used your uploaded dataset. artifact-4 - -## Resuming a Training Run - -If your training run is interrupted for any reason, e.g. disrupted internet connection, you can resume the run using the `resume` flag and the Comet Run Path. - -The Run Path has the following format `comet:////`. - -This will restore the run to its state before the interruption, which includes restoring the model from a checkpoint, restoring all hyperparameters and training arguments and downloading Comet dataset Artifacts if they were used in the original run. The resumed run will continue logging to the existing Experiment in the Comet UI - -```shell -python train.py \ ---resume "comet://" -``` - -## Hyperparameter Search with the Comet Optimizer - -YOLOv5 is also integrated with Comet's Optimizer, making is simple to visualize hyperparameter sweeps in the Comet UI. - -### Configuring an Optimizer Sweep - -To configure the Comet Optimizer, you will have to create a JSON file with the information about the sweep. An example file has been provided in `utils/loggers/comet/optimizer_config.json` - -```shell -python utils/loggers/comet/hpo.py \ - --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" -``` - -The `hpo.py` script accepts the same arguments as `train.py`. If you wish to pass additional arguments to your sweep simply add them after the script. - -```shell -python utils/loggers/comet/hpo.py \ - --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" \ - --save-period 1 \ - --bbox_interval 1 -``` - -### Running a Sweep in Parallel - -```shell -comet optimizer -j utils/loggers/comet/hpo.py \ - utils/loggers/comet/optimizer_config.json" -``` - -## Visualizing Results - -Comet provides a number of ways to visualize the results of your sweep. Take a look at a [project with a completed sweep here](https://www.comet.com/examples/comet-example-yolov5/view/PrlArHGuuhDTKC1UuBmTtOSXD/panels?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) - -hyperparameter-yolo diff --git a/ultralytics-main/docs/en/yolov5/tutorials/hyperparameter_evolution.md b/ultralytics-main/docs/en/yolov5/tutorials/hyperparameter_evolution.md deleted file mode 100644 index 13e29ca..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/hyperparameter_evolution.md +++ /dev/null @@ -1,166 +0,0 @@ ---- -comments: true -description: Learn how to optimize YOLOv5 with hyperparameter evolution using Genetic Algorithm. This guide provides steps to initialize, define, evolve and visualize hyperparameters for top performance. -keywords: Ultralytics, YOLOv5, Hyperparameter Optimization, Genetic Algorithm, Machine Learning, Deep Learning, AI, Object Detection, Image Classification, Python ---- - -📚 This guide explains **hyperparameter evolution** for YOLOv5 🚀. Hyperparameter evolution is a method of [Hyperparameter Optimization](https://en.wikipedia.org/wiki/Hyperparameter_optimization) using a [Genetic Algorithm](https://en.wikipedia.org/wiki/Genetic_algorithm) (GA) for optimization. - -Hyperparameters in ML control various aspects of training, and finding optimal values for them can be a challenge. Traditional methods like grid searches can quickly become intractable due to 1) the high dimensional search space 2) unknown correlations among the dimensions, and 3) expensive nature of evaluating the fitness at each point, making GA a suitable candidate for hyperparameter searches. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## 1. Initialize Hyperparameters - -YOLOv5 has about 30 hyperparameters used for various training settings. These are defined in `*.yaml` files in the `/data/hyps` directory. Better initial guesses will produce better final results, so it is important to initialize these values properly before evolving. If in doubt, simply use the default values, which are optimized for YOLOv5 COCO training from scratch. - -```yaml -# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license -# Hyperparameters for low-augmentation COCO training from scratch -# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear -# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials - -lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) -lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf) -momentum: 0.937 # SGD momentum/Adam beta1 -weight_decay: 0.0005 # optimizer weight decay 5e-4 -warmup_epochs: 3.0 # warmup epochs (fractions ok) -warmup_momentum: 0.8 # warmup initial momentum -warmup_bias_lr: 0.1 # warmup initial bias lr -box: 0.05 # box loss gain -cls: 0.5 # cls loss gain -cls_pw: 1.0 # cls BCELoss positive_weight -obj: 1.0 # obj loss gain (scale with pixels) -obj_pw: 1.0 # obj BCELoss positive_weight -iou_t: 0.20 # IoU training threshold -anchor_t: 4.0 # anchor-multiple threshold -# anchors: 3 # anchors per output layer (0 to ignore) -fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) -hsv_h: 0.015 # image HSV-Hue augmentation (fraction) -hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) -hsv_v: 0.4 # image HSV-Value augmentation (fraction) -degrees: 0.0 # image rotation (+/- deg) -translate: 0.1 # image translation (+/- fraction) -scale: 0.5 # image scale (+/- gain) -shear: 0.0 # image shear (+/- deg) -perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 -flipud: 0.0 # image flip up-down (probability) -fliplr: 0.5 # image flip left-right (probability) -mosaic: 1.0 # image mosaic (probability) -mixup: 0.0 # image mixup (probability) -copy_paste: 0.0 # segment copy-paste (probability) -``` - -## 2. Define Fitness - -Fitness is the value we seek to maximize. In YOLOv5 we define a default fitness function as a weighted combination of metrics: `mAP@0.5` contributes 10% of the weight and `mAP@0.5:0.95` contributes the remaining 90%, with [Precision `P` and Recall `R`](https://en.wikipedia.org/wiki/Precision_and_recall) absent. You may adjust these as you see fit or use the default fitness definition in utils/metrics.py (recommended). - -```python -def fitness(x): - # Model fitness as a weighted combination of metrics - w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] - return (x[:, :4] * w).sum(1) -``` - -## 3. Evolve - -Evolution is performed about a base scenario which we seek to improve upon. The base scenario in this example is finetuning COCO128 for 10 epochs using pretrained YOLOv5s. The base scenario training command is: - -```bash -python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache -``` - -To evolve hyperparameters **specific to this scenario**, starting from our initial values defined in **Section 1.**, and maximizing the fitness defined in **Section 2.**, append `--evolve`: - -```bash -# Single-GPU -python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache --evolve - -# Multi-GPU -for i in 0 1 2 3 4 5 6 7; do - sleep $(expr 30 \* $i) && # 30-second delay (optional) - echo 'Starting GPU '$i'...' && - nohup python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache --device $i --evolve > evolve_gpu_$i.log & -done - -# Multi-GPU bash-while (not recommended) -for i in 0 1 2 3 4 5 6 7; do - sleep $(expr 30 \* $i) && # 30-second delay (optional) - echo 'Starting GPU '$i'...' && - "$(while true; do nohup python train.py... --device $i --evolve 1 > evolve_gpu_$i.log; done)" & -done -``` - -The default evolution settings will run the base scenario 300 times, i.e. for 300 generations. You can modify generations via the `--evolve` argument, i.e. `python train.py --evolve 1000`. - -The main genetic operators are **crossover** and **mutation**. In this work mutation is used, with an 80% probability and a 0.04 variance to create new offspring based on a combination of the best parents from all previous generations. Results are logged to `runs/evolve/exp/evolve.csv`, and the highest fitness offspring is saved every generation as `runs/evolve/hyp_evolved.yaml`: - -```yaml -# YOLOv5 Hyperparameter Evolution Results -# Best generation: 287 -# Last generation: 300 -# metrics/precision, metrics/recall, metrics/mAP_0.5, metrics/mAP_0.5:0.95, val/box_loss, val/obj_loss, val/cls_loss -# 0.54634, 0.55625, 0.58201, 0.33665, 0.056451, 0.042892, 0.013441 - -lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) -lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) -momentum: 0.937 # SGD momentum/Adam beta1 -weight_decay: 0.0005 # optimizer weight decay 5e-4 -warmup_epochs: 3.0 # warmup epochs (fractions ok) -warmup_momentum: 0.8 # warmup initial momentum -warmup_bias_lr: 0.1 # warmup initial bias lr -box: 0.05 # box loss gain -cls: 0.5 # cls loss gain -cls_pw: 1.0 # cls BCELoss positive_weight -obj: 1.0 # obj loss gain (scale with pixels) -obj_pw: 1.0 # obj BCELoss positive_weight -iou_t: 0.20 # IoU training threshold -anchor_t: 4.0 # anchor-multiple threshold -# anchors: 3 # anchors per output layer (0 to ignore) -fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) -hsv_h: 0.015 # image HSV-Hue augmentation (fraction) -hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) -hsv_v: 0.4 # image HSV-Value augmentation (fraction) -degrees: 0.0 # image rotation (+/- deg) -translate: 0.1 # image translation (+/- fraction) -scale: 0.5 # image scale (+/- gain) -shear: 0.0 # image shear (+/- deg) -perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 -flipud: 0.0 # image flip up-down (probability) -fliplr: 0.5 # image flip left-right (probability) -mosaic: 1.0 # image mosaic (probability) -mixup: 0.0 # image mixup (probability) -copy_paste: 0.0 # segment copy-paste (probability) -``` - -We recommend a minimum of 300 generations of evolution for best results. Note that **evolution is generally expensive and time-consuming**, as the base scenario is trained hundreds of times, possibly requiring hundreds or thousands of GPU hours. - -## 4. Visualize - -`evolve.csv` is plotted as `evolve.png` by `utils.plots.plot_evolve()` after evolution finishes with one subplot per hyperparameter showing fitness (y-axis) vs hyperparameter values (x-axis). Yellow indicates higher concentrations. Vertical distributions indicate that a parameter has been disabled and does not mutate. This is user selectable in the `meta` dictionary in train.py, and is useful for fixing parameters and preventing them from evolving. - -![evolve](https://user-images.githubusercontent.com/26833433/89130469-f43e8e00-d4b9-11ea-9e28-f8ae3622516d.png) - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/model_ensembling.md b/ultralytics-main/docs/en/yolov5/tutorials/model_ensembling.md deleted file mode 100644 index 25fd218..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/model_ensembling.md +++ /dev/null @@ -1,147 +0,0 @@ ---- -comments: true -description: Learn how to ensemble YOLOv5 models for improved mAP and Recall! Clone the repo, install requirements, and start testing and inference. -keywords: YOLOv5, object detection, ensemble learning, mAP, Recall ---- - -📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and Recall. - -From [https://en.wikipedia.org/wiki/Ensemble_learning](https://en.wikipedia.org/wiki/Ensemble_learning): - -> Ensemble modeling is a process where multiple diverse models are created to predict an outcome, either by using many different modeling algorithms or using different training data sets. The ensemble model then aggregates the prediction of each base model and results in once final prediction for the unseen data. The motivation for using ensemble models is to reduce the generalization error of the prediction. As long as the base models are diverse and independent, the prediction error of the model decreases when the ensemble approach is used. The approach seeks the wisdom of crowds in making a prediction. Even though the ensemble model has multiple base models within the model, it acts and performs as a single model. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## Test Normally - -Before ensembling we want to establish the baseline performance of a single model. This command tests YOLOv5x on COCO val2017 at image size 640 pixels. `yolov5x.pt` is the largest and most accurate model available. Other options are `yolov5s.pt`, `yolov5m.pt` and `yolov5l.pt`, or you own checkpoint from training a custom dataset `./weights/best.pt`. For details on all available models please see our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints). - -```bash -python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half -``` - -Output: - -```shell -val: data=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Fusing layers... -Model Summary: 476 layers, 87730285 parameters, 0 gradients - -val: Scanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2846.03it/s] -val: New cache created: ../datasets/coco/val2017.cache - Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [02:30<00:00, 1.05it/s] - all 5000 36335 0.746 0.626 0.68 0.49 -Speed: 0.1ms pre-process, 22.4ms inference, 1.4ms NMS per image at shape (32, 3, 640, 640) # <--- baseline speed - -Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json... -... - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504 # <--- baseline mAP - Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688 - Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546 - Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351 - Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551 - Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.628 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681 # <--- baseline mAR - Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524 - Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735 - Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.826 -``` - -## Ensemble Test - -Multiple pretrained models may be ensembled together at test and inference time by simply appending extra models to the `--weights` argument in any existing val.py or detect.py command. This example tests an ensemble of 2 models together: - -- YOLOv5x -- YOLOv5l6 - -```bash -python val.py --weights yolov5x.pt yolov5l6.pt --data coco.yaml --img 640 --half -``` - -Output: - -```shell -val: data=./data/coco.yaml, weights=['yolov5x.pt', 'yolov5l6.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Fusing layers... -Model Summary: 476 layers, 87730285 parameters, 0 gradients # Model 1 -Fusing layers... -Model Summary: 501 layers, 77218620 parameters, 0 gradients # Model 2 -Ensemble created with ['yolov5x.pt', 'yolov5l6.pt'] # Ensemble notice - -val: Scanning '../datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:00<00:00, 49695545.02it/s] - Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [03:58<00:00, 1.52s/it] - all 5000 36335 0.747 0.637 0.692 0.502 -Speed: 0.1ms pre-process, 39.5ms inference, 2.0ms NMS per image at shape (32, 3, 640, 640) # <--- ensemble speed - -Evaluating pycocotools mAP... saving runs/val/exp3/yolov5x_predictions.json... -... - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.515 # <--- ensemble mAP - Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.699 - Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.557 - Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.356 - Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.563 - Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.668 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.387 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.638 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.689 # <--- ensemble mAR - Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.526 - Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.743 - Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.844 -``` - -## Ensemble Inference - -Append extra models to the `--weights` argument to run ensemble inference: - -```bash -python detect.py --weights yolov5x.pt yolov5l6.pt --img 640 --source data/images -``` - -Output: - -```bash -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Fusing layers... -Model Summary: 476 layers, 87730285 parameters, 0 gradients -Fusing layers... -Model Summary: 501 layers, 77218620 parameters, 0 gradients -Ensemble created with ['yolov5x.pt', 'yolov5l6.pt'] - -image 1/2 /content/yolov5/data/images/bus.jpg: 640x512 4 persons, 1 bus, 1 tie, Done. (0.063s) -image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 3 persons, 2 ties, Done. (0.056s) -Results saved to runs/detect/exp2 -Done. (0.223s) -``` - -YOLO inference result - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/model_export.md b/ultralytics-main/docs/en/yolov5/tutorials/model_export.md deleted file mode 100644 index abc5730..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/model_export.md +++ /dev/null @@ -1,247 +0,0 @@ ---- -comments: true -description: Learn how to export a trained YOLOv5 model from PyTorch to different formats including TorchScript, ONNX, OpenVINO, TensorRT, and CoreML, and how to use these models. -keywords: Ultralytics, YOLOv5, model export, PyTorch, TorchScript, ONNX, OpenVINO, TensorRT, CoreML, TensorFlow ---- - -# TFLite, ONNX, CoreML, TensorRT Export - -📚 This guide explains how to export a trained YOLOv5 🚀 model from PyTorch to ONNX and TorchScript formats. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -For [TensorRT](https://developer.nvidia.com/tensorrt) export example (requires GPU) see our Colab [notebook](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb#scrollTo=VTRwsvA9u7ln&line=2&uniqifier=1) appendix section. Open In Colab - -## Formats - -YOLOv5 inference is officially supported in 11 formats: - -💡 ProTip: Export to ONNX or OpenVINO for up to 3x CPU speedup. See [CPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6613). 💡 ProTip: Export to TensorRT for up to 5x GPU speedup. See [GPU Benchmarks](https://github.com/ultralytics/yolov5/pull/6963). - -| Format | `export.py --include` | Model | -|:---------------------------------------------------------------------------|:----------------------|:--------------------------| -| [PyTorch](https://pytorch.org/) | - | `yolov5s.pt` | -| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov5s.torchscript` | -| [ONNX](https://onnx.ai/) | `onnx` | `yolov5s.onnx` | -| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov5s_openvino_model/` | -| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov5s.engine` | -| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov5s.mlmodel` | -| [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov5s_saved_model/` | -| [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov5s.pb` | -| [TensorFlow Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov5s.tflite` | -| [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov5s_edgetpu.tflite` | -| [TensorFlow.js](https://www.tensorflow.org/js) | `tfjs` | `yolov5s_web_model/` | -| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov5s_paddle_model/` | - -## Benchmarks - -Benchmarks below run on a Colab Pro with the YOLOv5 tutorial notebook Open In Colab. To reproduce: - -```bash -python benchmarks.py --weights yolov5s.pt --imgsz 640 --device 0 -``` - -### Colab Pro V100 GPU - -``` -benchmarks: weights=/content/yolov5/yolov5s.pt, imgsz=640, batch_size=1, data=/content/yolov5/data/coco128.yaml, device=0, half=False, test=False -Checking setup... -YOLOv5 🚀 v6.1-135-g7926afc torch 1.10.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB) -Setup complete ✅ (8 CPUs, 51.0 GB RAM, 46.7/166.8 GB disk) - -Benchmarks complete (458.07s) - Format mAP@0.5:0.95 Inference time (ms) -0 PyTorch 0.4623 10.19 -1 TorchScript 0.4623 6.85 -2 ONNX 0.4623 14.63 -3 OpenVINO NaN NaN -4 TensorRT 0.4617 1.89 -5 CoreML NaN NaN -6 TensorFlow SavedModel 0.4623 21.28 -7 TensorFlow GraphDef 0.4623 21.22 -8 TensorFlow Lite NaN NaN -9 TensorFlow Edge TPU NaN NaN -10 TensorFlow.js NaN NaN -``` - -### Colab Pro CPU - -``` -benchmarks: weights=/content/yolov5/yolov5s.pt, imgsz=640, batch_size=1, data=/content/yolov5/data/coco128.yaml, device=cpu, half=False, test=False -Checking setup... -YOLOv5 🚀 v6.1-135-g7926afc torch 1.10.0+cu111 CPU -Setup complete ✅ (8 CPUs, 51.0 GB RAM, 41.5/166.8 GB disk) - -Benchmarks complete (241.20s) - Format mAP@0.5:0.95 Inference time (ms) -0 PyTorch 0.4623 127.61 -1 TorchScript 0.4623 131.23 -2 ONNX 0.4623 69.34 -3 OpenVINO 0.4623 66.52 -4 TensorRT NaN NaN -5 CoreML NaN NaN -6 TensorFlow SavedModel 0.4623 123.79 -7 TensorFlow GraphDef 0.4623 121.57 -8 TensorFlow Lite 0.4623 316.61 -9 TensorFlow Edge TPU NaN NaN -10 TensorFlow.js NaN NaN -``` - -## Export a Trained YOLOv5 Model - -This command exports a pretrained YOLOv5s model to TorchScript and ONNX formats. `yolov5s.pt` is the 'small' model, the second-smallest model available. Other options are `yolov5n.pt`, `yolov5m.pt`, `yolov5l.pt` and `yolov5x.pt`, along with their P6 counterparts i.e. `yolov5s6.pt` or you own custom training checkpoint i.e. `runs/exp/weights/best.pt`. For details on all available models please see our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints). - -```bash -python export.py --weights yolov5s.pt --include torchscript onnx -``` - -💡 ProTip: Add `--half` to export models at FP16 half precision for smaller file sizes - -Output: - -```bash -export: data=data/coco128.yaml, weights=['yolov5s.pt'], imgsz=[640, 640], batch_size=1, device=cpu, half=False, inplace=False, train=False, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=12, verbose=False, workspace=4, nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, conf_thres=0.25, include=['torchscript', 'onnx'] -YOLOv5 🚀 v6.2-104-ge3e5122 Python-3.8.0 torch-1.12.1+cu113 CPU - -Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt to yolov5s.pt... -100% 14.1M/14.1M [00:00<00:00, 274MB/s] - -Fusing layers... -YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients - -PyTorch: starting from yolov5s.pt with output shape (1, 25200, 85) (14.1 MB) - -TorchScript: starting export with torch 1.12.1+cu113... -TorchScript: export success ✅ 1.7s, saved as yolov5s.torchscript (28.1 MB) - -ONNX: starting export with onnx 1.12.0... -ONNX: export success ✅ 2.3s, saved as yolov5s.onnx (28.0 MB) - -Export complete (5.5s) -Results saved to /content/yolov5 -Detect: python detect.py --weights yolov5s.onnx -Validate: python val.py --weights yolov5s.onnx -PyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.onnx') -Visualize: https://netron.app/ -``` - -The 3 exported models will be saved alongside the original PyTorch model: - -

YOLO export locations

- -[Netron Viewer](https://github.com/lutzroeder/netron) is recommended for visualizing exported models: - -

YOLO model visualization

- -## Exported Model Usage Examples - -`detect.py` runs inference on exported models: - -```bash -python detect.py --weights yolov5s.pt # PyTorch - yolov5s.torchscript # TorchScript - yolov5s.onnx # ONNX Runtime or OpenCV DNN with dnn=True - yolov5s_openvino_model # OpenVINO - yolov5s.engine # TensorRT - yolov5s.mlmodel # CoreML (macOS only) - yolov5s_saved_model # TensorFlow SavedModel - yolov5s.pb # TensorFlow GraphDef - yolov5s.tflite # TensorFlow Lite - yolov5s_edgetpu.tflite # TensorFlow Edge TPU - yolov5s_paddle_model # PaddlePaddle -``` - -`val.py` runs validation on exported models: - -```bash -python val.py --weights yolov5s.pt # PyTorch - yolov5s.torchscript # TorchScript - yolov5s.onnx # ONNX Runtime or OpenCV DNN with dnn=True - yolov5s_openvino_model # OpenVINO - yolov5s.engine # TensorRT - yolov5s.mlmodel # CoreML (macOS Only) - yolov5s_saved_model # TensorFlow SavedModel - yolov5s.pb # TensorFlow GraphDef - yolov5s.tflite # TensorFlow Lite - yolov5s_edgetpu.tflite # TensorFlow Edge TPU - yolov5s_paddle_model # PaddlePaddle -``` - -Use PyTorch Hub with exported YOLOv5 models: - -```python -import torch - -# Model -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.pt') -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.torchscript ') # TorchScript -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.onnx') # ONNX Runtime -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s_openvino_model') # OpenVINO -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.engine') # TensorRT -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.mlmodel') # CoreML (macOS Only) -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s_saved_model') # TensorFlow SavedModel -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.pb') # TensorFlow GraphDef -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.tflite') # TensorFlow Lite -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s_edgetpu.tflite') # TensorFlow Edge TPU -model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s_paddle_model') # PaddlePaddle - -# Images -img = 'https://ultralytics.com/images/zidane.jpg' # or file, Path, PIL, OpenCV, numpy, list - -# Inference -results = model(img) - -# Results -results.print() # or .show(), .save(), .crop(), .pandas(), etc. -``` - -## OpenCV DNN inference - -OpenCV inference with ONNX models: - -```bash -python export.py --weights yolov5s.pt --include onnx - -python detect.py --weights yolov5s.onnx --dnn # detect -python val.py --weights yolov5s.onnx --dnn # validate -``` - -## C++ Inference - -YOLOv5 OpenCV DNN C++ inference on exported ONNX model examples: - -- [https://github.com/Hexmagic/ONNX-yolov5/blob/master/src/test.cpp](https://github.com/Hexmagic/ONNX-yolov5/blob/master/src/test.cpp) -- [https://github.com/doleron/yolov5-opencv-cpp-python](https://github.com/doleron/yolov5-opencv-cpp-python) - -YOLOv5 OpenVINO C++ inference examples: - -- [https://github.com/dacquaviva/yolov5-openvino-cpp-python](https://github.com/dacquaviva/yolov5-openvino-cpp-python) -- [https://github.com/UNeedCryDear/yolov5-seg-opencv-dnn-cpp](https://github.com/UNeedCryDear/yolov5-seg-opencv-dnn-cpp) - -## TensorFlow.js Web Browser Inference - -- [https://aukerul-shuvo.github.io/YOLOv5_TensorFlow-JS/](https://aukerul-shuvo.github.io/YOLOv5_TensorFlow-JS/) - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md b/ultralytics-main/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md deleted file mode 100644 index fddd1c6..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md +++ /dev/null @@ -1,110 +0,0 @@ ---- -comments: true -description: Improve YOLOv5 model efficiency by pruning with Ultralytics. Understand the process, conduct tests and view the impact on accuracy and sparsity. Test-maintained API environments. -keywords: YOLOv5, YOLO, Ultralytics, model pruning, PyTorch, machine learning, deep learning, computer vision, object detection ---- - -📚 This guide explains how to apply **pruning** to YOLOv5 🚀 models. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## Test Normally - -Before pruning we want to establish a baseline performance to compare to. This command tests YOLOv5x on COCO val2017 at image size 640 pixels. `yolov5x.pt` is the largest and most accurate model available. Other options are `yolov5s.pt`, `yolov5m.pt` and `yolov5l.pt`, or you own checkpoint from training a custom dataset `./weights/best.pt`. For details on all available models please see our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints). - -```bash -python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half -``` - -Output: - -```shell -val: data=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True, dnn=False -YOLOv5 🚀 v6.0-224-g4c40933 torch 1.10.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB) - -Fusing layers... -Model Summary: 444 layers, 86705005 parameters, 0 gradients -val: Scanning '/content/datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:00 - -30% pruned output: - -```bash -val: data=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True, dnn=False -YOLOv5 🚀 v6.0-224-g4c40933 torch 1.10.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB) - -Fusing layers... -Model Summary: 444 layers, 86705005 parameters, 0 gradients -Pruning model... 0.3 global sparsity -val: Scanning '/content/datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:00Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/multi_gpu_training.md b/ultralytics-main/docs/en/yolov5/tutorials/multi_gpu_training.md deleted file mode 100644 index 35c17fd..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/multi_gpu_training.md +++ /dev/null @@ -1,190 +0,0 @@ ---- -comments: true -description: Learn how to train datasets on single or multiple GPUs using YOLOv5. Includes setup, training modes and result profiling for efficient leveraging of multiple GPUs. -keywords: YOLOv5, multi-GPU Training, YOLOv5 training, deep learning, machine learning, object detection, Ultralytics ---- - -📚 This guide explains how to properly use **multiple** GPUs to train a dataset with YOLOv5 🚀 on single or multiple machine(s). - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -💡 ProTip! **Docker Image** is recommended for all Multi-GPU trainings. See [Docker Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/docker_image_quickstart_tutorial/) Docker Pulls - -💡 ProTip! `torch.distributed.run` replaces `torch.distributed.launch` in **PyTorch>=1.9**. See [docs](https://pytorch.org/docs/stable/distributed.html) for details. - -## Training - -Select a pretrained model to start training from. Here we select [YOLOv5s](https://github.com/ultralytics/yolov5/blob/master/models/yolov5s.yaml), the smallest and fastest model available. See our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints) for a full comparison of all models. We will train this model with Multi-GPU on the [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) dataset. - -

YOLOv5 Models

- -### Single GPU - -```bash -python train.py --batch 64 --data coco.yaml --weights yolov5s.pt --device 0 -``` - -### Multi-GPU [DataParallel](https://pytorch.org/docs/stable/nn.html#torch.nn.DataParallel) Mode (⚠️ not recommended) - -You can increase the `device` to use Multiple GPUs in DataParallel mode. - -```bash -python train.py --batch 64 --data coco.yaml --weights yolov5s.pt --device 0,1 -``` - -This method is slow and barely speeds up training compared to using just 1 GPU. - -### Multi-GPU [DistributedDataParallel](https://pytorch.org/docs/stable/nn.html#torch.nn.parallel.DistributedDataParallel) Mode (✅ recommended) - -You will have to pass `python -m torch.distributed.run --nproc_per_node`, followed by the usual arguments. - -```bash -python -m torch.distributed.run --nproc_per_node 2 train.py --batch 64 --data coco.yaml --weights yolov5s.pt --device 0,1 -``` - -`--nproc_per_node` specifies how many GPUs you would like to use. In the example above, it is 2. -`--batch ` is the total batch-size. It will be divided evenly to each GPU. In the example above, it is 64/2=32 per GPU. - -The code above will use GPUs `0... (N-1)`. - -
- Use specific GPUs (click to expand) - -You can do so by simply passing `--device` followed by your specific GPUs. For example, in the code below, we will use GPUs `2,3`. - -```bash -python -m torch.distributed.run --nproc_per_node 2 train.py --batch 64 --data coco.yaml --cfg yolov5s.yaml --weights '' --device 2,3 -``` - -
- -
- Use SyncBatchNorm (click to expand) - -[SyncBatchNorm](https://pytorch.org/docs/master/generated/torch.nn.SyncBatchNorm.html) could increase accuracy for multiple gpu training, however, it will slow down training by a significant factor. It is **only** available for Multiple GPU DistributedDataParallel training. - -It is best used when the batch-size on **each** GPU is small (<= 8). - -To use SyncBatchNorm, simple pass `--sync-bn` to the command like below, - -```bash -python -m torch.distributed.run --nproc_per_node 2 train.py --batch 64 --data coco.yaml --cfg yolov5s.yaml --weights '' --sync-bn -``` - -
- -
- Use Multiple machines (click to expand) - -This is **only** available for Multiple GPU DistributedDataParallel training. - -Before we continue, make sure the files on all machines are the same, dataset, codebase, etc. Afterward, make sure the machines can communicate to each other. - -You will have to choose a master machine(the machine that the others will talk to). Note down its address(`master_addr`) and choose a port(`master_port`). I will use `master_addr = 192.168.1.1` and `master_port = 1234` for the example below. - -To use it, you can do as the following, - -```bash -# On master machine 0 -python -m torch.distributed.run --nproc_per_node G --nnodes N --node_rank 0 --master_addr "192.168.1.1" --master_port 1234 train.py --batch 64 --data coco.yaml --cfg yolov5s.yaml --weights '' -``` - -```bash -# On machine R -python -m torch.distributed.run --nproc_per_node G --nnodes N --node_rank R --master_addr "192.168.1.1" --master_port 1234 train.py --batch 64 --data coco.yaml --cfg yolov5s.yaml --weights '' -``` - -where `G` is number of GPU per machine, `N` is the number of machines, and `R` is the machine number from `0...(N-1)`. Let's say I have two machines with two GPUs each, it would be `G = 2` , `N = 2`, and `R = 1` for the above. - -Training will not start until all `N` machines are connected. Output will only be shown on master machine! - -
- -### Notes - -- Windows support is untested, Linux is recommended. -- `--batch ` must be a multiple of the number of GPUs. -- GPU 0 will take slightly more memory than the other GPUs as it maintains EMA and is responsible for checkpointing etc. -- If you get `RuntimeError: Address already in use`, it could be because you are running multiple trainings at a time. To fix this, simply use a different port number by adding `--master_port` like below, - -```bash -python -m torch.distributed.run --master_port 1234 --nproc_per_node 2 ... -``` - -## Results - -DDP profiling results on an [AWS EC2 P4d instance](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial/) with 8x A100 SXM4-40GB for YOLOv5l for 1 COCO epoch. - -
- Profiling code - -```bash -# prepare -t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/coco:/usr/src/coco $t -pip3 install torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html -cd .. && rm -rf app && git clone https://github.com/ultralytics/yolov5 -b master app && cd app -cp data/coco.yaml data/coco_profile.yaml - -# profile -python train.py --batch-size 16 --data coco_profile.yaml --weights yolov5l.pt --epochs 1 --device 0 -python -m torch.distributed.run --nproc_per_node 2 train.py --batch-size 32 --data coco_profile.yaml --weights yolov5l.pt --epochs 1 --device 0,1 -python -m torch.distributed.run --nproc_per_node 4 train.py --batch-size 64 --data coco_profile.yaml --weights yolov5l.pt --epochs 1 --device 0,1,2,3 -python -m torch.distributed.run --nproc_per_node 8 train.py --batch-size 128 --data coco_profile.yaml --weights yolov5l.pt --epochs 1 --device 0,1,2,3,4,5,6,7 -``` - -
- -| GPUs
A100 | batch-size | CUDA_mem
device0 (G) | COCO
train | COCO
val | -|--------------|------------|------------------------------|--------------------|------------------| -| 1x | 16 | 26GB | 20:39 | 0:55 | -| 2x | 32 | 26GB | 11:43 | 0:57 | -| 4x | 64 | 26GB | 5:57 | 0:55 | -| 8x | 128 | 26GB | 3:09 | 0:57 | - -## FAQ - -If an error occurs, please read the checklist below first! (It could save your time) - -
- Checklist (click to expand) - -
    -
  • Have you properly read this post?
    • -
  • Have you tried to re-clone the codebase? The code changes daily.
    • -
  • Have you tried to search for your error? Someone may have already encountered it in this repo or in another and have the solution.
    • -
  • Have you installed all the requirements listed on top (including the correct Python and Pytorch versions)?
    • -
  • Have you tried in other environments listed in the "Environments" section below?
    • -
  • Have you tried with another dataset like coco128 or coco2017? It will make it easier to find the root cause.
    • -
- -If you went through all the above, feel free to raise an Issue by giving as much detail as possible following the template. - -
- -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. - -## Credits - -We would like to thank @MagicFrogSJTU, who did all the heavy lifting, and @glenn-jocher for guiding us along the way. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md b/ultralytics-main/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md deleted file mode 100644 index 37c89c1..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/neural_magic_pruning_quantization.md +++ /dev/null @@ -1,264 +0,0 @@ ---- -comments: true -description: Explore how to achieve exceptional AI performance with DeepSparse's incredible inference speed. Discover how to deploy YOLOv5, and learn about model sparsification and fine-tuning with SparseML. -keywords: YOLOv5, DeepSparse, Ultralytics, Neural Magic, sparsification, inference runtime, deep learning, deployment, model fine-tuning, SparseML, AI performance, GPU-class performance ---- - - - -Welcome to software-delivered AI. - -This guide explains how to deploy YOLOv5 with Neural Magic's DeepSparse. - -DeepSparse is an inference runtime with exceptional performance on CPUs. For instance, compared to the ONNX Runtime baseline, DeepSparse offers a 5.8x speed-up for YOLOv5s, running on the same machine! - -

- YOLOv5 speed improvement -

- -For the first time, your deep learning workloads can meet the performance demands of production without the complexity and costs of hardware accelerators. Put simply, DeepSparse gives you the performance of GPUs and the simplicity of software: - -- **Flexible Deployments**: Run consistently across cloud, data center, and edge with any hardware provider from Intel to AMD to ARM -- **Infinite Scalability**: Scale vertically to 100s of cores, out with standard Kubernetes, or fully-abstracted with Serverless -- **Easy Integration**: Clean APIs for integrating your model into an application and monitoring it in production - -### How Does DeepSparse Achieve GPU-Class Performance? - -DeepSparse takes advantage of model sparsity to gain its performance speedup. - -Sparsification through pruning and quantization is a broadly studied technique, allowing order-of-magnitude reductions in the size and compute needed to execute a network, while maintaining high accuracy. DeepSparse is sparsity-aware, meaning it skips the zeroed out parameters, shrinking amount of compute in a forward pass. Since the sparse computation is now memory bound, DeepSparse executes the network depth-wise, breaking the problem into Tensor Columns, vertical stripes of computation that fit in cache. - -

- YOLO model pruning -

- -Sparse networks with compressed computation, executed depth-wise in cache, allows DeepSparse to deliver GPU-class performance on CPUs! - -### How Do I Create A Sparse Version of YOLOv5 Trained on My Data? - -Neural Magic's open-source model repository, SparseZoo, contains pre-sparsified checkpoints of each YOLOv5 model. Using SparseML, which is integrated with Ultralytics, you can fine-tune a sparse checkpoint onto your data with a single CLI command. - -[Checkout Neural Magic's YOLOv5 documentation for more details](https://docs.neuralmagic.com/computer-vision/object-detection/). - -## DeepSparse Usage - -We will walk through an example benchmarking and deploying a sparse version of YOLOv5s with DeepSparse. - -### Install DeepSparse - -Run the following to install DeepSparse. We recommend you use a virtual environment with Python. - -```bash -pip install "deepsparse[server,yolo,onnxruntime]" -``` - -### Collect an ONNX File - -DeepSparse accepts a model in the ONNX format, passed either as: - -- A SparseZoo stub which identifies an ONNX file in the SparseZoo -- A local path to an ONNX model in a filesystem - -The examples below use the standard dense and pruned-quantized YOLOv5s checkpoints, identified by the following SparseZoo stubs: - -```bash -zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -``` - -### Deploy a Model - -DeepSparse offers convenient APIs for integrating your model into an application. - -To try the deployment examples below, pull down a sample image and save it as `basilica.jpg` with the following: - -```bash -wget -O basilica.jpg https://raw.githubusercontent.com/neuralmagic/deepsparse/main/src/deepsparse/yolo/sample_images/basilica.jpg -``` - -#### Python API - -`Pipelines` wrap pre-processing and output post-processing around the runtime, providing a clean interface for adding DeepSparse to an application. The DeepSparse-Ultralytics integration includes an out-of-the-box `Pipeline` that accepts raw images and outputs the bounding boxes. - -Create a `Pipeline` and run inference: - -```python -from deepsparse import Pipeline - -# list of images in local filesystem -images = ["basilica.jpg"] - -# create Pipeline -model_stub = "zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none" -yolo_pipeline = Pipeline.create( - task="yolo", - model_path=model_stub, -) - -# run inference on images, receive bounding boxes + classes -pipeline_outputs = yolo_pipeline(images=images, iou_thres=0.6, conf_thres=0.001) -print(pipeline_outputs) -``` - -If you are running in the cloud, you may get an error that open-cv cannot find `libGL.so.1`. Running the following on Ubuntu installs it: - -``` -apt-get install libgl1 -``` - -#### HTTP Server - -DeepSparse Server runs on top of the popular FastAPI web framework and Uvicorn web server. With just a single CLI command, you can easily setup a model service endpoint with DeepSparse. The Server supports any Pipeline from DeepSparse, including object detection with YOLOv5, enabling you to send raw images to the endpoint and receive the bounding boxes. - -Spin up the Server with the pruned-quantized YOLOv5s: - -```bash -deepsparse.server \ - --task yolo \ - --model_path zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -``` - -An example request, using Python's `requests` package: - -```python -import requests, json - -# list of images for inference (local files on client side) -path = ['basilica.jpg'] -files = [('request', open(img, 'rb')) for img in path] - -# send request over HTTP to /predict/from_files endpoint -url = 'http://0.0.0.0:5543/predict/from_files' -resp = requests.post(url=url, files=files) - -# response is returned in JSON -annotations = json.loads(resp.text) # dictionary of annotation results -bounding_boxes = annotations["boxes"] -labels = annotations["labels"] -``` - -#### Annotate CLI - -You can also use the annotate command to have the engine save an annotated photo on disk. Try --source 0 to annotate your live webcam feed! - -```bash -deepsparse.object_detection.annotate --model_filepath zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none --source basilica.jpg -``` - -Running the above command will create an `annotation-results` folder and save the annotated image inside. - -

-annotated -

- -## Benchmarking Performance - -We will compare DeepSparse's throughput to ONNX Runtime's throughput on YOLOv5s, using DeepSparse's benchmarking script. - -The benchmarks were run on an AWS `c6i.8xlarge` instance (16 cores). - -### Batch 32 Performance Comparison - -#### ONNX Runtime Baseline - -At batch 32, ONNX Runtime achieves 42 images/sec with the standard dense YOLOv5s: - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -s sync -b 32 -nstreams 1 -e onnxruntime - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -> Batch Size: 32 -> Scenario: sync -> Throughput (items/sec): 41.9025 -``` - -#### DeepSparse Dense Performance - -While DeepSparse offers its best performance with optimized sparse models, it also performs well with the standard dense YOLOv5s. - -At batch 32, DeepSparse achieves 70 images/sec with the standard dense YOLOv5s, a **1.7x performance improvement over ORT**! - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -s sync -b 32 -nstreams 1 - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -> Batch Size: 32 -> Scenario: sync -> Throughput (items/sec): 69.5546 -``` - -#### DeepSparse Sparse Performance - -When sparsity is applied to the model, DeepSparse's performance gains over ONNX Runtime is even stronger. - -At batch 32, DeepSparse achieves 241 images/sec with the pruned-quantized YOLOv5s, a **5.8x performance improvement over ORT**! - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -s sync -b 32 -nstreams 1 - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -> Batch Size: 32 -> Scenario: sync -> Throughput (items/sec): 241.2452 -``` - -### Batch 1 Performance Comparison - -DeepSparse is also able to gain a speed-up over ONNX Runtime for the latency-sensitive, batch 1 scenario. - -#### ONNX Runtime Baseline - -At batch 1, ONNX Runtime achieves 48 images/sec with the standard, dense YOLOv5s. - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -s sync -b 1 -nstreams 1 -e onnxruntime - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none -> Batch Size: 1 -> Scenario: sync -> Throughput (items/sec): 48.0921 -``` - -#### DeepSparse Sparse Performance - -At batch 1, DeepSparse achieves 135 items/sec with a pruned-quantized YOLOv5s, **a 2.8x performance gain over ONNX Runtime!** - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -s sync -b 1 -nstreams 1 - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned65_quant-none -> Batch Size: 1 -> Scenario: sync -> Throughput (items/sec): 134.9468 -``` - -Since `c6i.8xlarge` instances have VNNI instructions, DeepSparse's throughput can be pushed further if weights are pruned in blocks of 4. - -At batch 1, DeepSparse achieves 180 items/sec with a 4-block pruned-quantized YOLOv5s, a **3.7x performance gain over ONNX Runtime!** - -```bash -deepsparse.benchmark zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned35_quant-none-vnni -s sync -b 1 -nstreams 1 - -> Original Model Path: zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned35_quant-none-vnni -> Batch Size: 1 -> Scenario: sync -> Throughput (items/sec): 179.7375 -``` - -## Get Started With DeepSparse - -**Research or Testing?** DeepSparse Community is free for research and testing. Get started with our [Documentation](https://docs.neuralmagic.com/). diff --git a/ultralytics-main/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md b/ultralytics-main/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md deleted file mode 100644 index 4cc828d..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md +++ /dev/null @@ -1,372 +0,0 @@ ---- -comments: true -description: Detailed guide on loading YOLOv5 from PyTorch Hub. Includes examples & tips on inference settings, multi-GPU inference, training and more. -keywords: Ultralytics, YOLOv5, PyTorch, loading YOLOv5, PyTorch Hub, inference, multi-GPU inference, training ---- - -📚 This guide explains how to load YOLOv5 🚀 from PyTorch Hub at [https://pytorch.org/hub/ultralytics_yolov5](https://pytorch.org/hub/ultralytics_yolov5). - -## Before You Start - -Install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -pip install -r https://raw.githubusercontent.com/ultralytics/yolov5/master/requirements.txt -``` - -💡 ProTip: Cloning [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5) is **not** required 😃 - -## Load YOLOv5 with PyTorch Hub - -### Simple Example - -This example loads a pretrained YOLOv5s model from PyTorch Hub as `model` and passes an image for inference. `'yolov5s'` is the lightest and fastest YOLOv5 model. For details on all available models please see the [README](https://github.com/ultralytics/yolov5#pretrained-checkpoints). - -```python -import torch - -# Model -model = torch.hub.load('ultralytics/yolov5', 'yolov5s') - -# Image -im = 'https://ultralytics.com/images/zidane.jpg' - -# Inference -results = model(im) - -results.pandas().xyxy[0] -# xmin ymin xmax ymax confidence class name -# 0 749.50 43.50 1148.0 704.5 0.874023 0 person -# 1 433.50 433.50 517.5 714.5 0.687988 27 tie -# 2 114.75 195.75 1095.0 708.0 0.624512 0 person -# 3 986.00 304.00 1028.0 420.0 0.286865 27 tie -``` - -### Detailed Example - -This example shows **batched inference** with **PIL** and **OpenCV** image sources. `results` can be **printed** to console, **saved** to `runs/hub`, **showed** to screen on supported environments, and returned as **tensors** or **pandas** dataframes. - -```python -import cv2 -import torch -from PIL import Image - -# Model -model = torch.hub.load('ultralytics/yolov5', 'yolov5s') - -# Images -for f in 'zidane.jpg', 'bus.jpg': - torch.hub.download_url_to_file('https://ultralytics.com/images/' + f, f) # download 2 images -im1 = Image.open('zidane.jpg') # PIL image -im2 = cv2.imread('bus.jpg')[..., ::-1] # OpenCV image (BGR to RGB) - -# Inference -results = model([im1, im2], size=640) # batch of images - -# Results -results.print() -results.save() # or .show() - -results.xyxy[0] # im1 predictions (tensor) -results.pandas().xyxy[0] # im1 predictions (pandas) -# xmin ymin xmax ymax confidence class name -# 0 749.50 43.50 1148.0 704.5 0.874023 0 person -# 1 433.50 433.50 517.5 714.5 0.687988 27 tie -# 2 114.75 195.75 1095.0 708.0 0.624512 0 person -# 3 986.00 304.00 1028.0 420.0 0.286865 27 tie -``` - -YOLO inference results on zidane.jpg -YOLO inference results on bus.jpg - -For all inference options see YOLOv5 `AutoShape()` forward [method](https://github.com/ultralytics/yolov5/blob/30e4c4f09297b67afedf8b2bcd851833ddc9dead/models/common.py#L243-L252). - -### Inference Settings - -YOLOv5 models contain various inference attributes such as **confidence threshold**, **IoU threshold**, etc. which can be set by: - -```python -model.conf = 0.25 # NMS confidence threshold -iou = 0.45 # NMS IoU threshold -agnostic = False # NMS class-agnostic -multi_label = False # NMS multiple labels per box -classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs -max_det = 1000 # maximum number of detections per image -amp = False # Automatic Mixed Precision (AMP) inference - -results = model(im, size=320) # custom inference size -``` - -### Device - -Models can be transferred to any device after creation: - -```python -model.cpu() # CPU -model.cuda() # GPU -model.to(device) # i.e. device=torch.device(0) -``` - -Models can also be created directly on any `device`: - -```python -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', device='cpu') # load on CPU -``` - -💡 ProTip: Input images are automatically transferred to the correct model device before inference. - -### Silence Outputs - -Models can be loaded silently with `_verbose=False`: - -```python -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', _verbose=False) # load silently -``` - -### Input Channels - -To load a pretrained YOLOv5s model with 4 input channels rather than the default 3: - -```python -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', channels=4) -``` - -In this case the model will be composed of pretrained weights **except for** the very first input layer, which is no longer the same shape as the pretrained input layer. The input layer will remain initialized by random weights. - -### Number of Classes - -To load a pretrained YOLOv5s model with 10 output classes rather than the default 80: - -```python -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', classes=10) -``` - -In this case the model will be composed of pretrained weights **except for** the output layers, which are no longer the same shape as the pretrained output layers. The output layers will remain initialized by random weights. - -### Force Reload - -If you run into problems with the above steps, setting `force_reload=True` may help by discarding the existing cache and force a fresh download of the latest YOLOv5 version from PyTorch Hub. - -```python -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True) # force reload -``` - -### Screenshot Inference - -To run inference on your desktop screen: - -```python -import torch -from PIL import ImageGrab - -# Model -model = torch.hub.load('ultralytics/yolov5', 'yolov5s') - -# Image -im = ImageGrab.grab() # take a screenshot - -# Inference -results = model(im) -``` - -### Multi-GPU Inference - -YOLOv5 models can be loaded to multiple GPUs in parallel with threaded inference: - -```python -import torch -import threading - - -def run(model, im): - results = model(im) - results.save() - - -# Models -model0 = torch.hub.load('ultralytics/yolov5', 'yolov5s', device=0) -model1 = torch.hub.load('ultralytics/yolov5', 'yolov5s', device=1) - -# Inference -threading.Thread(target=run, args=[model0, 'https://ultralytics.com/images/zidane.jpg'], daemon=True).start() -threading.Thread(target=run, args=[model1, 'https://ultralytics.com/images/bus.jpg'], daemon=True).start() -``` - -### Training - -To load a YOLOv5 model for training rather than inference, set `autoshape=False`. To load a model with randomly initialized weights (to train from scratch) use `pretrained=False`. You must provide your own training script in this case. Alternatively see our YOLOv5 [Train Custom Data Tutorial](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data) for model training. - -```python -import torch - -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False) # load pretrained -model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False, pretrained=False) # load scratch -``` - -### Base64 Results - -For use with API services. See https://github.com/ultralytics/yolov5/pull/2291 and [Flask REST API](https://github.com/ultralytics/yolov5/tree/master/utils/flask_rest_api) example for details. - -```python -results = model(im) # inference - -results.ims # array of original images (as np array) passed to model for inference -results.render() # updates results.ims with boxes and labels -for im in results.ims: - buffered = BytesIO() - im_base64 = Image.fromarray(im) - im_base64.save(buffered, format="JPEG") - print(base64.b64encode(buffered.getvalue()).decode('utf-8')) # base64 encoded image with results -``` - -### Cropped Results - -Results can be returned and saved as detection crops: - -```python -results = model(im) # inference -crops = results.crop(save=True) # cropped detections dictionary -``` - -### Pandas Results - -Results can be returned as [Pandas DataFrames](https://pandas.pydata.org/): - -```python -results = model(im) # inference -results.pandas().xyxy[0] # Pandas DataFrame -``` - -
- Pandas Output (click to expand) - -```python -print(results.pandas().xyxy[0]) -# xmin ymin xmax ymax confidence class name -# 0 749.50 43.50 1148.0 704.5 0.874023 0 person -# 1 433.50 433.50 517.5 714.5 0.687988 27 tie -# 2 114.75 195.75 1095.0 708.0 0.624512 0 person -# 3 986.00 304.00 1028.0 420.0 0.286865 27 tie -``` - -
- -### Sorted Results - -Results can be sorted by column, i.e. to sort license plate digit detection left-to-right (x-axis): - -```python -results = model(im) # inference -results.pandas().xyxy[0].sort_values('xmin') # sorted left-right -``` - -### Box-Cropped Results - -Results can be returned and saved as detection crops: - -```python -results = model(im) # inference -crops = results.crop(save=True) # cropped detections dictionary -``` - -### JSON Results - -Results can be returned in JSON format once converted to `.pandas()` dataframes using the `.to_json()` method. The JSON format can be modified using the `orient` argument. See pandas `.to_json()` [documentation](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_json.html) for details. - -```python -results = model(ims) # inference -results.pandas().xyxy[0].to_json(orient="records") # JSON img1 predictions -``` - -
- JSON Output (click to expand) - -```json -[ - { - "xmin": 749.5, - "ymin": 43.5, - "xmax": 1148.0, - "ymax": 704.5, - "confidence": 0.8740234375, - "class": 0, - "name": "person" - }, - { - "xmin": 433.5, - "ymin": 433.5, - "xmax": 517.5, - "ymax": 714.5, - "confidence": 0.6879882812, - "class": 27, - "name": "tie" - }, - { - "xmin": 115.25, - "ymin": 195.75, - "xmax": 1096.0, - "ymax": 708.0, - "confidence": 0.6254882812, - "class": 0, - "name": "person" - }, - { - "xmin": 986.0, - "ymin": 304.0, - "xmax": 1028.0, - "ymax": 420.0, - "confidence": 0.2873535156, - "class": 27, - "name": "tie" - } -] -``` - -
- -## Custom Models - -This example loads a custom 20-class [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml)-trained YOLOv5s model `'best.pt'` with PyTorch Hub. - -```python -import torch - -model = torch.hub.load('ultralytics/yolov5', 'custom', path='path/to/best.pt') # local model -model = torch.hub.load('path/to/yolov5', 'custom', path='path/to/best.pt', source='local') # local repo -``` - -## TensorRT, ONNX and OpenVINO Models - -PyTorch Hub supports inference on most YOLOv5 export formats, including custom trained models. See [TFLite, ONNX, CoreML, TensorRT Export tutorial](https://docs.ultralytics.com/yolov5/tutorials/model_export) for details on exporting models. - -💡 ProTip: **TensorRT** may be up to 2-5X faster than PyTorch on [**GPU benchmarks**](https://github.com/ultralytics/yolov5/pull/6963) -💡 ProTip: **ONNX** and **OpenVINO** may be up to 2-3X faster than PyTorch on [**CPU benchmarks**](https://github.com/ultralytics/yolov5/pull/6613) - -```python -import torch - -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.pt') # PyTorch -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.torchscript') # TorchScript -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.onnx') # ONNX -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s_openvino_model/') # OpenVINO -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.engine') # TensorRT -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.mlmodel') # CoreML (macOS-only) -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s.tflite') # TFLite -model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5s_paddle_model/') # PaddlePaddle -``` - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/roboflow_datasets_integration.md b/ultralytics-main/docs/en/yolov5/tutorials/roboflow_datasets_integration.md deleted file mode 100644 index c3a83be..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/roboflow_datasets_integration.md +++ /dev/null @@ -1,73 +0,0 @@ ---- -comments: true -description: Learn how to use Roboflow for organizing, labelling, preparing, and hosting your datasets for YOLOv5 models. Enhance your model deployments with our platform. -keywords: Ultralytics, YOLOv5, Roboflow, data organization, data labelling, data preparation, model deployment, active learning, machine learning pipeline ---- - -# Roboflow Datasets - -You can now use Roboflow to organize, label, prepare, version, and host your datasets for training YOLOv5 🚀 models. Roboflow is free to use with YOLOv5 if you make your workspace public. - -!!! Question "Licensing" - - Ultralytics offers two licensing options: - - - The [AGPL-3.0 License](https://github.com/ultralytics/ultralytics/blob/main/LICENSE), an [OSI-approved](https://opensource.org/licenses/) open-source license ideal for students and enthusiasts. - - The [Enterprise License](https://ultralytics.com/license) for businesses seeking to incorporate our AI models into their products and services. - - For more details see [Ultralytics Licensing](https://ultralytics.com/license). - -## Upload - -You can upload your data to Roboflow via [web UI](https://docs.roboflow.com/adding-data), [REST API](https://docs.roboflow.com/adding-data/upload-api), or [Python](https://docs.roboflow.com/python). - -## Labeling - -After uploading data to Roboflow, you can label your data and review previous labels. - -[![Roboflow Annotate](https://roboflow-darknet.s3.us-east-2.amazonaws.com/roboflow-annotate.gif)](https://roboflow.com/annotate) - -## Versioning - -You can make versions of your dataset with different preprocessing and offline augmentation options. YOLOv5 does online augmentations natively, so be intentional when layering Roboflow's offline augmentations on top. - -![Roboflow Preprocessing](https://roboflow-darknet.s3.us-east-2.amazonaws.com/robolfow-preprocessing.png) - -## Exporting Data - -You can download your data in YOLOv5 format to quickly begin training. - -``` -from roboflow import Roboflow -rf = Roboflow(api_key="YOUR API KEY HERE") -project = rf.workspace().project("YOUR PROJECT") -dataset = project.version("YOUR VERSION").download("yolov5") -``` - -## Custom Training - -We have released a custom training tutorial demonstrating all of the above capabilities. You can access the code here: - -[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb) - -## Active Learning - -The real world is messy and your model will invariably encounter situations your dataset didn't anticipate. Using [active learning](https://blog.roboflow.com/what-is-active-learning/) is an important strategy to iteratively improve your dataset and model. With the Roboflow and YOLOv5 integration, you can quickly make improvements on your model deployments by using a battle tested machine learning pipeline. - -

Roboflow active learning

- -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/running_on_jetson_nano.md b/ultralytics-main/docs/en/yolov5/tutorials/running_on_jetson_nano.md deleted file mode 100644 index 8db446c..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/running_on_jetson_nano.md +++ /dev/null @@ -1,319 +0,0 @@ ---- -comments: true -description: Detailed guide on deploying trained models on NVIDIA Jetson using TensorRT and DeepStream SDK. Optimize the inference performance on Jetson with Ultralytics. -keywords: TensorRT, NVIDIA Jetson, DeepStream SDK, deployment, Ultralytics, YOLO, Machine Learning, AI, Deep Learning, model optimization, inference performance ---- - -# Deploy on NVIDIA Jetson using TensorRT and DeepStream SDK - -📚 This guide explains how to deploy a trained model into NVIDIA Jetson Platform and perform inference using TensorRT and DeepStream SDK. Here we use TensorRT to maximize the inference performance on the Jetson platform. - -## Hardware Verification - -We have tested and verified this guide on the following Jetson devices - -- [Seeed reComputer J1010 built with Jetson Nano module](https://www.seeedstudio.com/Jetson-10-1-A0-p-5336.html) -- [Seeed reComputer J2021 built with Jetson Xavier NX module](https://www.seeedstudio.com/reComputer-J2021-p-5438.html) - -## Before You Start - -Make sure you have properly installed **JetPack SDK** with all the **SDK Components** and **DeepStream SDK** on the Jetson device as this includes CUDA, TensorRT and DeepStream SDK which are needed for this guide. - -JetPack SDK provides a full development environment for hardware-accelerated AI-at-the-edge development. All Jetson modules and developer kits are supported by JetPack SDK. - -There are two major installation methods including, - -1. SD Card Image Method -2. NVIDIA SDK Manager Method - -You can find a very detailed installation guide from NVIDIA [official website](https://developer.nvidia.com/jetpack-sdk-461). You can also find guides corresponding to the above-mentioned [reComputer J1010](https://wiki.seeedstudio.com/reComputer_J1010_J101_Flash_Jetpack) and [reComputer J2021](https://wiki.seeedstudio.com/reComputer_J2021_J202_Flash_Jetpack). - -## Install Necessary Packages - -- **Step 1.** Access the terminal of Jetson device, install pip and upgrade it - -```sh -sudo apt update -sudo apt install -y python3-pip -pip3 install --upgrade pip -``` - -- **Step 2.** Clone the following repo - -```sh -git clone https://github.com/ultralytics/yolov5 -``` - -- **Step 3.** Open **requirements.txt** - -```sh -cd yolov5 -vi requirements.txt -``` - -- **Step 5.** Edit the following lines. Here you need to press **i** first to enter editing mode. Press **ESC**, then type **:wq** to save and quit - -```sh -# torch>=1.8.0 -# torchvision>=0.9.0 -``` - -**Note:** torch and torchvision are excluded for now because they will be installed later. - -- **Step 6.** install the below dependency - -```sh -sudo apt install -y libfreetype6-dev -``` - -- **Step 7.** Install the necessary packages - -```sh -pip3 install -r requirements.txt -``` - -## Install PyTorch and Torchvision - -We cannot install PyTorch and Torchvision from pip because they are not compatible to run on Jetson platform which is based on **ARM aarch64 architecture**. Therefore, we need to manually install pre-built PyTorch pip wheel and compile/ install Torchvision from source. - -Visit [this page](https://forums.developer.nvidia.com/t/pytorch-for-jetson) to access all the PyTorch and Torchvision links. - -Here are some of the versions supported by JetPack 4.6 and above. - -**PyTorch v1.10.0** - -Supported by JetPack 4.4 (L4T R32.4.3) / JetPack 4.4.1 (L4T R32.4.4) / JetPack 4.5 (L4T R32.5.0) / JetPack 4.5.1 (L4T R32.5.1) / JetPack 4.6 (L4T R32.6.1) with Python 3.6 - -- **file_name:** torch-1.10.0-cp36-cp36m-linux_aarch64.whl -- **URL:** [https://nvidia.box.com/shared/static/fjtbno0vpo676a25cgvuqc1wty0fkkg6.whl](https://nvidia.box.com/shared/static/fjtbno0vpo676a25cgvuqc1wty0fkkg6.whl) - -**PyTorch v1.12.0** - -Supported by JetPack 5.0 (L4T R34.1.0) / JetPack 5.0.1 (L4T R34.1.1) / JetPack 5.0.2 (L4T R35.1.0) with Python 3.8 - -- **file_name:** torch-1.12.0a0+2c916ef.nv22.3-cp38-cp38-linux_aarch64.whl -- **URL:** [https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.12.0a0+2c916ef.nv22.3-cp38-cp38-linux_aarch64.whl](https://developer.download.nvidia.com/compute/redist/jp/v50/pytorch/torch-1.12.0a0+2c916ef.nv22.3-cp38-cp38-linux_aarch64.whl) - -- **Step 1.** Install torch according to your JetPack version in the following format - -```sh -wget -O -pip3 install -``` - -For example, here we are running **JP4.6.1**, and therefore we choose **PyTorch v1.10.0** - -```sh -cd ~ -sudo apt-get install -y libopenblas-base libopenmpi-dev -wget https://nvidia.box.com/shared/static/fjtbno0vpo676a25cgvuqc1wty0fkkg6.whl -O torch-1.10.0-cp36-cp36m-linux_aarch64.whl -pip3 install torch-1.10.0-cp36-cp36m-linux_aarch64.whl -``` - -- **Step 2.** Install torchvision depending on the version of PyTorch that you have installed. For example, we chose **PyTorch v1.10.0**, which means, we need to choose **Torchvision v0.11.1** - -```sh -sudo apt install -y libjpeg-dev zlib1g-dev -git clone --branch v0.11.1 https://github.com/pytorch/vision torchvision -cd torchvision -sudo python3 setup.py install -``` - -Here a list of the corresponding torchvision version that you need to install according to the PyTorch version: - -- PyTorch v1.10 - torchvision v0.11.1 -- PyTorch v1.12 - torchvision v0.13.0 - -## DeepStream Configuration for YOLOv5 - -- **Step 1.** Clone the following repo - -```sh -cd ~ -git clone https://github.com/marcoslucianops/DeepStream-Yolo -``` - -- **Step 2.** Copy **gen_wts_yoloV5.py** from **DeepStream-Yolo/utils** into **yolov5** directory - -```sh -cp DeepStream-Yolo/utils/gen_wts_yoloV5.py yolov5 -``` - -- **Step 3.** Inside the yolov5 repo, download **pt file** from YOLOv5 releases (example for YOLOv5s 6.1) - -```sh -cd yolov5 -wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt -``` - -- **Step 4.** Generate the **cfg** and **wts** files - -```sh -python3 gen_wts_yoloV5.py -w yolov5s.pt -``` - -**Note**: To change the inference size (default: 640) - -```sh --s SIZE ---size SIZE --s HEIGHT WIDTH ---size HEIGHT WIDTH - -Example for 1280: - --s 1280 -or --s 1280 1280 -``` - -- **Step 5.** Copy the generated **cfg** and **wts** files into the **DeepStream-Yolo** folder - -```sh -cp yolov5s.cfg ~/DeepStream-Yolo -cp yolov5s.wts ~/DeepStream-Yolo -``` - -- **Step 6.** Open the **DeepStream-Yolo** folder and compile the library - -```sh -cd ~/DeepStream-Yolo -CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo # for DeepStream 6.1 -CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo # for DeepStream 6.0.1 / 6.0 -``` - -- **Step 7.** Edit the **config_infer_primary_yoloV5.txt** file according to your model - -```sh -[property] -... -custom-network-config=yolov5s.cfg -model-file=yolov5s.wts -... -``` - -- **Step 8.** Edit the **deepstream_app_config** file - -```sh -... -[primary-gie] -... -config-file=config_infer_primary_yoloV5.txt -``` - -- **Step 9.** Change the video source in **deepstream_app_config** file. Here a default video file is loaded as you can see below - -```sh -... -[source0] -... -uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4 -``` - -## Run the Inference - -```sh -deepstream-app -c deepstream_app_config.txt -``` - -
YOLOv5 with deepstream FP32
- -The above result is running on **Jetson Xavier NX** with **FP32** and **YOLOv5s 640x640**. We can see that the **FPS** is around **30**. - -## INT8 Calibration - -If you want to use INT8 precision for inference, you need to follow the steps below - -- **Step 1.** Install OpenCV - -```sh -sudo apt-get install libopencv-dev -``` - -- **Step 2.** Compile/recompile the **nvdsinfer_custom_impl_Yolo** library with OpenCV support - -```sh -cd ~/DeepStream-Yolo -CUDA_VER=11.4 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo # for DeepStream 6.1 -CUDA_VER=10.2 OPENCV=1 make -C nvdsinfer_custom_impl_Yolo # for DeepStream 6.0.1 / 6.0 -``` - -- **Step 3.** For COCO dataset, download the [val2017](https://drive.google.com/file/d/1gbvfn7mcsGDRZ_luJwtITL-ru2kK99aK/view?usp=sharing), extract, and move to **DeepStream-Yolo** folder - -- **Step 4.** Make a new directory for calibration images - -```sh -mkdir calibration -``` - -- **Step 5.** Run the following to select 1000 random images from COCO dataset to run calibration - -```sh -for jpg in $(ls -1 val2017/*.jpg | sort -R | head -1000); do \ - cp ${jpg} calibration/; \ -done -``` - -**Note:** NVIDIA recommends at least 500 images to get a good accuracy. On this example, 1000 images are chosen to get better accuracy (more images = more accuracy). Higher INT8_CALIB_BATCH_SIZE values will result in more accuracy and faster calibration speed. Set it according to you GPU memory. You can set it from **head -1000**. For example, for 2000 images, **head -2000**. This process can take a long time. - -- **Step 6.** Create the **calibration.txt** file with all selected images - -```sh -realpath calibration/*jpg > calibration.txt -``` - -- **Step 7.** Set environment variables - -```sh -export INT8_CALIB_IMG_PATH=calibration.txt -export INT8_CALIB_BATCH_SIZE=1 -``` - -- **Step 8.** Update the **config_infer_primary_yoloV5.txt** file - -From - -```sh -... -model-engine-file=model_b1_gpu0_fp32.engine -#int8-calib-file=calib.table -... -network-mode=0 -... -``` - -To - -```sh -... -model-engine-file=model_b1_gpu0_int8.engine -int8-calib-file=calib.table -... -network-mode=1 -... -``` - -- **Step 9.** Run the inference - -```sh -deepstream-app -c deepstream_app_config.txt -``` - -
YOLOv5 with deepstream INT8
- -The above result is running on **Jetson Xavier NX** with **INT8** and **YOLOv5s 640x640**. We can see that the **FPS** is around **60**. - -## Benchmark results - -The following table summarizes how different models perform on **Jetson Xavier NX**. - -| Model Name | Precision | Inference Size | Inference Time (ms) | FPS | -|------------|-----------|----------------|---------------------|-----| -| YOLOv5s | FP32 | 320x320 | 16.66 | 60 | -| | FP32 | 640x640 | 33.33 | 30 | -| | INT8 | 640x640 | 16.66 | 60 | -| YOLOv5n | FP32 | 640x640 | 16.66 | 60 | - -### Additional - -This tutorial is written by our friends at seeed @lakshanthad and Elaine diff --git a/ultralytics-main/docs/en/yolov5/tutorials/test_time_augmentation.md b/ultralytics-main/docs/en/yolov5/tutorials/test_time_augmentation.md deleted file mode 100644 index 6a585ef..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/test_time_augmentation.md +++ /dev/null @@ -1,164 +0,0 @@ ---- -comments: true -description: Boost your YOLOv5 performance with our step-by-step guide on Test-Time Augmentation (TTA). Learn to enhance your model's mAP and Recall during testing and inference. -keywords: YOLOv5, Ultralytics, Test-Time Augmentation, TTA, mAP, Recall, model performance, guide ---- - -# Test-Time Augmentation (TTA) - -📚 This guide explains how to use Test Time Augmentation (TTA) during testing and inference for improved mAP and Recall with YOLOv5 🚀. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## Test Normally - -Before trying TTA we want to establish a baseline performance to compare to. This command tests YOLOv5x on COCO val2017 at image size 640 pixels. `yolov5x.pt` is the largest and most accurate model available. Other options are `yolov5s.pt`, `yolov5m.pt` and `yolov5l.pt`, or you own checkpoint from training a custom dataset `./weights/best.pt`. For details on all available models please see our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints). - -```bash -python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half -``` - -Output: - -```shell -val: data=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Fusing layers... -Model Summary: 476 layers, 87730285 parameters, 0 gradients - -val: Scanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2846.03it/s] -val: New cache created: ../datasets/coco/val2017.cache - Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [02:30<00:00, 1.05it/s] - all 5000 36335 0.746 0.626 0.68 0.49 -Speed: 0.1ms pre-process, 22.4ms inference, 1.4ms NMS per image at shape (32, 3, 640, 640) # <--- baseline speed - -Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json... -... - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504 # <--- baseline mAP - Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688 - Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546 - Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351 - Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551 - Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.628 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681 # <--- baseline mAR - Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524 - Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735 - Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.826 -``` - -## Test with TTA - -Append `--augment` to any existing `val.py` command to enable TTA, and increase the image size by about 30% for improved results. Note that inference with TTA enabled will typically take about 2-3X the time of normal inference as the images are being left-right flipped and processed at 3 different resolutions, with the outputs merged before NMS. Part of the speed decrease is simply due to larger image sizes (832 vs 640), while part is due to the actual TTA operations. - -```bash -python val.py --weights yolov5x.pt --data coco.yaml --img 832 --augment --half -``` - -Output: - -```shell -val: data=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=832, conf_thres=0.001, iou_thres=0.6, task=val, device=, single_cls=False, augment=True, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Fusing layers... -/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at /pytorch/c10/core/TensorImpl.h:1156.) - return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode) -Model Summary: 476 layers, 87730285 parameters, 0 gradients -val: Scanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2885.61it/s] -val: New cache created: ../datasets/coco/val2017.cache - Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [07:29<00:00, 2.86s/it] - all 5000 36335 0.718 0.656 0.695 0.503 -Speed: 0.2ms pre-process, 80.6ms inference, 2.7ms NMS per image at shape (32, 3, 832, 832) # <--- TTA speed - -Evaluating pycocotools mAP... saving runs/val/exp2/yolov5x_predictions.json... -... - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.516 # <--- TTA mAP - Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.701 - Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.562 - Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.361 - Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.564 - Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.656 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.388 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.640 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.696 # <--- TTA mAR - Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.553 - Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.744 - Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833 -``` - -## Inference with TTA - -`detect.py` TTA inference operates identically to `val.py` TTA: simply append `--augment` to any existing `detect.py` command: - -```bash -python detect.py --weights yolov5s.pt --img 832 --source data/images --augment -``` - -Output: - -```bash -YOLOv5 🚀 v5.0-267-g6a3ee7c torch 1.9.0+cu102 CUDA:0 (Tesla P100-PCIE-16GB, 16280.875MB) - -Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5s.pt to yolov5s.pt... -100% 14.1M/14.1M [00:00<00:00, 81.9MB/s] - -Fusing layers... -Model Summary: 224 layers, 7266973 parameters, 0 gradients -image 1/2 /content/yolov5/data/images/bus.jpg: 832x640 4 persons, 1 bus, 1 fire hydrant, Done. (0.029s) -image 2/2 /content/yolov5/data/images/zidane.jpg: 480x832 3 persons, 3 ties, Done. (0.024s) -Results saved to runs/detect/exp -Done. (0.156s) -``` - -YOLOv5 test time augmentations - -### PyTorch Hub TTA - -TTA is automatically integrated into all [YOLOv5 PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5) models, and can be accessed by passing `augment=True` at inference time. - -```python -import torch - -# Model -model = torch.hub.load('ultralytics/yolov5', 'yolov5s') # or yolov5m, yolov5x, custom - -# Images -img = 'https://ultralytics.com/images/zidane.jpg' # or file, PIL, OpenCV, numpy, multiple - -# Inference -results = model(img, augment=True) # <--- TTA inference - -# Results -results.print() # or .show(), .save(), .crop(), .pandas(), etc. -``` - -### Customize - -You can customize the TTA ops applied in the YOLOv5 `forward_augment()` method [here](https://github.com/ultralytics/yolov5/blob/8c6f9e15bfc0000d18b976a95b9d7c17d407ec91/models/yolo.py#L125-L137). - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/tips_for_best_training_results.md b/ultralytics-main/docs/en/yolov5/tutorials/tips_for_best_training_results.md deleted file mode 100644 index 10dcff3..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/tips_for_best_training_results.md +++ /dev/null @@ -1,65 +0,0 @@ ---- -comments: true -description: Our comprehensive guide provides insights on how to train your YOLOv5 system to get the best mAP. Master dataset preparation, model selection, training settings, and more. -keywords: Ultralytics, YOLOv5, Training guide, dataset preparation, model selection, training settings, mAP results, Machine Learning, Object Detection ---- - -📚 This guide explains how to produce the best mAP and training results with YOLOv5 🚀. - -Most of the time good results can be obtained with no changes to the models or training settings, **provided your dataset is sufficiently large and well labelled**. If at first you don't get good results, there are steps you might be able to take to improve, but we always recommend users **first train with all default settings** before considering any changes. This helps establish a performance baseline and spot areas for improvement. - -If you have questions about your training results **we recommend you provide the maximum amount of information possible** if you expect a helpful response, including results plots (train losses, val losses, P, R, mAP), PR curve, confusion matrix, training mosaics, test results and dataset statistics images such as labels.png. All of these are located in your `project/name` directory, typically `yolov5/runs/train/exp`. - -We've put together a full guide for users looking to get the best results on their YOLOv5 trainings below. - -## Dataset - -- **Images per class.** ≥ 1500 images per class recommended -- **Instances per class.** ≥ 10000 instances (labeled objects) per class recommended -- **Image variety.** Must be representative of deployed environment. For real-world use cases we recommend images from different times of day, different seasons, different weather, different lighting, different angles, different sources (scraped online, collected locally, different cameras) etc. -- **Label consistency.** All instances of all classes in all images must be labelled. Partial labelling will not work. -- **Label accuracy.** Labels must closely enclose each object. No space should exist between an object and it's bounding box. No objects should be missing a label. -- **Label verification.** View `train_batch*.jpg` on train start to verify your labels appear correct, i.e. see [example](https://docs.ultralytics.com/yolov5/tutorials/train_custom_data#local-logging) mosaic. -- **Background images.** Background images are images with no objects that are added to a dataset to reduce False Positives (FP). We recommend about 0-10% background images to help reduce FPs (COCO has 1000 background images for reference, 1% of the total). No labels are required for background images. - -COCO Analysis - -## Model Selection - -Larger models like YOLOv5x and [YOLOv5x6](https://github.com/ultralytics/yolov5/releases/tag/v5.0) will produce better results in nearly all cases, but have more parameters, require more CUDA memory to train, and are slower to run. For **mobile** deployments we recommend YOLOv5s/m, for **cloud** deployments we recommend YOLOv5l/x. See our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints) for a full comparison of all models. - -

YOLOv5 Models

- -- **Start from Pretrained weights.** Recommended for small to medium-sized datasets (i.e. [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml)). Pass the name of the model to the `--weights` argument. Models download automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). - -```shell -python train.py --data custom.yaml --weights yolov5s.pt - yolov5m.pt - yolov5l.pt - yolov5x.pt - custom_pretrained.pt -``` - -- **Start from Scratch.** Recommended for large datasets (i.e. [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [OIv6](https://storage.googleapis.com/openimages/web/index.html)). Pass the model architecture YAML you are interested in, along with an empty `--weights ''` argument: - -```bash -python train.py --data custom.yaml --weights '' --cfg yolov5s.yaml - yolov5m.yaml - yolov5l.yaml - yolov5x.yaml -``` - -## Training Settings - -Before modifying anything, **first train with default settings to establish a performance baseline**. A full list of train.py settings can be found in the [train.py](https://github.com/ultralytics/yolov5/blob/master/train.py) argparser. - -- **Epochs.** Start with 300 epochs. If this overfits early then you can reduce epochs. If overfitting does not occur after 300 epochs, train longer, i.e. 600, 1200 etc. epochs. -- **Image size.** COCO trains at native resolution of `--img 640`, though due to the high amount of small objects in the dataset it can benefit from training at higher resolutions such as `--img 1280`. If there are many small objects then custom datasets will benefit from training at native or higher resolution. Best inference results are obtained at the same `--img` as the training was run at, i.e. if you train at `--img 1280` you should also test and detect at `--img 1280`. -- **Batch size.** Use the largest `--batch-size` that your hardware allows for. Small batch sizes produce poor batchnorm statistics and should be avoided. -- **Hyperparameters.** Default hyperparameters are in [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml). We recommend you train with default hyperparameters first before thinking of modifying any. In general, increasing augmentation hyperparameters will reduce and delay overfitting, allowing for longer trainings and higher final mAP. Reduction in loss component gain hyperparameters like `hyp['obj']` will help reduce overfitting in those specific loss components. For an automated method of optimizing these hyperparameters, see our [Hyperparameter Evolution Tutorial](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution). - -## Further Reading - -If you'd like to know more, a good place to start is Karpathy's 'Recipe for Training Neural Networks', which has great ideas for training that apply broadly across all ML domains: [https://karpathy.github.io/2019/04/25/recipe/](https://karpathy.github.io/2019/04/25/recipe/) - -Good luck 🍀 and let us know if you have any other questions! diff --git a/ultralytics-main/docs/en/yolov5/tutorials/train_custom_data.md b/ultralytics-main/docs/en/yolov5/tutorials/train_custom_data.md deleted file mode 100644 index c6e501c..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/train_custom_data.md +++ /dev/null @@ -1,224 +0,0 @@ ---- -comments: true -description: Learn how to train your data on custom datasets using YOLOv5. Simple and updated guide on collection and organization of images, labelling, model training and deployment. -keywords: YOLOv5, train on custom dataset, image collection, model training, object detection, image labelling, Ultralytics, PyTorch, machine learning ---- - -📚 This guide explains how to train your own **custom dataset** with [YOLOv5](https://github.com/ultralytics/yolov5) 🚀. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## Train On Custom Data - - -Ultralytics active learning -
-
- -Creating a custom model to detect your objects is an iterative process of collecting and organizing images, labeling your objects of interest, training a model, deploying it into the wild to make predictions, and then using that deployed model to collect examples of edge cases to repeat and improve. - -!!! Question "Licensing" - - Ultralytics offers two licensing options: - - - The [AGPL-3.0 License](https://github.com/ultralytics/ultralytics/blob/main/LICENSE), an [OSI-approved](https://opensource.org/licenses/) open-source license ideal for students and enthusiasts. - - The [Enterprise License](https://ultralytics.com/license) for businesses seeking to incorporate our AI models into their products and services. - - For more details see [Ultralytics Licensing](https://ultralytics.com/license). - -YOLOv5 models must be trained on labelled data in order to learn classes of objects in that data. There are two options for creating your dataset before you start training: - -## Option 1: Create a Roboflow Dataset - -### 1.1 Collect Images - -Your model will learn by example. Training on images similar to the ones it will see in the wild is of the utmost importance. Ideally, you will collect a wide variety of images from the same configuration (camera, angle, lighting, etc.) as you will ultimately deploy your project. - -If this is not possible, you can start from [a public dataset](https://universe.roboflow.com/?ref=ultralytics) to train your initial model and then [sample images from the wild during inference](https://blog.roboflow.com/computer-vision-active-learning-tips/?ref=ultralytics) to improve your dataset and model iteratively. - -### 1.2 Create Labels - -Once you have collected images, you will need to annotate the objects of interest to create a ground truth for your model to learn from. - -

YOLOv5 accuracies

- -[Roboflow Annotate](https://roboflow.com/annotate?ref=ultralytics) is a simple web-based tool for managing and labeling your images with your team and exporting them in [YOLOv5's annotation format](https://roboflow.com/formats/yolov5-pytorch-txt?ref=ultralytics). - -### 1.3 Prepare Dataset for YOLOv5 - -Whether you [label your images with Roboflow](https://roboflow.com/annotate?ref=ultralytics) or not, you can use it to convert your dataset into YOLO format, create a YOLOv5 YAML configuration file, and host it for importing into your training script. - -[Create a free Roboflow account](https://app.roboflow.com/?model=yolov5&ref=ultralytics) and upload your dataset to a `Public` workspace, label any unannotated images, then generate and export a version of your dataset in `YOLOv5 Pytorch` format. - -Note: YOLOv5 does online augmentation during training, so we do not recommend applying any augmentation steps in Roboflow for training with YOLOv5. But we recommend applying the following preprocessing steps: - -

Recommended Preprocessing Steps

- -- **Auto-Orient** - to strip EXIF orientation from your images. -- **Resize (Stretch)** - to the square input size of your model (640x640 is the YOLOv5 default). - -Generating a version will give you a snapshot of your dataset, so you can always go back and compare your future model training runs against it, even if you add more images or change its configuration later. - -

Export in YOLOv5 Format

- -Export in `YOLOv5 Pytorch` format, then copy the snippet into your training script or notebook to download your dataset. - -

Roboflow dataset download snippet

- -## Option 2: Create a Manual Dataset - -### 2.1 Create `dataset.yaml` - -[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](https://cocodataset.org/) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of overfitting. [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or `*.txt` files with image paths) and 2) a class `names` dictionary: - -```yaml -# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] -path: ../datasets/coco128 # dataset root dir -train: images/train2017 # train images (relative to 'path') 128 images -val: images/train2017 # val images (relative to 'path') 128 images -test: # test images (optional) - -# Classes (80 COCO classes) -names: - 0: person - 1: bicycle - 2: car - # ... - 77: teddy bear - 78: hair drier - 79: toothbrush -``` - -### 2.2 Create Labels - -After using an annotation tool to label your images, export your labels to **YOLO format**, with one `*.txt` file per image (if no objects in image, no `*.txt` file is required). The `*.txt` file specifications are: - -- One row per object -- Each row is `class x_center y_center width height` format. -- Box coordinates must be in **normalized xywh** format (from 0 to 1). If your boxes are in pixels, divide `x_center` and `width` by image width, and `y_center` and `height` by image height. -- Class numbers are zero-indexed (start from 0). - -

Roboflow annotations

- -The label file corresponding to the above image contains 2 persons (class `0`) and a tie (class `27`): - -

Roboflow dataset preprocessing

- -### 2.3 Organize Directories - -Organize your train and val images and labels according to the example below. YOLOv5 assumes `/coco128` is inside a `/datasets` directory **next to** the `/yolov5` directory. **YOLOv5 locates labels automatically for each image** by replacing the last instance of `/images/` in each image path with `/labels/`. For example: - -```bash -../datasets/coco128/images/im0.jpg # image -../datasets/coco128/labels/im0.txt # label -``` - -

YOLOv5 dataset structure

- -## 3. Select a Model - -Select a pretrained model to start training from. Here we select [YOLOv5s](https://github.com/ultralytics/yolov5/blob/master/models/yolov5s.yaml), the second-smallest and fastest model available. See our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints) for a full comparison of all models. - -

YOLOv5 models

- -## 4. Train - -Train a YOLOv5s model on COCO128 by specifying dataset, batch-size, image size and either pretrained `--weights yolov5s.pt` (recommended), or randomly initialized `--weights '' --cfg yolov5s.yaml` (not recommended). Pretrained weights are auto-downloaded from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). - -```bash -python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt -``` - -!!! Tip "Tip" - - 💡 Add `--cache ram` or `--cache disk` to speed up training (requires significant RAM/disk resources). - -!!! Tip "Tip" - - 💡 Always train from a local dataset. Mounted or network drives like Google Drive will be very slow. - -All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc. For more details see the Training section of our tutorial notebook. Open In Colab Open In Kaggle - -## 5. Visualize - -### Comet Logging and Visualization 🌟 NEW - -[Comet](https://bit.ly/yolov5-readme-comet) is now fully integrated with YOLOv5. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://bit.ly/yolov5-colab-comet-panels)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes! - -Getting started is easy: - -```shell -pip install comet_ml # 1. install -export COMET_API_KEY= # 2. paste API key -python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt # 3. train -``` - -To learn more about all the supported Comet features for this integration, check out the [Comet Tutorial](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration). If you'd like to learn more about Comet, head over to our [documentation](https://bit.ly/yolov5-colab-comet-docs). Get started by trying out the Comet Colab Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing) - -YOLO UI - -### ClearML Logging and Automation 🌟 NEW - -[ClearML](https://clear.ml/) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML: - -- `pip install clearml` -- run `clearml-init` to connect to a ClearML server - -You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers). - -You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the [ClearML Tutorial](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) for details! - - -ClearML Experiment Management UI - -### Local Logging - -Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. - -This directory contains train and val statistics, mosaics, labels, predictions and augmented mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices. - -Local logging results - -Results file `results.csv` is updated after each epoch, and then plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually: - -```python -from utils.plots import plot_results - -plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png' -``` - -

results.png

- -## Next Steps - -Once your model is trained you can use your best checkpoint `best.pt` to: - -- Run [CLI](https://github.com/ultralytics/yolov5#quick-start-examples) or [Python](https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading) inference on new images and videos -- [Validate](https://github.com/ultralytics/yolov5/blob/master/val.py) accuracy on train, val and test splits -- [Export](https://docs.ultralytics.com/yolov5/tutorials/model_export) to TensorFlow, Keras, ONNX, TFlite, TF.js, CoreML and TensorRT formats -- [Evolve](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter_evolution) hyperparameters to improve performance -- [Improve](https://docs.roboflow.com/adding-data/upload-api?ref=ultralytics) your model by sampling real-world images and adding them to your dataset - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md b/ultralytics-main/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md deleted file mode 100644 index 8fb0da8..0000000 --- a/ultralytics-main/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md +++ /dev/null @@ -1,155 +0,0 @@ ---- -comments: true -description: Learn to freeze YOLOv5 layers for efficient transfer learning. Optimize your model retraining with less resources and faster training times. -keywords: YOLOv5, freeze layers, transfer learning, model retraining, Ultralytics ---- - -📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **transfer learning**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire network. Instead, part of the initial weights are frozen in place, and the rest of the weights are used to compute loss and are updated by the optimizer. This requires less resources than normal training and allows for faster training times, though it may also result in reductions to final trained accuracy. - -## Before You Start - -Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a [**Python>=3.8.0**](https://www.python.org/) environment, including [**PyTorch>=1.8**](https://pytorch.org/get-started/locally/). [Models](https://github.com/ultralytics/yolov5/tree/master/models) and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). - -```bash -git clone https://github.com/ultralytics/yolov5 # clone -cd yolov5 -pip install -r requirements.txt # install -``` - -## Freeze Backbone - -All layers that match the train.py `freeze` list in train.py will be frozen by setting their gradients to zero before training starts. - -```python -# Freeze -freeze = [f'model.{x}.' for x in range(freeze)] # layers to freeze -for k, v in model.named_parameters(): - v.requires_grad = True # train all layers - if any(x in k for x in freeze): - print(f'freezing {k}') - v.requires_grad = False -``` - -To see a list of module names: - -```python -for k, v in model.named_parameters(): - print(k) - -"""Output: -model.0.conv.conv.weight -model.0.conv.bn.weight -model.0.conv.bn.bias -model.1.conv.weight -model.1.bn.weight -model.1.bn.bias -model.2.cv1.conv.weight -model.2.cv1.bn.weight -... -model.23.m.0.cv2.bn.weight -model.23.m.0.cv2.bn.bias -model.24.m.0.weight -model.24.m.0.bias -model.24.m.1.weight -model.24.m.1.bias -model.24.m.2.weight -model.24.m.2.bias -""" -``` - -Looking at the model architecture we can see that the model backbone is layers 0-9: - -```yaml -# YOLOv5 v6.0 backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3, [128]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3, [256]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 9, C3, [512]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C3, [1024]] - - [-1, 1, SPPF, [1024, 5]] # 9 - - -# YOLOv5 v6.0 head -head: - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3, [512, False]] # 13 - - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3, [256, False]] # 17 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3, [512, False]] # 20 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 10], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3, [1024, False]] # 23 (P5/32-large) - - - [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5) -``` - -so we can define the freeze list to contain all modules with 'model.0.' - 'model.9.' in their names: - -```bash -python train.py --freeze 10 -``` - -## Freeze All Layers - -To freeze the full model except for the final output convolution layers in Detect(), we set freeze list to contain all modules with 'model.0.' - 'model.23.' in their names: - -```bash -python train.py --freeze 24 -``` - -## Results - -We train YOLOv5m on VOC on both of the above scenarios, along with a default model (no freezing), starting from the official COCO pretrained `--weights yolov5m.pt`: - -```bash -train.py --batch 48 --weights yolov5m.pt --data voc.yaml --epochs 50 --cache --img 512 --hyp hyp.finetune.yaml -``` - -### Accuracy Comparison - -The results show that freezing speeds up training, but reduces final accuracy slightly. - -![Freezing training mAP50 results](https://user-images.githubusercontent.com/26833433/98394454-11579f80-205b-11eb-8e57-d8318e1cc2f8.png) - -![Freezing training mAP50-95 results](https://user-images.githubusercontent.com/26833433/98394459-13216300-205b-11eb-871b-49e20691a423.png) - -Table results - -### GPU Utilization Comparison - -Interestingly, the more modules are frozen the less GPU memory is required to train, and the lower GPU utilization. This indicates that larger models, or models trained at larger --image-size may benefit from freezing in order to train faster. - -![Training GPU memory allocated percent](https://user-images.githubusercontent.com/26833433/98394920-c2f6d080-205b-11eb-9611-fd68522b4e0e.png) - -![Training GPU memory utilization percent](https://user-images.githubusercontent.com/26833433/98394918-bf634980-205b-11eb-948d-311036ef9325.png) - -## Supported Environments - -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - -- **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle -- **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) -- **Amazon**: [AWS Quickstart Guide](../environments/aws_quickstart_tutorial.md) -- **Azure**: [AzureML Quickstart Guide](../environments/azureml_quickstart_tutorial.md) -- **Docker**: [Docker Quickstart Guide](../environments/docker_image_quickstart_tutorial.md) Docker Pulls - -## Project Status - -YOLOv5 CI - -This badge indicates that all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are successfully passing. These CI tests rigorously check the functionality and performance of YOLOv5 across various key aspects: [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py), and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py). They ensure consistent and reliable operation on macOS, Windows, and Ubuntu, with tests conducted every 24 hours and upon each new commit. diff --git a/ultralytics-main/docs/overrides/assets/favicon.ico b/ultralytics-main/docs/overrides/assets/favicon.ico deleted file mode 100644 index 7aa5066..0000000 Binary files a/ultralytics-main/docs/overrides/assets/favicon.ico and /dev/null differ diff --git a/ultralytics-main/docs/overrides/javascript/extra.js b/ultralytics-main/docs/overrides/javascript/extra.js deleted file mode 100644 index 3233a64..0000000 --- a/ultralytics-main/docs/overrides/javascript/extra.js +++ /dev/null @@ -1,69 +0,0 @@ -// Function that applies light/dark theme based on the user's preference -const applyAutoTheme = () => { - // Determine the user's preferred color scheme - const prefersLight = window.matchMedia("(prefers-color-scheme: light)").matches; - const prefersDark = window.matchMedia("(prefers-color-scheme: dark)").matches; - - // Apply the appropriate attributes based on the user's preference - if (prefersLight) { - document.body.setAttribute("data-md-color-scheme", "default"); - document.body.setAttribute("data-md-color-primary", "indigo"); - } else if (prefersDark) { - document.body.setAttribute("data-md-color-scheme", "slate"); - document.body.setAttribute("data-md-color-primary", "black"); - } -}; - -// Function that checks and applies light/dark theme based on the user's preference (if auto theme is enabled) -function checkAutoTheme() { - // Array of supported language codes -> each language has its own palette (stored in local storage) - const supportedLangCodes = ["en", "zh", "ko", "ja", "ru", "de", "fr", "es", "pt", "it", "tr", "vi", "nl"]; - // Get the URL path - const path = window.location.pathname; - // Extract the language code from the URL (assuming it's in the format /xx/...) - const langCode = path.split("/")[1]; - // Check if the extracted language code is in the supported languages - const isValidLangCode = supportedLangCodes.includes(langCode); - // Construct the local storage key based on the language code if valid, otherwise default to the root key - const localStorageKey = isValidLangCode ? `/${langCode}/.__palette` : "/.__palette"; - // Retrieve the palette from local storage using the constructed key - const palette = localStorage.getItem(localStorageKey); - if (palette) { - // Check if the palette's index is 0 (auto theme) - const paletteObj = JSON.parse(palette); - if (paletteObj && paletteObj.index === 0) { - applyAutoTheme(); - } - } -} - -// Run function when the script loads -checkAutoTheme(); - -// Re-run the function when the user's preference changes (when the user changes their system theme) -window.matchMedia("(prefers-color-scheme: light)").addEventListener("change", checkAutoTheme); -window.matchMedia("(prefers-color-scheme: dark)").addEventListener("change", checkAutoTheme); - -// Re-run the function when the palette changes (e.g. user switched from dark theme to auto theme) -// ! We can't use window.addEventListener("storage", checkAutoTheme) because it will NOT be triggered on the current tab -// ! So we have to use the following workaround: -// Get the palette input for auto theme -var autoThemeInput = document.getElementById("__palette_1"); -if (autoThemeInput) { - // Add a click event listener to the input - autoThemeInput.addEventListener("click", function () { - // Check if the auto theme is selected - if (autoThemeInput.checked) { - // Re-run the function after a short delay (to ensure that the palette has been updated) - setTimeout(applyAutoTheme); - } - }); -} - -// Add iframe navigation -window.onhashchange = function() { - window.parent.postMessage({ - type: 'navigation', - hash: window.location.pathname + window.location.search + window.location.hash - }, '*'); -}; diff --git a/ultralytics-main/docs/overrides/main.html b/ultralytics-main/docs/overrides/main.html deleted file mode 100644 index bc088ce..0000000 --- a/ultralytics-main/docs/overrides/main.html +++ /dev/null @@ -1,12 +0,0 @@ - - -{% extends "base.html" %} - -{% block announce %} - -{% endblock %} diff --git a/ultralytics-main/docs/overrides/partials/comments.html b/ultralytics-main/docs/overrides/partials/comments.html deleted file mode 100644 index a99f4f8..0000000 --- a/ultralytics-main/docs/overrides/partials/comments.html +++ /dev/null @@ -1,51 +0,0 @@ -{% if page.meta.comments %} -

{{ lang.t("meta.comments") }}

- - - - - - -{% endif %} diff --git a/ultralytics-main/docs/overrides/partials/source-file.html b/ultralytics-main/docs/overrides/partials/source-file.html deleted file mode 100644 index 84e2ab1..0000000 --- a/ultralytics-main/docs/overrides/partials/source-file.html +++ /dev/null @@ -1,26 +0,0 @@ -{% import "partials/language.html" as lang with context %} - - - -
-
- - - - {% if page.meta.git_revision_date_localized %} - 📅 {{ lang.t("source.file.date.updated") }}: - {{ page.meta.git_revision_date_localized }} - {% if page.meta.git_creation_date_localized %} -
- 🎂 {{ lang.t("source.file.date.created") }}: - {{ page.meta.git_creation_date_localized }} - {% endif %} - - - {% elif page.meta.revision_date %} - 📅 {{ lang.t("source.file.date.updated") }}: - {{ page.meta.revision_date }} - {% endif %} - -
diff --git a/ultralytics-main/docs/overrides/stylesheets/style.css b/ultralytics-main/docs/overrides/stylesheets/style.css deleted file mode 100644 index 6607002..0000000 --- a/ultralytics-main/docs/overrides/stylesheets/style.css +++ /dev/null @@ -1,57 +0,0 @@ -/* Table format like GitHub ----------------------------------------------------------------------------------------- */ -th, -td { - border: 1px solid var(--md-typeset-table-color); - border-spacing: 0; - border-bottom: none; - border-left: none; - border-top: none; -} - -.md-typeset__table { - line-height: 1; -} - -.md-typeset__table table:not([class]) { - font-size: 0.74rem; - border-right: none; -} - -.md-typeset__table table:not([class]) td, -.md-typeset__table table:not([class]) th { - padding: 9px; -} - -/* light mode alternating table bg colors */ -.md-typeset__table tr:nth-child(2n) { - background-color: #f6f8fa; -} - -/* dark mode alternating table bg colors */ -[data-md-color-scheme="slate"] .md-typeset__table tr:nth-child(2n) { - background-color: #161b22; -} -/* Table format like GitHub ----------------------------------------------------------------------------------------- */ - -/* Code block vertical scroll */ -div.highlight { - max-height: 20rem; - overflow-y: auto; /* for adding a scrollbar when needed */ -} - -/* Set content width */ -.md-grid { - max-width: 1440px; -} - -/* Set language dropdown maximum height to screen height */ -.md-header .md-select:hover .md-select__inner { - max-height: 75vh; -} - -/* Update the background of the banner (same as the one on the Ultralytics website) */ -.md-banner { - background-image: url(https://uploads-ssl.webflow.com/646dd1f1a3703e451ba81ecc/65e60cd6a4080bba757850a3_banner_ct.webp); - background-size: cover; - background-position: center; -} diff --git a/ultralytics-main/examples/README.md b/ultralytics-main/examples/README.md deleted file mode 100644 index 42c3bd5..0000000 --- a/ultralytics-main/examples/README.md +++ /dev/null @@ -1,36 +0,0 @@ -## Ultralytics YOLOv8 Example Applications - -This repository features a collection of real-world applications and walkthroughs, provided as either Python files or notebooks. Explore the examples below to see how YOLOv8 can be integrated into various applications. - -### Ultralytics YOLO Example Applications - -| Title | Format | Contributor | -| ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------ | ----------------------------------------------------------------------------------------- | -| [YOLO ONNX Detection Inference with C++](./YOLOv8-CPP-Inference) | C++/ONNX | [Justas Bartnykas](https://github.com/JustasBart) | -| [YOLO OpenCV ONNX Detection Python](./YOLOv8-OpenCV-ONNX-Python) | OpenCV/Python/ONNX | [Farid Inawan](https://github.com/frdteknikelektro) | -| [YOLOv8 .NET ONNX ImageSharp](https://github.com/dme-compunet/YOLOv8) | C#/ONNX/ImageSharp | [Compunet](https://github.com/dme-compunet) | -| [YOLO .Net ONNX Detection C#](https://www.nuget.org/packages/Yolov8.Net) | C# .Net | [Samuel Stainback](https://github.com/sstainba) | -| [YOLOv8 on NVIDIA Jetson(TensorRT and DeepStream)](https://wiki.seeedstudio.com/YOLOv8-DeepStream-TRT-Jetson/) | Python | [Lakshantha](https://github.com/lakshanthad) | -| [YOLOv8 ONNXRuntime Python](./YOLOv8-ONNXRuntime) | Python/ONNXRuntime | [Semih Demirel](https://github.com/semihhdemirel) | -| [YOLOv8 ONNXRuntime CPP](./YOLOv8-ONNXRuntime-CPP) | C++/ONNXRuntime | [DennisJcy](https://github.com/DennisJcy), [Onuralp Sezer](https://github.com/onuralpszr) | -| [RTDETR ONNXRuntime C#](https://github.com/Kayzwer/yolo-cs/blob/master/RTDETR.cs) | C#/ONNX | [Kayzwer](https://github.com/Kayzwer) | -| [YOLOv8 SAHI Video Inference](https://github.com/RizwanMunawar/ultralytics/blob/main/examples/YOLOv8-SAHI-Inference-Video/yolov8_sahi.py) | Python | [Muhammad Rizwan Munawar](https://github.com/RizwanMunawar) | -| [YOLOv8 Region Counter](https://github.com/RizwanMunawar/ultralytics/blob/main/examples/YOLOv8-Region-Counter/yolov8_region_counter.py) | Python | [Muhammad Rizwan Munawar](https://github.com/RizwanMunawar) | -| [YOLOv8 Segmentation ONNXRuntime Python](./YOLOv8-Segmentation-ONNXRuntime-Python) | Python/ONNXRuntime | [jamjamjon](https://github.com/jamjamjon) | -| [YOLOv8 LibTorch CPP](./YOLOv8-LibTorch-CPP-Inference) | C++/LibTorch | [Myyura](https://github.com/Myyura) | -| [YOLOv8 OpenCV INT8 TFLite Python](./YOLOv8-OpenCV-int8-tflite-Python) | Python | [Wamiq Raza](https://github.com/wamiqraza) | - -### How to Contribute - -We greatly appreciate contributions from the community, including examples, applications, and guides. If you'd like to contribute, please follow these guidelines: - -1. Create a pull request (PR) with the title prefix `[Example]`, adding your new example folder to the `examples/` directory within the repository. -2. Make sure your project adheres to the following standards: - - Makes use of the `ultralytics` package. - - Includes a `README.md` with clear instructions for setting up and running the example. - - Refrains from adding large files or dependencies unless they are absolutely necessary for the example. - - Contributors should be willing to provide support for their examples and address related issues. - -For more detailed information and guidance on contributing, please visit our [contribution documentation](https://docs.ultralytics.com/help/contributing). - -If you encounter any questions or concerns regarding these guidelines, feel free to open a PR or an issue in the repository, and we will assist you in the contribution process. diff --git a/ultralytics-main/examples/YOLOv8-CPP-Inference/CMakeLists.txt b/ultralytics-main/examples/YOLOv8-CPP-Inference/CMakeLists.txt deleted file mode 100644 index bc2f33f..0000000 --- a/ultralytics-main/examples/YOLOv8-CPP-Inference/CMakeLists.txt +++ /dev/null @@ -1,28 +0,0 @@ -cmake_minimum_required(VERSION 3.5) - -project(Yolov8CPPInference VERSION 0.1) - -set(CMAKE_INCLUDE_CURRENT_DIR ON) - -# CUDA -set(CUDA_TOOLKIT_ROOT_DIR "/usr/local/cuda") -find_package(CUDA 11 REQUIRED) - -set(CMAKE_CUDA_STANDARD 11) -set(CMAKE_CUDA_STANDARD_REQUIRED ON) -# !CUDA - -# OpenCV -find_package(OpenCV REQUIRED) -include_directories(${OpenCV_INCLUDE_DIRS}) -# !OpenCV - -set(PROJECT_SOURCES - main.cpp - - inference.h - inference.cpp -) - -add_executable(Yolov8CPPInference ${PROJECT_SOURCES}) -target_link_libraries(Yolov8CPPInference ${OpenCV_LIBS}) diff --git a/ultralytics-main/examples/YOLOv8-CPP-Inference/README.md b/ultralytics-main/examples/YOLOv8-CPP-Inference/README.md deleted file mode 100644 index 601c1d0..0000000 --- a/ultralytics-main/examples/YOLOv8-CPP-Inference/README.md +++ /dev/null @@ -1,50 +0,0 @@ -# YOLOv8/YOLOv5 Inference C++ - -This example demonstrates how to perform inference using YOLOv8 and YOLOv5 models in C++ with OpenCV's DNN API. - -## Usage - -```bash -git clone ultralytics -cd ultralytics -pip install . -cd examples/YOLOv8-CPP-Inference - -# Add a **yolov8\_.onnx** and/or **yolov5\_.onnx** model(s) to the ultralytics folder. -# Edit the **main.cpp** to change the **projectBasePath** to match your user. - -# Note that by default the CMake file will try and import the CUDA library to be used with the OpenCVs dnn (cuDNN) GPU Inference. -# If your OpenCV build does not use CUDA/cuDNN you can remove that import call and run the example on CPU. - -mkdir build -cd build -cmake .. -make -./Yolov8CPPInference -``` - -## Exporting YOLOv8 and YOLOv5 Models - -To export YOLOv8 models: - -```commandline -yolo export model=yolov8s.pt imgsz=480,640 format=onnx opset=12 -``` - -To export YOLOv5 models: - -```commandline -python3 export.py --weights yolov5s.pt --img 480 640 --include onnx --opset 12 -``` - -yolov8s.onnx: - -![image](https://user-images.githubusercontent.com/40023722/217356132-a4cecf2e-2729-4acb-b80a-6559022d7707.png) - -yolov5s.onnx: - -![image](https://user-images.githubusercontent.com/40023722/217357005-07464492-d1da-42e3-98a7-fc753f87d5e6.png) - -This repository utilizes OpenCV's DNN API to run ONNX exported models of YOLOv5 and YOLOv8. In theory, it should work for YOLOv6 and YOLOv7 as well, but they have not been tested. Note that the example networks are exported with rectangular (640x480) resolutions, but any exported resolution will work. You may want to use the letterbox approach for square images, depending on your use case. - -The **main** branch version uses Qt as a GUI wrapper. The primary focus here is the **Inference** class file, which demonstrates how to transpose YOLOv8 models to work as YOLOv5 models. diff --git a/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.cpp b/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.cpp deleted file mode 100644 index 12c2607..0000000 --- a/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.cpp +++ /dev/null @@ -1,185 +0,0 @@ -#include "inference.h" - -Inference::Inference(const std::string &onnxModelPath, const cv::Size &modelInputShape, const std::string &classesTxtFile, const bool &runWithCuda) -{ - modelPath = onnxModelPath; - modelShape = modelInputShape; - classesPath = classesTxtFile; - cudaEnabled = runWithCuda; - - loadOnnxNetwork(); - // loadClassesFromFile(); The classes are hard-coded for this example -} - -std::vector Inference::runInference(const cv::Mat &input) -{ - cv::Mat modelInput = input; - if (letterBoxForSquare && modelShape.width == modelShape.height) - modelInput = formatToSquare(modelInput); - - cv::Mat blob; - cv::dnn::blobFromImage(modelInput, blob, 1.0/255.0, modelShape, cv::Scalar(), true, false); - net.setInput(blob); - - std::vector outputs; - net.forward(outputs, net.getUnconnectedOutLayersNames()); - - int rows = outputs[0].size[1]; - int dimensions = outputs[0].size[2]; - - bool yolov8 = false; - // yolov5 has an output of shape (batchSize, 25200, 85) (Num classes + box[x,y,w,h] + confidence[c]) - // yolov8 has an output of shape (batchSize, 84, 8400) (Num classes + box[x,y,w,h]) - if (dimensions > rows) // Check if the shape[2] is more than shape[1] (yolov8) - { - yolov8 = true; - rows = outputs[0].size[2]; - dimensions = outputs[0].size[1]; - - outputs[0] = outputs[0].reshape(1, dimensions); - cv::transpose(outputs[0], outputs[0]); - } - float *data = (float *)outputs[0].data; - - float x_factor = modelInput.cols / modelShape.width; - float y_factor = modelInput.rows / modelShape.height; - - std::vector class_ids; - std::vector confidences; - std::vector boxes; - - for (int i = 0; i < rows; ++i) - { - if (yolov8) - { - float *classes_scores = data+4; - - cv::Mat scores(1, classes.size(), CV_32FC1, classes_scores); - cv::Point class_id; - double maxClassScore; - - minMaxLoc(scores, 0, &maxClassScore, 0, &class_id); - - if (maxClassScore > modelScoreThreshold) - { - confidences.push_back(maxClassScore); - class_ids.push_back(class_id.x); - - float x = data[0]; - float y = data[1]; - float w = data[2]; - float h = data[3]; - - int left = int((x - 0.5 * w) * x_factor); - int top = int((y - 0.5 * h) * y_factor); - - int width = int(w * x_factor); - int height = int(h * y_factor); - - boxes.push_back(cv::Rect(left, top, width, height)); - } - } - else // yolov5 - { - float confidence = data[4]; - - if (confidence >= modelConfidenceThreshold) - { - float *classes_scores = data+5; - - cv::Mat scores(1, classes.size(), CV_32FC1, classes_scores); - cv::Point class_id; - double max_class_score; - - minMaxLoc(scores, 0, &max_class_score, 0, &class_id); - - if (max_class_score > modelScoreThreshold) - { - confidences.push_back(confidence); - class_ids.push_back(class_id.x); - - float x = data[0]; - float y = data[1]; - float w = data[2]; - float h = data[3]; - - int left = int((x - 0.5 * w) * x_factor); - int top = int((y - 0.5 * h) * y_factor); - - int width = int(w * x_factor); - int height = int(h * y_factor); - - boxes.push_back(cv::Rect(left, top, width, height)); - } - } - } - - data += dimensions; - } - - std::vector nms_result; - cv::dnn::NMSBoxes(boxes, confidences, modelScoreThreshold, modelNMSThreshold, nms_result); - - std::vector detections{}; - for (unsigned long i = 0; i < nms_result.size(); ++i) - { - int idx = nms_result[i]; - - Detection result; - result.class_id = class_ids[idx]; - result.confidence = confidences[idx]; - - std::random_device rd; - std::mt19937 gen(rd()); - std::uniform_int_distribution dis(100, 255); - result.color = cv::Scalar(dis(gen), - dis(gen), - dis(gen)); - - result.className = classes[result.class_id]; - result.box = boxes[idx]; - - detections.push_back(result); - } - - return detections; -} - -void Inference::loadClassesFromFile() -{ - std::ifstream inputFile(classesPath); - if (inputFile.is_open()) - { - std::string classLine; - while (std::getline(inputFile, classLine)) - classes.push_back(classLine); - inputFile.close(); - } -} - -void Inference::loadOnnxNetwork() -{ - net = cv::dnn::readNetFromONNX(modelPath); - if (cudaEnabled) - { - std::cout << "\nRunning on CUDA" << std::endl; - net.setPreferableBackend(cv::dnn::DNN_BACKEND_CUDA); - net.setPreferableTarget(cv::dnn::DNN_TARGET_CUDA); - } - else - { - std::cout << "\nRunning on CPU" << std::endl; - net.setPreferableBackend(cv::dnn::DNN_BACKEND_OPENCV); - net.setPreferableTarget(cv::dnn::DNN_TARGET_CPU); - } -} - -cv::Mat Inference::formatToSquare(const cv::Mat &source) -{ - int col = source.cols; - int row = source.rows; - int _max = MAX(col, row); - cv::Mat result = cv::Mat::zeros(_max, _max, CV_8UC3); - source.copyTo(result(cv::Rect(0, 0, col, row))); - return result; -} diff --git a/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.h b/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.h deleted file mode 100644 index dc6149f..0000000 --- a/ultralytics-main/examples/YOLOv8-CPP-Inference/inference.h +++ /dev/null @@ -1,52 +0,0 @@ -#ifndef INFERENCE_H -#define INFERENCE_H - -// Cpp native -#include -#include -#include -#include - -// OpenCV / DNN / Inference -#include -#include -#include - -struct Detection -{ - int class_id{0}; - std::string className{}; - float confidence{0.0}; - cv::Scalar color{}; - cv::Rect box{}; -}; - -class Inference -{ -public: - Inference(const std::string &onnxModelPath, const cv::Size &modelInputShape = {640, 640}, const std::string &classesTxtFile = "", const bool &runWithCuda = true); - std::vector runInference(const cv::Mat &input); - -private: - void loadClassesFromFile(); - void loadOnnxNetwork(); - cv::Mat formatToSquare(const cv::Mat &source); - - std::string modelPath{}; - std::string classesPath{}; - bool cudaEnabled{}; - - std::vector classes{"person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"}; - - cv::Size2f modelShape{}; - - float modelConfidenceThreshold {0.25}; - float modelScoreThreshold {0.45}; - float modelNMSThreshold {0.50}; - - bool letterBoxForSquare = true; - - cv::dnn::Net net; -}; - -#endif // INFERENCE_H diff --git a/ultralytics-main/examples/YOLOv8-CPP-Inference/main.cpp b/ultralytics-main/examples/YOLOv8-CPP-Inference/main.cpp deleted file mode 100644 index 6d1ba98..0000000 --- a/ultralytics-main/examples/YOLOv8-CPP-Inference/main.cpp +++ /dev/null @@ -1,70 +0,0 @@ -#include -#include -#include - -#include - -#include "inference.h" - -using namespace std; -using namespace cv; - -int main(int argc, char **argv) -{ - std::string projectBasePath = "/home/user/ultralytics"; // Set your ultralytics base path - - bool runOnGPU = true; - - // - // Pass in either: - // - // "yolov8s.onnx" or "yolov5s.onnx" - // - // To run Inference with yolov8/yolov5 (ONNX) - // - - // Note that in this example the classes are hard-coded and 'classes.txt' is a place holder. - Inference inf(projectBasePath + "/yolov8s.onnx", cv::Size(640, 480), "classes.txt", runOnGPU); - - std::vector imageNames; - imageNames.push_back(projectBasePath + "/ultralytics/assets/bus.jpg"); - imageNames.push_back(projectBasePath + "/ultralytics/assets/zidane.jpg"); - - for (int i = 0; i < imageNames.size(); ++i) - { - cv::Mat frame = cv::imread(imageNames[i]); - - // Inference starts here... - std::vector output = inf.runInference(frame); - - int detections = output.size(); - std::cout << "Number of detections:" << detections << std::endl; - - for (int i = 0; i < detections; ++i) - { - Detection detection = output[i]; - - cv::Rect box = detection.box; - cv::Scalar color = detection.color; - - // Detection box - cv::rectangle(frame, box, color, 2); - - // Detection box text - std::string classString = detection.className + ' ' + std::to_string(detection.confidence).substr(0, 4); - cv::Size textSize = cv::getTextSize(classString, cv::FONT_HERSHEY_DUPLEX, 1, 2, 0); - cv::Rect textBox(box.x, box.y - 40, textSize.width + 10, textSize.height + 20); - - cv::rectangle(frame, textBox, color, cv::FILLED); - cv::putText(frame, classString, cv::Point(box.x + 5, box.y - 10), cv::FONT_HERSHEY_DUPLEX, 1, cv::Scalar(0, 0, 0), 2, 0); - } - // Inference ends here... - - // This is only for preview purposes - float scale = 0.8; - cv::resize(frame, frame, cv::Size(frame.cols*scale, frame.rows*scale)); - cv::imshow("Inference", frame); - - cv::waitKey(-1); - } -} diff --git a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/CMakeLists.txt b/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/CMakeLists.txt deleted file mode 100644 index 2cbd796..0000000 --- a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/CMakeLists.txt +++ /dev/null @@ -1,47 +0,0 @@ -cmake_minimum_required(VERSION 3.18 FATAL_ERROR) - -project(yolov8_libtorch_example) - -set(CMAKE_CXX_STANDARD 17) -set(CMAKE_CXX_STANDARD_REQUIRED ON) -set(CMAKE_CXX_EXTENSIONS OFF) - - -# -------------- OpenCV -------------- -set(OpenCV_DIR "/path/to/opencv/lib/cmake/opencv4") -find_package(OpenCV REQUIRED) - -message(STATUS "OpenCV library status:") -message(STATUS " config: ${OpenCV_DIR}") -message(STATUS " version: ${OpenCV_VERSION}") -message(STATUS " libraries: ${OpenCV_LIBS}") -message(STATUS " include path: ${OpenCV_INCLUDE_DIRS}") - -include_directories(${OpenCV_INCLUDE_DIRS}) - -# -------------- libtorch -------------- -list(APPEND CMAKE_PREFIX_PATH "/path/to/libtorch") -set(Torch_DIR "/path/to/libtorch/share/cmake/Torch") - -find_package(Torch REQUIRED) -set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}") -message("${TORCH_LIBRARIES}") -message("${TORCH_INCLUDE_DIRS}") - -# The following code block is suggested to be used on Windows. -# According to https://github.com/pytorch/pytorch/issues/25457, -# the DLLs need to be copied to avoid memory errors. -# if (MSVC) -# file(GLOB TORCH_DLLS "${TORCH_INSTALL_PREFIX}/lib/*.dll") -# add_custom_command(TARGET yolov8_libtorch_example -# POST_BUILD -# COMMAND ${CMAKE_COMMAND} -E copy_if_different -# ${TORCH_DLLS} -# $) -# endif (MSVC) - -include_directories(${TORCH_INCLUDE_DIRS}) - -add_executable(yolov8_libtorch_inference "${CMAKE_CURRENT_SOURCE_DIR}/main.cc") -target_link_libraries(yolov8_libtorch_inference ${TORCH_LIBRARIES} ${OpenCV_LIBS}) -set_property(TARGET yolov8_libtorch_inference PROPERTY CXX_STANDARD 17) diff --git a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/README.md b/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/README.md deleted file mode 100644 index 930c3cd..0000000 --- a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/README.md +++ /dev/null @@ -1,35 +0,0 @@ -# YOLOv8 LibTorch Inference C++ - -This example demonstrates how to perform inference using YOLOv8 models in C++ with LibTorch API. - -## Dependencies - -| Dependency | Version | -| ------------ | -------- | -| OpenCV | >=4.0.0 | -| C++ Standard | >=17 | -| Cmake | >=3.18 | -| Libtorch | >=1.12.1 | - -## Usage - -```bash -git clone ultralytics -cd ultralytics -pip install . -cd examples/YOLOv8-LibTorch-CPP-Inference - -mkdir build -cd build -cmake .. -make -./yolov8_libtorch_inference -``` - -## Exporting YOLOv8 - -To export YOLOv8 models: - -```commandline -yolo export model=yolov8s.pt imgsz=640 format=torchscript -``` diff --git a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/main.cc b/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/main.cc deleted file mode 100644 index ebb1a75..0000000 --- a/ultralytics-main/examples/YOLOv8-LibTorch-CPP-Inference/main.cc +++ /dev/null @@ -1,259 +0,0 @@ -#include - -#include -#include -#include -#include -#include - -using torch::indexing::Slice; -using torch::indexing::None; - - -float generate_scale(cv::Mat& image, const std::vector& target_size) { - int origin_w = image.cols; - int origin_h = image.rows; - - int target_h = target_size[0]; - int target_w = target_size[1]; - - float ratio_h = static_cast(target_h) / static_cast(origin_h); - float ratio_w = static_cast(target_w) / static_cast(origin_w); - float resize_scale = std::min(ratio_h, ratio_w); - return resize_scale; -} - - -float letterbox(cv::Mat &input_image, cv::Mat &output_image, const std::vector &target_size) { - if (input_image.cols == target_size[1] && input_image.rows == target_size[0]) { - if (input_image.data == output_image.data) { - return 1.; - } else { - output_image = input_image.clone(); - return 1.; - } - } - - float resize_scale = generate_scale(input_image, target_size); - int new_shape_w = std::round(input_image.cols * resize_scale); - int new_shape_h = std::round(input_image.rows * resize_scale); - float padw = (target_size[1] - new_shape_w) / 2.; - float padh = (target_size[0] - new_shape_h) / 2.; - - int top = std::round(padh - 0.1); - int bottom = std::round(padh + 0.1); - int left = std::round(padw - 0.1); - int right = std::round(padw + 0.1); - - cv::resize(input_image, output_image, - cv::Size(new_shape_w, new_shape_h), - 0, 0, cv::INTER_AREA); - - cv::copyMakeBorder(output_image, output_image, top, bottom, left, right, - cv::BORDER_CONSTANT, cv::Scalar(114.)); - return resize_scale; -} - - -torch::Tensor xyxy2xywh(const torch::Tensor& x) { - auto y = torch::empty_like(x); - y.index_put_({"...", 0}, (x.index({"...", 0}) + x.index({"...", 2})).div(2)); - y.index_put_({"...", 1}, (x.index({"...", 1}) + x.index({"...", 3})).div(2)); - y.index_put_({"...", 2}, x.index({"...", 2}) - x.index({"...", 0})); - y.index_put_({"...", 3}, x.index({"...", 3}) - x.index({"...", 1})); - return y; -} - - -torch::Tensor xywh2xyxy(const torch::Tensor& x) { - auto y = torch::empty_like(x); - auto dw = x.index({"...", 2}).div(2); - auto dh = x.index({"...", 3}).div(2); - y.index_put_({"...", 0}, x.index({"...", 0}) - dw); - y.index_put_({"...", 1}, x.index({"...", 1}) - dh); - y.index_put_({"...", 2}, x.index({"...", 0}) + dw); - y.index_put_({"...", 3}, x.index({"...", 1}) + dh); - return y; -} - - -// Reference: https://github.com/pytorch/vision/blob/main/torchvision/csrc/ops/cpu/nms_kernel.cpp -torch::Tensor nms(const torch::Tensor& bboxes, const torch::Tensor& scores, float iou_threshold) { - if (bboxes.numel() == 0) - return torch::empty({0}, bboxes.options().dtype(torch::kLong)); - - auto x1_t = bboxes.select(1, 0).contiguous(); - auto y1_t = bboxes.select(1, 1).contiguous(); - auto x2_t = bboxes.select(1, 2).contiguous(); - auto y2_t = bboxes.select(1, 3).contiguous(); - - torch::Tensor areas_t = (x2_t - x1_t) * (y2_t - y1_t); - - auto order_t = std::get<1>( - scores.sort(/*stable=*/true, /*dim=*/0, /* descending=*/true)); - - auto ndets = bboxes.size(0); - torch::Tensor suppressed_t = torch::zeros({ndets}, bboxes.options().dtype(torch::kByte)); - torch::Tensor keep_t = torch::zeros({ndets}, bboxes.options().dtype(torch::kLong)); - - auto suppressed = suppressed_t.data_ptr(); - auto keep = keep_t.data_ptr(); - auto order = order_t.data_ptr(); - auto x1 = x1_t.data_ptr(); - auto y1 = y1_t.data_ptr(); - auto x2 = x2_t.data_ptr(); - auto y2 = y2_t.data_ptr(); - auto areas = areas_t.data_ptr(); - - int64_t num_to_keep = 0; - - for (int64_t _i = 0; _i < ndets; _i++) { - auto i = order[_i]; - if (suppressed[i] == 1) - continue; - keep[num_to_keep++] = i; - auto ix1 = x1[i]; - auto iy1 = y1[i]; - auto ix2 = x2[i]; - auto iy2 = y2[i]; - auto iarea = areas[i]; - - for (int64_t _j = _i + 1; _j < ndets; _j++) { - auto j = order[_j]; - if (suppressed[j] == 1) - continue; - auto xx1 = std::max(ix1, x1[j]); - auto yy1 = std::max(iy1, y1[j]); - auto xx2 = std::min(ix2, x2[j]); - auto yy2 = std::min(iy2, y2[j]); - - auto w = std::max(static_cast(0), xx2 - xx1); - auto h = std::max(static_cast(0), yy2 - yy1); - auto inter = w * h; - auto ovr = inter / (iarea + areas[j] - inter); - if (ovr > iou_threshold) - suppressed[j] = 1; - } - } - return keep_t.narrow(0, 0, num_to_keep); -} - - -torch::Tensor non_max_supperession(torch::Tensor& prediction, float conf_thres = 0.25, float iou_thres = 0.45, int max_det = 300) { - auto bs = prediction.size(0); - auto nc = prediction.size(1) - 4; - auto nm = prediction.size(1) - nc - 4; - auto mi = 4 + nc; - auto xc = prediction.index({Slice(), Slice(4, mi)}).amax(1) > conf_thres; - - prediction = prediction.transpose(-1, -2); - prediction.index_put_({"...", Slice({None, 4})}, xywh2xyxy(prediction.index({"...", Slice(None, 4)}))); - - std::vector output; - for (int i = 0; i < bs; i++) { - output.push_back(torch::zeros({0, 6 + nm}, prediction.device())); - } - - for (int xi = 0; xi < prediction.size(0); xi++) { - auto x = prediction[xi]; - x = x.index({xc[xi]}); - auto x_split = x.split({4, nc, nm}, 1); - auto box = x_split[0], cls = x_split[1], mask = x_split[2]; - auto [conf, j] = cls.max(1, true); - x = torch::cat({box, conf, j.toType(torch::kFloat), mask}, 1); - x = x.index({conf.view(-1) > conf_thres}); - int n = x.size(0); - if (!n) { continue; } - - // NMS - auto c = x.index({Slice(), Slice{5, 6}}) * 7680; - auto boxes = x.index({Slice(), Slice(None, 4)}) + c; - auto scores = x.index({Slice(), 4}); - auto i = nms(boxes, scores, iou_thres); - i = i.index({Slice(None, max_det)}); - output[xi] = x.index({i}); - } - - return torch::stack(output); -} - - -torch::Tensor clip_boxes(torch::Tensor& boxes, const std::vector& shape) { - boxes.index_put_({"...", 0}, boxes.index({"...", 0}).clamp(0, shape[1])); - boxes.index_put_({"...", 1}, boxes.index({"...", 1}).clamp(0, shape[0])); - boxes.index_put_({"...", 2}, boxes.index({"...", 2}).clamp(0, shape[1])); - boxes.index_put_({"...", 3}, boxes.index({"...", 3}).clamp(0, shape[0])); - return boxes; -} - - -torch::Tensor scale_boxes(const std::vector& img1_shape, torch::Tensor& boxes, const std::vector& img0_shape) { - auto gain = (std::min)((float)img1_shape[0] / img0_shape[0], (float)img1_shape[1] / img0_shape[1]); - auto pad0 = std::round((float)(img1_shape[1] - img0_shape[1] * gain) / 2. - 0.1); - auto pad1 = std::round((float)(img1_shape[0] - img0_shape[0] * gain) / 2. - 0.1); - - boxes.index_put_({"...", 0}, boxes.index({"...", 0}) - pad0); - boxes.index_put_({"...", 2}, boxes.index({"...", 2}) - pad0); - boxes.index_put_({"...", 1}, boxes.index({"...", 1}) - pad1); - boxes.index_put_({"...", 3}, boxes.index({"...", 3}) - pad1); - boxes.index_put_({"...", Slice(None, 4)}, boxes.index({"...", Slice(None, 4)}).div(gain)); - return boxes; -} - - -int main() { - // Device - torch::Device device(torch::cuda::is_available() ? torch::kCUDA :torch::kCPU); - - // Note that in this example the classes are hard-coded - std::vector classes {"person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", - "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", - "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", - "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", - "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", - "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", - "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"}; - - try { - // Load the model (e.g. yolov8s.torchscript) - std::string model_path = "/path/to/yolov8s.torchscript"; - torch::jit::script::Module yolo_model; - yolo_model = torch::jit::load(model_path); - yolo_model.eval(); - yolo_model.to(device, torch::kFloat32); - - // Load image and preprocess - cv::Mat image = cv::imread("/path/to/bus.jpg"); - cv::Mat input_image; - letterbox(image, input_image, {640, 640}); - - torch::Tensor image_tensor = torch::from_blob(input_image.data, {input_image.rows, input_image.cols, 3}, torch::kByte).to(device); - image_tensor = image_tensor.toType(torch::kFloat32).div(255); - image_tensor = image_tensor.permute({2, 0, 1}); - image_tensor = image_tensor.unsqueeze(0); - std::vector inputs {image_tensor}; - - // Inference - torch::Tensor output = yolo_model.forward(inputs).toTensor().cpu(); - - // NMS - auto keep = non_max_supperession(output)[0]; - auto boxes = keep.index({Slice(), Slice(None, 4)}); - keep.index_put_({Slice(), Slice(None, 4)}, scale_boxes({input_image.rows, input_image.cols}, boxes, {image.rows, image.cols})); - - // Show the results - for (int i = 0; i < keep.size(0); i++) { - int x1 = keep[i][0].item().toFloat(); - int y1 = keep[i][1].item().toFloat(); - int x2 = keep[i][2].item().toFloat(); - int y2 = keep[i][3].item().toFloat(); - float conf = keep[i][4].item().toFloat(); - int cls = keep[i][5].item().toInt(); - std::cout << "Rect: [" << x1 << "," << y1 << "," << x2 << "," << y2 << "] Conf: " << conf << " Class: " << classes[cls] << std::endl; - } - } catch (const c10::Error& e) { - std::cout << e.msg() << std::endl; - } - - return 0; -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/CMakeLists.txt b/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/CMakeLists.txt deleted file mode 100644 index 86232cc..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/CMakeLists.txt +++ /dev/null @@ -1,96 +0,0 @@ -cmake_minimum_required(VERSION 3.5) - -set(PROJECT_NAME Yolov8OnnxRuntimeCPPInference) -project(${PROJECT_NAME} VERSION 0.0.1 LANGUAGES CXX) - - -# -------------- Support C++17 for using filesystem ------------------# -set(CMAKE_CXX_STANDARD 17) -set(CMAKE_CXX_STANDARD_REQUIRED ON) -set(CMAKE_CXX_EXTENSIONS ON) -set(CMAKE_INCLUDE_CURRENT_DIR ON) - - -# -------------- OpenCV ------------------# -find_package(OpenCV REQUIRED) -include_directories(${OpenCV_INCLUDE_DIRS}) - - -# -------------- Compile CUDA for FP16 inference if needed ------------------# -option(USE_CUDA "Enable CUDA support" ON) -if (NOT APPLE AND USE_CUDA) - find_package(CUDA REQUIRED) - include_directories(${CUDA_INCLUDE_DIRS}) - add_definitions(-DUSE_CUDA) -else () - set(USE_CUDA OFF) -endif () - -# -------------- ONNXRUNTIME ------------------# - -# Set ONNXRUNTIME_VERSION -set(ONNXRUNTIME_VERSION 1.15.1) - -if (WIN32) - if (USE_CUDA) - set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-win-x64-gpu-${ONNXRUNTIME_VERSION}") - else () - set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-win-x64-${ONNXRUNTIME_VERSION}") - endif () -elseif (LINUX) - if (USE_CUDA) - set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-linux-x64-gpu-${ONNXRUNTIME_VERSION}") - else () - set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-linux-x64-${ONNXRUNTIME_VERSION}") - endif () -elseif (APPLE) - set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-arm64-${ONNXRUNTIME_VERSION}") - # Apple X64 binary - # set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-x64-${ONNXRUNTIME_VERSION}") - # Apple Universal binary - # set(ONNXRUNTIME_ROOT "${CMAKE_CURRENT_SOURCE_DIR}/onnxruntime-osx-universal2-${ONNXRUNTIME_VERSION}") -endif () - -include_directories(${PROJECT_NAME} ${ONNXRUNTIME_ROOT}/include) - -set(PROJECT_SOURCES - main.cpp - inference.h - inference.cpp -) - -add_executable(${PROJECT_NAME} ${PROJECT_SOURCES}) - -if (WIN32) - target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/onnxruntime.lib) - if (USE_CUDA) - target_link_libraries(${PROJECT_NAME} ${CUDA_LIBRARIES}) - endif () -elseif (LINUX) - target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/libonnxruntime.so) - if (USE_CUDA) - target_link_libraries(${PROJECT_NAME} ${CUDA_LIBRARIES}) - endif () -elseif (APPLE) - target_link_libraries(${PROJECT_NAME} ${OpenCV_LIBS} ${ONNXRUNTIME_ROOT}/lib/libonnxruntime.dylib) -endif () - -# For windows system, copy onnxruntime.dll to the same folder of the executable file -if (WIN32) - add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD - COMMAND ${CMAKE_COMMAND} -E copy_if_different - "${ONNXRUNTIME_ROOT}/lib/onnxruntime.dll" - $) -endif () - -# Download https://raw.githubusercontent.com/ultralytics/ultralytics/main/ultralytics/cfg/datasets/coco.yaml -# and put it in the same folder of the executable file -configure_file(coco.yaml ${CMAKE_CURRENT_BINARY_DIR}/coco.yaml COPYONLY) - -# Copy yolov8n.onnx file to the same folder of the executable file -configure_file(yolov8n.onnx ${CMAKE_CURRENT_BINARY_DIR}/yolov8n.onnx COPYONLY) - -# Create folder name images in the same folder of the executable file -add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD - COMMAND ${CMAKE_COMMAND} -E make_directory ${CMAKE_CURRENT_BINARY_DIR}/images -) diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/README.md b/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/README.md deleted file mode 100644 index 1cb6eb3..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/README.md +++ /dev/null @@ -1,107 +0,0 @@ -# YOLOv8 OnnxRuntime C++ - -C++ Onnx-runtime - -This example demonstrates how to perform inference using YOLOv8 in C++ with ONNX Runtime and OpenCV's API. - -## Benefits ✨ - -- Friendly for deployment in the industrial sector. -- Faster than OpenCV's DNN inference on both CPU and GPU. -- Supports FP32 and FP16 CUDA acceleration. - -## Note ☕ - -1. Benefit for Ultralytics' latest release, a `Transpose` op is added to the YOLOv8 model, while make v8 and v5 has the same output shape. Therefore, you can run inference with YOLOv5/v7/v8 via this project. - -## Exporting YOLOv8 Models 📦 - -To export YOLOv8 models, use the following Python script: - -```python -from ultralytics import YOLO - -# Load a YOLOv8 model -model = YOLO("yolov8n.pt") - -# Export the model -model.export(format="onnx", opset=12, simplify=True, dynamic=False, imgsz=640) -``` - -Alternatively, you can use the following command for exporting the model in the terminal - -```bash -yolo export model=yolov8n.pt opset=12 simplify=True dynamic=False format=onnx imgsz=640,640 -``` - -## Exporting YOLOv8 FP16 Models 📦 - -```python -import onnx -from onnxconverter_common import float16 - -model = onnx.load(R'YOUR_ONNX_PATH') -model_fp16 = float16.convert_float_to_float16(model) -onnx.save(model_fp16, R'YOUR_FP16_ONNX_PATH') -``` - -## Download COCO.yaml file 📂 - -In order to run example, you also need to download coco.yaml. You can download the file manually from [here](https://raw.githubusercontent.com/ultralytics/ultralytics/main/ultralytics/cfg/datasets/coco.yaml) - -## Dependencies ⚙️ - -| Dependency | Version | -| -------------------------------- | -------------- | -| Onnxruntime(linux,windows,macos) | >=1.14.1 | -| OpenCV | >=4.0.0 | -| C++ Standard | >=17 | -| Cmake | >=3.5 | -| Cuda (Optional) | >=11.4 \<12.0 | -| cuDNN (Cuda required) | =8 | - -Note: The dependency on C++17 is due to the usage of the C++17 filesystem feature. - -Note (2): Due to ONNX Runtime, we need to use CUDA 11 and cuDNN 8. Keep in mind that this requirement might change in the future. - -## Build 🛠️ - -1. Clone the repository to your local machine. - -2. Navigate to the root directory of the repository. - -3. Create a build directory and navigate to it: - - ```console - mkdir build && cd build - ``` - -4. Run CMake to generate the build files: - - ```console - cmake .. - ``` - -5. Build the project: - - ```console - make - ``` - -6. The built executable should now be located in the `build` directory. - -## Usage 🚀 - -```c++ -//change your param as you like -//Pay attention to your device and the onnx model type(fp32 or fp16) -DL_INIT_PARAM params; -params.rectConfidenceThreshold = 0.1; -params.iouThreshold = 0.5; -params.modelPath = "yolov8n.onnx"; -params.imgSize = { 640, 640 }; -params.cudaEnable = true; -params.modelType = YOLO_DETECT_V8; -yoloDetector->CreateSession(params); -Detector(yoloDetector); -``` diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.cpp b/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.cpp deleted file mode 100644 index 0bf07de..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.cpp +++ /dev/null @@ -1,363 +0,0 @@ -#include "inference.h" -#include - -#define benchmark -#define min(a,b) (((a) < (b)) ? (a) : (b)) -YOLO_V8::YOLO_V8() { - -} - - -YOLO_V8::~YOLO_V8() { - delete session; -} - -#ifdef USE_CUDA -namespace Ort -{ - template<> - struct TypeToTensorType { static constexpr ONNXTensorElementDataType type = ONNX_TENSOR_ELEMENT_DATA_TYPE_FLOAT16; }; -} -#endif - - -template -char* BlobFromImage(cv::Mat& iImg, T& iBlob) { - int channels = iImg.channels(); - int imgHeight = iImg.rows; - int imgWidth = iImg.cols; - - for (int c = 0; c < channels; c++) - { - for (int h = 0; h < imgHeight; h++) - { - for (int w = 0; w < imgWidth; w++) - { - iBlob[c * imgWidth * imgHeight + h * imgWidth + w] = typename std::remove_pointer::type( - (iImg.at(h, w)[c]) / 255.0f); - } - } - } - return RET_OK; -} - - -char* YOLO_V8::PreProcess(cv::Mat& iImg, std::vector iImgSize, cv::Mat& oImg) -{ - if (iImg.channels() == 3) - { - oImg = iImg.clone(); - cv::cvtColor(oImg, oImg, cv::COLOR_BGR2RGB); - } - else - { - cv::cvtColor(iImg, oImg, cv::COLOR_GRAY2RGB); - } - - switch (modelType) - { - case YOLO_DETECT_V8: - case YOLO_POSE: - case YOLO_DETECT_V8_HALF: - case YOLO_POSE_V8_HALF://LetterBox - { - if (iImg.cols >= iImg.rows) - { - resizeScales = iImg.cols / (float)iImgSize.at(0); - cv::resize(oImg, oImg, cv::Size(iImgSize.at(0), int(iImg.rows / resizeScales))); - } - else - { - resizeScales = iImg.rows / (float)iImgSize.at(0); - cv::resize(oImg, oImg, cv::Size(int(iImg.cols / resizeScales), iImgSize.at(1))); - } - cv::Mat tempImg = cv::Mat::zeros(iImgSize.at(0), iImgSize.at(1), CV_8UC3); - oImg.copyTo(tempImg(cv::Rect(0, 0, oImg.cols, oImg.rows))); - oImg = tempImg; - break; - } - case YOLO_CLS://CenterCrop - { - int h = iImg.rows; - int w = iImg.cols; - int m = min(h, w); - int top = (h - m) / 2; - int left = (w - m) / 2; - cv::resize(oImg(cv::Rect(left, top, m, m)), oImg, cv::Size(iImgSize.at(0), iImgSize.at(1))); - break; - } - } - return RET_OK; -} - - -char* YOLO_V8::CreateSession(DL_INIT_PARAM& iParams) { - char* Ret = RET_OK; - std::regex pattern("[\u4e00-\u9fa5]"); - bool result = std::regex_search(iParams.modelPath, pattern); - if (result) - { - Ret = "[YOLO_V8]:Your model path is error.Change your model path without chinese characters."; - std::cout << Ret << std::endl; - return Ret; - } - try - { - rectConfidenceThreshold = iParams.rectConfidenceThreshold; - iouThreshold = iParams.iouThreshold; - imgSize = iParams.imgSize; - modelType = iParams.modelType; - env = Ort::Env(ORT_LOGGING_LEVEL_WARNING, "Yolo"); - Ort::SessionOptions sessionOption; - if (iParams.cudaEnable) - { - cudaEnable = iParams.cudaEnable; - OrtCUDAProviderOptions cudaOption; - cudaOption.device_id = 0; - sessionOption.AppendExecutionProvider_CUDA(cudaOption); - } - sessionOption.SetGraphOptimizationLevel(GraphOptimizationLevel::ORT_ENABLE_ALL); - sessionOption.SetIntraOpNumThreads(iParams.intraOpNumThreads); - sessionOption.SetLogSeverityLevel(iParams.logSeverityLevel); - -#ifdef _WIN32 - int ModelPathSize = MultiByteToWideChar(CP_UTF8, 0, iParams.modelPath.c_str(), static_cast(iParams.modelPath.length()), nullptr, 0); - wchar_t* wide_cstr = new wchar_t[ModelPathSize + 1]; - MultiByteToWideChar(CP_UTF8, 0, iParams.modelPath.c_str(), static_cast(iParams.modelPath.length()), wide_cstr, ModelPathSize); - wide_cstr[ModelPathSize] = L'\0'; - const wchar_t* modelPath = wide_cstr; -#else - const char* modelPath = iParams.modelPath.c_str(); -#endif // _WIN32 - - session = new Ort::Session(env, modelPath, sessionOption); - Ort::AllocatorWithDefaultOptions allocator; - size_t inputNodesNum = session->GetInputCount(); - for (size_t i = 0; i < inputNodesNum; i++) - { - Ort::AllocatedStringPtr input_node_name = session->GetInputNameAllocated(i, allocator); - char* temp_buf = new char[50]; - strcpy(temp_buf, input_node_name.get()); - inputNodeNames.push_back(temp_buf); - } - size_t OutputNodesNum = session->GetOutputCount(); - for (size_t i = 0; i < OutputNodesNum; i++) - { - Ort::AllocatedStringPtr output_node_name = session->GetOutputNameAllocated(i, allocator); - char* temp_buf = new char[10]; - strcpy(temp_buf, output_node_name.get()); - outputNodeNames.push_back(temp_buf); - } - options = Ort::RunOptions{ nullptr }; - WarmUpSession(); - return RET_OK; - } - catch (const std::exception& e) - { - const char* str1 = "[YOLO_V8]:"; - const char* str2 = e.what(); - std::string result = std::string(str1) + std::string(str2); - char* merged = new char[result.length() + 1]; - std::strcpy(merged, result.c_str()); - std::cout << merged << std::endl; - delete[] merged; - return "[YOLO_V8]:Create session failed."; - } - -} - - -char* YOLO_V8::RunSession(cv::Mat& iImg, std::vector& oResult) { -#ifdef benchmark - clock_t starttime_1 = clock(); -#endif // benchmark - - char* Ret = RET_OK; - cv::Mat processedImg; - PreProcess(iImg, imgSize, processedImg); - if (modelType < 4) - { - float* blob = new float[processedImg.total() * 3]; - BlobFromImage(processedImg, blob); - std::vector inputNodeDims = { 1, 3, imgSize.at(0), imgSize.at(1) }; - TensorProcess(starttime_1, iImg, blob, inputNodeDims, oResult); - } - else - { -#ifdef USE_CUDA - half* blob = new half[processedImg.total() * 3]; - BlobFromImage(processedImg, blob); - std::vector inputNodeDims = { 1,3,imgSize.at(0),imgSize.at(1) }; - TensorProcess(starttime_1, iImg, blob, inputNodeDims, oResult); -#endif - } - - return Ret; -} - - -template -char* YOLO_V8::TensorProcess(clock_t& starttime_1, cv::Mat& iImg, N& blob, std::vector& inputNodeDims, - std::vector& oResult) { - Ort::Value inputTensor = Ort::Value::CreateTensor::type>( - Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1), - inputNodeDims.data(), inputNodeDims.size()); -#ifdef benchmark - clock_t starttime_2 = clock(); -#endif // benchmark - auto outputTensor = session->Run(options, inputNodeNames.data(), &inputTensor, 1, outputNodeNames.data(), - outputNodeNames.size()); -#ifdef benchmark - clock_t starttime_3 = clock(); -#endif // benchmark - - Ort::TypeInfo typeInfo = outputTensor.front().GetTypeInfo(); - auto tensor_info = typeInfo.GetTensorTypeAndShapeInfo(); - std::vector outputNodeDims = tensor_info.GetShape(); - auto output = outputTensor.front().GetTensorMutableData::type>(); - delete[] blob; - switch (modelType) - { - case YOLO_DETECT_V8: - case YOLO_DETECT_V8_HALF: - { - int strideNum = outputNodeDims[1];//8400 - int signalResultNum = outputNodeDims[2];//84 - std::vector class_ids; - std::vector confidences; - std::vector boxes; - cv::Mat rawData; - if (modelType == YOLO_DETECT_V8) - { - // FP32 - rawData = cv::Mat(strideNum, signalResultNum, CV_32F, output); - } - else - { - // FP16 - rawData = cv::Mat(strideNum, signalResultNum, CV_16F, output); - rawData.convertTo(rawData, CV_32F); - } - //Note: - //ultralytics add transpose operator to the output of yolov8 model.which make yolov8/v5/v7 has same shape - //https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt - //rowData = rowData.t(); - - float* data = (float*)rawData.data; - - for (int i = 0; i < strideNum; ++i) - { - float* classesScores = data + 4; - cv::Mat scores(1, this->classes.size(), CV_32FC1, classesScores); - cv::Point class_id; - double maxClassScore; - cv::minMaxLoc(scores, 0, &maxClassScore, 0, &class_id); - if (maxClassScore > rectConfidenceThreshold) - { - confidences.push_back(maxClassScore); - class_ids.push_back(class_id.x); - float x = data[0]; - float y = data[1]; - float w = data[2]; - float h = data[3]; - - int left = int((x - 0.5 * w) * resizeScales); - int top = int((y - 0.5 * h) * resizeScales); - - int width = int(w * resizeScales); - int height = int(h * resizeScales); - - boxes.push_back(cv::Rect(left, top, width, height)); - } - data += signalResultNum; - } - std::vector nmsResult; - cv::dnn::NMSBoxes(boxes, confidences, rectConfidenceThreshold, iouThreshold, nmsResult); - for (int i = 0; i < nmsResult.size(); ++i) - { - int idx = nmsResult[i]; - DL_RESULT result; - result.classId = class_ids[idx]; - result.confidence = confidences[idx]; - result.box = boxes[idx]; - oResult.push_back(result); - } - -#ifdef benchmark - clock_t starttime_4 = clock(); - double pre_process_time = (double)(starttime_2 - starttime_1) / CLOCKS_PER_SEC * 1000; - double process_time = (double)(starttime_3 - starttime_2) / CLOCKS_PER_SEC * 1000; - double post_process_time = (double)(starttime_4 - starttime_3) / CLOCKS_PER_SEC * 1000; - if (cudaEnable) - { - std::cout << "[YOLO_V8(CUDA)]: " << pre_process_time << "ms pre-process, " << process_time << "ms inference, " << post_process_time << "ms post-process." << std::endl; - } - else - { - std::cout << "[YOLO_V8(CPU)]: " << pre_process_time << "ms pre-process, " << process_time << "ms inference, " << post_process_time << "ms post-process." << std::endl; - } -#endif // benchmark - - break; - } - case YOLO_CLS: - { - DL_RESULT result; - for (int i = 0; i < this->classes.size(); i++) - { - result.classId = i; - result.confidence = output[i]; - oResult.push_back(result); - } - break; - } - default: - std::cout << "[YOLO_V8]: " << "Not support model type." << std::endl; - } - return RET_OK; - -} - - -char* YOLO_V8::WarmUpSession() { - clock_t starttime_1 = clock(); - cv::Mat iImg = cv::Mat(cv::Size(imgSize.at(0), imgSize.at(1)), CV_8UC3); - cv::Mat processedImg; - PreProcess(iImg, imgSize, processedImg); - if (modelType < 4) - { - float* blob = new float[iImg.total() * 3]; - BlobFromImage(processedImg, blob); - std::vector YOLO_input_node_dims = { 1, 3, imgSize.at(0), imgSize.at(1) }; - Ort::Value input_tensor = Ort::Value::CreateTensor( - Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1), - YOLO_input_node_dims.data(), YOLO_input_node_dims.size()); - auto output_tensors = session->Run(options, inputNodeNames.data(), &input_tensor, 1, outputNodeNames.data(), - outputNodeNames.size()); - delete[] blob; - clock_t starttime_4 = clock(); - double post_process_time = (double)(starttime_4 - starttime_1) / CLOCKS_PER_SEC * 1000; - if (cudaEnable) - { - std::cout << "[YOLO_V8(CUDA)]: " << "Cuda warm-up cost " << post_process_time << " ms. " << std::endl; - } - } - else - { -#ifdef USE_CUDA - half* blob = new half[iImg.total() * 3]; - BlobFromImage(processedImg, blob); - std::vector YOLO_input_node_dims = { 1,3,imgSize.at(0),imgSize.at(1) }; - Ort::Value input_tensor = Ort::Value::CreateTensor(Ort::MemoryInfo::CreateCpu(OrtDeviceAllocator, OrtMemTypeCPU), blob, 3 * imgSize.at(0) * imgSize.at(1), YOLO_input_node_dims.data(), YOLO_input_node_dims.size()); - auto output_tensors = session->Run(options, inputNodeNames.data(), &input_tensor, 1, outputNodeNames.data(), outputNodeNames.size()); - delete[] blob; - clock_t starttime_4 = clock(); - double post_process_time = (double)(starttime_4 - starttime_1) / CLOCKS_PER_SEC * 1000; - if (cudaEnable) - { - std::cout << "[YOLO_V8(CUDA)]: " << "Cuda warm-up cost " << post_process_time << " ms. " << std::endl; - } -#endif - } - return RET_OK; -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.h b/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.h deleted file mode 100644 index 3174ae9..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/inference.h +++ /dev/null @@ -1,93 +0,0 @@ -#pragma once - -#define RET_OK nullptr - -#ifdef _WIN32 -#include -#include -#include -#endif - -#include -#include -#include -#include -#include "onnxruntime_cxx_api.h" - -#ifdef USE_CUDA -#include -#endif - - -enum MODEL_TYPE -{ - //FLOAT32 MODEL - YOLO_DETECT_V8 = 1, - YOLO_POSE = 2, - YOLO_CLS = 3, - - //FLOAT16 MODEL - YOLO_DETECT_V8_HALF = 4, - YOLO_POSE_V8_HALF = 5, -}; - - -typedef struct _DL_INIT_PARAM -{ - std::string modelPath; - MODEL_TYPE modelType = YOLO_DETECT_V8; - std::vector imgSize = { 640, 640 }; - float rectConfidenceThreshold = 0.6; - float iouThreshold = 0.5; - int keyPointsNum = 2;//Note:kpt number for pose - bool cudaEnable = false; - int logSeverityLevel = 3; - int intraOpNumThreads = 1; -} DL_INIT_PARAM; - - -typedef struct _DL_RESULT -{ - int classId; - float confidence; - cv::Rect box; - std::vector keyPoints; -} DL_RESULT; - - -class YOLO_V8 -{ -public: - YOLO_V8(); - - ~YOLO_V8(); - -public: - char* CreateSession(DL_INIT_PARAM& iParams); - - char* RunSession(cv::Mat& iImg, std::vector& oResult); - - char* WarmUpSession(); - - template - char* TensorProcess(clock_t& starttime_1, cv::Mat& iImg, N& blob, std::vector& inputNodeDims, - std::vector& oResult); - - char* PreProcess(cv::Mat& iImg, std::vector iImgSize, cv::Mat& oImg); - - std::vector classes{}; - -private: - Ort::Env env; - Ort::Session* session; - bool cudaEnable; - Ort::RunOptions options; - std::vector inputNodeNames; - std::vector outputNodeNames; - - MODEL_TYPE modelType; - std::vector imgSize; - float rectConfidenceThreshold; - float iouThreshold; - float resizeScales;//letterbox scale -}; diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/main.cpp b/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/main.cpp deleted file mode 100644 index 6e4ef1d..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-CPP/main.cpp +++ /dev/null @@ -1,193 +0,0 @@ -#include -#include -#include "inference.h" -#include -#include -#include - -void Detector(YOLO_V8*& p) { - std::filesystem::path current_path = std::filesystem::current_path(); - std::filesystem::path imgs_path = current_path / "images"; - for (auto& i : std::filesystem::directory_iterator(imgs_path)) - { - if (i.path().extension() == ".jpg" || i.path().extension() == ".png" || i.path().extension() == ".jpeg") - { - std::string img_path = i.path().string(); - cv::Mat img = cv::imread(img_path); - std::vector res; - p->RunSession(img, res); - - for (auto& re : res) - { - cv::RNG rng(cv::getTickCount()); - cv::Scalar color(rng.uniform(0, 256), rng.uniform(0, 256), rng.uniform(0, 256)); - - cv::rectangle(img, re.box, color, 3); - - float confidence = floor(100 * re.confidence) / 100; - std::cout << std::fixed << std::setprecision(2); - std::string label = p->classes[re.classId] + " " + - std::to_string(confidence).substr(0, std::to_string(confidence).size() - 4); - - cv::rectangle( - img, - cv::Point(re.box.x, re.box.y - 25), - cv::Point(re.box.x + label.length() * 15, re.box.y), - color, - cv::FILLED - ); - - cv::putText( - img, - label, - cv::Point(re.box.x, re.box.y - 5), - cv::FONT_HERSHEY_SIMPLEX, - 0.75, - cv::Scalar(0, 0, 0), - 2 - ); - - - } - std::cout << "Press any key to exit" << std::endl; - cv::imshow("Result of Detection", img); - cv::waitKey(0); - cv::destroyAllWindows(); - } - } -} - - -void Classifier(YOLO_V8*& p) -{ - std::filesystem::path current_path = std::filesystem::current_path(); - std::filesystem::path imgs_path = current_path;// / "images" - std::random_device rd; - std::mt19937 gen(rd()); - std::uniform_int_distribution dis(0, 255); - for (auto& i : std::filesystem::directory_iterator(imgs_path)) - { - if (i.path().extension() == ".jpg" || i.path().extension() == ".png") - { - std::string img_path = i.path().string(); - //std::cout << img_path << std::endl; - cv::Mat img = cv::imread(img_path); - std::vector res; - char* ret = p->RunSession(img, res); - - float positionY = 50; - for (int i = 0; i < res.size(); i++) - { - int r = dis(gen); - int g = dis(gen); - int b = dis(gen); - cv::putText(img, std::to_string(i) + ":", cv::Point(10, positionY), cv::FONT_HERSHEY_SIMPLEX, 1, cv::Scalar(b, g, r), 2); - cv::putText(img, std::to_string(res.at(i).confidence), cv::Point(70, positionY), cv::FONT_HERSHEY_SIMPLEX, 1, cv::Scalar(b, g, r), 2); - positionY += 50; - } - - cv::imshow("TEST_CLS", img); - cv::waitKey(0); - cv::destroyAllWindows(); - //cv::imwrite("E:\\output\\" + std::to_string(k) + ".png", img); - } - - } -} - - - -int ReadCocoYaml(YOLO_V8*& p) { - // Open the YAML file - std::ifstream file("coco.yaml"); - if (!file.is_open()) - { - std::cerr << "Failed to open file" << std::endl; - return 1; - } - - // Read the file line by line - std::string line; - std::vector lines; - while (std::getline(file, line)) - { - lines.push_back(line); - } - - // Find the start and end of the names section - std::size_t start = 0; - std::size_t end = 0; - for (std::size_t i = 0; i < lines.size(); i++) - { - if (lines[i].find("names:") != std::string::npos) - { - start = i + 1; - } - else if (start > 0 && lines[i].find(':') == std::string::npos) - { - end = i; - break; - } - } - - // Extract the names - std::vector names; - for (std::size_t i = start; i < end; i++) - { - std::stringstream ss(lines[i]); - std::string name; - std::getline(ss, name, ':'); // Extract the number before the delimiter - std::getline(ss, name); // Extract the string after the delimiter - names.push_back(name); - } - - p->classes = names; - return 0; -} - - -void DetectTest() -{ - YOLO_V8* yoloDetector = new YOLO_V8; - ReadCocoYaml(yoloDetector); - DL_INIT_PARAM params; - params.rectConfidenceThreshold = 0.1; - params.iouThreshold = 0.5; - params.modelPath = "yolov8n.onnx"; - params.imgSize = { 640, 640 }; -#ifdef USE_CUDA - params.cudaEnable = true; - - // GPU FP32 inference - params.modelType = YOLO_DETECT_V8; - // GPU FP16 inference - //Note: change fp16 onnx model - //params.modelType = YOLO_DETECT_V8_HALF; - -#else - // CPU inference - params.modelType = YOLO_DETECT_V8; - params.cudaEnable = false; - -#endif - yoloDetector->CreateSession(params); - Detector(yoloDetector); -} - - -void ClsTest() -{ - YOLO_V8* yoloDetector = new YOLO_V8; - std::string model_path = "cls.onnx"; - ReadCocoYaml(yoloDetector); - DL_INIT_PARAM params{ model_path, YOLO_CLS, {224, 224} }; - yoloDetector->CreateSession(params); - Classifier(yoloDetector); -} - - -int main() -{ - //DetectTest(); - ClsTest(); -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/Cargo.toml b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/Cargo.toml deleted file mode 100644 index 101f72e..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/Cargo.toml +++ /dev/null @@ -1,21 +0,0 @@ -[package] -name = "yolov8-rs" -version = "0.1.0" -edition = "2021" - -# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html - -[dependencies] -clap = { version = "4.2.4", features = ["derive"] } -image = { version = "0.24.7", default-features = false, features = ["jpeg", "png", "webp-encoder"] } -imageproc = { version = "0.23.0", default-features = false } -ndarray = { version = "0.15.6" } -ort = {version = "1.16.3", default-features = false, features = ["load-dynamic", "copy-dylibs", "half"]} -rusttype = { version = "0.9", default-features = false } -anyhow = { version = "1.0.75"} -regex = { version = "1.5.4" } -rand = { version ="0.8.5" } -chrono = { version = "0.4.30" } -half = { version = "2.3.1" } -dirs = { version = "5.0.1" } -ureq = { version = "2.9.1" } diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/README.md b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/README.md deleted file mode 100644 index 8961d9c..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/README.md +++ /dev/null @@ -1,221 +0,0 @@ -# YOLOv8-ONNXRuntime-Rust for All the Key YOLO Tasks - -This repository provides a Rust demo for performing YOLOv8 tasks like `Classification`, `Segmentation`, `Detection` and `Pose Detection` using ONNXRuntime. - -## Features - -- Support `Classification`, `Segmentation`, `Detection`, `Pose(Keypoints)-Detection` tasks. -- Support `FP16` & `FP32` ONNX models. -- Support `CPU`, `CUDA` and `TensorRT` execution provider to accelerate computation. -- Support dynamic input shapes(`batch`, `width`, `height`). - -## Installation - -### 1. Install Rust - -Please follow the Rust official installation. (https://www.rust-lang.org/tools/install) - -### 2. Install ONNXRuntime - -This repository use `ort` crate, which is ONNXRuntime wrapper for Rust. (https://docs.rs/ort/latest/ort/) - -You can follow the instruction with `ort` doc or simply do this: - -- step1: Download ONNXRuntime(https://github.com/microsoft/onnxruntime/releases) -- setp2: Set environment variable `PATH` for linking. - -On ubuntu, You can do like this: - -``` -vim ~/.bashrc - -# Add the path of ONNXRUntime lib -export LD_LIBRARY_PATH=/home/qweasd/Documents/onnxruntime-linux-x64-gpu-1.16.3/lib${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}} - -source ~/.bashrc -``` - -### 3. \[Optional\] Install CUDA & CuDNN & TensorRT - -- CUDA execution provider requires CUDA v11.6+. -- TensorRT execution provider requires CUDA v11.4+ and TensorRT v8.4+. - -## Get Started - -### 1. Export the YOLOv8 ONNX Models - -```bash -pip install -U ultralytics - -# export onnx model with dynamic shapes -yolo export model=yolov8m.pt format=onnx simplify dynamic -yolo export model=yolov8m-cls.pt format=onnx simplify dynamic -yolo export model=yolov8m-pose.pt format=onnx simplify dynamic -yolo export model=yolov8m-seg.pt format=onnx simplify dynamic - - -# export onnx model with constant shapes -yolo export model=yolov8m.pt format=onnx simplify -yolo export model=yolov8m-cls.pt format=onnx simplify -yolo export model=yolov8m-pose.pt format=onnx simplify -yolo export model=yolov8m-seg.pt format=onnx simplify -``` - -### 2. Run Inference - -It will perform inference with the ONNX model on the source image. - -``` -cargo run --release -- --model --source -``` - -Set `--cuda` to use CUDA execution provider to speed up inference. - -``` -cargo run --release -- --cuda --model --source -``` - -Set `--trt` to use TensorRT execution provider, and you can set `--fp16` at the same time to use TensorRT FP16 engine. - -``` -cargo run --release -- --trt --fp16 --model --source -``` - -Set `--device_id` to select which device to run. When you have only one GPU, and you set `device_id` to 1 will not cause program panic, the `ort` would automatically fall back to `CPU` EP. - -``` -cargo run --release -- --cuda --device_id 0 --model --source -``` - -Set `--batch` to do multi-batch-size inference. - -If you're using `--trt`, you can also set `--batch-min` and `--batch-max` to explicitly specify min/max/opt batch for dynamic batch input.(https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html#explicit-shape-range-for-dynamic-shape-input).(Note that the ONNX model should exported with dynamic shapes) - -``` -cargo run --release -- --cuda --batch 2 --model --source -``` - -Set `--height` and `--width` to do dynamic image size inference. (Note that the ONNX model should exported with dynamic shapes) - -``` -cargo run --release -- --cuda --width 480 --height 640 --model --source -``` - -Set `--profile` to check time consumed in each stage.(Note that the model usually needs to take 1~3 times dry run to warmup. Make sure to run enough times to evaluate the result.) - -``` -cargo run --release -- --trt --fp16 --profile --model --source -``` - -Results: (yolov8m.onnx, batch=1, 3 times, trt, fp16, RTX 3060Ti) - -``` -==> 0 -[Model Preprocess]: 12.75788ms -[ORT H2D]: 237.118µs -[ORT Inference]: 507.895469ms -[ORT D2H]: 191.655µs -[Model Inference]: 508.34589ms -[Model Postprocess]: 1.061122ms -==> 1 -[Model Preprocess]: 13.658655ms -[ORT H2D]: 209.975µs -[ORT Inference]: 5.12372ms -[ORT D2H]: 182.389µs -[Model Inference]: 5.530022ms -[Model Postprocess]: 1.04851ms -==> 2 -[Model Preprocess]: 12.475332ms -[ORT H2D]: 246.127µs -[ORT Inference]: 5.048432ms -[ORT D2H]: 187.117µs -[Model Inference]: 5.493119ms -[Model Postprocess]: 1.040906ms -``` - -And also: - -`--conf`: confidence threshold \[default: 0.3\] - -`--iou`: iou threshold in NMS \[default: 0.45\] - -`--kconf`: confidence threshold of keypoint \[default: 0.55\] - -`--plot`: plot inference result with random RGB color and save - -you can check out all CLI arguments by: - -``` -git clone https://github.com/ultralytics/ultralytics -cd ultralytics/examples/YOLOv8-ONNXRuntime-Rust -cargo run --release -- --help -``` - -## Examples - -### Classification - -Running dynamic shape ONNX model on `CPU` with image size `--height 224 --width 224`. Saving plotted image in `runs` directory. - -``` -cargo run --release -- --model ../assets/weights/yolov8m-cls-dyn.onnx --source ../assets/images/dog.jpg --height 224 --width 224 --plot --profile -``` - -You will see result like: - -``` -Summary: -> Task: Classify (Ultralytics 8.0.217) -> EP: Cpu -> Dtype: Float32 -> Batch: 1 (Dynamic), Height: 224 (Dynamic), Width: 224 (Dynamic) -> nc: 1000 nk: 0, nm: 0, conf: 0.3, kconf: 0.55, iou: 0.45 - -[Model Preprocess]: 16.363477ms -[ORT H2D]: 50.722µs -[ORT Inference]: 16.295808ms -[ORT D2H]: 8.37µs -[Model Inference]: 16.367046ms -[Model Postprocess]: 3.527µs -[ - YOLOResult { - Probs(top5): Some([(208, 0.6950566), (209, 0.13823675), (178, 0.04849795), (215, 0.019029364), (212, 0.016506357)]), - Bboxes: None, - Keypoints: None, - Masks: None, - }, -] - -``` - -![2023-11-25-22-02-02-156623351](https://github.com/jamjamjon/ultralytics/assets/51357717/ef75c2ae-c5ab-44cc-9d9e-e60b51e39662) - -### Object Detection - -Using `CUDA` EP and dynamic image size `--height 640 --width 480` - -``` -cargo run --release -- --cuda --model ../assets/weights/yolov8m-dynamic.onnx --source ../assets/images/bus.jpg --plot --height 640 --width 480 -``` - -![det](https://github.com/jamjamjon/ultralytics/assets/51357717/5d89a19d-0c96-4a59-875c-defab6887a2c) - -### Pose Detection - -using `TensorRT` EP - -``` -cargo run --release -- --trt --model ../assets/weights/yolov8m-pose.onnx --source ../assets/images/bus.jpg --plot -``` - -![2023-11-25-22-31-45-127054025](https://github.com/jamjamjon/ultralytics/assets/51357717/157b5ba7-bfcf-47cf-bee7-68b62e0de1c4) - -### Instance Segmentation - -using `TensorRT` EP and FP16 model `--fp16` - -``` -cargo run --release -- --trt --fp16 --model ../assets/weights/yolov8m-seg.onnx --source ../assets/images/0172.jpg --plot -``` - -![seg](https://github.com/jamjamjon/ultralytics/assets/51357717/cf046f4f-9533-478a-adc7-4de22443a641) diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/cli.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/cli.rs deleted file mode 100644 index 2ba0dd4..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/cli.rs +++ /dev/null @@ -1,87 +0,0 @@ -use clap::Parser; - -use crate::YOLOTask; - -#[derive(Parser, Clone)] -#[command(author, version, about, long_about = None)] -pub struct Args { - /// ONNX model path - #[arg(long, required = true)] - pub model: String, - - /// input path - #[arg(long, required = true)] - pub source: String, - - /// device id - #[arg(long, default_value_t = 0)] - pub device_id: u32, - - /// using TensorRT EP - #[arg(long)] - pub trt: bool, - - /// using CUDA EP - #[arg(long)] - pub cuda: bool, - - /// input batch size - #[arg(long, default_value_t = 1)] - pub batch: u32, - - /// trt input min_batch size - #[arg(long, default_value_t = 1)] - pub batch_min: u32, - - /// trt input max_batch size - #[arg(long, default_value_t = 32)] - pub batch_max: u32, - - /// using TensorRT --fp16 - #[arg(long)] - pub fp16: bool, - - /// specify YOLO task - #[arg(long, value_enum)] - pub task: Option, - - /// num_classes - #[arg(long)] - pub nc: Option, - - /// num_keypoints - #[arg(long)] - pub nk: Option, - - /// num_masks - #[arg(long)] - pub nm: Option, - - /// input image width - #[arg(long)] - pub width: Option, - - /// input image height - #[arg(long)] - pub height: Option, - - /// confidence threshold - #[arg(long, required = false, default_value_t = 0.3)] - pub conf: f32, - - /// iou threshold in NMS - #[arg(long, required = false, default_value_t = 0.45)] - pub iou: f32, - - /// confidence threshold of keypoint - #[arg(long, required = false, default_value_t = 0.55)] - pub kconf: f32, - - /// plot inference result and save - #[arg(long)] - pub plot: bool, - - /// check time consumed in each stage - #[arg(long)] - pub profile: bool, -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/lib.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/lib.rs deleted file mode 100644 index 1af7f7c..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/lib.rs +++ /dev/null @@ -1,119 +0,0 @@ -#![allow(clippy::type_complexity)] - -use std::io::{Read, Write}; - -pub mod cli; -pub mod model; -pub mod ort_backend; -pub mod yolo_result; -pub use crate::cli::Args; -pub use crate::model::YOLOv8; -pub use crate::ort_backend::{Batch, OrtBackend, OrtConfig, OrtEP, YOLOTask}; -pub use crate::yolo_result::{Bbox, Embedding, Point2, YOLOResult}; - -pub fn non_max_suppression( - xs: &mut Vec<(Bbox, Option>, Option>)>, - iou_threshold: f32, -) { - xs.sort_by(|b1, b2| b2.0.confidence().partial_cmp(&b1.0.confidence()).unwrap()); - - let mut current_index = 0; - for index in 0..xs.len() { - let mut drop = false; - for prev_index in 0..current_index { - let iou = xs[prev_index].0.iou(&xs[index].0); - if iou > iou_threshold { - drop = true; - break; - } - } - if !drop { - xs.swap(current_index, index); - current_index += 1; - } - } - xs.truncate(current_index); -} - -pub fn gen_time_string(delimiter: &str) -> String { - let offset = chrono::FixedOffset::east_opt(8 * 60 * 60).unwrap(); // Beijing - let t_now = chrono::Utc::now().with_timezone(&offset); - let fmt = format!( - "%Y{}%m{}%d{}%H{}%M{}%S{}%f", - delimiter, delimiter, delimiter, delimiter, delimiter, delimiter - ); - t_now.format(&fmt).to_string() -} - -pub const SKELETON: [(usize, usize); 16] = [ - (0, 1), - (0, 2), - (1, 3), - (2, 4), - (5, 6), - (5, 11), - (6, 12), - (11, 12), - (5, 7), - (6, 8), - (7, 9), - (8, 10), - (11, 13), - (12, 14), - (13, 15), - (14, 16), -]; - -pub fn check_font(font: &str) -> rusttype::Font<'static> { - // check then load font - - // ultralytics font path - let font_path_config = match dirs::config_dir() { - Some(mut d) => { - d.push("Ultralytics"); - d.push(font); - d - } - None => panic!("Unsupported operating system. Now support Linux, MacOS, Windows."), - }; - - // current font path - let font_path_current = std::path::PathBuf::from(font); - - // check font - let font_path = if font_path_config.exists() { - font_path_config - } else if font_path_current.exists() { - font_path_current - } else { - println!("Downloading font..."); - let source_url = "https://ultralytics.com/assets/Arial.ttf"; - let resp = ureq::get(source_url) - .timeout(std::time::Duration::from_secs(500)) - .call() - .unwrap_or_else(|err| panic!("> Failed to download font: {source_url}: {err:?}")); - - // read to buffer - let mut buffer = vec![]; - let total_size = resp - .header("Content-Length") - .and_then(|s| s.parse::().ok()) - .unwrap(); - let _reader = resp - .into_reader() - .take(total_size) - .read_to_end(&mut buffer) - .unwrap(); - - // save - let _path = std::fs::File::create(font).unwrap(); - let mut writer = std::io::BufWriter::new(_path); - writer.write_all(&buffer).unwrap(); - println!("Font saved at: {:?}", font_path_current.display()); - font_path_current - }; - - // load font - let buffer = std::fs::read(font_path).unwrap(); - rusttype::Font::try_from_vec(buffer).unwrap() -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/main.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/main.rs deleted file mode 100644 index 8dd1567..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/main.rs +++ /dev/null @@ -1,28 +0,0 @@ -use clap::Parser; - -use yolov8_rs::{Args, YOLOv8}; - -fn main() -> Result<(), Box> { - let args = Args::parse(); - - // 1. load image - let x = image::io::Reader::open(&args.source)? - .with_guessed_format()? - .decode()?; - - // 2. model support dynamic batch inference, so input should be a Vec - let xs = vec![x]; - - // You can test `--batch 2` with this - // let xs = vec![x.clone(), x]; - - // 3. build yolov8 model - let mut model = YOLOv8::new(args)?; - model.summary(); // model info - - // 4. run - let ys = model.run(&xs)?; - println!("{:?}", ys); - - Ok(()) -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/model.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/model.rs deleted file mode 100644 index 1c0e5e4..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/model.rs +++ /dev/null @@ -1,642 +0,0 @@ -#![allow(clippy::type_complexity)] - -use anyhow::Result; -use image::{DynamicImage, GenericImageView, ImageBuffer}; -use ndarray::{s, Array, Axis, IxDyn}; -use rand::{thread_rng, Rng}; -use std::path::PathBuf; - -use crate::{ - check_font, gen_time_string, non_max_suppression, Args, Batch, Bbox, Embedding, OrtBackend, - OrtConfig, OrtEP, Point2, YOLOResult, YOLOTask, SKELETON, -}; - -pub struct YOLOv8 { - // YOLOv8 model for all yolo-tasks - engine: OrtBackend, - nc: u32, - nk: u32, - nm: u32, - height: u32, - width: u32, - batch: u32, - task: YOLOTask, - conf: f32, - kconf: f32, - iou: f32, - names: Vec, - color_palette: Vec<(u8, u8, u8)>, - profile: bool, - plot: bool, -} - -impl YOLOv8 { - pub fn new(config: Args) -> Result { - // execution provider - let ep = if config.trt { - OrtEP::Trt(config.device_id) - } else if config.cuda { - OrtEP::Cuda(config.device_id) - } else { - OrtEP::Cpu - }; - - // batch - let batch = Batch { - opt: config.batch, - min: config.batch_min, - max: config.batch_max, - }; - - // build ort engine - let ort_args = OrtConfig { - ep, - batch, - f: config.model, - task: config.task, - trt_fp16: config.fp16, - image_size: (config.height, config.width), - }; - let engine = OrtBackend::build(ort_args)?; - - // get batch, height, width, tasks, nc, nk, nm - let (batch, height, width, task) = ( - engine.batch(), - engine.height(), - engine.width(), - engine.task(), - ); - let nc = engine.nc().or(config.nc).unwrap_or_else(|| { - panic!("Failed to get num_classes, make it explicit with `--nc`"); - }); - let (nk, nm) = match task { - YOLOTask::Pose => { - let nk = engine.nk().or(config.nk).unwrap_or_else(|| { - panic!("Failed to get num_keypoints, make it explicit with `--nk`"); - }); - (nk, 0) - } - YOLOTask::Segment => { - let nm = engine.nm().or(config.nm).unwrap_or_else(|| { - panic!("Failed to get num_masks, make it explicit with `--nm`"); - }); - (0, nm) - } - _ => (0, 0), - }; - - // class names - let names = engine.names().unwrap_or(vec!["Unknown".to_string()]); - - // color palette - let mut rng = thread_rng(); - let color_palette: Vec<_> = names - .iter() - .map(|_| { - ( - rng.gen_range(0..=255), - rng.gen_range(0..=255), - rng.gen_range(0..=255), - ) - }) - .collect(); - - Ok(Self { - engine, - names, - conf: config.conf, - kconf: config.kconf, - iou: config.iou, - color_palette, - profile: config.profile, - plot: config.plot, - nc, - nk, - nm, - height, - width, - batch, - task, - }) - } - - pub fn scale_wh(&self, w0: f32, h0: f32, w1: f32, h1: f32) -> (f32, f32, f32) { - let r = (w1 / w0).min(h1 / h0); - (r, (w0 * r).round(), (h0 * r).round()) - } - - pub fn preprocess(&mut self, xs: &Vec) -> Result> { - let mut ys = - Array::ones((xs.len(), 3, self.height() as usize, self.width() as usize)).into_dyn(); - ys.fill(144.0 / 255.0); - for (idx, x) in xs.iter().enumerate() { - let img = match self.task() { - YOLOTask::Classify => x.resize_exact( - self.width(), - self.height(), - image::imageops::FilterType::Triangle, - ), - _ => { - let (w0, h0) = x.dimensions(); - let w0 = w0 as f32; - let h0 = h0 as f32; - let (_, w_new, h_new) = - self.scale_wh(w0, h0, self.width() as f32, self.height() as f32); // f32 round - x.resize_exact( - w_new as u32, - h_new as u32, - if let YOLOTask::Segment = self.task() { - image::imageops::FilterType::CatmullRom - } else { - image::imageops::FilterType::Triangle - }, - ) - } - }; - - for (x, y, rgb) in img.pixels() { - let x = x as usize; - let y = y as usize; - let [r, g, b, _] = rgb.0; - ys[[idx, 0, y, x]] = (r as f32) / 255.0; - ys[[idx, 1, y, x]] = (g as f32) / 255.0; - ys[[idx, 2, y, x]] = (b as f32) / 255.0; - } - } - - Ok(ys) - } - - pub fn run(&mut self, xs: &Vec) -> Result> { - // pre-process - let t_pre = std::time::Instant::now(); - let xs_ = self.preprocess(xs)?; - if self.profile { - println!("[Model Preprocess]: {:?}", t_pre.elapsed()); - } - - // run - let t_run = std::time::Instant::now(); - let ys = self.engine.run(xs_, self.profile)?; - if self.profile { - println!("[Model Inference]: {:?}", t_run.elapsed()); - } - - // post-process - let t_post = std::time::Instant::now(); - let ys = self.postprocess(ys, xs)?; - if self.profile { - println!("[Model Postprocess]: {:?}", t_post.elapsed()); - } - - // plot and save - if self.plot { - self.plot_and_save(&ys, xs, Some(&SKELETON)); - } - Ok(ys) - } - - pub fn postprocess( - &self, - xs: Vec>, - xs0: &[DynamicImage], - ) -> Result> { - if let YOLOTask::Classify = self.task() { - let mut ys = Vec::new(); - let preds = &xs[0]; - for batch in preds.axis_iter(Axis(0)) { - ys.push(YOLOResult::new( - Some(Embedding::new(batch.into_owned())), - None, - None, - None, - )); - } - Ok(ys) - } else { - const CXYWH_OFFSET: usize = 4; // cxcywh - const KPT_STEP: usize = 3; // xyconf - let preds = &xs[0]; - let protos = { - if xs.len() > 1 { - Some(&xs[1]) - } else { - None - } - }; - let mut ys = Vec::new(); - for (idx, anchor) in preds.axis_iter(Axis(0)).enumerate() { - // [bs, 4 + nc + nm, anchors] - // input image - let width_original = xs0[idx].width() as f32; - let height_original = xs0[idx].height() as f32; - let ratio = (self.width() as f32 / width_original) - .min(self.height() as f32 / height_original); - - // save each result - let mut data: Vec<(Bbox, Option>, Option>)> = Vec::new(); - for pred in anchor.axis_iter(Axis(1)) { - // split preds for different tasks - let bbox = pred.slice(s![0..CXYWH_OFFSET]); - let clss = pred.slice(s![CXYWH_OFFSET..CXYWH_OFFSET + self.nc() as usize]); - let kpts = { - if let YOLOTask::Pose = self.task() { - Some(pred.slice(s![pred.len() - KPT_STEP * self.nk() as usize..])) - } else { - None - } - }; - let coefs = { - if let YOLOTask::Segment = self.task() { - Some(pred.slice(s![pred.len() - self.nm() as usize..]).to_vec()) - } else { - None - } - }; - - // confidence and id - let (id, &confidence) = clss - .into_iter() - .enumerate() - .reduce(|max, x| if x.1 > max.1 { x } else { max }) - .unwrap(); // definitely will not panic! - - // confidence filter - if confidence < self.conf { - continue; - } - - // bbox re-scale - let cx = bbox[0] / ratio; - let cy = bbox[1] / ratio; - let w = bbox[2] / ratio; - let h = bbox[3] / ratio; - let x = cx - w / 2.; - let y = cy - h / 2.; - let y_bbox = Bbox::new( - x.max(0.0f32).min(width_original), - y.max(0.0f32).min(height_original), - w, - h, - id, - confidence, - ); - - // kpts - let y_kpts = { - if let Some(kpts) = kpts { - let mut kpts_ = Vec::new(); - // rescale - for i in 0..self.nk() as usize { - let kx = kpts[KPT_STEP * i] / ratio; - let ky = kpts[KPT_STEP * i + 1] / ratio; - let kconf = kpts[KPT_STEP * i + 2]; - if kconf < self.kconf { - kpts_.push(Point2::default()); - } else { - kpts_.push(Point2::new_with_conf( - kx.max(0.0f32).min(width_original), - ky.max(0.0f32).min(height_original), - kconf, - )); - } - } - Some(kpts_) - } else { - None - } - }; - - // data merged - data.push((y_bbox, y_kpts, coefs)); - } - - // nms - non_max_suppression(&mut data, self.iou); - - // decode - let mut y_bboxes: Vec = Vec::new(); - let mut y_kpts: Vec> = Vec::new(); - let mut y_masks: Vec> = Vec::new(); - for elem in data.into_iter() { - if let Some(kpts) = elem.1 { - y_kpts.push(kpts) - } - - // decode masks - if let Some(coefs) = elem.2 { - let proto = protos.unwrap().slice(s![idx, .., .., ..]); - let (nm, nh, nw) = proto.dim(); - - // coefs * proto -> mask - let coefs = Array::from_shape_vec((1, nm), coefs)?; // (n, nm) - let proto = proto.to_owned().into_shape((nm, nh * nw))?; // (nm, nh*nw) - let mask = coefs.dot(&proto).into_shape((nh, nw, 1))?; // (nh, nw, n) - - // build image from ndarray - let mask_im: ImageBuffer, Vec> = - match ImageBuffer::from_raw(nw as u32, nh as u32, mask.into_raw_vec()) { - Some(image) => image, - None => panic!("can not create image from ndarray"), - }; - let mut mask_im = image::DynamicImage::from(mask_im); // -> dyn - - // rescale masks - let (_, w_mask, h_mask) = - self.scale_wh(width_original, height_original, nw as f32, nh as f32); - let mask_cropped = mask_im.crop(0, 0, w_mask as u32, h_mask as u32); - let mask_original = mask_cropped.resize_exact( - // resize_to_fill - width_original as u32, - height_original as u32, - match self.task() { - YOLOTask::Segment => image::imageops::FilterType::CatmullRom, - _ => image::imageops::FilterType::Triangle, - }, - ); - - // crop-mask with bbox - let mut mask_original_cropped = mask_original.into_luma8(); - for y in 0..height_original as usize { - for x in 0..width_original as usize { - if x < elem.0.xmin() as usize - || x > elem.0.xmax() as usize - || y < elem.0.ymin() as usize - || y > elem.0.ymax() as usize - { - mask_original_cropped.put_pixel( - x as u32, - y as u32, - image::Luma([0u8]), - ); - } - } - } - y_masks.push(mask_original_cropped.into_raw()); - } - y_bboxes.push(elem.0); - } - - // save each result - let y = YOLOResult { - probs: None, - bboxes: if !y_bboxes.is_empty() { - Some(y_bboxes) - } else { - None - }, - keypoints: if !y_kpts.is_empty() { - Some(y_kpts) - } else { - None - }, - masks: if !y_masks.is_empty() { - Some(y_masks) - } else { - None - }, - }; - ys.push(y); - } - - Ok(ys) - } - } - - pub fn plot_and_save( - &self, - ys: &[YOLOResult], - xs0: &[DynamicImage], - skeletons: Option<&[(usize, usize)]>, - ) { - // check font then load - let font = check_font("Arial.ttf"); - for (_idb, (img0, y)) in xs0.iter().zip(ys.iter()).enumerate() { - let mut img = img0.to_rgb8(); - - // draw for classifier - if let Some(probs) = y.probs() { - for (i, k) in probs.topk(5).iter().enumerate() { - let legend = format!("{} {:.2}%", self.names[k.0], k.1); - let scale = 32; - let legend_size = img.width().max(img.height()) / scale; - let x = img.width() / 20; - let y = img.height() / 20 + i as u32 * legend_size; - imageproc::drawing::draw_text_mut( - &mut img, - image::Rgb([0, 255, 0]), - x as i32, - y as i32, - rusttype::Scale::uniform(legend_size as f32 - 1.), - &font, - &legend, - ); - } - } - - // draw bboxes & keypoints - if let Some(bboxes) = y.bboxes() { - for (_idx, bbox) in bboxes.iter().enumerate() { - // rect - imageproc::drawing::draw_hollow_rect_mut( - &mut img, - imageproc::rect::Rect::at(bbox.xmin() as i32, bbox.ymin() as i32) - .of_size(bbox.width() as u32, bbox.height() as u32), - image::Rgb(self.color_palette[bbox.id()].into()), - ); - - // text - let legend = format!("{} {:.2}%", self.names[bbox.id()], bbox.confidence()); - let scale = 40; - let legend_size = img.width().max(img.height()) / scale; - imageproc::drawing::draw_text_mut( - &mut img, - image::Rgb(self.color_palette[bbox.id()].into()), - bbox.xmin() as i32, - (bbox.ymin() - legend_size as f32) as i32, - rusttype::Scale::uniform(legend_size as f32 - 1.), - &font, - &legend, - ); - } - } - - // draw kpts - if let Some(keypoints) = y.keypoints() { - for kpts in keypoints.iter() { - for kpt in kpts.iter() { - // filter - if kpt.confidence() < self.kconf { - continue; - } - - // draw point - imageproc::drawing::draw_filled_circle_mut( - &mut img, - (kpt.x() as i32, kpt.y() as i32), - 2, - image::Rgb([0, 255, 0]), - ); - } - - // draw skeleton if has - if let Some(skeletons) = skeletons { - for &(idx1, idx2) in skeletons.iter() { - let kpt1 = &kpts[idx1]; - let kpt2 = &kpts[idx2]; - if kpt1.confidence() < self.kconf || kpt2.confidence() < self.kconf { - continue; - } - imageproc::drawing::draw_line_segment_mut( - &mut img, - (kpt1.x(), kpt1.y()), - (kpt2.x(), kpt2.y()), - image::Rgb([233, 14, 57]), - ); - } - } - } - } - - // draw mask - if let Some(masks) = y.masks() { - for (mask, _bbox) in masks.iter().zip(y.bboxes().unwrap().iter()) { - let mask_nd: ImageBuffer, Vec> = - match ImageBuffer::from_vec(img.width(), img.height(), mask.to_vec()) { - Some(image) => image, - None => panic!("can not crate image from ndarray"), - }; - - for _x in 0..img.width() { - for _y in 0..img.height() { - let mask_p = imageproc::drawing::Canvas::get_pixel(&mask_nd, _x, _y); - if mask_p.0[0] > 0 { - let mut img_p = imageproc::drawing::Canvas::get_pixel(&img, _x, _y); - // img_p.0[2] = self.color_palette[bbox.id()].2 / 2; - // img_p.0[1] = self.color_palette[bbox.id()].1 / 2; - // img_p.0[0] = self.color_palette[bbox.id()].0 / 2; - img_p.0[2] /= 2; - img_p.0[1] = 255 - (255 - img_p.0[2]) / 2; - img_p.0[0] /= 2; - imageproc::drawing::Canvas::draw_pixel(&mut img, _x, _y, img_p) - } - } - } - } - } - - // mkdir and save - let mut runs = PathBuf::from("runs"); - if !runs.exists() { - std::fs::create_dir_all(&runs).unwrap(); - } - runs.push(gen_time_string("-")); - let saveout = format!("{}.jpg", runs.to_str().unwrap()); - let _ = img.save(saveout); - } - } - - pub fn summary(&self) { - println!( - "\nSummary:\n\ - > Task: {:?}{}\n\ - > EP: {:?} {}\n\ - > Dtype: {:?}\n\ - > Batch: {} ({}), Height: {} ({}), Width: {} ({})\n\ - > nc: {} nk: {}, nm: {}, conf: {}, kconf: {}, iou: {}\n\ - ", - self.task(), - match self.engine.author().zip(self.engine.version()) { - Some((author, ver)) => format!(" ({} {})", author, ver), - None => String::from(""), - }, - self.engine.ep(), - if let OrtEP::Cpu = self.engine.ep() { - "" - } else { - "(May still fall back to CPU)" - }, - self.engine.dtype(), - self.batch(), - if self.engine.is_batch_dynamic() { - "Dynamic" - } else { - "Const" - }, - self.height(), - if self.engine.is_height_dynamic() { - "Dynamic" - } else { - "Const" - }, - self.width(), - if self.engine.is_width_dynamic() { - "Dynamic" - } else { - "Const" - }, - self.nc(), - self.nk(), - self.nm(), - self.conf, - self.kconf, - self.iou, - ); - } - - pub fn engine(&self) -> &OrtBackend { - &self.engine - } - - pub fn conf(&self) -> f32 { - self.conf - } - - pub fn set_conf(&mut self, val: f32) { - self.conf = val; - } - - pub fn conf_mut(&mut self) -> &mut f32 { - &mut self.conf - } - - pub fn kconf(&self) -> f32 { - self.kconf - } - - pub fn iou(&self) -> f32 { - self.iou - } - - pub fn task(&self) -> &YOLOTask { - &self.task - } - - pub fn batch(&self) -> u32 { - self.batch - } - - pub fn width(&self) -> u32 { - self.width - } - - pub fn height(&self) -> u32 { - self.height - } - - pub fn nc(&self) -> u32 { - self.nc - } - - pub fn nk(&self) -> u32 { - self.nk - } - - pub fn nm(&self) -> u32 { - self.nm - } - - pub fn names(&self) -> &Vec { - &self.names - } -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/ort_backend.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/ort_backend.rs deleted file mode 100644 index 5be93bd..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/ort_backend.rs +++ /dev/null @@ -1,534 +0,0 @@ -use anyhow::Result; -use clap::ValueEnum; -use half::f16; -use ndarray::{Array, CowArray, IxDyn}; -use ort::execution_providers::{CUDAExecutionProviderOptions, TensorRTExecutionProviderOptions}; -use ort::tensor::TensorElementDataType; -use ort::{Environment, ExecutionProvider, Session, SessionBuilder, Value}; -use regex::Regex; - -#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, ValueEnum)] -pub enum YOLOTask { - // YOLO tasks - Classify, - Detect, - Pose, - Segment, -} - -#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord)] -pub enum OrtEP { - // ONNXRuntime execution provider - Cpu, - Cuda(u32), - Trt(u32), -} - -#[derive(Debug)] -pub struct Batch { - pub opt: u32, - pub min: u32, - pub max: u32, -} - -impl Default for Batch { - fn default() -> Self { - Self { - opt: 1, - min: 1, - max: 1, - } - } -} - -#[derive(Debug, Default)] -pub struct OrtInputs { - // ONNX model inputs attrs - pub shapes: Vec>, - pub dtypes: Vec, - pub names: Vec, - pub sizes: Vec>, -} - -impl OrtInputs { - pub fn new(session: &Session) -> Self { - let mut shapes = Vec::new(); - let mut dtypes = Vec::new(); - let mut names = Vec::new(); - for i in session.inputs.iter() { - let shape: Vec = i - .dimensions() - .map(|x| if let Some(x) = x { x as i32 } else { -1i32 }) - .collect(); - shapes.push(shape); - dtypes.push(i.input_type); - names.push(i.name.clone()); - } - Self { - shapes, - dtypes, - names, - ..Default::default() - } - } -} - -#[derive(Debug)] -pub struct OrtConfig { - // ORT config - pub f: String, - pub task: Option, - pub ep: OrtEP, - pub trt_fp16: bool, - pub batch: Batch, - pub image_size: (Option, Option), -} - -#[derive(Debug)] -pub struct OrtBackend { - // ORT engine - session: Session, - task: YOLOTask, - ep: OrtEP, - batch: Batch, - inputs: OrtInputs, -} - -impl OrtBackend { - pub fn build(args: OrtConfig) -> Result { - // build env & session - let env = Environment::builder() - .with_name("YOLOv8") - .with_log_level(ort::LoggingLevel::Verbose) - .build()? - .into_arc(); - let session = SessionBuilder::new(&env)?.with_model_from_file(&args.f)?; - - // get inputs - let mut inputs = OrtInputs::new(&session); - - // batch size - let mut batch = args.batch; - let batch = if inputs.shapes[0][0] == -1 { - batch - } else { - assert_eq!( - inputs.shapes[0][0] as u32, batch.opt, - "Expected batch size: {}, got {}. Try using `--batch {}`.", - inputs.shapes[0][0] as u32, batch.opt, inputs.shapes[0][0] as u32 - ); - batch.opt = inputs.shapes[0][0] as u32; - batch - }; - - // input size: height and width - let height = if inputs.shapes[0][2] == -1 { - match args.image_size.0 { - Some(height) => height, - None => panic!("Failed to get model height. Make it explicit with `--height`"), - } - } else { - inputs.shapes[0][2] as u32 - }; - let width = if inputs.shapes[0][3] == -1 { - match args.image_size.1 { - Some(width) => width, - None => panic!("Failed to get model width. Make it explicit with `--width`"), - } - } else { - inputs.shapes[0][3] as u32 - }; - inputs.sizes.push(vec![height, width]); - - // build provider - let (ep, provider) = match args.ep { - OrtEP::Cuda(device_id) => Self::set_ep_cuda(device_id), - OrtEP::Trt(device_id) => Self::set_ep_trt(device_id, args.trt_fp16, &batch, &inputs), - _ => (OrtEP::Cpu, ExecutionProvider::CPU(Default::default())), - }; - - // build session again with the new provider - let session = SessionBuilder::new(&env)? - // .with_optimization_level(ort::GraphOptimizationLevel::Level3)? - .with_execution_providers([provider])? - .with_model_from_file(args.f)?; - - // task: using given one or guessing - let task = match args.task { - Some(task) => task, - None => match session.metadata() { - Err(_) => panic!("No metadata found. Try making it explicit by `--task`"), - Ok(metadata) => match metadata.custom("task") { - Err(_) => panic!("Can not get custom value. Try making it explicit by `--task`"), - Ok(value) => match value { - None => panic!("No correspoing value of `task` found in metadata. Make it explicit by `--task`"), - Some(task) => match task.as_str() { - "classify" => YOLOTask::Classify, - "detect" => YOLOTask::Detect, - "pose" => YOLOTask::Pose, - "segment" => YOLOTask::Segment, - x => todo!("{:?} is not supported for now!", x), - }, - }, - }, - }, - }; - - Ok(Self { - session, - task, - ep, - batch, - inputs, - }) - } - - pub fn fetch_inputs_from_session( - session: &Session, - ) -> (Vec>, Vec, Vec) { - // get inputs attrs from ONNX model - let mut shapes = Vec::new(); - let mut dtypes = Vec::new(); - let mut names = Vec::new(); - for i in session.inputs.iter() { - let shape: Vec = i - .dimensions() - .map(|x| if let Some(x) = x { x as i32 } else { -1i32 }) - .collect(); - shapes.push(shape); - dtypes.push(i.input_type); - names.push(i.name.clone()); - } - (shapes, dtypes, names) - } - - pub fn set_ep_cuda(device_id: u32) -> (OrtEP, ExecutionProvider) { - // set CUDA - if ExecutionProvider::CUDA(Default::default()).is_available() { - ( - OrtEP::Cuda(device_id), - ExecutionProvider::CUDA(CUDAExecutionProviderOptions { - device_id, - ..Default::default() - }), - ) - } else { - println!("> CUDA is not available! Using CPU."); - (OrtEP::Cpu, ExecutionProvider::CPU(Default::default())) - } - } - - pub fn set_ep_trt( - device_id: u32, - fp16: bool, - batch: &Batch, - inputs: &OrtInputs, - ) -> (OrtEP, ExecutionProvider) { - // set TensorRT - if ExecutionProvider::TensorRT(Default::default()).is_available() { - let (height, width) = (inputs.sizes[0][0], inputs.sizes[0][1]); - - // dtype match checking - if inputs.dtypes[0] == TensorElementDataType::Float16 && !fp16 { - panic!( - "Dtype mismatch! Expected: Float32, got: {:?}. You should use `--fp16`", - inputs.dtypes[0] - ); - } - - // dynamic shape: input_tensor_1:dim_1xdim_2x...,input_tensor_2:dim_3xdim_4x...,... - let mut opt_string = String::new(); - let mut min_string = String::new(); - let mut max_string = String::new(); - for name in inputs.names.iter() { - let s_opt = format!("{}:{}x3x{}x{},", name, batch.opt, height, width); - let s_min = format!("{}:{}x3x{}x{},", name, batch.min, height, width); - let s_max = format!("{}:{}x3x{}x{},", name, batch.max, height, width); - opt_string.push_str(s_opt.as_str()); - min_string.push_str(s_min.as_str()); - max_string.push_str(s_max.as_str()); - } - let _ = opt_string.pop(); - let _ = min_string.pop(); - let _ = max_string.pop(); - ( - OrtEP::Trt(device_id), - ExecutionProvider::TensorRT(TensorRTExecutionProviderOptions { - device_id, - fp16_enable: fp16, - timing_cache_enable: true, - profile_min_shapes: min_string, - profile_max_shapes: max_string, - profile_opt_shapes: opt_string, - ..Default::default() - }), - ) - } else { - println!("> TensorRT is not available! Try using CUDA..."); - Self::set_ep_cuda(device_id) - } - } - - pub fn fetch_from_metadata(&self, key: &str) -> Option { - // fetch value from onnx model file by key - match self.session.metadata() { - Err(_) => None, - Ok(metadata) => match metadata.custom(key) { - Err(_) => None, - Ok(value) => value, - }, - } - } - - pub fn run(&self, xs: Array, profile: bool) -> Result>> { - // ORT inference - match self.dtype() { - TensorElementDataType::Float16 => self.run_fp16(xs, profile), - TensorElementDataType::Float32 => self.run_fp32(xs, profile), - _ => todo!(), - } - } - - pub fn run_fp16(&self, xs: Array, profile: bool) -> Result>> { - // f32->f16 - let t = std::time::Instant::now(); - let xs = xs.mapv(f16::from_f32); - if profile { - println!("[ORT f32->f16]: {:?}", t.elapsed()); - } - - // h2d - let t = std::time::Instant::now(); - let xs = CowArray::from(xs); - let xs = vec![Value::from_array(self.session.allocator(), &xs)?]; - if profile { - println!("[ORT H2D]: {:?}", t.elapsed()); - } - - // run - let t = std::time::Instant::now(); - let ys = self.session.run(xs)?; - if profile { - println!("[ORT Inference]: {:?}", t.elapsed()); - } - - // d2h - Ok(ys - .iter() - .map(|x| { - // d2h - let t = std::time::Instant::now(); - let x = x.try_extract::<_>().unwrap().view().clone().into_owned(); - if profile { - println!("[ORT D2H]: {:?}", t.elapsed()); - } - - // f16->f32 - let t_ = std::time::Instant::now(); - let x = x.mapv(f16::to_f32); - if profile { - println!("[ORT f16->f32]: {:?}", t_.elapsed()); - } - x - }) - .collect::>>()) - } - - pub fn run_fp32(&self, xs: Array, profile: bool) -> Result>> { - // h2d - let t = std::time::Instant::now(); - let xs = CowArray::from(xs); - let xs = vec![Value::from_array(self.session.allocator(), &xs)?]; - if profile { - println!("[ORT H2D]: {:?}", t.elapsed()); - } - - // run - let t = std::time::Instant::now(); - let ys = self.session.run(xs)?; - if profile { - println!("[ORT Inference]: {:?}", t.elapsed()); - } - - // d2h - Ok(ys - .iter() - .map(|x| { - let t = std::time::Instant::now(); - let x = x.try_extract::<_>().unwrap().view().clone().into_owned(); - if profile { - println!("[ORT D2H]: {:?}", t.elapsed()); - } - x - }) - .collect::>>()) - } - - pub fn output_shapes(&self) -> Vec> { - let mut shapes = Vec::new(); - for o in &self.session.outputs { - let shape: Vec<_> = o - .dimensions() - .map(|x| if let Some(x) = x { x as i32 } else { -1i32 }) - .collect(); - shapes.push(shape); - } - shapes - } - - pub fn output_dtypes(&self) -> Vec { - let mut dtypes = Vec::new(); - self.session - .outputs - .iter() - .for_each(|x| dtypes.push(x.output_type)); - dtypes - } - - pub fn input_shapes(&self) -> &Vec> { - &self.inputs.shapes - } - - pub fn input_names(&self) -> &Vec { - &self.inputs.names - } - - pub fn input_dtypes(&self) -> &Vec { - &self.inputs.dtypes - } - - pub fn dtype(&self) -> TensorElementDataType { - self.input_dtypes()[0] - } - - pub fn height(&self) -> u32 { - self.inputs.sizes[0][0] - } - - pub fn width(&self) -> u32 { - self.inputs.sizes[0][1] - } - - pub fn is_height_dynamic(&self) -> bool { - self.input_shapes()[0][2] == -1 - } - - pub fn is_width_dynamic(&self) -> bool { - self.input_shapes()[0][3] == -1 - } - - pub fn batch(&self) -> u32 { - self.batch.opt - } - - pub fn is_batch_dynamic(&self) -> bool { - self.input_shapes()[0][0] == -1 - } - - pub fn ep(&self) -> &OrtEP { - &self.ep - } - - pub fn task(&self) -> YOLOTask { - self.task.clone() - } - - pub fn names(&self) -> Option> { - // class names, metadata parsing - // String format: `{0: 'person', 1: 'bicycle', 2: 'sports ball', ..., 27: "yellow_lady's_slipper"}` - match self.fetch_from_metadata("names") { - Some(names) => { - let re = Regex::new(r#"(['"])([-()\w '"]+)(['"])"#).unwrap(); - let mut names_ = vec![]; - for (_, [_, name, _]) in re.captures_iter(&names).map(|x| x.extract()) { - names_.push(name.to_string()); - } - Some(names_) - } - None => None, - } - } - - pub fn nk(&self) -> Option { - // num_keypoints, metadata parsing: String `nk` in onnx model: `[17, 3]` - match self.fetch_from_metadata("kpt_shape") { - None => None, - Some(kpt_string) => { - let re = Regex::new(r"([0-9]+), ([0-9]+)").unwrap(); - let caps = re.captures(&kpt_string).unwrap(); - Some(caps.get(1).unwrap().as_str().parse::().unwrap()) - } - } - } - - pub fn nc(&self) -> Option { - // num_classes - match self.names() { - // by names - Some(names) => Some(names.len() as u32), - None => match self.task() { - // by task calculation - YOLOTask::Classify => Some(self.output_shapes()[0][1] as u32), - YOLOTask::Detect => { - if self.output_shapes()[0][1] == -1 { - None - } else { - // cxywhclss - Some(self.output_shapes()[0][1] as u32 - 4) - } - } - YOLOTask::Pose => { - match self.nk() { - None => None, - Some(nk) => { - if self.output_shapes()[0][1] == -1 { - None - } else { - // cxywhclss3*kpt - Some(self.output_shapes()[0][1] as u32 - 4 - 3 * nk) - } - } - } - } - YOLOTask::Segment => { - if self.output_shapes()[0][1] == -1 { - None - } else { - // cxywhclssnm - Some((self.output_shapes()[0][1] - self.output_shapes()[1][1]) as u32 - 4) - } - } - }, - } - } - - pub fn nm(&self) -> Option { - // num_masks - match self.task() { - YOLOTask::Segment => Some(self.output_shapes()[1][1] as u32), - _ => None, - } - } - - pub fn na(&self) -> Option { - // num_anchors - match self.task() { - YOLOTask::Segment | YOLOTask::Detect | YOLOTask::Pose => { - if self.output_shapes()[0][2] == -1 { - None - } else { - Some(self.output_shapes()[0][2] as u32) - } - } - _ => None, - } - } - - pub fn author(&self) -> Option { - self.fetch_from_metadata("author") - } - - pub fn version(&self) -> Option { - self.fetch_from_metadata("version") - } -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/yolo_result.rs b/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/yolo_result.rs deleted file mode 100644 index 2fcc6d8..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime-Rust/src/yolo_result.rs +++ /dev/null @@ -1,235 +0,0 @@ -use ndarray::{Array, Axis, IxDyn}; - -#[derive(Clone, PartialEq, Default)] -pub struct YOLOResult { - // YOLO tasks results of an image - pub probs: Option, - pub bboxes: Option>, - pub keypoints: Option>>, - pub masks: Option>>, -} - -impl std::fmt::Debug for YOLOResult { - fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result { - f.debug_struct("YOLOResult") - .field( - "Probs(top5)", - &format_args!("{:?}", self.probs().map(|probs| probs.topk(5))), - ) - .field("Bboxes", &self.bboxes) - .field("Keypoints", &self.keypoints) - .field( - "Masks", - &format_args!("{:?}", self.masks().map(|masks| masks.len())), - ) - .finish() - } -} - -impl YOLOResult { - pub fn new( - probs: Option, - bboxes: Option>, - keypoints: Option>>, - masks: Option>>, - ) -> Self { - Self { - probs, - bboxes, - keypoints, - masks, - } - } - - pub fn probs(&self) -> Option<&Embedding> { - self.probs.as_ref() - } - - pub fn keypoints(&self) -> Option<&Vec>> { - self.keypoints.as_ref() - } - - pub fn masks(&self) -> Option<&Vec>> { - self.masks.as_ref() - } - - pub fn bboxes(&self) -> Option<&Vec> { - self.bboxes.as_ref() - } - - pub fn bboxes_mut(&mut self) -> Option<&mut Vec> { - self.bboxes.as_mut() - } -} - -#[derive(Debug, PartialEq, Clone, Default)] -pub struct Point2 { - // A point2d with x, y, conf - x: f32, - y: f32, - confidence: f32, -} - -impl Point2 { - pub fn new_with_conf(x: f32, y: f32, confidence: f32) -> Self { - Self { x, y, confidence } - } - - pub fn new(x: f32, y: f32) -> Self { - Self { - x, - y, - ..Default::default() - } - } - - pub fn x(&self) -> f32 { - self.x - } - - pub fn y(&self) -> f32 { - self.y - } - - pub fn confidence(&self) -> f32 { - self.confidence - } -} - -#[derive(Debug, Clone, PartialEq, Default)] -pub struct Embedding { - // An float32 n-dims tensor - data: Array, -} - -impl Embedding { - pub fn new(data: Array) -> Self { - Self { data } - } - - pub fn data(&self) -> &Array { - &self.data - } - - pub fn topk(&self, k: usize) -> Vec<(usize, f32)> { - let mut probs = self - .data - .iter() - .enumerate() - .map(|(a, b)| (a, *b)) - .collect::>(); - probs.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap()); - let mut topk = Vec::new(); - for &(id, confidence) in probs.iter().take(k) { - topk.push((id, confidence)); - } - topk - } - - pub fn norm(&self) -> Array { - let std_ = self.data.mapv(|x| x * x).sum_axis(Axis(0)).mapv(f32::sqrt); - self.data.clone() / std_ - } - - pub fn top1(&self) -> (usize, f32) { - self.topk(1)[0] - } -} - -#[derive(Debug, Clone, PartialEq, Default)] -pub struct Bbox { - // a bounding box around an object - xmin: f32, - ymin: f32, - width: f32, - height: f32, - id: usize, - confidence: f32, -} - -impl Bbox { - pub fn new_from_xywh(xmin: f32, ymin: f32, width: f32, height: f32) -> Self { - Self { - xmin, - ymin, - width, - height, - ..Default::default() - } - } - - pub fn new(xmin: f32, ymin: f32, width: f32, height: f32, id: usize, confidence: f32) -> Self { - Self { - xmin, - ymin, - width, - height, - id, - confidence, - } - } - - pub fn width(&self) -> f32 { - self.width - } - - pub fn height(&self) -> f32 { - self.height - } - - pub fn xmin(&self) -> f32 { - self.xmin - } - - pub fn ymin(&self) -> f32 { - self.ymin - } - - pub fn xmax(&self) -> f32 { - self.xmin + self.width - } - - pub fn ymax(&self) -> f32 { - self.ymin + self.height - } - - pub fn tl(&self) -> Point2 { - Point2::new(self.xmin, self.ymin) - } - - pub fn br(&self) -> Point2 { - Point2::new(self.xmax(), self.ymax()) - } - - pub fn cxcy(&self) -> Point2 { - Point2::new(self.xmin + self.width / 2., self.ymin + self.height / 2.) - } - - pub fn id(&self) -> usize { - self.id - } - - pub fn confidence(&self) -> f32 { - self.confidence - } - - pub fn area(&self) -> f32 { - self.width * self.height - } - - pub fn intersection_area(&self, another: &Bbox) -> f32 { - let l = self.xmin.max(another.xmin); - let r = (self.xmin + self.width).min(another.xmin + another.width); - let t = self.ymin.max(another.ymin); - let b = (self.ymin + self.height).min(another.ymin + another.height); - (r - l + 1.).max(0.) * (b - t + 1.).max(0.) - } - - pub fn union(&self, another: &Bbox) -> f32 { - self.area() + another.area() - self.intersection_area(another) - } - - pub fn iou(&self, another: &Bbox) -> f32 { - self.intersection_area(another) / self.union(another) - } -} diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime/README.md b/ultralytics-main/examples/YOLOv8-ONNXRuntime/README.md deleted file mode 100644 index b206b2e..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime/README.md +++ /dev/null @@ -1,43 +0,0 @@ -# YOLOv8 - ONNX Runtime - -This project implements YOLOv8 using ONNX Runtime. - -## Installation - -To run this project, you need to install the required dependencies. The following instructions will guide you through the installation process. - -### Installing Required Dependencies - -You can install the required dependencies by running the following command: - -```bash -pip install -r requirements.txt -``` - -### Installing `onnxruntime-gpu` - -If you have an NVIDIA GPU and want to leverage GPU acceleration, you can install the onnxruntime-gpu package using the following command: - -```bash -pip install onnxruntime-gpu -``` - -Note: Make sure you have the appropriate GPU drivers installed on your system. - -### Installing `onnxruntime` (CPU version) - -If you don't have an NVIDIA GPU or prefer to use the CPU version of onnxruntime, you can install the onnxruntime package using the following command: - -```bash -pip install onnxruntime -``` - -### Usage - -After successfully installing the required packages, you can run the YOLOv8 implementation using the following command: - -```bash -python main.py --model yolov8n.onnx --img image.jpg --conf-thres 0.5 --iou-thres 0.5 -``` - -Make sure to replace yolov8n.onnx with the path to your YOLOv8 ONNX model file, image.jpg with the path to your input image, and adjust the confidence threshold (conf-thres) and IoU threshold (iou-thres) values as needed. diff --git a/ultralytics-main/examples/YOLOv8-ONNXRuntime/main.py b/ultralytics-main/examples/YOLOv8-ONNXRuntime/main.py deleted file mode 100644 index e1e83f3..0000000 --- a/ultralytics-main/examples/YOLOv8-ONNXRuntime/main.py +++ /dev/null @@ -1,231 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse - -import cv2 -import numpy as np -import onnxruntime as ort -import torch - -from ultralytics.utils import ASSETS, yaml_load -from ultralytics.utils.checks import check_requirements, check_yaml - - -class YOLOv8: - """YOLOv8 object detection model class for handling inference and visualization.""" - - def __init__(self, onnx_model, input_image, confidence_thres, iou_thres): - """ - Initializes an instance of the YOLOv8 class. - - Args: - onnx_model: Path to the ONNX model. - input_image: Path to the input image. - confidence_thres: Confidence threshold for filtering detections. - iou_thres: IoU (Intersection over Union) threshold for non-maximum suppression. - """ - self.onnx_model = onnx_model - self.input_image = input_image - self.confidence_thres = confidence_thres - self.iou_thres = iou_thres - - # Load the class names from the COCO dataset - self.classes = yaml_load(check_yaml("coco128.yaml"))["names"] - - # Generate a color palette for the classes - self.color_palette = np.random.uniform(0, 255, size=(len(self.classes), 3)) - - def draw_detections(self, img, box, score, class_id): - """ - Draws bounding boxes and labels on the input image based on the detected objects. - - Args: - img: The input image to draw detections on. - box: Detected bounding box. - score: Corresponding detection score. - class_id: Class ID for the detected object. - - Returns: - None - """ - - # Extract the coordinates of the bounding box - x1, y1, w, h = box - - # Retrieve the color for the class ID - color = self.color_palette[class_id] - - # Draw the bounding box on the image - cv2.rectangle(img, (int(x1), int(y1)), (int(x1 + w), int(y1 + h)), color, 2) - - # Create the label text with class name and score - label = f"{self.classes[class_id]}: {score:.2f}" - - # Calculate the dimensions of the label text - (label_width, label_height), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1) - - # Calculate the position of the label text - label_x = x1 - label_y = y1 - 10 if y1 - 10 > label_height else y1 + 10 - - # Draw a filled rectangle as the background for the label text - cv2.rectangle( - img, (label_x, label_y - label_height), (label_x + label_width, label_y + label_height), color, cv2.FILLED - ) - - # Draw the label text on the image - cv2.putText(img, label, (label_x, label_y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA) - - def preprocess(self): - """ - Preprocesses the input image before performing inference. - - Returns: - image_data: Preprocessed image data ready for inference. - """ - # Read the input image using OpenCV - self.img = cv2.imread(self.input_image) - - # Get the height and width of the input image - self.img_height, self.img_width = self.img.shape[:2] - - # Convert the image color space from BGR to RGB - img = cv2.cvtColor(self.img, cv2.COLOR_BGR2RGB) - - # Resize the image to match the input shape - img = cv2.resize(img, (self.input_width, self.input_height)) - - # Normalize the image data by dividing it by 255.0 - image_data = np.array(img) / 255.0 - - # Transpose the image to have the channel dimension as the first dimension - image_data = np.transpose(image_data, (2, 0, 1)) # Channel first - - # Expand the dimensions of the image data to match the expected input shape - image_data = np.expand_dims(image_data, axis=0).astype(np.float32) - - # Return the preprocessed image data - return image_data - - def postprocess(self, input_image, output): - """ - Performs post-processing on the model's output to extract bounding boxes, scores, and class IDs. - - Args: - input_image (numpy.ndarray): The input image. - output (numpy.ndarray): The output of the model. - - Returns: - numpy.ndarray: The input image with detections drawn on it. - """ - - # Transpose and squeeze the output to match the expected shape - outputs = np.transpose(np.squeeze(output[0])) - - # Get the number of rows in the outputs array - rows = outputs.shape[0] - - # Lists to store the bounding boxes, scores, and class IDs of the detections - boxes = [] - scores = [] - class_ids = [] - - # Calculate the scaling factors for the bounding box coordinates - x_factor = self.img_width / self.input_width - y_factor = self.img_height / self.input_height - - # Iterate over each row in the outputs array - for i in range(rows): - # Extract the class scores from the current row - classes_scores = outputs[i][4:] - - # Find the maximum score among the class scores - max_score = np.amax(classes_scores) - - # If the maximum score is above the confidence threshold - if max_score >= self.confidence_thres: - # Get the class ID with the highest score - class_id = np.argmax(classes_scores) - - # Extract the bounding box coordinates from the current row - x, y, w, h = outputs[i][0], outputs[i][1], outputs[i][2], outputs[i][3] - - # Calculate the scaled coordinates of the bounding box - left = int((x - w / 2) * x_factor) - top = int((y - h / 2) * y_factor) - width = int(w * x_factor) - height = int(h * y_factor) - - # Add the class ID, score, and box coordinates to the respective lists - class_ids.append(class_id) - scores.append(max_score) - boxes.append([left, top, width, height]) - - # Apply non-maximum suppression to filter out overlapping bounding boxes - indices = cv2.dnn.NMSBoxes(boxes, scores, self.confidence_thres, self.iou_thres) - - # Iterate over the selected indices after non-maximum suppression - for i in indices: - # Get the box, score, and class ID corresponding to the index - box = boxes[i] - score = scores[i] - class_id = class_ids[i] - - # Draw the detection on the input image - self.draw_detections(input_image, box, score, class_id) - - # Return the modified input image - return input_image - - def main(self): - """ - Performs inference using an ONNX model and returns the output image with drawn detections. - - Returns: - output_img: The output image with drawn detections. - """ - # Create an inference session using the ONNX model and specify execution providers - session = ort.InferenceSession(self.onnx_model, providers=["CUDAExecutionProvider", "CPUExecutionProvider"]) - - # Get the model inputs - model_inputs = session.get_inputs() - - # Store the shape of the input for later use - input_shape = model_inputs[0].shape - self.input_width = input_shape[2] - self.input_height = input_shape[3] - - # Preprocess the image data - img_data = self.preprocess() - - # Run inference using the preprocessed image data - outputs = session.run(None, {model_inputs[0].name: img_data}) - - # Perform post-processing on the outputs to obtain output image. - return self.postprocess(self.img, outputs) # output image - - -if __name__ == "__main__": - # Create an argument parser to handle command-line arguments - parser = argparse.ArgumentParser() - parser.add_argument("--model", type=str, default="yolov8n.onnx", help="Input your ONNX model.") - parser.add_argument("--img", type=str, default=str(ASSETS / "bus.jpg"), help="Path to input image.") - parser.add_argument("--conf-thres", type=float, default=0.5, help="Confidence threshold") - parser.add_argument("--iou-thres", type=float, default=0.5, help="NMS IoU threshold") - args = parser.parse_args() - - # Check the requirements and select the appropriate backend (CPU or GPU) - check_requirements("onnxruntime-gpu" if torch.cuda.is_available() else "onnxruntime") - - # Create an instance of the YOLOv8 class with the specified arguments - detection = YOLOv8(args.model, args.img, args.conf_thres, args.iou_thres) - - # Perform object detection and obtain the output image - output_image = detection.main() - - # Display the output image in a window - cv2.namedWindow("Output", cv2.WINDOW_NORMAL) - cv2.imshow("Output", output_image) - - # Wait for a key press to exit - cv2.waitKey(0) diff --git a/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/README.md b/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/README.md deleted file mode 100644 index c9076fa..0000000 --- a/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/README.md +++ /dev/null @@ -1,19 +0,0 @@ -# YOLOv8 - OpenCV - -Implementation YOLOv8 on OpenCV using ONNX Format. - -Just simply clone and run - -```bash -pip install -r requirements.txt -python main.py --model yolov8n.onnx --img image.jpg -``` - -If you start from scratch: - -```bash -pip install ultralytics -yolo export model=yolov8n.pt imgsz=640 format=onnx opset=12 -``` - -_\*Make sure to include "opset=12"_ diff --git a/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/main.py b/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/main.py deleted file mode 100644 index 8d9c7a5..0000000 --- a/ultralytics-main/examples/YOLOv8-OpenCV-ONNX-Python/main.py +++ /dev/null @@ -1,130 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse - -import cv2.dnn -import numpy as np - -from ultralytics.utils import ASSETS, yaml_load -from ultralytics.utils.checks import check_yaml - -CLASSES = yaml_load(check_yaml("coco128.yaml"))["names"] -colors = np.random.uniform(0, 255, size=(len(CLASSES), 3)) - - -def draw_bounding_box(img, class_id, confidence, x, y, x_plus_w, y_plus_h): - """ - Draws bounding boxes on the input image based on the provided arguments. - - Args: - img (numpy.ndarray): The input image to draw the bounding box on. - class_id (int): Class ID of the detected object. - confidence (float): Confidence score of the detected object. - x (int): X-coordinate of the top-left corner of the bounding box. - y (int): Y-coordinate of the top-left corner of the bounding box. - x_plus_w (int): X-coordinate of the bottom-right corner of the bounding box. - y_plus_h (int): Y-coordinate of the bottom-right corner of the bounding box. - """ - label = f"{CLASSES[class_id]} ({confidence:.2f})" - color = colors[class_id] - cv2.rectangle(img, (x, y), (x_plus_w, y_plus_h), color, 2) - cv2.putText(img, label, (x - 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2) - - -def main(onnx_model, input_image): - """ - Main function to load ONNX model, perform inference, draw bounding boxes, and display the output image. - - Args: - onnx_model (str): Path to the ONNX model. - input_image (str): Path to the input image. - - Returns: - list: List of dictionaries containing detection information such as class_id, class_name, confidence, etc. - """ - # Load the ONNX model - model: cv2.dnn.Net = cv2.dnn.readNetFromONNX(onnx_model) - - # Read the input image - original_image: np.ndarray = cv2.imread(input_image) - [height, width, _] = original_image.shape - - # Prepare a square image for inference - length = max((height, width)) - image = np.zeros((length, length, 3), np.uint8) - image[0:height, 0:width] = original_image - - # Calculate scale factor - scale = length / 640 - - # Preprocess the image and prepare blob for model - blob = cv2.dnn.blobFromImage(image, scalefactor=1 / 255, size=(640, 640), swapRB=True) - model.setInput(blob) - - # Perform inference - outputs = model.forward() - - # Prepare output array - outputs = np.array([cv2.transpose(outputs[0])]) - rows = outputs.shape[1] - - boxes = [] - scores = [] - class_ids = [] - - # Iterate through output to collect bounding boxes, confidence scores, and class IDs - for i in range(rows): - classes_scores = outputs[0][i][4:] - (minScore, maxScore, minClassLoc, (x, maxClassIndex)) = cv2.minMaxLoc(classes_scores) - if maxScore >= 0.25: - box = [ - outputs[0][i][0] - (0.5 * outputs[0][i][2]), - outputs[0][i][1] - (0.5 * outputs[0][i][3]), - outputs[0][i][2], - outputs[0][i][3], - ] - boxes.append(box) - scores.append(maxScore) - class_ids.append(maxClassIndex) - - # Apply NMS (Non-maximum suppression) - result_boxes = cv2.dnn.NMSBoxes(boxes, scores, 0.25, 0.45, 0.5) - - detections = [] - - # Iterate through NMS results to draw bounding boxes and labels - for i in range(len(result_boxes)): - index = result_boxes[i] - box = boxes[index] - detection = { - "class_id": class_ids[index], - "class_name": CLASSES[class_ids[index]], - "confidence": scores[index], - "box": box, - "scale": scale, - } - detections.append(detection) - draw_bounding_box( - original_image, - class_ids[index], - scores[index], - round(box[0] * scale), - round(box[1] * scale), - round((box[0] + box[2]) * scale), - round((box[1] + box[3]) * scale), - ) - - # Display the image with bounding boxes - cv2.imshow("image", original_image) - cv2.waitKey(0) - cv2.destroyAllWindows() - - return detections - - -if __name__ == "__main__": - parser = argparse.ArgumentParser() - parser.add_argument("--model", default="yolov8n.onnx", help="Input your ONNX model.") - parser.add_argument("--img", default=str(ASSETS / "bus.jpg"), help="Path to input image.") - args = parser.parse_args() - main(args.model, args.img) diff --git a/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/README.md b/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/README.md deleted file mode 100644 index ea14e44..0000000 --- a/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/README.md +++ /dev/null @@ -1,65 +0,0 @@ -# YOLOv8 - Int8-TFLite Runtime - -Welcome to the YOLOv8 Int8 TFLite Runtime for efficient and optimized object detection project. This README provides comprehensive instructions for installing and using our YOLOv8 implementation. - -## Installation - -Ensure a smooth setup by following these steps to install necessary dependencies. - -### Installing Required Dependencies - -Install all required dependencies with this simple command: - -```bash -pip install -r requirements.txt -``` - -### Installing `tflite-runtime` - -To load TFLite models, install the `tflite-runtime` package using: - -```bash -pip install tflite-runtime -``` - -### Installing `tensorflow-gpu` (For NVIDIA GPU Users) - -Leverage GPU acceleration with NVIDIA GPUs by installing `tensorflow-gpu`: - -```bash -pip install tensorflow-gpu -``` - -**Note:** Ensure you have compatible GPU drivers installed on your system. - -### Installing `tensorflow` (CPU Version) - -For CPU usage or non-NVIDIA GPUs, install TensorFlow with: - -```bash -pip install tensorflow -``` - -## Usage - -Follow these instructions to run YOLOv8 after successful installation. - -Convert the YOLOv8 model to Int8 TFLite format: - -```bash -yolo export model=yolov8n.pt imgsz=640 format=tflite int8 -``` - -Locate the Int8 TFLite model in `yolov8n_saved_model`. Choose `best_full_integer_quant` or verify quantization at [Netron](https://netron.app/). Then, execute the following in your terminal: - -```bash -python main.py --model yolov8n_full_integer_quant.tflite --img image.jpg --conf-thres 0.5 --iou-thres 0.5 -``` - -Replace `best_full_integer_quant.tflite` with your model file's path, `image.jpg` with your input image, and adjust the confidence (conf-thres) and IoU thresholds (iou-thres) as necessary. - -### Output - -The output is displayed as annotated images, showcasing the model's detection capabilities: - -![image](https://github.com/wamiqraza/Attribute-recognition-and-reidentification-Market1501-dataset/blob/main/img/bus.jpg) diff --git a/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/main.py b/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/main.py deleted file mode 100644 index 53fba1f..0000000 --- a/ultralytics-main/examples/YOLOv8-OpenCV-int8-tflite-Python/main.py +++ /dev/null @@ -1,299 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse - -import cv2 -import numpy as np -from tflite_runtime import interpreter as tflite - -from ultralytics.utils import ASSETS, yaml_load -from ultralytics.utils.checks import check_yaml - -# Declare as global variables, can be updated based trained model image size -img_width = 640 -img_height = 640 - - -class LetterBox: - def __init__( - self, new_shape=(img_width, img_height), auto=False, scaleFill=False, scaleup=True, center=True, stride=32 - ): - self.new_shape = new_shape - self.auto = auto - self.scaleFill = scaleFill - self.scaleup = scaleup - self.stride = stride - self.center = center # Put the image in the middle or top-left - - def __call__(self, labels=None, image=None): - """Return updated labels and image with added border.""" - - if labels is None: - labels = {} - img = labels.get("img") if image is None else image - shape = img.shape[:2] # current shape [height, width] - new_shape = labels.pop("rect_shape", self.new_shape) - if isinstance(new_shape, int): - new_shape = (new_shape, new_shape) - - # Scale ratio (new / old) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - if not self.scaleup: # only scale down, do not scale up (for better val mAP) - r = min(r, 1.0) - - # Compute padding - ratio = r, r # width, height ratios - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding - if self.auto: # minimum rectangle - dw, dh = np.mod(dw, self.stride), np.mod(dh, self.stride) # wh padding - elif self.scaleFill: # stretch - dw, dh = 0.0, 0.0 - new_unpad = (new_shape[1], new_shape[0]) - ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios - - if self.center: - dw /= 2 # divide padding into 2 sides - dh /= 2 - - if shape[::-1] != new_unpad: # resize - img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(dh - 0.1)) if self.center else 0, int(round(dh + 0.1)) - left, right = int(round(dw - 0.1)) if self.center else 0, int(round(dw + 0.1)) - img = cv2.copyMakeBorder( - img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114) - ) # add border - if labels.get("ratio_pad"): - labels["ratio_pad"] = (labels["ratio_pad"], (left, top)) # for evaluation - - if len(labels): - labels = self._update_labels(labels, ratio, dw, dh) - labels["img"] = img - labels["resized_shape"] = new_shape - return labels - else: - return img - - def _update_labels(self, labels, ratio, padw, padh): - """Update labels.""" - - labels["instances"].convert_bbox(format="xyxy") - labels["instances"].denormalize(*labels["img"].shape[:2][::-1]) - labels["instances"].scale(*ratio) - labels["instances"].add_padding(padw, padh) - return labels - - -class Yolov8TFLite: - def __init__(self, tflite_model, input_image, confidence_thres, iou_thres): - """ - Initializes an instance of the Yolov8TFLite class. - - Args: - tflite_model: Path to the TFLite model. - input_image: Path to the input image. - confidence_thres: Confidence threshold for filtering detections. - iou_thres: IoU (Intersection over Union) threshold for non-maximum suppression. - """ - - self.tflite_model = tflite_model - self.input_image = input_image - self.confidence_thres = confidence_thres - self.iou_thres = iou_thres - - # Load the class names from the COCO dataset - self.classes = yaml_load(check_yaml("coco128.yaml"))["names"] - - # Generate a color palette for the classes - self.color_palette = np.random.uniform(0, 255, size=(len(self.classes), 3)) - - def draw_detections(self, img, box, score, class_id): - """ - Draws bounding boxes and labels on the input image based on the detected objects. - - Args: - img: The input image to draw detections on. - box: Detected bounding box. - score: Corresponding detection score. - class_id: Class ID for the detected object. - - Returns: - None - """ - - # Extract the coordinates of the bounding box - x1, y1, w, h = box - - # Retrieve the color for the class ID - color = self.color_palette[class_id] - - # Draw the bounding box on the image - cv2.rectangle(img, (int(x1), int(y1)), (int(x1 + w), int(y1 + h)), color, 2) - - # Create the label text with class name and score - label = f"{self.classes[class_id]}: {score:.2f}" - - # Calculate the dimensions of the label text - (label_width, label_height), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1) - - # Calculate the position of the label text - label_x = x1 - label_y = y1 - 10 if y1 - 10 > label_height else y1 + 10 - - # Draw a filled rectangle as the background for the label text - cv2.rectangle( - img, - (int(label_x), int(label_y - label_height)), - (int(label_x + label_width), int(label_y + label_height)), - color, - cv2.FILLED, - ) - - # Draw the label text on the image - cv2.putText(img, label, (int(label_x), int(label_y)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA) - - def preprocess(self): - """ - Preprocesses the input image before performing inference. - - Returns: - image_data: Preprocessed image data ready for inference. - """ - - # Read the input image using OpenCV - self.img = cv2.imread(self.input_image) - - print("image before", self.img) - # Get the height and width of the input image - self.img_height, self.img_width = self.img.shape[:2] - - letterbox = LetterBox(new_shape=[img_width, img_height], auto=False, stride=32) - image = letterbox(image=self.img) - image = [image] - image = np.stack(image) - image = image[..., ::-1].transpose((0, 3, 1, 2)) - img = np.ascontiguousarray(image) - # n, h, w, c - image = img.astype(np.float32) - return image / 255 - - def postprocess(self, input_image, output): - """ - Performs post-processing on the model's output to extract bounding boxes, scores, and class IDs. - - Args: - input_image (numpy.ndarray): The input image. - output (numpy.ndarray): The output of the model. - - Returns: - numpy.ndarray: The input image with detections drawn on it. - """ - - boxes = [] - scores = [] - class_ids = [] - for pred in output: - pred = np.transpose(pred) - for box in pred: - x, y, w, h = box[:4] - x1 = x - w / 2 - y1 = y - h / 2 - boxes.append([x1, y1, w, h]) - idx = np.argmax(box[4:]) - scores.append(box[idx + 4]) - class_ids.append(idx) - - indices = cv2.dnn.NMSBoxes(boxes, scores, self.confidence_thres, self.iou_thres) - - for i in indices: - # Get the box, score, and class ID corresponding to the index - box = boxes[i] - gain = min(img_width / self.img_width, img_height / self.img_height) - pad = ( - round((img_width - self.img_width * gain) / 2 - 0.1), - round((img_height - self.img_height * gain) / 2 - 0.1), - ) - box[0] = (box[0] - pad[0]) / gain - box[1] = (box[1] - pad[1]) / gain - box[2] = box[2] / gain - box[3] = box[3] / gain - score = scores[i] - class_id = class_ids[i] - if score > 0.25: - print(box, score, class_id) - # Draw the detection on the input image - self.draw_detections(input_image, box, score, class_id) - - return input_image - - def main(self): - """ - Performs inference using a TFLite model and returns the output image with drawn detections. - - Returns: - output_img: The output image with drawn detections. - """ - - # Create an interpreter for the TFLite model - interpreter = tflite.Interpreter(model_path=self.tflite_model) - self.model = interpreter - interpreter.allocate_tensors() - - # Get the model inputs - input_details = interpreter.get_input_details() - output_details = interpreter.get_output_details() - - # Store the shape of the input for later use - input_shape = input_details[0]["shape"] - self.input_width = input_shape[1] - self.input_height = input_shape[2] - - # Preprocess the image data - img_data = self.preprocess() - img_data = img_data - # img_data = img_data.cpu().numpy() - # Set the input tensor to the interpreter - print(input_details[0]["index"]) - print(img_data.shape) - img_data = img_data.transpose((0, 2, 3, 1)) - - scale, zero_point = input_details[0]["quantization"] - interpreter.set_tensor(input_details[0]["index"], img_data) - - # Run inference - interpreter.invoke() - - # Get the output tensor from the interpreter - output = interpreter.get_tensor(output_details[0]["index"]) - scale, zero_point = output_details[0]["quantization"] - output = (output.astype(np.float32) - zero_point) * scale - - output[:, [0, 2]] *= img_width - output[:, [1, 3]] *= img_height - print(output) - # Perform post-processing on the outputs to obtain output image. - return self.postprocess(self.img, output) - - -if __name__ == "__main__": - # Create an argument parser to handle command-line arguments - parser = argparse.ArgumentParser() - parser.add_argument( - "--model", type=str, default="yolov8n_full_integer_quant.tflite", help="Input your TFLite model." - ) - parser.add_argument("--img", type=str, default=str(ASSETS / "bus.jpg"), help="Path to input image.") - parser.add_argument("--conf-thres", type=float, default=0.5, help="Confidence threshold") - parser.add_argument("--iou-thres", type=float, default=0.5, help="NMS IoU threshold") - args = parser.parse_args() - - # Create an instance of the Yolov8TFLite class with the specified arguments - detection = Yolov8TFLite(args.model, args.img, args.conf_thres, args.iou_thres) - - # Perform object detection and obtain the output image - output_image = detection.main() - - # Display the output image in a window - cv2.imshow("Output", output_image) - - # Wait for a key press to exit - cv2.waitKey(0) diff --git a/ultralytics-main/examples/YOLOv8-Region-Counter/readme.md b/ultralytics-main/examples/YOLOv8-Region-Counter/readme.md deleted file mode 100644 index 2acf0a5..0000000 --- a/ultralytics-main/examples/YOLOv8-Region-Counter/readme.md +++ /dev/null @@ -1,123 +0,0 @@ -# Regions Counting Using YOLOv8 (Inference on Video) - -- Region counting is a method employed to tally the objects within a specified area, allowing for more sophisticated analyses when multiple regions are considered. These regions can be adjusted interactively using a Left Mouse Click, and the counting process occurs in real time. -- Regions can be adjusted to suit the user's preferences and requirements. - -
-

- YOLOv8 region counting visual 1 - YOLOv8 region counting visual 2 -

-
- -## Table of Contents - -- [Step 1: Install the Required Libraries](#step-1-install-the-required-libraries) -- [Step 2: Run the Region Counting Using Ultralytics YOLOv8](#step-2-run-the-region-counting-using-ultralytics-yolov8) -- [Usage Options](#usage-options) -- [FAQ](#faq) - -## Step 1: Install the Required Libraries - -Clone the repository, install dependencies and `cd` to this local directory for commands in Step 2. - -```bash -# Clone ultralytics repo -git clone https://github.com/ultralytics/ultralytics - -# cd to local directory -cd ultralytics/examples/YOLOv8-Region-Counter -``` - -## Step 2: Run the Region Counting Using Ultralytics YOLOv8 - -Here are the basic commands for running the inference: - -### Note - -After the video begins playing, you can freely move the region anywhere within the video by simply clicking and dragging using the left mouse button. - -```bash -# If you want to save results -python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --view-img - -# If you want to run model on CPU -python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --view-img --device cpu - -# If you want to change model file -python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --weights "path/to/model.pt" - -# If you want to detect specific class (first class and third class) -python yolov8_region_counter.py --source "path/to/video.mp4" --classes 0 2 --weights "path/to/model.pt" - -# If you dont want to save results -python yolov8_region_counter.py --source "path/to/video.mp4" --view-img -``` - -## Usage Options - -- `--source`: Specifies the path to the video file you want to run inference on. -- `--device`: Specifies the device `cpu` or `0` -- `--save-img`: Flag to save the detection results as images. -- `--weights`: Specifies a different YOLOv8 model file (e.g., `yolov8n.pt`, `yolov8s.pt`, `yolov8m.pt`, `yolov8l.pt`, `yolov8x.pt`). -- `--classes`: Specifies the class to be detected -- `--line-thickness`: Specifies the bounding box thickness -- `--region-thickness`: Specifies the region boxes thickness -- `--track-thickness`: Specifies the track line thickness - -## FAQ - -**1. What Does Region Counting Involve?** - -Region counting is a computational method utilized to ascertain the quantity of objects within a specific area in recorded video or real-time streams. This technique finds frequent application in image processing, computer vision, and pattern recognition, facilitating the analysis and segmentation of objects or features based on their spatial relationships. - -**2. Is Friendly Region Plotting Supported by the Region Counter?** - -The Region Counter offers the capability to create regions in various formats, such as polygons and rectangles. You have the flexibility to modify region attributes, including coordinates, colors, and other details, as demonstrated in the following code: - -```python -from shapely.geometry import Polygon - -counting_regions = [ - { - "name": "YOLOv8 Polygon Region", - "polygon": Polygon( - [(50, 80), (250, 20), (450, 80), (400, 350), (100, 350)] - ), # Polygon with five points (Pentagon) - "counts": 0, - "dragging": False, - "region_color": (255, 42, 4), # BGR Value - "text_color": (255, 255, 255), # Region Text Color - }, - { - "name": "YOLOv8 Rectangle Region", - "polygon": Polygon( - [(200, 250), (440, 250), (440, 550), (200, 550)] - ), # Rectangle with four points - "counts": 0, - "dragging": False, - "region_color": (37, 255, 225), # BGR Value - "text_color": (0, 0, 0), # Region Text Color - }, -] -``` - -**3. Why Combine Region Counting with YOLOv8?** - -YOLOv8 specializes in the detection and tracking of objects in video streams. Region counting complements this by enabling object counting within designated areas, making it a valuable application of YOLOv8. - -**4. How Can I Troubleshoot Issues?** - -To gain more insights during inference, you can include the `--debug` flag in your command: - -```bash -python yolov8_region_counter.py --source "path to video file" --debug -``` - -**5. Can I Employ Other YOLO Versions?** - -Certainly, you have the flexibility to specify different YOLO model weights using the `--weights` option. - -**6. Where Can I Access Additional Information?** - -For a comprehensive guide on using YOLOv8 with Object Tracking, please refer to [Multi-Object Tracking with Ultralytics YOLO](https://docs.ultralytics.com/modes/track/). diff --git a/ultralytics-main/examples/YOLOv8-Region-Counter/yolov8_region_counter.py b/ultralytics-main/examples/YOLOv8-Region-Counter/yolov8_region_counter.py deleted file mode 100644 index b7e9c3b..0000000 --- a/ultralytics-main/examples/YOLOv8-Region-Counter/yolov8_region_counter.py +++ /dev/null @@ -1,251 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse -from collections import defaultdict -from pathlib import Path - -import cv2 -import numpy as np -from shapely.geometry import Polygon -from shapely.geometry.point import Point - -from ultralytics import YOLO -from ultralytics.utils.files import increment_path -from ultralytics.utils.plotting import Annotator, colors - -track_history = defaultdict(list) - -current_region = None -counting_regions = [ - { - "name": "YOLOv8 Polygon Region", - "polygon": Polygon([(50, 80), (250, 20), (450, 80), (400, 350), (100, 350)]), # Polygon points - "counts": 0, - "dragging": False, - "region_color": (255, 42, 4), # BGR Value - "text_color": (255, 255, 255), # Region Text Color - }, - { - "name": "YOLOv8 Rectangle Region", - "polygon": Polygon([(200, 250), (440, 250), (440, 550), (200, 550)]), # Polygon points - "counts": 0, - "dragging": False, - "region_color": (37, 255, 225), # BGR Value - "text_color": (0, 0, 0), # Region Text Color - }, -] - - -def mouse_callback(event, x, y, flags, param): - """ - Handles mouse events for region manipulation. - - Parameters: - event (int): The mouse event type (e.g., cv2.EVENT_LBUTTONDOWN). - x (int): The x-coordinate of the mouse pointer. - y (int): The y-coordinate of the mouse pointer. - flags (int): Additional flags passed by OpenCV. - param: Additional parameters passed to the callback (not used in this function). - - Global Variables: - current_region (dict): A dictionary representing the current selected region. - - Mouse Events: - - LBUTTONDOWN: Initiates dragging for the region containing the clicked point. - - MOUSEMOVE: Moves the selected region if dragging is active. - - LBUTTONUP: Ends dragging for the selected region. - - Notes: - - This function is intended to be used as a callback for OpenCV mouse events. - - Requires the existence of the 'counting_regions' list and the 'Polygon' class. - - Example: - >>> cv2.setMouseCallback(window_name, mouse_callback) - """ - global current_region - - # Mouse left button down event - if event == cv2.EVENT_LBUTTONDOWN: - for region in counting_regions: - if region["polygon"].contains(Point((x, y))): - current_region = region - current_region["dragging"] = True - current_region["offset_x"] = x - current_region["offset_y"] = y - - # Mouse move event - elif event == cv2.EVENT_MOUSEMOVE: - if current_region is not None and current_region["dragging"]: - dx = x - current_region["offset_x"] - dy = y - current_region["offset_y"] - current_region["polygon"] = Polygon( - [(p[0] + dx, p[1] + dy) for p in current_region["polygon"].exterior.coords] - ) - current_region["offset_x"] = x - current_region["offset_y"] = y - - # Mouse left button up event - elif event == cv2.EVENT_LBUTTONUP: - if current_region is not None and current_region["dragging"]: - current_region["dragging"] = False - - -def run( - weights="yolov8n.pt", - source=None, - device="cpu", - view_img=False, - save_img=False, - exist_ok=False, - classes=None, - line_thickness=2, - track_thickness=2, - region_thickness=2, -): - """ - Run Region counting on a video using YOLOv8 and ByteTrack. - - Supports movable region for real time counting inside specific area. - Supports multiple regions counting. - Regions can be Polygons or rectangle in shape - - Args: - weights (str): Model weights path. - source (str): Video file path. - device (str): processing device cpu, 0, 1 - view_img (bool): Show results. - save_img (bool): Save results. - exist_ok (bool): Overwrite existing files. - classes (list): classes to detect and track - line_thickness (int): Bounding box thickness. - track_thickness (int): Tracking line thickness - region_thickness (int): Region thickness. - """ - vid_frame_count = 0 - - # Check source path - if not Path(source).exists(): - raise FileNotFoundError(f"Source path '{source}' does not exist.") - - # Setup Model - model = YOLO(f"{weights}") - model.to("cuda") if device == "0" else model.to("cpu") - - # Extract classes names - names = model.model.names - - # Video setup - videocapture = cv2.VideoCapture(source) - frame_width, frame_height = int(videocapture.get(3)), int(videocapture.get(4)) - fps, fourcc = int(videocapture.get(5)), cv2.VideoWriter_fourcc(*"mp4v") - - # Output setup - save_dir = increment_path(Path("ultralytics_rc_output") / "exp", exist_ok) - save_dir.mkdir(parents=True, exist_ok=True) - video_writer = cv2.VideoWriter(str(save_dir / f"{Path(source).stem}.mp4"), fourcc, fps, (frame_width, frame_height)) - - # Iterate over video frames - while videocapture.isOpened(): - success, frame = videocapture.read() - if not success: - break - vid_frame_count += 1 - - # Extract the results - results = model.track(frame, persist=True, classes=classes) - - if results[0].boxes.id is not None: - boxes = results[0].boxes.xyxy.cpu() - track_ids = results[0].boxes.id.int().cpu().tolist() - clss = results[0].boxes.cls.cpu().tolist() - - annotator = Annotator(frame, line_width=line_thickness, example=str(names)) - - for box, track_id, cls in zip(boxes, track_ids, clss): - annotator.box_label(box, str(names[cls]), color=colors(cls, True)) - bbox_center = (box[0] + box[2]) / 2, (box[1] + box[3]) / 2 # Bbox center - - track = track_history[track_id] # Tracking Lines plot - track.append((float(bbox_center[0]), float(bbox_center[1]))) - if len(track) > 30: - track.pop(0) - points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines(frame, [points], isClosed=False, color=colors(cls, True), thickness=track_thickness) - - # Check if detection inside region - for region in counting_regions: - if region["polygon"].contains(Point((bbox_center[0], bbox_center[1]))): - region["counts"] += 1 - - # Draw regions (Polygons/Rectangles) - for region in counting_regions: - region_label = str(region["counts"]) - region_color = region["region_color"] - region_text_color = region["text_color"] - - polygon_coords = np.array(region["polygon"].exterior.coords, dtype=np.int32) - centroid_x, centroid_y = int(region["polygon"].centroid.x), int(region["polygon"].centroid.y) - - text_size, _ = cv2.getTextSize( - region_label, cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.7, thickness=line_thickness - ) - text_x = centroid_x - text_size[0] // 2 - text_y = centroid_y + text_size[1] // 2 - cv2.rectangle( - frame, - (text_x - 5, text_y - text_size[1] - 5), - (text_x + text_size[0] + 5, text_y + 5), - region_color, - -1, - ) - cv2.putText( - frame, region_label, (text_x, text_y), cv2.FONT_HERSHEY_SIMPLEX, 0.7, region_text_color, line_thickness - ) - cv2.polylines(frame, [polygon_coords], isClosed=True, color=region_color, thickness=region_thickness) - - if view_img: - if vid_frame_count == 1: - cv2.namedWindow("Ultralytics YOLOv8 Region Counter Movable") - cv2.setMouseCallback("Ultralytics YOLOv8 Region Counter Movable", mouse_callback) - cv2.imshow("Ultralytics YOLOv8 Region Counter Movable", frame) - - if save_img: - video_writer.write(frame) - - for region in counting_regions: # Reinitialize count for each region - region["counts"] = 0 - - if cv2.waitKey(1) & 0xFF == ord("q"): - break - - del vid_frame_count - video_writer.release() - videocapture.release() - cv2.destroyAllWindows() - - -def parse_opt(): - """Parse command line arguments.""" - parser = argparse.ArgumentParser() - parser.add_argument("--weights", type=str, default="yolov8n.pt", help="initial weights path") - parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu") - parser.add_argument("--source", type=str, required=True, help="video file path") - parser.add_argument("--view-img", action="store_true", help="show results") - parser.add_argument("--save-img", action="store_true", help="save results") - parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment") - parser.add_argument("--classes", nargs="+", type=int, help="filter by class: --classes 0, or --classes 0 2 3") - parser.add_argument("--line-thickness", type=int, default=2, help="bounding box thickness") - parser.add_argument("--track-thickness", type=int, default=2, help="Tracking line thickness") - parser.add_argument("--region-thickness", type=int, default=4, help="Region thickness") - - return parser.parse_args() - - -def main(opt): - """Main function.""" - run(**vars(opt)) - - -if __name__ == "__main__": - opt = parse_opt() - main(opt) diff --git a/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/readme.md b/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/readme.md deleted file mode 100644 index f24df30..0000000 --- a/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/readme.md +++ /dev/null @@ -1,69 +0,0 @@ -# YOLOv8 with SAHI (Inference on Video) - -[SAHI](https://docs.ultralytics.com/guides/sahi-tiled-inference/) is designed to optimize object detection algorithms for large-scale and high-resolution imagery. It partitions images into manageable slices, performs object detection on each slice, and then stitches the results back together. This tutorial will guide you through the process of running YOLOv8 inference on video files with the aid of SAHI. - -## Table of Contents - -- [Step 1: Install the Required Libraries](#step-1-install-the-required-libraries) -- [Step 2: Run the Inference with SAHI using Ultralytics YOLOv8](#step-2-run-the-inference-with-sahi-using-ultralytics-yolov8) -- [Usage Options](#usage-options) -- [FAQ](#faq) - -## Step 1: Install the Required Libraries - -Clone the repository, install dependencies and `cd` to this local directory for commands in Step 2. - -```bash -# Clone ultralytics repo -git clone https://github.com/ultralytics/ultralytics - -# Install dependencies -pip install sahi ultralytics - -# cd to local directory -cd ultralytics/examples/YOLOv8-SAHI-Inference-Video -``` - -## Step 2: Run the Inference with SAHI using Ultralytics YOLOv8 - -Here are the basic commands for running the inference: - -```bash -#if you want to save results -python yolov8_sahi.py --source "path/to/video.mp4" --save-img - -#if you want to change model file -python yolov8_sahi.py --source "path/to/video.mp4" --save-img --weights "yolov8n.pt" -``` - -## Usage Options - -- `--source`: Specifies the path to the video file you want to run inference on. -- `--save-img`: Flag to save the detection results as images. -- `--weights`: Specifies a different YOLOv8 model file (e.g., `yolov8n.pt`, `yolov8s.pt`, `yolov8m.pt`, `yolov8l.pt`, `yolov8x.pt`). - -## FAQ - -**1. What is SAHI?** - -SAHI stands for Slicing, Analysis, and Healing of Images. It is a library designed to optimize object detection algorithms for large-scale and high-resolution images. The library source code is available on [GitHub](https://github.com/obss/sahi). - -**2. Why use SAHI with YOLOv8?** - -SAHI can handle large-scale images by slicing them into smaller, more manageable sizes without compromising the detection quality. This makes it a great companion to YOLOv8, especially when working with high-resolution videos. - -**3. How do I debug issues?** - -You can add the `--debug` flag to your command to print out more information during inference: - -```bash -python yolov8_sahi.py --source "path to video file" --debug -``` - -**4. Can I use other YOLO versions?** - -Yes, you can specify different YOLO model weights using the `--weights` option. - -**5. Where can I find more information?** - -For a full guide to YOLOv8 with SAHI see [https://docs.ultralytics.com/guides/sahi-tiled-inference](https://docs.ultralytics.com/guides/sahi-tiled-inference/). diff --git a/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/yolov8_sahi.py b/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/yolov8_sahi.py deleted file mode 100644 index f2b8274..0000000 --- a/ultralytics-main/examples/YOLOv8-SAHI-Inference-Video/yolov8_sahi.py +++ /dev/null @@ -1,111 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse -from pathlib import Path - -import cv2 -from sahi import AutoDetectionModel -from sahi.predict import get_sliced_prediction -from sahi.utils.yolov8 import download_yolov8s_model - -from ultralytics.utils.files import increment_path - - -def run(weights="yolov8n.pt", source="test.mp4", view_img=False, save_img=False, exist_ok=False): - """ - Run object detection on a video using YOLOv8 and SAHI. - - Args: - weights (str): Model weights path. - source (str): Video file path. - view_img (bool): Show results. - save_img (bool): Save results. - exist_ok (bool): Overwrite existing files. - """ - - # Check source path - if not Path(source).exists(): - raise FileNotFoundError(f"Source path '{source}' does not exist.") - - yolov8_model_path = f"models/{weights}" - download_yolov8s_model(yolov8_model_path) - detection_model = AutoDetectionModel.from_pretrained( - model_type="yolov8", model_path=yolov8_model_path, confidence_threshold=0.3, device="cpu" - ) - - # Video setup - videocapture = cv2.VideoCapture(source) - frame_width, frame_height = int(videocapture.get(3)), int(videocapture.get(4)) - fps, fourcc = int(videocapture.get(5)), cv2.VideoWriter_fourcc(*"mp4v") - - # Output setup - save_dir = increment_path(Path("ultralytics_results_with_sahi") / "exp", exist_ok) - save_dir.mkdir(parents=True, exist_ok=True) - video_writer = cv2.VideoWriter(str(save_dir / f"{Path(source).stem}.mp4"), fourcc, fps, (frame_width, frame_height)) - - while videocapture.isOpened(): - success, frame = videocapture.read() - if not success: - break - - results = get_sliced_prediction( - frame, detection_model, slice_height=512, slice_width=512, overlap_height_ratio=0.2, overlap_width_ratio=0.2 - ) - object_prediction_list = results.object_prediction_list - - boxes_list = [] - clss_list = [] - for ind, _ in enumerate(object_prediction_list): - boxes = ( - object_prediction_list[ind].bbox.minx, - object_prediction_list[ind].bbox.miny, - object_prediction_list[ind].bbox.maxx, - object_prediction_list[ind].bbox.maxy, - ) - clss = object_prediction_list[ind].category.name - boxes_list.append(boxes) - clss_list.append(clss) - - for box, cls in zip(boxes_list, clss_list): - x1, y1, x2, y2 = box - cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (56, 56, 255), 2) - label = str(cls) - t_size = cv2.getTextSize(label, 0, fontScale=0.6, thickness=1)[0] - cv2.rectangle( - frame, (int(x1), int(y1) - t_size[1] - 3), (int(x1) + t_size[0], int(y1) + 3), (56, 56, 255), -1 - ) - cv2.putText( - frame, label, (int(x1), int(y1) - 2), 0, 0.6, [255, 255, 255], thickness=1, lineType=cv2.LINE_AA - ) - - if view_img: - cv2.imshow(Path(source).stem, frame) - if save_img: - video_writer.write(frame) - - if cv2.waitKey(1) & 0xFF == ord("q"): - break - video_writer.release() - videocapture.release() - cv2.destroyAllWindows() - - -def parse_opt(): - """Parse command line arguments.""" - parser = argparse.ArgumentParser() - parser.add_argument("--weights", type=str, default="yolov8n.pt", help="initial weights path") - parser.add_argument("--source", type=str, required=True, help="video file path") - parser.add_argument("--view-img", action="store_true", help="show results") - parser.add_argument("--save-img", action="store_true", help="save results") - parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment") - return parser.parse_args() - - -def main(opt): - """Main function.""" - run(**vars(opt)) - - -if __name__ == "__main__": - opt = parse_opt() - main(opt) diff --git a/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/README.md b/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/README.md deleted file mode 100644 index 9327f1f..0000000 --- a/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/README.md +++ /dev/null @@ -1,63 +0,0 @@ -# YOLOv8-Segmentation-ONNXRuntime-Python Demo - -This repository provides a Python demo for performing segmentation with YOLOv8 using ONNX Runtime, highlighting the interoperability of YOLOv8 models without the need for the full PyTorch stack. - -## Features - -- **Framework Agnostic**: Runs segmentation inference purely on ONNX Runtime without importing PyTorch. -- **Efficient Inference**: Supports both FP32 and FP16 precision for ONNX models, catering to different computational needs. -- **Ease of Use**: Utilizes simple command-line arguments for model execution. -- **Broad Compatibility**: Leverages Numpy and OpenCV for image processing, ensuring broad compatibility with various environments. - -## Installation - -Install the required packages using pip. You will need `ultralytics` for exporting YOLOv8-seg ONNX model and using some utility functions, `onnxruntime-gpu` for GPU-accelerated inference, and `opencv-python` for image processing. - -```bash -pip install ultralytics -pip install onnxruntime-gpu # For GPU support -# pip install onnxruntime # Use this instead if you don't have an NVIDIA GPU -pip install numpy -pip install opencv-python -``` - -## Getting Started - -### 1. Export the YOLOv8 ONNX Model - -Export the YOLOv8 segmentation model to ONNX format using the provided `ultralytics` package. - -```bash -yolo export model=yolov8s-seg.pt imgsz=640 format=onnx opset=12 simplify -``` - -### 2. Run Inference - -Perform inference with the exported ONNX model on your images. - -```bash -python main.py --model-path --source -``` - -### Example Output - -After running the command, you should see segmentation results similar to this: - -Segmentation Demo - -## Advanced Usage - -For more advanced usage, including real-time video processing, please refer to the `main.py` script's command-line arguments. - -## Contributing - -We welcome contributions to improve this demo! Please submit issues and pull requests for bug reports, feature requests, or submitting a new algorithm enhancement. - -## License - -This project is licensed under the AGPL-3.0 License - see the [LICENSE](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) file for details. - -## Acknowledgments - -- The YOLOv8-Segmentation-ONNXRuntime-Python demo is contributed by GitHub user [jamjamjon](https://github.com/jamjamjon). -- Thanks to the ONNX Runtime community for providing a robust and efficient inference engine. diff --git a/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/main.py b/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/main.py deleted file mode 100644 index 141d21b..0000000 --- a/ultralytics-main/examples/YOLOv8-Segmentation-ONNXRuntime-Python/main.py +++ /dev/null @@ -1,342 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import argparse - -import cv2 -import numpy as np -import onnxruntime as ort - -from ultralytics.utils import ASSETS, yaml_load -from ultralytics.utils.checks import check_yaml -from ultralytics.utils.plotting import Colors - - -class YOLOv8Seg: - """YOLOv8 segmentation model.""" - - def __init__(self, onnx_model): - """ - Initialization. - - Args: - onnx_model (str): Path to the ONNX model. - """ - - # Build Ort session - self.session = ort.InferenceSession( - onnx_model, - providers=["CUDAExecutionProvider", "CPUExecutionProvider"] - if ort.get_device() == "GPU" - else ["CPUExecutionProvider"], - ) - - # Numpy dtype: support both FP32 and FP16 onnx model - self.ndtype = np.half if self.session.get_inputs()[0].type == "tensor(float16)" else np.single - - # Get model width and height(YOLOv8-seg only has one input) - self.model_height, self.model_width = [x.shape for x in self.session.get_inputs()][0][-2:] - - # Load COCO class names - self.classes = yaml_load(check_yaml("coco128.yaml"))["names"] - - # Create color palette - self.color_palette = Colors() - - def __call__(self, im0, conf_threshold=0.4, iou_threshold=0.45, nm=32): - """ - The whole pipeline: pre-process -> inference -> post-process. - - Args: - im0 (Numpy.ndarray): original input image. - conf_threshold (float): confidence threshold for filtering predictions. - iou_threshold (float): iou threshold for NMS. - nm (int): the number of masks. - - Returns: - boxes (List): list of bounding boxes. - segments (List): list of segments. - masks (np.ndarray): [N, H, W], output masks. - """ - - # Pre-process - im, ratio, (pad_w, pad_h) = self.preprocess(im0) - - # Ort inference - preds = self.session.run(None, {self.session.get_inputs()[0].name: im}) - - # Post-process - boxes, segments, masks = self.postprocess( - preds, - im0=im0, - ratio=ratio, - pad_w=pad_w, - pad_h=pad_h, - conf_threshold=conf_threshold, - iou_threshold=iou_threshold, - nm=nm, - ) - return boxes, segments, masks - - def preprocess(self, img): - """ - Pre-processes the input image. - - Args: - img (Numpy.ndarray): image about to be processed. - - Returns: - img_process (Numpy.ndarray): image preprocessed for inference. - ratio (tuple): width, height ratios in letterbox. - pad_w (float): width padding in letterbox. - pad_h (float): height padding in letterbox. - """ - - # Resize and pad input image using letterbox() (Borrowed from Ultralytics) - shape = img.shape[:2] # original image shape - new_shape = (self.model_height, self.model_width) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - ratio = r, r - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - pad_w, pad_h = (new_shape[1] - new_unpad[0]) / 2, (new_shape[0] - new_unpad[1]) / 2 # wh padding - if shape[::-1] != new_unpad: # resize - img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(pad_h - 0.1)), int(round(pad_h + 0.1)) - left, right = int(round(pad_w - 0.1)), int(round(pad_w + 0.1)) - img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)) - - # Transforms: HWC to CHW -> BGR to RGB -> div(255) -> contiguous -> add axis(optional) - img = np.ascontiguousarray(np.einsum("HWC->CHW", img)[::-1], dtype=self.ndtype) / 255.0 - img_process = img[None] if len(img.shape) == 3 else img - return img_process, ratio, (pad_w, pad_h) - - def postprocess(self, preds, im0, ratio, pad_w, pad_h, conf_threshold, iou_threshold, nm=32): - """ - Post-process the prediction. - - Args: - preds (Numpy.ndarray): predictions come from ort.session.run(). - im0 (Numpy.ndarray): [h, w, c] original input image. - ratio (tuple): width, height ratios in letterbox. - pad_w (float): width padding in letterbox. - pad_h (float): height padding in letterbox. - conf_threshold (float): conf threshold. - iou_threshold (float): iou threshold. - nm (int): the number of masks. - - Returns: - boxes (List): list of bounding boxes. - segments (List): list of segments. - masks (np.ndarray): [N, H, W], output masks. - """ - x, protos = preds[0], preds[1] # Two outputs: predictions and protos - - # Transpose the first output: (Batch_size, xywh_conf_cls_nm, Num_anchors) -> (Batch_size, Num_anchors, xywh_conf_cls_nm) - x = np.einsum("bcn->bnc", x) - - # Predictions filtering by conf-threshold - x = x[np.amax(x[..., 4:-nm], axis=-1) > conf_threshold] - - # Create a new matrix which merge these(box, score, cls, nm) into one - # For more details about `numpy.c_()`: https://numpy.org/doc/1.26/reference/generated/numpy.c_.html - x = np.c_[x[..., :4], np.amax(x[..., 4:-nm], axis=-1), np.argmax(x[..., 4:-nm], axis=-1), x[..., -nm:]] - - # NMS filtering - x = x[cv2.dnn.NMSBoxes(x[:, :4], x[:, 4], conf_threshold, iou_threshold)] - - # Decode and return - if len(x) > 0: - # Bounding boxes format change: cxcywh -> xyxy - x[..., [0, 1]] -= x[..., [2, 3]] / 2 - x[..., [2, 3]] += x[..., [0, 1]] - - # Rescales bounding boxes from model shape(model_height, model_width) to the shape of original image - x[..., :4] -= [pad_w, pad_h, pad_w, pad_h] - x[..., :4] /= min(ratio) - - # Bounding boxes boundary clamp - x[..., [0, 2]] = x[:, [0, 2]].clip(0, im0.shape[1]) - x[..., [1, 3]] = x[:, [1, 3]].clip(0, im0.shape[0]) - - # Process masks - masks = self.process_mask(protos[0], x[:, 6:], x[:, :4], im0.shape) - - # Masks -> Segments(contours) - segments = self.masks2segments(masks) - return x[..., :6], segments, masks # boxes, segments, masks - else: - return [], [], [] - - @staticmethod - def masks2segments(masks): - """ - It takes a list of masks(n,h,w) and returns a list of segments(n,xy) (Borrowed from - https://github.com/ultralytics/ultralytics/blob/465df3024f44fa97d4fad9986530d5a13cdabdca/ultralytics/utils/ops.py#L750) - - Args: - masks (numpy.ndarray): the output of the model, which is a tensor of shape (batch_size, 160, 160). - - Returns: - segments (List): list of segment masks. - """ - segments = [] - for x in masks.astype("uint8"): - c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0] # CHAIN_APPROX_SIMPLE - if c: - c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2) - else: - c = np.zeros((0, 2)) # no segments found - segments.append(c.astype("float32")) - return segments - - @staticmethod - def crop_mask(masks, boxes): - """ - It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box. (Borrowed from - https://github.com/ultralytics/ultralytics/blob/465df3024f44fa97d4fad9986530d5a13cdabdca/ultralytics/utils/ops.py#L599) - - Args: - masks (Numpy.ndarray): [n, h, w] tensor of masks. - boxes (Numpy.ndarray): [n, 4] tensor of bbox coordinates in relative point form. - - Returns: - (Numpy.ndarray): The masks are being cropped to the bounding box. - """ - n, h, w = masks.shape - x1, y1, x2, y2 = np.split(boxes[:, :, None], 4, 1) - r = np.arange(w, dtype=x1.dtype)[None, None, :] - c = np.arange(h, dtype=x1.dtype)[None, :, None] - return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2)) - - def process_mask(self, protos, masks_in, bboxes, im0_shape): - """ - Takes the output of the mask head, and applies the mask to the bounding boxes. This produces masks of higher quality - but is slower. (Borrowed from https://github.com/ultralytics/ultralytics/blob/465df3024f44fa97d4fad9986530d5a13cdabdca/ultralytics/utils/ops.py#L618) - - Args: - protos (numpy.ndarray): [mask_dim, mask_h, mask_w]. - masks_in (numpy.ndarray): [n, mask_dim], n is number of masks after nms. - bboxes (numpy.ndarray): bboxes re-scaled to original image shape. - im0_shape (tuple): the size of the input image (h,w,c). - - Returns: - (numpy.ndarray): The upsampled masks. - """ - c, mh, mw = protos.shape - masks = np.matmul(masks_in, protos.reshape((c, -1))).reshape((-1, mh, mw)).transpose(1, 2, 0) # HWN - masks = np.ascontiguousarray(masks) - masks = self.scale_mask(masks, im0_shape) # re-scale mask from P3 shape to original input image shape - masks = np.einsum("HWN -> NHW", masks) # HWN -> NHW - masks = self.crop_mask(masks, bboxes) - return np.greater(masks, 0.5) - - @staticmethod - def scale_mask(masks, im0_shape, ratio_pad=None): - """ - Takes a mask, and resizes it to the original image size. (Borrowed from - https://github.com/ultralytics/ultralytics/blob/465df3024f44fa97d4fad9986530d5a13cdabdca/ultralytics/utils/ops.py#L305) - - Args: - masks (np.ndarray): resized and padded masks/images, [h, w, num]/[h, w, 3]. - im0_shape (tuple): the original image shape. - ratio_pad (tuple): the ratio of the padding to the original image. - - Returns: - masks (np.ndarray): The masks that are being returned. - """ - im1_shape = masks.shape[:2] - if ratio_pad is None: # calculate from im0_shape - gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new - pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding - else: - pad = ratio_pad[1] - - # Calculate tlbr of mask - top, left = int(round(pad[1] - 0.1)), int(round(pad[0] - 0.1)) # y, x - bottom, right = int(round(im1_shape[0] - pad[1] + 0.1)), int(round(im1_shape[1] - pad[0] + 0.1)) - if len(masks.shape) < 2: - raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') - masks = masks[top:bottom, left:right] - masks = cv2.resize( - masks, (im0_shape[1], im0_shape[0]), interpolation=cv2.INTER_LINEAR - ) # INTER_CUBIC would be better - if len(masks.shape) == 2: - masks = masks[:, :, None] - return masks - - def draw_and_visualize(self, im, bboxes, segments, vis=False, save=True): - """ - Draw and visualize results. - - Args: - im (np.ndarray): original image, shape [h, w, c]. - bboxes (numpy.ndarray): [n, 4], n is number of bboxes. - segments (List): list of segment masks. - vis (bool): imshow using OpenCV. - save (bool): save image annotated. - - Returns: - None - """ - - # Draw rectangles and polygons - im_canvas = im.copy() - for (*box, conf, cls_), segment in zip(bboxes, segments): - # draw contour and fill mask - cv2.polylines(im, np.int32([segment]), True, (255, 255, 255), 2) # white borderline - cv2.fillPoly(im_canvas, np.int32([segment]), self.color_palette(int(cls_), bgr=True)) - - # draw bbox rectangle - cv2.rectangle( - im, - (int(box[0]), int(box[1])), - (int(box[2]), int(box[3])), - self.color_palette(int(cls_), bgr=True), - 1, - cv2.LINE_AA, - ) - cv2.putText( - im, - f"{self.classes[cls_]}: {conf:.3f}", - (int(box[0]), int(box[1] - 9)), - cv2.FONT_HERSHEY_SIMPLEX, - 0.7, - self.color_palette(int(cls_), bgr=True), - 2, - cv2.LINE_AA, - ) - - # Mix image - im = cv2.addWeighted(im_canvas, 0.3, im, 0.7, 0) - - # Show image - if vis: - cv2.imshow("demo", im) - cv2.waitKey(0) - cv2.destroyAllWindows() - - # Save image - if save: - cv2.imwrite("demo.jpg", im) - - -if __name__ == "__main__": - # Create an argument parser to handle command-line arguments - parser = argparse.ArgumentParser() - parser.add_argument("--model", type=str, required=True, help="Path to ONNX model") - parser.add_argument("--source", type=str, default=str(ASSETS / "bus.jpg"), help="Path to input image") - parser.add_argument("--conf", type=float, default=0.25, help="Confidence threshold") - parser.add_argument("--iou", type=float, default=0.45, help="NMS IoU threshold") - args = parser.parse_args() - - # Build model - model = YOLOv8Seg(args.model) - - # Read image by OpenCV - img = cv2.imread(args.source) - - # Inference - boxes, segments, _ = model(img, conf_threshold=args.conf, iou_threshold=args.iou) - - # Draw bboxes and polygons - if len(boxes) > 0: - model.draw_and_visualize(img, boxes, segments, vis=False, save=True) diff --git a/ultralytics-main/examples/heatmaps.ipynb b/ultralytics-main/examples/heatmaps.ipynb deleted file mode 100644 index 0cc520c..0000000 --- a/ultralytics-main/examples/heatmaps.ipynb +++ /dev/null @@ -1,145 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "provenance": [], - "gpuType": "T4" - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - }, - "accelerator": "GPU" - }, - "cells": [ - { - "cell_type": "markdown", - "source": [ - "
\n", - "\n", - " \n", - " \n", - "\n", - " [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)\n", - "\n", - " \"Open\n", - "\n", - "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) AI models developed by Ultralytics. This notebook serves as the starting point for exploring the heatmaps and understand its features and capabilities.\n", - "\n", - "YOLOv8 models are fast, accurate, and easy to use, making them ideal for various object detection and image segmentation tasks. They can be trained on large datasets and run on diverse hardware platforms, from CPUs to GPUs.\n", - "\n", - "We hope that the resources in this notebook will help you get the most out of Ultralytics Heatmaps. Please browse the YOLOv8 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n", - "\n", - "
" - ], - "metadata": { - "id": "PN1cAxdvd61e" - } - }, - { - "cell_type": "markdown", - "source": [ - "# Setup\n", - "\n", - "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." - ], - "metadata": { - "id": "o68Sg1oOeZm2" - } - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "9dSwz_uOReMI" - }, - "outputs": [], - "source": [ - "!pip install ultralytics" - ] - }, - { - "cell_type": "markdown", - "source": [ - "# Ultralytics Heatmaps\n", - "\n", - "Heatmap is color-coded matrix, generated by Ultralytics YOLOv8, simplifies intricate data by using vibrant colors. This visual representation employs warmer hues for higher intensities and cooler tones for lower values. Heatmaps are effective in illustrating complex data patterns, correlations, and anomalies, providing a user-friendly and engaging way to interpret data across various domains." - ], - "metadata": { - "id": "m7VkxQ2aeg7k" - } - }, - { - "cell_type": "code", - "source": [ - "from ultralytics import YOLO\n", - "from ultralytics.solutions import heatmap\n", - "import cv2\n", - "\n", - "model = YOLO(\"yolov8n.pt\")\n", - "cap = cv2.VideoCapture(\"path/to/video/file.mp4\")\n", - "assert cap.isOpened(), \"Error reading video file\"\n", - "w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))\n", - "\n", - "# Video writer\n", - "video_writer = cv2.VideoWriter(\"heatmap_output.avi\",\n", - " cv2.VideoWriter_fourcc(*'mp4v'),\n", - " fps,\n", - " (w, h))\n", - "\n", - "# Init heatmap\n", - "heatmap_obj = heatmap.Heatmap()\n", - "heatmap_obj.set_args(colormap=cv2.COLORMAP_PARULA,\n", - " imw=w,\n", - " imh=h,\n", - " view_img=True,\n", - " shape=\"circle\")\n", - "\n", - "while cap.isOpened():\n", - " success, im0 = cap.read()\n", - " if not success:\n", - " print(\"Video frame is empty or video processing has been successfully completed.\")\n", - " break\n", - " tracks = model.track(im0, persist=True, show=False)\n", - "\n", - " im0 = heatmap_obj.generate_heatmap(im0, tracks)\n", - " video_writer.write(im0)\n", - "\n", - "cap.release()\n", - "video_writer.release()\n", - "cv2.destroyAllWindows()" - ], - "metadata": { - "id": "Cx-u59HQdu2o" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "#Community Support\n", - "\n", - "For more information, you can explore Ultralytics Heatmaps Docs\n", - "\n", - "Ultralytics ⚡ resources\n", - "- About Us – https://ultralytics.com/about\n", - "- Join Our Team – https://ultralytics.com/work\n", - "- Contact Us – https://ultralytics.com/contact\n", - "- Discord – https://discord.gg/2wNGbc6g9X\n", - "- Ultralytics License – https://ultralytics.com/license\n", - "\n", - "YOLOv8 🚀 resources\n", - "- GitHub – https://github.com/ultralytics/ultralytics\n", - "- Docs – https://docs.ultralytics.com/" - ], - "metadata": { - "id": "QrlKg-y3fEyD" - } - } - ] -} \ No newline at end of file diff --git a/ultralytics-main/examples/hub.ipynb b/ultralytics-main/examples/hub.ipynb deleted file mode 100644 index 29d8ff1..0000000 --- a/ultralytics-main/examples/hub.ipynb +++ /dev/null @@ -1,106 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "name": "Ultralytics HUB", - "provenance": [] - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - }, - "accelerator": "GPU" - }, - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "FIzICjaph_Wy" - }, - "source": [ - "\n", - "\n", - "\n", - "
\n", - "\n", - "[中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)\n", - "\n", - " \n", - " \"CI\n", - " \n", - " \"Open\n", - "\n", - "Welcome to the [Ultralytics](https://ultralytics.com/) HUB notebook!\n", - "\n", - "This notebook allows you to train [YOLOv5](https://github.com/ultralytics/yolov5) and [YOLOv8](https://github.com/ultralytics/ultralytics) 🚀 models using [HUB](https://hub.ultralytics.com/). Please browse the HUB Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n", - "
" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "eRQ2ow94MiOv" - }, - "source": [ - "# Setup\n", - "\n", - "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "FyDnXd-n4c7Y", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "01e34b44-a26f-4dbc-a5a1-6e29bca01a1b" - }, - "source": [ - "%pip install ultralytics # install\n", - "from ultralytics import YOLO, checks, hub\n", - "checks() # checks" - ], - "execution_count": null, - "outputs": [ - { - "output_type": "stream", - "name": "stderr", - "text": [ - "Ultralytics YOLOv8.0.210 🚀 Python-3.10.12 torch-2.0.1+cu118 CUDA:0 (Tesla T4, 15102MiB)\n", - "Setup complete ✅ (2 CPUs, 12.7 GB RAM, 24.4/78.2 GB disk)\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "cQ9BwaAqxAm4" - }, - "source": [ - "# Start\n", - "\n", - "Login with your [API key](https://hub.ultralytics.com/settings?tab=api+keys), select your YOLO 🚀 model and start training!" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "XSlZaJ9Iw_iZ" - }, - "source": [ - "hub.login('API_KEY') # use your API key\n", - "\n", - "model = YOLO('https://hub.ultralytics.com/MODEL_ID') # use your model URL\n", - "results = model.train() # train model" - ], - "execution_count": null, - "outputs": [] - } - ] -} diff --git a/ultralytics-main/examples/object_counting.ipynb b/ultralytics-main/examples/object_counting.ipynb deleted file mode 100644 index ce11044..0000000 --- a/ultralytics-main/examples/object_counting.ipynb +++ /dev/null @@ -1,147 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "provenance": [], - "gpuType": "T4" - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - }, - "accelerator": "GPU" - }, - "cells": [ - { - "cell_type": "markdown", - "source": [ - "
\n", - "\n", - " \n", - " \n", - "\n", - " [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)\n", - "\n", - " \"Open\n", - "\n", - "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) AI models developed by Ultralytics. This notebook serves as the starting point for exploring the Object Counting and understand its features and capabilities.\n", - "\n", - "YOLOv8 models are fast, accurate, and easy to use, making them ideal for various object detection and image segmentation tasks. They can be trained on large datasets and run on diverse hardware platforms, from CPUs to GPUs.\n", - "\n", - "We hope that the resources in this notebook will help you get the most out of Ultralytics Object Counting. Please browse the YOLOv8 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n", - "\n", - "
" - ], - "metadata": { - "id": "PN1cAxdvd61e" - } - }, - { - "cell_type": "markdown", - "source": [ - "# Setup\n", - "\n", - "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." - ], - "metadata": { - "id": "o68Sg1oOeZm2" - } - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "9dSwz_uOReMI" - }, - "outputs": [], - "source": [ - "!pip install ultralytics" - ] - }, - { - "cell_type": "markdown", - "source": [ - "# Ultralytics Object Counting\n", - "\n", - "Counting objects using Ultralytics YOLOv8 entails the precise detection and enumeration of specific objects within videos and camera streams. YOLOv8 demonstrates exceptional performance in real-time applications, delivering efficient and accurate object counting across diverse scenarios such as crowd analysis and surveillance. This is attributed to its advanced algorithms and deep learning capabilities." - ], - "metadata": { - "id": "m7VkxQ2aeg7k" - } - }, - { - "cell_type": "code", - "source": [ - "from ultralytics import YOLO\n", - "from ultralytics.solutions import object_counter\n", - "import cv2\n", - "\n", - "model = YOLO(\"yolov8n.pt\")\n", - "cap = cv2.VideoCapture(\"path/to/video/file.mp4\")\n", - "assert cap.isOpened(), \"Error reading video file\"\n", - "w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))\n", - "\n", - "# Define region points\n", - "region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)]\n", - "\n", - "# Video writer\n", - "video_writer = cv2.VideoWriter(\"object_counting_output.avi\",\n", - " cv2.VideoWriter_fourcc(*'mp4v'),\n", - " fps,\n", - " (w, h))\n", - "\n", - "# Init Object Counter\n", - "counter = object_counter.ObjectCounter()\n", - "counter.set_args(view_img=True,\n", - " reg_pts=region_points,\n", - " classes_names=model.names,\n", - " draw_tracks=True)\n", - "\n", - "while cap.isOpened():\n", - " success, im0 = cap.read()\n", - " if not success:\n", - " print(\"Video frame is empty or video processing has been successfully completed.\")\n", - " break\n", - " tracks = model.track(im0, persist=True, show=False)\n", - "\n", - " im0 = counter.start_counting(im0, tracks)\n", - " video_writer.write(im0)\n", - "\n", - "cap.release()\n", - "video_writer.release()\n", - "cv2.destroyAllWindows()" - ], - "metadata": { - "id": "Cx-u59HQdu2o" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "#Community Support\n", - "\n", - "For more information, you can explore Ultralytics Object Counting Docs\n", - "\n", - "Ultralytics ⚡ resources\n", - "- About Us – https://ultralytics.com/about\n", - "- Join Our Team – https://ultralytics.com/work\n", - "- Contact Us – https://ultralytics.com/contact\n", - "- Discord – https://discord.gg/2wNGbc6g9X\n", - "- Ultralytics License – https://ultralytics.com/license\n", - "\n", - "YOLOv8 🚀 resources\n", - "- GitHub – https://github.com/ultralytics/ultralytics\n", - "- Docs – https://docs.ultralytics.com/" - ], - "metadata": { - "id": "QrlKg-y3fEyD" - } - } - ] -} \ No newline at end of file diff --git a/ultralytics-main/examples/object_tracking.ipynb b/ultralytics-main/examples/object_tracking.ipynb deleted file mode 100644 index e1a0d4e..0000000 --- a/ultralytics-main/examples/object_tracking.ipynb +++ /dev/null @@ -1,203 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "provenance": [], - "gpuType": "T4" - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "language_info": { - "name": "python" - }, - "accelerator": "GPU" - }, - "cells": [ - { - "cell_type": "markdown", - "source": [ - "
\n", - "\n", - " \n", - " \n", - "\n", - " [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)\n", - "\n", - " \"Open\n", - "\n", - "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) AI models developed by Ultralytics. This notebook serves as the starting point for exploring the Object Tracking and understand its features and capabilities.\n", - "\n", - "YOLOv8 models are fast, accurate, and easy to use, making them ideal for various object detection and image segmentation tasks. They can be trained on large datasets and run on diverse hardware platforms, from CPUs to GPUs.\n", - "\n", - "We hope that the resources in this notebook will help you get the most out of Ultralytics Object Tracking. Please browse the YOLOv8 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n", - "\n", - "
" - ], - "metadata": { - "id": "PN1cAxdvd61e" - } - }, - { - "cell_type": "markdown", - "source": [ - "# Setup\n", - "\n", - "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." - ], - "metadata": { - "id": "o68Sg1oOeZm2" - } - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "9dSwz_uOReMI" - }, - "outputs": [], - "source": [ - "!pip install ultralytics" - ] - }, - { - "cell_type": "markdown", - "source": [ - "# Ultralytics Object Tracking\n", - "\n", - "Within the domain of video analytics, object tracking stands out as a crucial undertaking. It goes beyond merely identifying the location and class of objects within the frame; it also involves assigning a unique ID to each detected object as the video unfolds. The applications of this technology are vast, spanning from surveillance and security to real-time sports analytics." - ], - "metadata": { - "id": "m7VkxQ2aeg7k" - } - }, - { - "cell_type": "markdown", - "source": [ - "## CLI" - ], - "metadata": { - "id": "-ZF9DM6e6gz0" - } - }, - { - "cell_type": "code", - "source": [ - "!yolo track source=\"/path/to/video/file.mp4\" save=True" - ], - "metadata": { - "id": "-XJqhOwo6iqT" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "## Python\n", - "\n", - "- Draw Object tracking trails" - ], - "metadata": { - "id": "XRcw0vIE6oNb" - } - }, - { - "cell_type": "code", - "source": [ - "import cv2\n", - "import numpy as np\n", - "from ultralytics import YOLO\n", - "\n", - "from ultralytics.utils.checks import check_imshow\n", - "from ultralytics.utils.plotting import Annotator, colors\n", - "\n", - "from collections import defaultdict\n", - "\n", - "track_history = defaultdict(lambda: [])\n", - "model = YOLO(\"yolov8n.pt\")\n", - "names = model.model.names\n", - "\n", - "video_path = \"/path/to/video/file.mp4\"\n", - "cap = cv2.VideoCapture(video_path)\n", - "assert cap.isOpened(), \"Error reading video file\"\n", - "\n", - "w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))\n", - "\n", - "result = cv2.VideoWriter(\"object_tracking.avi\",\n", - " cv2.VideoWriter_fourcc(*'mp4v'),\n", - " fps,\n", - " (w, h))\n", - "\n", - "while cap.isOpened():\n", - " success, frame = cap.read()\n", - " if success:\n", - " results = model.track(frame, persist=True, verbose=False)\n", - " boxes = results[0].boxes.xyxy.cpu()\n", - "\n", - " if results[0].boxes.id is not None:\n", - "\n", - " # Extract prediction results\n", - " clss = results[0].boxes.cls.cpu().tolist()\n", - " track_ids = results[0].boxes.id.int().cpu().tolist()\n", - " confs = results[0].boxes.conf.float().cpu().tolist()\n", - "\n", - " # Annotator Init\n", - " annotator = Annotator(frame, line_width=2)\n", - "\n", - " for box, cls, track_id in zip(boxes, clss, track_ids):\n", - " annotator.box_label(box, color=colors(int(cls), True), label=names[int(cls)])\n", - "\n", - " # Store tracking history\n", - " track = track_history[track_id]\n", - " track.append((int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)))\n", - " if len(track) > 30:\n", - " track.pop(0)\n", - "\n", - " # Plot tracks\n", - " points = np.array(track, dtype=np.int32).reshape((-1, 1, 2))\n", - " cv2.circle(frame, (track[-1]), 7, colors(int(cls), True), -1)\n", - " cv2.polylines(frame, [points], isClosed=False, color=colors(int(cls), True), thickness=2)\n", - "\n", - " result.write(frame)\n", - " if cv2.waitKey(1) & 0xFF == ord(\"q\"):\n", - " break\n", - " else:\n", - " break\n", - "\n", - "result.release()\n", - "cap.release()\n", - "cv2.destroyAllWindows()" - ], - "metadata": { - "id": "Cx-u59HQdu2o" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "#Community Support\n", - "\n", - "For more information, you can explore Ultralytics Object Tracking Docs\n", - "\n", - "Ultralytics ⚡ resources\n", - "- About Us – https://ultralytics.com/about\n", - "- Join Our Team – https://ultralytics.com/work\n", - "- Contact Us – https://ultralytics.com/contact\n", - "- Discord – https://discord.gg/2wNGbc6g9X\n", - "- Ultralytics License – https://ultralytics.com/license\n", - "\n", - "YOLOv8 🚀 resources\n", - "- GitHub – https://github.com/ultralytics/ultralytics\n", - "- Docs – https://docs.ultralytics.com/" - ], - "metadata": { - "id": "QrlKg-y3fEyD" - } - } - ] -} diff --git a/ultralytics-main/examples/tutorial.ipynb b/ultralytics-main/examples/tutorial.ipynb deleted file mode 100644 index 51e5c8f..0000000 --- a/ultralytics-main/examples/tutorial.ipynb +++ /dev/null @@ -1,649 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "name": "YOLOv8 Tutorial", - "provenance": [], - "toc_visible": true - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - }, - "accelerator": "GPU" - }, - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "t6MPjfT5NrKQ" - }, - "source": [ - "
\n", - "\n", - " \n", - " \n", - "\n", - " [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)\n", - "\n", - " \"Run\n", - " \"Open\n", - " \"Open\n", - "\n", - "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) AI models developed by Ultralytics. This notebook serves as the starting point for exploring the various resources available to help you get started with YOLOv8 and understand its features and capabilities.\n", - "\n", - "YOLOv8 models are fast, accurate, and easy to use, making them ideal for various object detection and image segmentation tasks. They can be trained on large datasets and run on diverse hardware platforms, from CPUs to GPUs.\n", - "\n", - "We hope that the resources in this notebook will help you get the most out of YOLOv8. Please browse the YOLOv8 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n", - "\n", - "
" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7mGmQbAO5pQb" - }, - "source": [ - "# Setup\n", - "\n", - "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "wbvMlHd_QwMG", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "51d15672-e688-4fb8-d9d0-00d1916d3532" - }, - "source": [ - "%pip install ultralytics\n", - "import ultralytics\n", - "ultralytics.checks()" - ], - "execution_count": 1, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ultralytics YOLOv8.1.23 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n", - "Setup complete ✅ (2 CPUs, 12.7 GB RAM, 26.3/78.2 GB disk)\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4JnkELT0cIJg" - }, - "source": [ - "# 1. Predict\n", - "\n", - "YOLOv8 may be used directly in the Command Line Interface (CLI) with a `yolo` command for a variety of tasks and modes and accepts additional arguments, i.e. `imgsz=640`. See a full list of available `yolo` [arguments](https://docs.ultralytics.com/usage/cfg/) and other details in the [YOLOv8 Predict Docs](https://docs.ultralytics.com/modes/train/).\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "zR9ZbuQCH7FX", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "37738db7-4284-47de-b3ed-b82f2431ed23" - }, - "source": [ - "# Run inference on an image with YOLOv8n\n", - "!yolo predict model=yolov8n.pt source='https://ultralytics.com/images/zidane.jpg'" - ], - "execution_count": 2, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Downloading https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt to 'yolov8n.pt'...\n", - "100% 6.23M/6.23M [00:00<00:00, 72.6MB/s]\n", - "Ultralytics YOLOv8.1.23 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n", - "YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs\n", - "\n", - "Downloading https://ultralytics.com/images/zidane.jpg to 'zidane.jpg'...\n", - "100% 165k/165k [00:00<00:00, 7.05MB/s]\n", - "image 1/1 /content/zidane.jpg: 384x640 2 persons, 1 tie, 162.0ms\n", - "Speed: 13.9ms preprocess, 162.0ms inference, 1259.5ms postprocess per image at shape (1, 3, 384, 640)\n", - "Results saved to \u001b[1mruns/detect/predict\u001b[0m\n", - "💡 Learn more at https://docs.ultralytics.com/modes/predict\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "hkAzDWJ7cWTr" - }, - "source": [ - "        \n", - "" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "0eq1SMWl6Sfn" - }, - "source": [ - "# 2. Val\n", - "Validate a model's accuracy on the [COCO](https://docs.ultralytics.com/datasets/detect/coco/) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used. See [YOLOv8 Val Docs](https://docs.ultralytics.com/modes/val/) for more information." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "WQPtK1QYVaD_" - }, - "source": [ - "# Download COCO val\n", - "import torch\n", - "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip') # download (780M - 5000 images)\n", - "!unzip -q tmp.zip -d datasets && rm tmp.zip # unzip" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "X58w8JLpMnjH", - "outputId": "61001937-ccd2-4157-a373-156a57495231", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "source": [ - "# Validate YOLOv8n on COCO8 val\n", - "!yolo val model=yolov8n.pt data=coco8.yaml" - ], - "execution_count": 3, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ultralytics YOLOv8.1.23 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n", - "YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs\n", - "\n", - "Dataset 'coco8.yaml' images not found ⚠️, missing path '/content/datasets/coco8/images/val'\n", - "Downloading https://ultralytics.com/assets/coco8.zip to '/content/datasets/coco8.zip'...\n", - "100% 433k/433k [00:00<00:00, 12.5MB/s]\n", - "Unzipping /content/datasets/coco8.zip to /content/datasets/coco8...: 100% 25/25 [00:00<00:00, 4546.38file/s]\n", - "Dataset download success ✅ (0.9s), saved to \u001b[1m/content/datasets\u001b[0m\n", - "\n", - "Downloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...\n", - "100% 755k/755k [00:00<00:00, 17.8MB/s]\n", - "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco8/labels/val... 4 images, 0 backgrounds, 0 corrupt: 100% 4/4 [00:00<00:00, 275.94it/s]\n", - "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco8/labels/val.cache\n", - " Class Images Instances Box(P R mAP50 mAP50-95): 100% 1/1 [00:02<00:00, 2.23s/it]\n", - " all 4 17 0.621 0.833 0.888 0.63\n", - " person 4 10 0.721 0.5 0.519 0.269\n", - " dog 4 1 0.37 1 0.995 0.597\n", - " horse 4 2 0.751 1 0.995 0.631\n", - " elephant 4 2 0.505 0.5 0.828 0.394\n", - " umbrella 4 1 0.564 1 0.995 0.995\n", - " potted plant 4 1 0.814 1 0.995 0.895\n", - "Speed: 0.3ms preprocess, 56.9ms inference, 0.0ms loss, 222.8ms postprocess per image\n", - "Results saved to \u001b[1mruns/detect/val\u001b[0m\n", - "💡 Learn more at https://docs.ultralytics.com/modes/val\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ZY2VXXXu74w5" - }, - "source": [ - "# 3. Train\n", - "\n", - "

\n", - "\n", - "Train YOLOv8 on [Detect](https://docs.ultralytics.com/tasks/detect/), [Segment](https://docs.ultralytics.com/tasks/segment/), [Classify](https://docs.ultralytics.com/tasks/classify/) and [Pose](https://docs.ultralytics.com/tasks/pose/) datasets. See [YOLOv8 Train Docs](https://docs.ultralytics.com/modes/train/) for more information." - ] - }, - { - "cell_type": "code", - "source": [ - "#@title Select YOLOv8 🚀 logger {run: 'auto'}\n", - "logger = 'Comet' #@param ['Comet', 'TensorBoard']\n", - "\n", - "if logger == 'Comet':\n", - " %pip install -q comet_ml\n", - " import comet_ml; comet_ml.init()\n", - "elif logger == 'TensorBoard':\n", - " %load_ext tensorboard\n", - " %tensorboard --logdir ." - ], - "metadata": { - "id": "ktegpM42AooT" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "1NcFxRcFdJ_O", - "outputId": "1ec62d53-41eb-444f-e2f7-cef5c18b9a27", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "source": [ - "# Train YOLOv8n on COCO8 for 3 epochs\n", - "!yolo train model=yolov8n.pt data=coco8.yaml epochs=3 imgsz=640" - ], - "execution_count": 4, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ultralytics YOLOv8.1.23 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n", - "\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=coco8.yaml, epochs=3, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train\n", - "\n", - " from n params module arguments \n", - " 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] \n", - " 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] \n", - " 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] \n", - " 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] \n", - " 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] \n", - " 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] \n", - " 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] \n", - " 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] \n", - " 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] \n", - " 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] \n", - " 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", - " 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n", - " 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] \n", - " 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", - " 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n", - " 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] \n", - " 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n", - " 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] \n", - " 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] \n", - " 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n", - " 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] \n", - " 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] \n", - " 22 [15, 18, 21] 1 897664 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]] \n", - "Model summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs\n", - "\n", - "Transferred 355/355 items from pretrained weights\n", - "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/detect/train', view at http://localhost:6006/\n", - "Freezing layer 'model.22.dfl.conv.weight'\n", - "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks with YOLOv8n...\n", - "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n", - "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/coco8/labels/train... 4 images, 0 backgrounds, 0 corrupt: 100% 4/4 [00:00<00:00, 43351.98it/s]\n", - "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco8/labels/train.cache\n", - "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n", - "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100% 4/4 [00:00\n" - ], - "metadata": { - "id": "Phm9ccmOKye5" - } - }, - { - "cell_type": "markdown", - "source": [ - "## 1. Detection\n", - "\n", - "YOLOv8 _detection_ models have no suffix and are the default YOLOv8 models, i.e. `yolov8n.pt` and are pretrained on COCO. See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for full details.\n" - ], - "metadata": { - "id": "yq26lwpYK1lq" - } - }, - { - "cell_type": "code", - "source": [ - "# Load YOLOv8n, train it on COCO128 for 3 epochs and predict an image with it\n", - "from ultralytics import YOLO\n", - "\n", - "model = YOLO('yolov8n.pt') # load a pretrained YOLOv8n detection model\n", - "model.train(data='coco128.yaml', epochs=3) # train the model\n", - "model('https://ultralytics.com/images/bus.jpg') # predict on an image" - ], - "metadata": { - "id": "8Go5qqS9LbC5" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "## 2. Segmentation\n", - "\n", - "YOLOv8 _segmentation_ models use the `-seg` suffix, i.e. `yolov8n-seg.pt` and are pretrained on COCO. See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for full details.\n" - ], - "metadata": { - "id": "7ZW58jUzK66B" - } - }, - { - "cell_type": "code", - "source": [ - "# Load YOLOv8n-seg, train it on COCO128-seg for 3 epochs and predict an image with it\n", - "from ultralytics import YOLO\n", - "\n", - "model = YOLO('yolov8n-seg.pt') # load a pretrained YOLOv8n segmentation model\n", - "model.train(data='coco128-seg.yaml', epochs=3) # train the model\n", - "model('https://ultralytics.com/images/bus.jpg') # predict on an image" - ], - "metadata": { - "id": "WFPJIQl_L5HT" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "## 3. Classification\n", - "\n", - "YOLOv8 _classification_ models use the `-cls` suffix, i.e. `yolov8n-cls.pt` and are pretrained on ImageNet. See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for full details.\n" - ], - "metadata": { - "id": "ax3p94VNK9zR" - } - }, - { - "cell_type": "code", - "source": [ - "# Load YOLOv8n-cls, train it on mnist160 for 3 epochs and predict an image with it\n", - "from ultralytics import YOLO\n", - "\n", - "model = YOLO('yolov8n-cls.pt') # load a pretrained YOLOv8n classification model\n", - "model.train(data='mnist160', epochs=3) # train the model\n", - "model('https://ultralytics.com/images/bus.jpg') # predict on an image" - ], - "metadata": { - "id": "5q9Zu6zlL5rS" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "## 4. Pose\n", - "\n", - "YOLOv8 _pose_ models use the `-pose` suffix, i.e. `yolov8n-pose.pt` and are pretrained on COCO Keypoints. See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for full details." - ], - "metadata": { - "id": "SpIaFLiO11TG" - } - }, - { - "cell_type": "code", - "source": [ - "# Load YOLOv8n-pose, train it on COCO8-pose for 3 epochs and predict an image with it\n", - "from ultralytics import YOLO\n", - "\n", - "model = YOLO('yolov8n-pose.pt') # load a pretrained YOLOv8n pose model\n", - "model.train(data='coco8-pose.yaml', epochs=3) # train the model\n", - "model('https://ultralytics.com/images/bus.jpg') # predict on an image" - ], - "metadata": { - "id": "si4aKFNg19vX" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "## 4. Oriented Bounding Boxes (OBB)\n", - "\n", - "YOLOv8 _OBB_ models use the `-obb` suffix, i.e. `yolov8n-obb.pt` and are pretrained on the DOTA dataset. See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for full details." - ], - "metadata": { - "id": "cf5j_T9-B5F0" - } - }, - { - "cell_type": "code", - "source": [ - "# Load YOLOv8n-obb, train it on DOTA8 for 3 epochs and predict an image with it\n", - "from ultralytics import YOLO\n", - "\n", - "model = YOLO('yolov8n-obb.pt') # load a pretrained YOLOv8n OBB model\n", - "model.train(data='coco8-dota.yaml', epochs=3) # train the model\n", - "model('https://ultralytics.com/images/bus.jpg') # predict on an image" - ], - "metadata": { - "id": "IJNKClOOB5YS" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "IEijrePND_2I" - }, - "source": [ - "# Appendix\n", - "\n", - "Additional content below." - ] - }, - { - "cell_type": "code", - "source": [ - "# Pip install from source\n", - "!pip install git+https://github.com/ultralytics/ultralytics@main" - ], - "metadata": { - "id": "pIdE6i8C3LYp" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "source": [ - "# Git clone and run tests on updates branch\n", - "!git clone https://github.com/ultralytics/ultralytics -b main\n", - "%pip install -qe ultralytics" - ], - "metadata": { - "id": "uRKlwxSJdhd1" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "source": [ - "# Run tests (Git clone only)\n", - "!pytest ultralytics/tests" - ], - "metadata": { - "id": "GtPlh7mcCGZX" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "source": [ - "# Validate multiple models\n", - "for x in 'nsmlx':\n", - " !yolo val model=yolov8{x}.pt data=coco.yaml" - ], - "metadata": { - "id": "Wdc6t_bfzDDk" - }, - "execution_count": null, - "outputs": [] - } - ] -} diff --git a/ultralytics-main/main.py b/ultralytics-main/main.py deleted file mode 100644 index a58649a..0000000 --- a/ultralytics-main/main.py +++ /dev/null @@ -1,56 +0,0 @@ -from ultralytics import YOLO -import cv2 -import os -from ultralytics.utils.plotting import Annotator, colors -if __name__ == '__main__': - # Load a model - # 直接使用预训练模型创建模型 - # model = YOLO('yolov8n.pt') - # model.train(**{'cfg':'ultralytics/cfg/default.yaml', 'data':'ultralytics/models/yolo/detect/mydata/traffic.yaml'}, epochs=10, imgsz=640, batch=32) - - - - # #使用yaml配置文件来创建模型，并导入预训练权重 - #model = YOLO('ultralytics/cfg/models/v8/yolov8n.yaml') # build a new model from YAML - #model.load('yolov8n.pt') - #model.train(**{'cfg': 'ultralytics/cfg/default.yaml', 'data': 'ultralytics/models/yolo/detect/mydata/traffic.yaml'}, - # epochs=10, imgsz=640, batch=32, name='train') # name：是此次训练结果保存的文件夹 数据集是我自己的数据集 - -# # # 模型验证：用验证集 -# model = YOLO('runs/detect/train/weights/best.pt') -# model.val(**{'data':'ultralytics/models/yolo/detect/mydata/traffic.yaml', 'name':'val', 'batch':32}) #模型验证用验证集 -# model.val(**{'data':'ultralytics/models/yolo/detect/mydata/traffic.yaml', 'split':'test', 'iou':0.9}) #模型验证用测试集 - -# # 推理： - '''model = YOLO('yolov8n.pt') - model.predict(source='ultralytics/assets', show=True, save=True)''' - # model.predict(source='ultralytics/assets', name='predict', **{'save':True}) # 写法二 - - # 分割： - model = YOLO('yolov8n-seg.pt') - model.predict(source='ultralytics/assets', show=True, save=True, classes=[2]) - - # 跟踪： - '''model = YOLO('yolov8n.pt') - model.track(source="ultralytics/assets", show=True, save=True)''' - - # 姿态估计： - '''model = YOLO('yolov8n-pose.pt') - model.predict(source="ultralytics/assets", show=True, save=True)''' - - # 检测、跟踪、分割： - '''model = YOLO('yolov8n-seg.pt') # 加载一个官方的分割模型 - model.track(source="ultralytics/assets", show=True, save=True)''' - - # 检测、跟踪、姿态估计： - '''model = YOLO('yolov8n-pose.pt') # 加载一个官方的分割模型 - model.track(source="ultralytics/assets", show=True, save=True)''' - #results = model.track(source="ultralytics/assets", show=True, tracker="bytetrack.yaml") # 使用ByteTrack追踪器进行追踪 （写法二） - - # model = YOLO('ultralytics/cfg/models/v8/yolov8n.yaml').load('yolov8n.pt') - # # Train the model - # model.train(data='ultralytics/cfg/datasets/coco.yaml', epochs=100, imgsz=640, save_period=5, device='cpu',batch=2) - '''model = YOLO('best.pt') - model.predict(source='ultralytics/assets', show=True, save=True)''' - - diff --git a/ultralytics-main/mkdocs.yml b/ultralytics-main/mkdocs.yml deleted file mode 100644 index e66b6a5..0000000 --- a/ultralytics-main/mkdocs.yml +++ /dev/null @@ -1,675 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -site_name: Ultralytics YOLOv8 Docs -site_description: Explore Ultralytics YOLOv8, a cutting-edge real-time object detection and image segmentation model for various applications and hardware platforms. -site_url: https://docs.ultralytics.com -site_author: Ultralytics -repo_url: https://github.com/ultralytics/ultralytics -edit_uri: https://github.com/ultralytics/ultralytics/tree/main/docs/en/ -repo_name: ultralytics/ultralytics -remote_name: https://github.com/ultralytics/docs -docs_dir: "docs/en/" # where to find the markdown files -site_dir: "site/" # where to publish to - -theme: - name: material - language: en - custom_dir: docs/overrides/ - logo: https://github.com/ultralytics/assets/raw/main/logo/Ultralytics_Logotype_Reverse.svg - favicon: assets/favicon.ico - icon: - repo: fontawesome/brands/github - # font: # disabled for faster page load times - # text: Helvetica - # code: Roboto Mono - palette: - - media: "(prefers-color-scheme)" - toggle: - icon: material/brightness-auto - name: Switch to light mode - - media: "(prefers-color-scheme: dark)" - scheme: slate - primary: black - accent: indigo - toggle: - icon: material/brightness-4 - name: Switch to system preference - - media: "(prefers-color-scheme: light)" - scheme: default - primary: indigo - accent: indigo - toggle: - icon: material/brightness-7 - name: Switch to dark mode - features: - # - announce.dismiss - - content.action.edit - - content.code.annotate - - content.code.copy - - content.tooltips - - search.highlight - - search.share - - search.suggest - - toc.follow - - navigation.top - - navigation.tabs - - navigation.tabs.sticky - - navigation.prune - - navigation.footer - - navigation.tracking - - navigation.instant - - navigation.instant.progress - - navigation.indexes - - navigation.sections # navigation.expand or navigation.sections - - content.tabs.link # all code tabs change simultaneously - -# Customization -copyright: © 2024 Ultralytics Inc. All rights reserved. -extra: # version: - # provider: mike # version drop-down menu - robots: robots.txt - analytics: - provider: google - property: G-2M5EHKC0BH - # alternate: # language drop-down - # - name: 🇬🇧 English - # link: / - # lang: en - # - name: 🇨🇳 简体中文 - # link: /zh/ - # lang: zh - # - name: 🇰🇷 한국어 - # link: /ko/ - # lang: ko - # - name: 🇯🇵 日本語 - # link: /ja/ - # lang: ja - # - name: 🇷🇺 Русский - # link: /ru/ - # lang: ru - # - name: 🇩🇪 Deutsch - # link: /de/ - # lang: de - # - name: 🇫🇷 Français - # link: /fr/ - # lang: fr - # - name: 🇪🇸 Español - # link: /es/ - # lang: es - # - name: 🇵🇹 Português - # link: /pt/ - # lang: pt - # - name: 🇮🇳 हिन्दी - # link: /hi/ - # lang: hi - # - name: 🇸🇦 العربية - # link: /ar/ - # lang: ar - social: - - icon: fontawesome/brands/github - link: https://github.com/ultralytics - - icon: fontawesome/brands/linkedin - link: https://www.linkedin.com/company/ultralytics/ - - icon: fontawesome/brands/x-twitter - link: https://twitter.com/ultralytics - - icon: fontawesome/brands/youtube - link: https://www.youtube.com/ultralytics - - icon: fontawesome/brands/docker - link: https://hub.docker.com/r/ultralytics/ultralytics/ - - icon: fontawesome/brands/python - link: https://pypi.org/project/ultralytics/ - - icon: fontawesome/brands/discord - link: https://ultralytics.com/discord - -extra_css: - - stylesheets/style.css -extra_javascript: - - javascript/extra.js - -markdown_extensions: - - admonition - - md_in_html - - tables - - attr_list - - def_list - - pymdownx.critic - - pymdownx.caret - - pymdownx.keys - - pymdownx.mark - - pymdownx.tilde - - pymdownx.details - - pymdownx.superfences - - pymdownx.inlinehilite - - pymdownx.highlight: - anchor_linenums: true - - pymdownx.snippets: - base_path: ./ - - pymdownx.emoji: - emoji_index: !!python/name:material.extensions.emoji.twemoji - emoji_generator: !!python/name:material.extensions.emoji.to_svg - - pymdownx.tabbed: - alternate_style: true - -# Primary navigation --------------------------------------------------------------------------------------------------- -nav: - - Home: - - Home: index.md - - Quickstart: quickstart.md - - Modes: - - modes/index.md - - Train: modes/train.md - - Val: modes/val.md - - Predict: modes/predict.md - - Export: modes/export.md - - Track: modes/track.md - - Benchmark: modes/benchmark.md - - Tasks: - - tasks/index.md - - Detect: tasks/detect.md - - Segment: tasks/segment.md - - Classify: tasks/classify.md - - Pose: tasks/pose.md - - OBB: tasks/obb.md - - Models: - - models/index.md - - Datasets: - - datasets/index.md - - Guides: - - guides/index.md - - NEW 🚀 Explorer: - - datasets/explorer/index.md - - Languages: - - 🇬🇧  English: https://ultralytics.com/docs/ - - 🇨🇳  简体中文: https://docs.ultralytics.com/zh/ - - 🇰🇷  한국어: https://docs.ultralytics.com/ko/ - - 🇯🇵  日本語: https://docs.ultralytics.com/ja/ - - 🇷🇺  Русский: https://docs.ultralytics.com/ru/ - - 🇩🇪  Deutsch: https://docs.ultralytics.com/de/ - - 🇫🇷  Français: https://docs.ultralytics.com/fr/ - - 🇪🇸  Español: https://docs.ultralytics.com/es/ - - 🇵🇹  Português: https://docs.ultralytics.com/pt/ - - 🇮🇳  हिन्दी: https://docs.ultralytics.com/hi/ - - 🇸🇦  العربية: https://docs.ultralytics.com/ar/ - - Quickstart: - - quickstart.md - - Usage: - - CLI: usage/cli.md - - Python: usage/python.md - - Callbacks: usage/callbacks.md - - Configuration: usage/cfg.md - - Simple Utilities: usage/simple-utilities.md - - Advanced Customization: usage/engine.md - - Modes: - - modes/index.md - - Train: modes/train.md - - Val: modes/val.md - - Predict: modes/predict.md - - Export: modes/export.md - - Track: modes/track.md - - Benchmark: modes/benchmark.md - - Tasks: - - tasks/index.md - - Detect: tasks/detect.md - - Segment: tasks/segment.md - - Classify: tasks/classify.md - - Pose: tasks/pose.md - - OBB: tasks/obb.md - - Models: - - models/index.md - - YOLOv3: models/yolov3.md - - YOLOv4: models/yolov4.md - - YOLOv5: models/yolov5.md - - YOLOv6: models/yolov6.md - - YOLOv7: models/yolov7.md - - YOLOv8: models/yolov8.md - - YOLOv9: models/yolov9.md - - SAM (Segment Anything Model): models/sam.md - - MobileSAM (Mobile Segment Anything Model): models/mobile-sam.md - - FastSAM (Fast Segment Anything Model): models/fast-sam.md - - YOLO-NAS (Neural Architecture Search): models/yolo-nas.md - - RT-DETR (Realtime Detection Transformer): models/rtdetr.md - - YOLO-World (Real-Time Open-Vocabulary Object Detection): models/yolo-world.md - - Datasets: - - datasets/index.md - - NEW 🚀 Explorer: - - datasets/explorer/index.md - - Explorer API: datasets/explorer/api.md - - Explorer Dashboard: datasets/explorer/dashboard.md - - VOC Exploration Example: datasets/explorer/explorer.ipynb - - Detection: - - datasets/detect/index.md - - Argoverse: datasets/detect/argoverse.md - - COCO: datasets/detect/coco.md - - COCO8: datasets/detect/coco8.md - - GlobalWheat2020: datasets/detect/globalwheat2020.md - - Objects365: datasets/detect/objects365.md - - OpenImagesV7: datasets/detect/open-images-v7.md - - SKU-110K: datasets/detect/sku-110k.md - - VisDrone: datasets/detect/visdrone.md - - VOC: datasets/detect/voc.md - - xView: datasets/detect/xview.md - - Roboflow 100: datasets/detect/roboflow-100.md - - Brain-tumor: datasets/detect/brain-tumor.md - - Segmentation: - - datasets/segment/index.md - - COCO: datasets/segment/coco.md - - COCO8-seg: datasets/segment/coco8-seg.md - - Crack-seg: datasets/segment/crack-seg.md - - Carparts-seg: datasets/segment/carparts-seg.md - - Package-seg: datasets/segment/package-seg.md - - Pose: - - datasets/pose/index.md - - COCO: datasets/pose/coco.md - - COCO8-pose: datasets/pose/coco8-pose.md - - Tiger-pose: datasets/pose/tiger-pose.md - - Classification: - - datasets/classify/index.md - - Caltech 101: datasets/classify/caltech101.md - - Caltech 256: datasets/classify/caltech256.md - - CIFAR-10: datasets/classify/cifar10.md - - CIFAR-100: datasets/classify/cifar100.md - - Fashion-MNIST: datasets/classify/fashion-mnist.md - - ImageNet: datasets/classify/imagenet.md - - ImageNet-10: datasets/classify/imagenet10.md - - Imagenette: datasets/classify/imagenette.md - - Imagewoof: datasets/classify/imagewoof.md - - MNIST: datasets/classify/mnist.md - - Oriented Bounding Boxes (OBB): - - datasets/obb/index.md - - DOTAv2: datasets/obb/dota-v2.md - - DOTA8: datasets/obb/dota8.md - - Multi-Object Tracking: - - datasets/track/index.md - - NEW 🚀 Explorer: - - datasets/explorer/index.md - - Explorer API: datasets/explorer/api.md - - Explorer Dashboard Demo: datasets/explorer/dashboard.md - - VOC Exploration Example: datasets/explorer/explorer.ipynb - - Guides: - - guides/index.md - - YOLO Common Issues: guides/yolo-common-issues.md - - YOLO Performance Metrics: guides/yolo-performance-metrics.md - - YOLO Thread-Safe Inference: guides/yolo-thread-safe-inference.md - - Model Deployment Options: guides/model-deployment-options.md - - K-Fold Cross Validation: guides/kfold-cross-validation.md - - Hyperparameter Tuning: guides/hyperparameter-tuning.md - - SAHI Tiled Inference: guides/sahi-tiled-inference.md - - AzureML Quickstart: guides/azureml-quickstart.md - - Conda Quickstart: guides/conda-quickstart.md - - Docker Quickstart: guides/docker-quickstart.md - - Raspberry Pi: guides/raspberry-pi.md - - Triton Inference Server: guides/triton-inference-server.md - - Isolating Segmentation Objects: guides/isolating-segmentation-objects.md - - Edge TPU on Raspberry Pi: guides/coral-edge-tpu-on-raspberry-pi.md - - Viewing Inference Images in a Terminal: guides/view-results-in-terminal.md - - OpenVINO Latency vs Throughput modes: guides/optimizing-openvino-latency-vs-throughput-modes.md - - Real-World Projects: - - Object Counting: guides/object-counting.md - - Object Cropping: guides/object-cropping.md - - Object Blurring: guides/object-blurring.md - - Workouts Monitoring: guides/workouts-monitoring.md - - Objects Counting in Regions: guides/region-counting.md - - Security Alarm System: guides/security-alarm-system.md - - Heatmaps: guides/heatmaps.md - - Instance Segmentation with Object Tracking: guides/instance-segmentation-and-tracking.md - - VisionEye Mapping: guides/vision-eye.md - - Speed Estimation: guides/speed-estimation.md - - Distance Calculation: guides/distance-calculation.md - - YOLOv5: - - yolov5/index.md - - Quickstart: yolov5/quickstart_tutorial.md - - Environments: - - Amazon Web Services (AWS): yolov5/environments/aws_quickstart_tutorial.md - - Google Cloud (GCP): yolov5/environments/google_cloud_quickstart_tutorial.md - - AzureML: yolov5/environments/azureml_quickstart_tutorial.md - - Docker Image: yolov5/environments/docker_image_quickstart_tutorial.md - - Tutorials: - - Train Custom Data: yolov5/tutorials/train_custom_data.md - - Tips for Best Training Results: yolov5/tutorials/tips_for_best_training_results.md - - Multi-GPU Training: yolov5/tutorials/multi_gpu_training.md - - PyTorch Hub: yolov5/tutorials/pytorch_hub_model_loading.md - - TFLite, ONNX, CoreML, TensorRT Export: yolov5/tutorials/model_export.md - - NVIDIA Jetson Nano Deployment: yolov5/tutorials/running_on_jetson_nano.md - - Test-Time Augmentation (TTA): yolov5/tutorials/test_time_augmentation.md - - Model Ensembling: yolov5/tutorials/model_ensembling.md - - Pruning/Sparsity Tutorial: yolov5/tutorials/model_pruning_and_sparsity.md - - Hyperparameter evolution: yolov5/tutorials/hyperparameter_evolution.md - - Transfer learning with frozen layers: yolov5/tutorials/transfer_learning_with_frozen_layers.md - - Architecture Summary: yolov5/tutorials/architecture_description.md - - Roboflow Datasets: yolov5/tutorials/roboflow_datasets_integration.md - - Neural Magic's DeepSparse: yolov5/tutorials/neural_magic_pruning_quantization.md - - Comet Logging: yolov5/tutorials/comet_logging_integration.md - - Clearml Logging: yolov5/tutorials/clearml_logging_integration.md - - Integrations: - - integrations/index.md - - TorchScript: integrations/torchscript.md - - ONNX: integrations/onnx.md - - OpenVINO: integrations/openvino.md - - TensorRT: integrations/tensorrt.md - - CoreML: integrations/coreml.md - - TFLite: integrations/tflite.md - - TFLite Edge TPU: integrations/edge-tpu.md - - PaddlePaddle: integrations/paddlepaddle.md - - NCNN: integrations/ncnn.md - - Comet ML: integrations/comet.md - - Ray Tune: integrations/ray-tune.md - - Roboflow: integrations/roboflow.md - - MLflow: integrations/mlflow.md - - ClearML: integrations/clearml.md - - DVC: integrations/dvc.md - - Weights & Biases: integrations/weights-biases.md - - Neural Magic: integrations/neural-magic.md - - Gradio: integrations/gradio.md - - TensorBoard: integrations/tensorboard.md - - Amazon SageMaker: integrations/amazon-sagemaker.md - - HUB: - - Cloud: - - hub/index.md - - Quickstart: hub/quickstart.md - - Datasets: hub/datasets.md - - Projects: hub/projects.md - - Models: hub/models.md - - Cloud Training: hub/cloud-training.md - - Integrations: hub/integrations.md - - Inference API: hub/inference-api.md - - On-Premise: - - hub/on-premise/index.md - - App: - - hub/app/index.md - - iOS: hub/app/ios.md - - Android: hub/app/android.md - - Python SDK: - - hub/sdk/index.md - - Quickstart: hub/sdk/quickstart.md - - Model: hub/sdk/model.md - - Dataset: hub/sdk/dataset.md - - Project: hub/sdk/project.md - - Reference: - - base: - - api_client: hub/sdk/reference/base/api_client.md - - auth: hub/sdk/reference/base/auth.md - - crud_client: hub/sdk/reference/base/crud_client.md - - paginated_list: hub/sdk/reference/base/paginated_list.md - - server_clients: hub/sdk/reference/base/server_clients.md - - helpers: - - error_handler: hub/sdk/reference/helpers/error_handler.md - - exceptions: hub/sdk/reference/helpers/exceptions.md - - logger: hub/sdk/reference/helpers/logger.md - - utils: hub/sdk/reference/helpers/utils.md - - hub_client: hub/sdk/reference/hub_client.md - - modules: - - datasets: hub/sdk/reference/modules/datasets.md - - models: hub/sdk/reference/modules/models.md - - projects: hub/sdk/reference/modules/projects.md - - teams: hub/sdk/reference/modules/teams.md - - users: hub/sdk/reference/modules/users.md - - REST API: - - hub/api/index.md - - - Reference: - - cfg: - - __init__: reference/cfg/__init__.md - - data: - - annotator: reference/data/annotator.md - - augment: reference/data/augment.md - - base: reference/data/base.md - - build: reference/data/build.md - - converter: reference/data/converter.md - - dataset: reference/data/dataset.md - - explorer: - - explorer: reference/data/explorer/explorer.md - - gui: - - dash: reference/data/explorer/gui/dash.md - - utils: reference/data/explorer/utils.md - - loaders: reference/data/loaders.md - - split_dota: reference/data/split_dota.md - - utils: reference/data/utils.md - - engine: - - exporter: reference/engine/exporter.md - - model: reference/engine/model.md - - predictor: reference/engine/predictor.md - - results: reference/engine/results.md - - trainer: reference/engine/trainer.md - - tuner: reference/engine/tuner.md - - validator: reference/engine/validator.md - - hub: - - __init__: reference/hub/__init__.md - - auth: reference/hub/auth.md - - session: reference/hub/session.md - - utils: reference/hub/utils.md - - models: - - fastsam: - - model: reference/models/fastsam/model.md - - predict: reference/models/fastsam/predict.md - - prompt: reference/models/fastsam/prompt.md - - utils: reference/models/fastsam/utils.md - - val: reference/models/fastsam/val.md - - nas: - - model: reference/models/nas/model.md - - predict: reference/models/nas/predict.md - - val: reference/models/nas/val.md - - rtdetr: - - model: reference/models/rtdetr/model.md - - predict: reference/models/rtdetr/predict.md - - train: reference/models/rtdetr/train.md - - val: reference/models/rtdetr/val.md - - sam: - - amg: reference/models/sam/amg.md - - build: reference/models/sam/build.md - - model: reference/models/sam/model.md - - modules: - - decoders: reference/models/sam/modules/decoders.md - - encoders: reference/models/sam/modules/encoders.md - - sam: reference/models/sam/modules/sam.md - - tiny_encoder: reference/models/sam/modules/tiny_encoder.md - - transformer: reference/models/sam/modules/transformer.md - - predict: reference/models/sam/predict.md - - utils: - - loss: reference/models/utils/loss.md - - ops: reference/models/utils/ops.md - - yolo: - - classify: - - predict: reference/models/yolo/classify/predict.md - - train: reference/models/yolo/classify/train.md - - val: reference/models/yolo/classify/val.md - - detect: - - predict: reference/models/yolo/detect/predict.md - - train: reference/models/yolo/detect/train.md - - val: reference/models/yolo/detect/val.md - - model: reference/models/yolo/model.md - - obb: - - predict: reference/models/yolo/obb/predict.md - - train: reference/models/yolo/obb/train.md - - val: reference/models/yolo/obb/val.md - - pose: - - predict: reference/models/yolo/pose/predict.md - - train: reference/models/yolo/pose/train.md - - val: reference/models/yolo/pose/val.md - - segment: - - predict: reference/models/yolo/segment/predict.md - - train: reference/models/yolo/segment/train.md - - val: reference/models/yolo/segment/val.md - - nn: - - autobackend: reference/nn/autobackend.md - - modules: - - block: reference/nn/modules/block.md - - conv: reference/nn/modules/conv.md - - head: reference/nn/modules/head.md - - transformer: reference/nn/modules/transformer.md - - utils: reference/nn/modules/utils.md - - tasks: reference/nn/tasks.md - - solutions: - - ai_gym: reference/solutions/ai_gym.md - - distance_calculation: reference/solutions/distance_calculation.md - - heatmap: reference/solutions/heatmap.md - - object_counter: reference/solutions/object_counter.md - - speed_estimation: reference/solutions/speed_estimation.md - - trackers: - - basetrack: reference/trackers/basetrack.md - - bot_sort: reference/trackers/bot_sort.md - - byte_tracker: reference/trackers/byte_tracker.md - - track: reference/trackers/track.md - - utils: - - gmc: reference/trackers/utils/gmc.md - - kalman_filter: reference/trackers/utils/kalman_filter.md - - matching: reference/trackers/utils/matching.md - - utils: - - __init__: reference/utils/__init__.md - - autobatch: reference/utils/autobatch.md - - benchmarks: reference/utils/benchmarks.md - - callbacks: - - base: reference/utils/callbacks/base.md - - clearml: reference/utils/callbacks/clearml.md - - comet: reference/utils/callbacks/comet.md - - dvc: reference/utils/callbacks/dvc.md - - hub: reference/utils/callbacks/hub.md - - mlflow: reference/utils/callbacks/mlflow.md - - neptune: reference/utils/callbacks/neptune.md - - raytune: reference/utils/callbacks/raytune.md - - tensorboard: reference/utils/callbacks/tensorboard.md - - wb: reference/utils/callbacks/wb.md - - checks: reference/utils/checks.md - - dist: reference/utils/dist.md - - downloads: reference/utils/downloads.md - - errors: reference/utils/errors.md - - files: reference/utils/files.md - - instance: reference/utils/instance.md - - loss: reference/utils/loss.md - - metrics: reference/utils/metrics.md - - ops: reference/utils/ops.md - - patches: reference/utils/patches.md - - plotting: reference/utils/plotting.md - - tal: reference/utils/tal.md - - torch_utils: reference/utils/torch_utils.md - - triton: reference/utils/triton.md - - tuner: reference/utils/tuner.md - - - Help: - - Help: help/index.md - - Frequently Asked Questions (FAQ): help/FAQ.md - - Contributing Guide: help/contributing.md - - Continuous Integration (CI) Guide: help/CI.md - - Contributor License Agreement (CLA): help/CLA.md - - Minimum Reproducible Example (MRE) Guide: help/minimum_reproducible_example.md - - Code of Conduct: help/code_of_conduct.md - - Environmental, Health and Safety (EHS) Policy: help/environmental-health-safety.md - - Security Policy: help/security.md - - Privacy Policy: help/privacy.md - -# Plugins including 301 redirects navigation --------------------------------------------------------------------------- -plugins: - - search: - lang: en - - mkdocstrings: - enabled: true - default_handler: python - handlers: - python: - options: - docstring_style: google - show_root_heading: true - show_source: true - - ultralytics: - add_desc: False - add_image: True - add_authors: True - add_json_ld: True - add_share_buttons: True - default_image: https://github.com/ultralytics/assets/blob/main/yolov8/banner-yolov8.png - - mkdocs-jupyter - - redirects: - redirect_maps: - callbacks.md: usage/callbacks.md - cfg.md: usage/cfg.md - cli.md: usage/cli.md - config.md: usage/cfg.md - engine.md: usage/engine.md - environments/AWS-Quickstart.md: yolov5/environments/aws_quickstart_tutorial.md - environments/Docker-Quickstart.md: yolov5/environments/docker_image_quickstart_tutorial.md - environments/GCP-Quickstart.md: yolov5/environments/google_cloud_quickstart_tutorial.md - FAQ/augmentation.md: yolov5/tutorials/tips_for_best_training_results.md - package-framework.md: index.md - package-framework/mock_detector.md: index.md - predict.md: modes/predict.md - python.md: usage/python.md - quick-start.md: quickstart.md - app.md: hub/app/index.md - sdk.md: index.md - hub/inference_api.md: hub/inference-api.md - usage/hyperparameter_tuning.md: integrations/ray-tune.md - reference/base_pred.md: reference/engine/predictor.md - reference/base_trainer.md: reference/engine/trainer.md - reference/exporter.md: reference/engine/exporter.md - reference/model.md: reference/engine/model.md - reference/nn.md: reference/nn/modules/head.md - reference/ops.md: reference/utils/ops.md - reference/results.md: reference/engine/results.md - reference/base_val.md: index.md - tasks/classification.md: tasks/classify.md - tasks/detection.md: tasks/detect.md - tasks/segmentation.md: tasks/segment.md - tasks/keypoints.md: tasks/pose.md - tasks/tracking.md: modes/track.md - SECURITY.md: help/security.md - tutorials/architecture-summary.md: yolov5/tutorials/architecture_description.md - tutorials/clearml-logging.md: yolov5/tutorials/clearml_logging_integration.md - tutorials/comet-logging.md: yolov5/tutorials/comet_logging_integration.md - tutorials/hyperparameter-evolution.md: yolov5/tutorials/hyperparameter_evolution.md - tutorials/model-ensembling.md: yolov5/tutorials/model_ensembling.md - tutorials/multi-gpu-training.md: yolov5/tutorials/multi_gpu_training.md - tutorials/nvidia-jetson.md: yolov5/tutorials/running_on_jetson_nano.md - tutorials/pruning-sparsity.md: yolov5/tutorials/model_pruning_and_sparsity.md - tutorials/pytorch-hub.md: yolov5/tutorials/pytorch_hub_model_loading.md - tutorials/roboflow.md: yolov5/tutorials/roboflow_datasets_integration.md - tutorials/test-time-augmentation.md: yolov5/tutorials/test_time_augmentation.md - tutorials/torchscript-onnx-coreml-export.md: yolov5/tutorials/model_export.md - tutorials/train-custom-datasets.md: yolov5/tutorials/train_custom_data.md - tutorials/training-tips-best-results.md: yolov5/tutorials/tips_for_best_training_results.md - tutorials/transfer-learning-froze-layers.md: yolov5/tutorials/transfer_learning_with_frozen_layers.md - tutorials/weights-and-biasis-logging.md: yolov5/tutorials/comet_logging_integration.md - yolov5/pytorch_hub.md: yolov5/tutorials/pytorch_hub_model_loading.md - yolov5/hyp_evolution.md: yolov5/tutorials/hyperparameter_evolution.md - yolov5/pruning_sparsity.md: yolov5/tutorials/model_pruning_and_sparsity.md - yolov5/roboflow.md: yolov5/tutorials/roboflow_datasets_integration.md - yolov5/comet.md: yolov5/tutorials/comet_logging_integration.md - yolov5/clearml.md: yolov5/tutorials/clearml_logging_integration.md - yolov5/tta.md: yolov5/tutorials/test_time_augmentation.md - yolov5/multi_gpu_training.md: yolov5/tutorials/multi_gpu_training.md - yolov5/ensemble.md: yolov5/tutorials/model_ensembling.md - yolov5/jetson_nano.md: yolov5/tutorials/running_on_jetson_nano.md - yolov5/transfer_learn_frozen.md: yolov5/tutorials/transfer_learning_with_frozen_layers.md - yolov5/neural_magic.md: yolov5/tutorials/neural_magic_pruning_quantization.md - yolov5/train_custom_data.md: yolov5/tutorials/train_custom_data.md - yolov5/architecture.md: yolov5/tutorials/architecture_description.md - yolov5/export.md: yolov5/tutorials/model_export.md - yolov5/yolov5_quickstart_tutorial.md: yolov5/quickstart_tutorial.md - yolov5/tips_for_best_training_results.md: yolov5/tutorials/tips_for_best_training_results.md - yolov5/tutorials/yolov5_neural_magic_tutorial.md: yolov5/tutorials/neural_magic_pruning_quantization.md - yolov5/tutorials/model_ensembling_tutorial.md: yolov5/tutorials/model_ensembling.md - yolov5/tutorials/pytorch_hub_tutorial.md: yolov5/tutorials/pytorch_hub_model_loading.md - yolov5/tutorials/yolov5_architecture_tutorial.md: yolov5/tutorials/architecture_description.md - yolov5/tutorials/multi_gpu_training_tutorial.md: yolov5/tutorials/multi_gpu_training.md - yolov5/tutorials/yolov5_pytorch_hub_tutorial.md: yolov5/tutorials/pytorch_hub_model_loading.md - yolov5/tutorials/model_export_tutorial.md: yolov5/tutorials/model_export.md - yolov5/tutorials/jetson_nano_tutorial.md: yolov5/tutorials/running_on_jetson_nano.md - yolov5/tutorials/yolov5_model_ensembling_tutorial.md: yolov5/tutorials/model_ensembling.md - yolov5/tutorials/roboflow_integration.md: yolov5/tutorials/roboflow_datasets_integration.md - yolov5/tutorials/pruning_and_sparsity_tutorial.md: yolov5/tutorials/model_pruning_and_sparsity.md - yolov5/tutorials/yolov5_transfer_learning_with_frozen_layers_tutorial.md: yolov5/tutorials/transfer_learning_with_frozen_layers.md - yolov5/tutorials/transfer_learning_with_frozen_layers_tutorial.md: yolov5/tutorials/transfer_learning_with_frozen_layers.md - yolov5/tutorials/yolov5_model_export_tutorial.md: yolov5/tutorials/model_export.md - yolov5/tutorials/neural_magic_tutorial.md: yolov5/tutorials/neural_magic_pruning_quantization.md - yolov5/tutorials/yolov5_clearml_integration_tutorial.md: yolov5/tutorials/clearml_logging_integration.md - yolov5/tutorials/yolov5_train_custom_data.md: yolov5/tutorials/train_custom_data.md - yolov5/tutorials/comet_integration_tutorial.md: yolov5/tutorials/comet_logging_integration.md - yolov5/tutorials/yolov5_pruning_and_sparsity_tutorial.md: yolov5/tutorials/model_pruning_and_sparsity.md - yolov5/tutorials/yolov5_jetson_nano_tutorial.md: yolov5/tutorials/running_on_jetson_nano.md - yolov5/tutorials/yolov5_roboflow_integration.md: yolov5/tutorials/roboflow_datasets_integration.md - yolov5/tutorials/hyperparameter_evolution_tutorial.md: yolov5/tutorials/hyperparameter_evolution.md - yolov5/tutorials/yolov5_hyperparameter_evolution_tutorial.md: yolov5/tutorials/hyperparameter_evolution.md - yolov5/tutorials/clearml_integration_tutorial.md: yolov5/tutorials/clearml_logging_integration.md - yolov5/tutorials/test_time_augmentation_tutorial.md: yolov5/tutorials/test_time_augmentation.md - yolov5/tutorials/yolov5_test_time_augmentation_tutorial.md: yolov5/tutorials/test_time_augmentation.md - yolov5/environments/yolov5_amazon_web_services_quickstart_tutorial.md: yolov5/environments/aws_quickstart_tutorial.md - yolov5/environments/yolov5_google_cloud_platform_quickstart_tutorial.md: yolov5/environments/google_cloud_quickstart_tutorial.md - yolov5/environments/yolov5_docker_image_quickstart_tutorial.md: yolov5/environments/docker_image_quickstart_tutorial.md diff --git a/ultralytics-main/pyproject.toml b/ultralytics-main/pyproject.toml deleted file mode 100644 index 6929457..0000000 --- a/ultralytics-main/pyproject.toml +++ /dev/null @@ -1,178 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -# Overview: -# This pyproject.toml file manages the build, packaging, and distribution of the Ultralytics library. -# It defines essential project metadata, dependencies, and settings used to develop and deploy the library. - -# Key Sections: -# - [build-system]: Specifies the build requirements and backend (e.g., setuptools, wheel). -# - [project]: Includes details like name, version, description, authors, dependencies and more. -# - [project.optional-dependencies]: Provides additional, optional packages for extended features. -# - [tool.*]: Configures settings for various tools (pytest, yapf, etc.) used in the project. - -# Installation: -# The Ultralytics library can be installed using the command: 'pip install ultralytics' -# For development purposes, you can install the package in editable mode with: 'pip install -e .' -# This approach allows for real-time code modifications without the need for re-installation. - -# Documentation: -# For comprehensive documentation and usage instructions, visit: https://docs.ultralytics.com - -[build-system] -requires = ["setuptools>=43.0.0", "wheel"] -build-backend = "setuptools.build_meta" - -# Project settings ----------------------------------------------------------------------------------------------------- -[project] -name = "ultralytics" -dynamic = ["version"] -description = "Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification." -readme = "README.md" -requires-python = ">=3.8" -license = { "text" = "AGPL-3.0" } -keywords = ["machine-learning", "deep-learning", "computer-vision", "ML", "DL", "AI", "YOLO", "YOLOv3", "YOLOv5", "YOLOv8", "HUB", "Ultralytics"] -authors = [ - { name = "Glenn Jocher" }, - { name = "Ayush Chaurasia" }, - { name = "Jing Qiu" } -] -maintainers = [ - { name = "Glenn Jocher" }, - { name = "Ayush Chaurasia" }, - { name = "Jing Qiu" } -] -classifiers = [ - "Development Status :: 4 - Beta", - "Intended Audience :: Developers", - "Intended Audience :: Education", - "Intended Audience :: Science/Research", - "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)", - "Programming Language :: Python :: 3", - "Programming Language :: Python :: 3.8", - "Programming Language :: Python :: 3.9", - "Programming Language :: Python :: 3.10", - "Programming Language :: Python :: 3.11", - "Programming Language :: Python :: 3.12", - "Topic :: Software Development", - "Topic :: Scientific/Engineering", - "Topic :: Scientific/Engineering :: Artificial Intelligence", - "Topic :: Scientific/Engineering :: Image Recognition", - "Operating System :: POSIX :: Linux", - "Operating System :: MacOS", - "Operating System :: Microsoft :: Windows", -] - -# Required dependencies ------------------------------------------------------------------------------------------------ -dependencies = [ - "matplotlib>=3.3.0", - "opencv-python>=4.6.0", - "pillow>=7.1.2", - "pyyaml>=5.3.1", - "requests>=2.23.0", - "scipy>=1.4.1", - "torch>=1.8.0", - "torchvision>=0.9.0", - "tqdm>=4.64.0", # progress bars - "psutil", # system utilization - "py-cpuinfo", # display CPU info - "thop>=0.1.1", # FLOPs computation - "pandas>=1.1.4", - "seaborn>=0.11.0", # plotting -] - -# Optional dependencies ------------------------------------------------------------------------------------------------ -[project.optional-dependencies] -dev = [ - "ipython", - "check-manifest", - "pre-commit", - "pytest", - "pytest-cov", - "coverage[toml]", - "mkdocs-material>=9.5.9", - "mkdocstrings[python]", - "mkdocs-jupyter", # for notebooks - "mkdocs-redirects", # for 301 redirects - "mkdocs-ultralytics-plugin>=0.0.44", # for meta descriptions and images, dates and authors -] -export = [ - "onnx>=1.12.0", # ONNX export - "coremltools>=7.0; platform_system != 'Windows' and python_version <= '3.11'", # CoreML supported on macOS and Linux - "openvino>=2024.0.0", # OpenVINO export - "tensorflow<=2.13.1; python_version <= '3.11'", # TF bug https://github.com/ultralytics/ultralytics/issues/5161 - "tensorflowjs>=3.9.0; python_version <= '3.11'", # TF.js export, automatically installs tensorflow -] -explorer = [ - "lancedb", # vector search - "duckdb<=0.9.2", # SQL queries, duckdb==0.10.0 bug https://github.com/ultralytics/ultralytics/pull/8181 - "streamlit", # visualizing with GUI -] -# tensorflow>=2.4.1,<=2.13.1 # TF exports (-cpu, -aarch64, -macos) -# tflite-support # for TFLite model metadata -# nvidia-pyindex # TensorRT export -# nvidia-tensorrt # TensorRT export -logging = [ - "comet", # https://docs.ultralytics.com/integrations/comet/ - "tensorboard>=2.13.0", - "dvclive>=2.12.0", -] -extra = [ - "hub-sdk>=0.0.2", # Ultralytics HUB - "ipython", # interactive notebook - "albumentations>=1.0.3", # training augmentations - "pycocotools>=2.0.7", # COCO mAP -] - -[project.urls] -"Bug Reports" = "https://github.com/ultralytics/ultralytics/issues" -"Funding" = "https://ultralytics.com" -"Source" = "https://github.com/ultralytics/ultralytics/" - -[project.scripts] -yolo = "ultralytics.cfg:entrypoint" -ultralytics = "ultralytics.cfg:entrypoint" - -# Tools settings ------------------------------------------------------------------------------------------------------- -[tool.setuptools] # configuration specific to the `setuptools` build backend. -packages = { find = { where = ["."], include = ["ultralytics", "ultralytics.*"] } } -package-data = { "ultralytics" = ["**/*.yaml"], "ultralytics.assets" = ["*.jpg"] } - -[tool.setuptools.dynamic] -version = { attr = "ultralytics.__version__" } - -[tool.pytest] -norecursedirs = [".git", "dist", "build"] -addopts = "--doctest-modules --durations=30 --color=yes" - -[tool.coverage.run] -source = ["ultralytics/"] -data_file = "tests/.coverage" -omit = ["ultralytics/utils/callbacks/*"] - -[tool.isort] -line_length = 120 -multi_line_output = 0 - -[tool.yapf] -based_on_style = "pep8" -spaces_before_comment = 2 -column_limit = 120 -coalesce_brackets = true -spaces_around_power_operator = true -space_between_ending_comma_and_closing_bracket = true -split_before_closing_bracket = false -split_before_first_argument = false - -[tool.ruff] -line-length = 120 - -[tool.docformatter] -wrap-summaries = 120 -wrap-descriptions = 120 -in-place = true -pre-summary-newline = true -close-quotes-on-newline = true - -[tool.codespell] -ignore-words-list = "crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall" -skip = '*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,__pycache__*,*.ico,*.jpg,*.png,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml' diff --git a/ultralytics-main/requirements.txt b/ultralytics-main/requirements.txt deleted file mode 100644 index fde5c44..0000000 --- a/ultralytics-main/requirements.txt +++ /dev/null @@ -1,47 +0,0 @@ -# Ultralytics requirements -# Example: pip install -r requirements.txt - -# Base ---------------------------------------- -matplotlib>=3.3.0 -numpy>=1.22.2 # pinned by Snyk to avoid a vulnerability -opencv-python>=4.6.0 -pillow>=7.1.2 -pyyaml>=5.3.1 -requests>=2.23.0 -scipy>=1.4.1 -# torch>=1.8.0 -# torchvision>=0.9.0 -tqdm>=4.64.0 - -# Logging ------------------------------------- -# tensorboard>=2.13.0 -# dvclive>=2.12.0 -# clearml -# comet - -# Plotting ------------------------------------ -pandas>=1.1.4 -seaborn>=0.11.0 - -# Export -------------------------------------- -# coremltools>=7.0 # CoreML export -# onnx>=1.12.0 # ONNX export -# onnxsim>=0.4.1 # ONNX simplifier -# nvidia-pyindex # TensorRT export -# nvidia-tensorrt # TensorRT export -# scikit-learn==0.19.2 # CoreML quantization -# tensorflow>=2.4.1,<=2.13.1 # TF exports (-cpu, -aarch64, -macos) -# tflite-support -# jax<=0.4.21 # tensorflowjs bug https://github.com/google/jax/issues/18978 -# jaxlib<=0.4.21 # tensorflowjs bug https://github.com/google/jax/issues/18978 -# tensorflowjs>=3.9.0 # TF.js export -# openvino-dev>=2023.0 # OpenVINO export - -# Extras -------------------------------------- -psutil # system utilization -py-cpuinfo # display CPU info -thop>=0.1.1 # FLOPs computation -# ipython # interactive notebook -# albumentations>=1.0.3 # training augmentations -# pycocotools>=2.0.6 # COCO mAP -# roboflow diff --git a/ultralytics-main/setup.py b/ultralytics-main/setup.py deleted file mode 100644 index 2b01df8..0000000 --- a/ultralytics-main/setup.py +++ /dev/null @@ -1,102 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import re -from pathlib import Path - -from setuptools import setup - -# Settings -FILE = Path(__file__).resolve() -PARENT = FILE.parent # root directory -README = (PARENT / 'README.md').read_text(encoding='utf-8') - - -def get_version(): - """ - Retrieve the version number from the 'ultralytics/__init__.py' file. - Returns: - (str): The version number extracted from the '__version__' attribute in the 'ultralytics/__init__.py' file. - """ - file = PARENT / 'ultralytics/__init__.py' - return re.search(r'^__version__ = [\'"]([^\'"]*)[\'"]', file.read_text(encoding='utf-8'), re.M)[1] - - -def parse_requirements(file_path: Path): - """ - Parse a requirements.txt file, ignoring lines that start with '#' and any text after '#'. - Args: - file_path (str | Path): Path to the requirements.txt file. - Returns: - (List[str]): List of parsed requirements. - """ - - requirements = [] - for line in Path(file_path).read_text().splitlines(): - line = line.strip() - if line and not line.startswith('#'): - requirements.append(line.split('#')[0].strip()) # ignore inline comments - - return requirements - - -setup( - name='ultralytics', # name of pypi package - version=get_version(), # version of pypi package - python_requires='>=3.8', - license='AGPL-3.0', - description=('Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, ' - 'pose estimation and image classification.'), - long_description=README, - long_description_content_type='text/markdown', - url='https://github.com/ultralytics/ultralytics', - project_urls={ - 'Bug Reports': 'https://github.com/ultralytics/ultralytics/issues', - 'Funding': 'https://ultralytics.com', - 'Source': 'https://github.com/ultralytics/ultralytics'}, - author='Ultralytics', - author_email='hello@ultralytics.com', - packages=['ultralytics'] + [str(x) for x in Path('ultralytics').rglob('*/') if x.is_dir() and '__' not in str(x)], - package_data={ - '': ['*.yaml'], - 'ultralytics.assets': ['*.jpg']}, - include_package_data=True, - install_requires=parse_requirements(PARENT / 'requirements.txt'), - extras_require={ - 'dev': [ - 'ipython', - 'check-manifest', - 'pre-commit', - 'pytest', - 'pytest-cov', - 'coverage', - 'mkdocs-material', - 'mkdocstrings[python]', - 'mkdocs-redirects', # for 301 redirects - 'mkdocs-ultralytics-plugin>=0.0.30', # for meta descriptions and images, dates and authors - ], - 'export': [ - 'coremltools>=7.0', - 'openvino-dev>=2023.0', - 'tensorflow<=2.13.1', - 'tensorflowjs', # automatically installs tensorflow - ], }, - classifiers=[ - 'Development Status :: 4 - Beta', - 'Intended Audience :: Developers', - 'Intended Audience :: Education', - 'Intended Audience :: Science/Research', - 'License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)', - 'Programming Language :: Python :: 3', - 'Programming Language :: Python :: 3.8', - 'Programming Language :: Python :: 3.9', - 'Programming Language :: Python :: 3.10', - 'Programming Language :: Python :: 3.11', - 'Topic :: Software Development', - 'Topic :: Scientific/Engineering', - 'Topic :: Scientific/Engineering :: Artificial Intelligence', - 'Topic :: Scientific/Engineering :: Image Recognition', - 'Operating System :: POSIX :: Linux', - 'Operating System :: MacOS', - 'Operating System :: Microsoft :: Windows', ], - keywords='machine-learning, deep-learning, vision, ML, DL, AI, YOLO, YOLOv3, YOLOv5, YOLOv8, HUB, Ultralytics', - entry_points={'console_scripts': ['yolo = ultralytics.cfg:entrypoint', 'ultralytics = ultralytics.cfg:entrypoint']}) \ No newline at end of file diff --git a/ultralytics-main/stereo-speed.py b/ultralytics-main/stereo-speed.py deleted file mode 100644 index b464b80..0000000 --- a/ultralytics-main/stereo-speed.py +++ /dev/null @@ -1,98 +0,0 @@ -import time -import cv2 -import numpy as np - -from ultralytics import YOLO -from stereo import stereoconfig_040_2 -from stereo.stereo import stereo_40 -from stereo.stereo import stereo_threading, MyThread -from stereo.dianyuntu_yolo import preprocess, undistortion, getRectifyTransform, draw_line, rectifyImage, \ - stereoMatchSGBM -from collections import defaultdict - -def detect(): - - model = YOLO("yolov8n.pt") - cv2.namedWindow('Speed Estimation', cv2.WINDOW_NORMAL) - cv2.resizeWindow('Speed Estimation', 1280, 360) # 设置宽高 - cap = cv2.VideoCapture('ultralytics/assets/a2.mp4') - out_video = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc(*'XVID'), 30, (2560, 720)) - previous_positions = {} - track_history = defaultdict(lambda: []) - assert cap.isOpened(), "Error reading video file" - while cap.isOpened(): - success, im0 = cap.read() - if not success: - print("Video frame is empty or video processing has been successfully completed.") - break - # start_time = time.time() - im0 = cv2.resize(im0, (2560, 720)) - config = stereoconfig_040_2.stereoCamera() - map1x, map1y, map2x, map2y, Q = getRectifyTransform(720, 1280, config) - thread = MyThread(stereo_threading, args=(config, im0, map1x, map1y, map2x, map2y, Q)) - thread.start() - start_time = time.time() - tracks = model.track(im0, persist=True) - track_ids = tracks[0].boxes.id.int().cpu().tolist() - annotated_frame = tracks[0].plot() - boxes = tracks[0].boxes.xywh.cpu() - - # for i, box in enumerate(boxes): - for i, (box, track_id) in enumerate(zip(boxes, track_ids)): - - x_center, y_center, width, height = box.tolist() - x1 = x_center - width / 2 - y1 = y_center - height / 2 - x2 = x_center + width / 2 - y2 = y_center + height / 2 - if (0 < x2 < 1280): - thread.join() - points_3d = thread.get_result() - a = points_3d[int(y_center), int(x_center), 0] / 1000 - b = points_3d[int(y_center), int(x_center), 1] / 1000 - c = points_3d[int(y_center), int(x_center), 2] / 1000 - distance = ((a ** 2 + b ** 2 + c ** 2) ** 0.5) - bbox_center_3d = (float(a), float(b), float(c)) - current_position = (a, b, c) - if i not in previous_positions: - previous_positions[i] = current_position - continue - tracks.append(bbox_center_3d) - previous_x, previous_y, previous_z = previous_positions[i] - displacement = ((a - previous_x) ** 2 + (b - previous_y) ** 2 + + (c - previous_z) ** 2) ** 0.5 - end_time = time.time() - run_time = end_time-start_time - speed = displacement / run_time - print(run_time) - # 更新上一帧位置 - previous_positions[i] = current_position - # 在这里使用速度进行你想要的操作，比如打印出来 - # print("目标 {} 的速度为: {} m/s".format(i, speed)) - print("速度为: {} m/s".format(speed)) - - track = track_history[track_id] - track.append((float(x_center), float(y_center))) # x, y center point - if len(track) > 30: # retain 90 tracks for 90 frames - track.pop(0) - - # Draw the tracking lines - points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines(annotated_frame, [points], isClosed=False, color=(0, 0, 255), thickness=3) - - if (distance != 0): - text_dis_avg = "dis:%0.2fm" % distance - cv2.putText(annotated_frame, text_dis_avg, (int(x2 + 5), int(y1 + 30)), cv2.FONT_ITALIC, 1.0, - (0, 255, 255), 2) - text_speed = "v:%0.2fm/s" % speed - cv2.putText(annotated_frame, text_speed, (int(x2 + 5), int(y1 + 60)), cv2.FONT_ITALIC, 1.0, - (255, 255, 0), 2) - - cv2.imshow("Speed Estimation", annotated_frame) - out_video.write(annotated_frame) - if cv2.waitKey(1) == ord('q'): - break - out_video.release() - cap.release() - cv2.destroyAllWindows() -if __name__ == '__main__': - detect() \ No newline at end of file diff --git a/ultralytics-main/stereo/dianyuntu_yolo.py b/ultralytics-main/stereo/dianyuntu_yolo.py deleted file mode 100644 index 56099ea..0000000 --- a/ultralytics-main/stereo/dianyuntu_yolo.py +++ /dev/null @@ -1,194 +0,0 @@ - # -*- coding: utf-8 -*- -import cv2 -import numpy as np -import stereo.stereoconfig_040_2 #导入相机标定的参数 -#import pcl -#import pcl.pcl_visualization - - -# 预处理 -def preprocess(img1, img2): - # 彩色图->灰度图 - if(img1.ndim == 3):#判断为三维数组 - img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY) # 通过OpenCV加载的图像通道顺序是BGR - if(img2.ndim == 3): - img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY) - - # 直方图均衡 - img1 = cv2.equalizeHist(img1) - img2 = cv2.equalizeHist(img2) - - return img1, img2 - - -# 消除畸变 -def undistortion(image, camera_matrix, dist_coeff): - undistortion_image = cv2.undistort(image, camera_matrix, dist_coeff) - - return undistortion_image - - -# 获取畸变校正和立体校正的映射变换矩阵、重投影矩阵 -# @param：config是一个类，存储着双目标定的参数:config = stereoconfig.stereoCamera() -def getRectifyTransform(height, width, config): - # 读取内参和外参 - left_K = config.cam_matrix_left - right_K = config.cam_matrix_right - left_distortion = config.distortion_l - right_distortion = config.distortion_r - R = config.R - T = config.T - - # 计算校正变换 - R1, R2, P1, P2, Q, roi1, roi2 = cv2.stereoRectify(left_K, left_distortion, right_K, right_distortion, - (width, height), R, T, alpha=0) - - map1x, map1y = cv2.initUndistortRectifyMap(left_K, left_distortion, R1, P1, (width, height), cv2.CV_32FC1) - map2x, map2y = cv2.initUndistortRectifyMap(right_K, right_distortion, R2, P2, (width, height), cv2.CV_32FC1) - - return map1x, map1y, map2x, map2y, Q - - -# 畸变校正和立体校正 -def rectifyImage(image1, image2, map1x, map1y, map2x, map2y): - rectifyed_img1 = cv2.remap(image1, map1x, map1y, cv2.INTER_AREA) - rectifyed_img2 = cv2.remap(image2, map2x, map2y, cv2.INTER_AREA) - - return rectifyed_img1, rectifyed_img2 - - -# 立体校正检验----画线 -def draw_line(image1, image2): - # 建立输出图像 - height = max(image1.shape[0], image2.shape[0]) - width = image1.shape[1] + image2.shape[1] - - output = np.zeros((height, width, 3), dtype=np.uint8) - output[0:image1.shape[0], 0:image1.shape[1]] = image1 - output[0:image2.shape[0], image1.shape[1]:] = image2 - - # 绘制等间距平行线 - line_interval = 50 # 直线间隔：50 - for k in range(height // line_interval): - cv2.line(output, (0, line_interval * (k + 1)), (2 * width, line_interval * (k + 1)), (0, 255, 0), thickness=2, lineType=cv2.LINE_AA) - - return output - - -# 视差计算 -def stereoMatchSGBM(left_image, right_image, down_scale=False): - # SGBM匹配参数设置 - if left_image.ndim == 2: - img_channels = 1 - else: - img_channels = 3 - blockSize = 5 - paraml = {'minDisparity': 0, - 'numDisparities': 128, - 'blockSize': blockSize, - 'P1': 8 * img_channels * blockSize ** 2, - 'P2': 32 * img_channels * blockSize ** 2, - 'disp12MaxDiff': 5, - 'preFilterCap': 63, - 'uniquenessRatio': 15, - 'speckleWindowSize': 100, - 'speckleRange': 1, - 'mode': cv2.STEREO_SGBM_MODE_SGBM_3WAY - } - - # 构建SGBM对象 - left_matcher = cv2.StereoSGBM_create(**paraml) - paramr = paraml - paramr['minDisparity'] = -paraml['numDisparities'] - right_matcher = cv2.StereoSGBM_create(**paramr) - - # 计算视差图 - size = (left_image.shape[1], left_image.shape[0]) - if down_scale == False: - disparity_left = left_matcher.compute(left_image, right_image) - disparity_right = right_matcher.compute(right_image, left_image) - - else: - left_image_down = cv2.pyrDown(left_image) - right_image_down = cv2.pyrDown(right_image) - factor = left_image.shape[1] / left_image_down.shape[1] - - disparity_left_half = left_matcher.compute(left_image_down, right_image_down) - disparity_right_half = right_matcher.compute(right_image_down, left_image_down) - disparity_left = cv2.resize(disparity_left_half, size, interpolation=cv2.INTER_AREA) - disparity_right = cv2.resize(disparity_right_half, size, interpolation=cv2.INTER_AREA) - disparity_left = factor * disparity_left - disparity_right = factor * disparity_right - - # 真实视差（因为SGBM算法得到的视差是×16的） - trueDisp_left = disparity_left.astype(np.float32) / 16. - trueDisp_right = disparity_right.astype(np.float32) / 16. - - return trueDisp_left, trueDisp_right - - -# 将h×w×3数组转换为N×3的数组 -def hw3ToN3(points): - height, width = points.shape[0:2] - - points_1 = points[:, :, 0].reshape(height * width, 1) - points_2 = points[:, :, 1].reshape(height * width, 1) - points_3 = points[:, :, 2].reshape(height * width, 1) - - points_ = np.hstack((points_1, points_2, points_3)) - - return points_ - - -# 深度、颜色转换为点云 -def DepthColor2Cloud(points_3d, colors): - rows, cols = points_3d.shape[0:2] - size = rows * cols - - points_ = hw3ToN3(points_3d) - colors_ = hw3ToN3(colors).astype(np.int64) - - # 颜色信息 - blue = colors_[:, 0].reshape(size, 1) - green = colors_[:, 1].reshape(size, 1) - red = colors_[:, 2].reshape(size, 1) - - rgb = np.left_shift(blue, 0) + np.left_shift(green, 8) + np.left_shift(red, 16) - - # 将坐标+颜色叠加为点云数组 - pointcloud = np.hstack((points_, rgb)).astype(np.float32) - - # 删掉一些不合适的点 - X = pointcloud[:, 0] - Y = pointcloud[:, 1] - Z = pointcloud[:, 2] - - remove_idx1 = np.where(Z <= 0) - remove_idx2 = np.where(Z > 10000) - remove_idx3 = np.where(X > 10000) - remove_idx4 = np.where(X < -10000) - remove_idx5 = np.where(Y > 10000) - remove_idx6 = np.where(Y < -10000) - remove_idx = np.hstack((remove_idx1[0], remove_idx2[0], remove_idx3[0], remove_idx4[0], remove_idx5[0], remove_idx6[0])) - - pointcloud_1 = np.delete(pointcloud, remove_idx, 0) - - return pointcloud_1 - - - -# 点云显示 -def view_cloud(pointcloud): - cloud = pcl.PointCloud_PointXYZRGBA() - cloud.from_array(pointcloud) - - try: - visual = pcl.pcl_visualization.CloudViewing() - visual.ShowColorACloud(cloud) - v = True - while v: - v = not (visual.WasStopped()) - except: - pass - - diff --git a/ultralytics-main/stereo/stereo.py b/ultralytics-main/stereo/stereo.py deleted file mode 100644 index f233288..0000000 --- a/ultralytics-main/stereo/stereo.py +++ /dev/null @@ -1,206 +0,0 @@ - # -*- coding: utf-8 -*- -import cv2 -import numpy as np - -#import numba - -import threading -from threading import Thread - -import stereo.stereoconfig_040_2 #导入相机标定的参数 -#import pcl -#import pcl.pcl_visualization - -#@cuda.jit -#@jit -#from numba import cuda, vectorize -#from numba import njit -#@cuda.jit -#@njit -#@vectorize(["float32 (float32 , float32 )"], target='cuda') -class stereo_40: - def __init__(self,imgl,imgr): - self.left = imgl - self.right = imgr - - # 预处理 - def preprocess(self, img1, img2): - # 彩色图->灰度图 - if(img1.ndim == 3):#判断为三维数组 - img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY) # 通过OpenCV加载的图像通道顺序是BGR - if(img2.ndim == 3): - img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY) - - # 直方图均衡 - img1 = cv2.equalizeHist(img1) - img2 = cv2.equalizeHist(img2) - - return img1, img2 - - ''' - # 消除畸变 - def undistortion(self, image, camera_matrix, dist_coeff): - undistortion_image = cv2.undistort(image, camera_matrix, dist_coeff) - - return undistortion_image - ''' - # 消除畸变 - def undistortion(self, imagleft,imagright, camera_matrix_left, camera_matrix_right, dist_coeff_left,dist_coeff_right): - undistortion_imagleft = cv2.undistort(imagleft, camera_matrix_left, dist_coeff_left ) - undistortion_imagright = cv2.undistort(imagright, camera_matrix_right, dist_coeff_right) - - return undistortion_imagleft, undistortion_imagright - - - - - # 畸变校正和立体校正 - def rectifyImage(self, image1, image2, map1x, map1y, map2x, map2y): - rectifyed_img1 = cv2.remap(image1, map1x, map1y, cv2.INTER_AREA) - rectifyed_img2 = cv2.remap(image2, map2x, map2y, cv2.INTER_AREA) - - return rectifyed_img1, rectifyed_img2 - - - # 立体校正检验----画线 - def draw_line(self, image1, image2): - # 建立输出图像 - height = max(image1.shape[0], image2.shape[0]) - width = image1.shape[1] + image2.shape[1] - - output = np.zeros((height, width, 3), dtype=np.uint8) - output[0:image1.shape[0], 0:image1.shape[1]] = image1 - output[0:image2.shape[0], image1.shape[1]:] = image2 - - # 绘制等间距平行线 - line_interval = 50 # 直线间隔：50 - for k in range(height // line_interval): - cv2.line(output, (0, line_interval * (k + 1)), (2 * width, line_interval * (k + 1)), (0, 255, 0), thickness=2, lineType=cv2.LINE_AA) - - return output - - - # 视差计算 - def stereoMatchSGBM(self, left_image, right_image, down_scale=False): - # SGBM匹配参数设置 - if left_image.ndim == 2: - img_channels = 1 - else: - img_channels = 3 - blockSize = 3 - paraml = {'minDisparity': 0, - 'numDisparities': 128, - 'blockSize': blockSize, - 'P1': 8 * img_channels * blockSize ** 2, - 'P2': 32 * img_channels * blockSize ** 2, - 'disp12MaxDiff': -1, - 'preFilterCap': 63, - 'uniquenessRatio': 10, - 'speckleWindowSize': 100, - 'speckleRange': 1, - 'mode': cv2.STEREO_SGBM_MODE_SGBM_3WAY - } - - # 构建SGBM对象 - left_matcher = cv2.StereoSGBM_create(**paraml) - paramr = paraml - paramr['minDisparity'] = -paraml['numDisparities'] - right_matcher = cv2.StereoSGBM_create(**paramr) - - # 计算视差图 - size = (left_image.shape[1], left_image.shape[0]) - if down_scale == False: - disparity_left = left_matcher.compute(left_image, right_image) - disparity_right = right_matcher.compute(right_image, left_image) - - else: - left_image_down = cv2.pyrDown(left_image) - right_image_down = cv2.pyrDown(right_image) - factor = left_image.shape[1] / left_image_down.shape[1] - - disparity_left_half = left_matcher.compute(left_image_down, right_image_down) - disparity_right_half = right_matcher.compute(right_image_down, left_image_down) - disparity_left = cv2.resize(disparity_left_half, size, interpolation=cv2.INTER_AREA) - disparity_right = cv2.resize(disparity_right_half, size, interpolation=cv2.INTER_AREA) - disparity_left = factor * disparity_left - disparity_right = factor * disparity_right - - # 真实视差（因为SGBM算法得到的视差是×16的） - trueDisp_left = disparity_left.astype(np.float32) / 16. - trueDisp_right = disparity_right.astype(np.float32) / 16. - - return trueDisp_left, trueDisp_right - - -def get_median(data): - data.sort() - half = len(data) // 2 - #return (data[half] + data[~half]) / 2 - return data[half] - -class MyThread(threading.Thread): - def __init__(self, func, args=()): - super(MyThread, self).__init__() - self.func = func - self.args = args - - def run(self): - self.result = self.func(*self.args) # 在执行函数的同时，把结果赋值给result, - # 然后通过get_result函数获取返回的结果 - - def get_result(self): - try: - return self.result - except Exception as e: - return None - - - -def stereo_threading(config,im0,map1x, map1y, map2x, map2y,Q): - height_0, width_0 = im0.shape[0:2] - - width_1 = width_0/2 - iml = im0[0:int(height_0), 0:int(width_0/2)] - imr = im0[0:int(height_0), int(width_0/2):int(width_0) ] - - stereo_test = stereo_40(iml,imr) - height, width = iml.shape[0:2] - - - - - #t6 = time_synchronized() #O.506s - - #print("Print Q!") - #print("Q[2,3]:%.3f"%Q[2,3]) - - #t6 = time_synchronized()#0.450s - iml_rectified, imr_rectified = stereo_test.rectifyImage(iml, imr, map1x, map1y, map2x, map2y) - - - #t6 = time_synchronized()#0.410s - # 消除畸变as - iml, imr = stereo_test.undistortion(iml,imr, config.cam_matrix_left, config.cam_matrix_right, config.distortion_l,config.distortion_r) - #t6 = time_synchronized()#0.299s - # 立体匹配 - iml_, imr_ = stereo_test.preprocess(iml, imr) # 预处理，一般可以削弱光照不均的影响，不做也可以 - - iml_rectified_l, imr_rectified_r = stereo_test.rectifyImage(iml_, imr_, map1x, map1y, map2x, map2y) - #t6 = time_synchronized()#0.260s - disp, _ = stereo_test.stereoMatchSGBM(iml_rectified_l, imr_rectified_r, True) - #cv2.imwrite('./yolo/%s视差%d.png' %(string,p), disp) - - #t6 = time_synchronized()#0.010s - # 计算像素点的3D坐标（左相机坐标系下） - points_3d = cv2.reprojectImageTo3D(disp, Q) # 可以使用上文的stereo_config.py给出的参数 - return points_3d - #t7 = time_synchronized() - #print(f'3D MATCH Done. ({t7 - t3:.3f}s)') - #print() - #print("############## Frame is %d !##################" %accel_frame) - - #t4 = time.time() # stereo time end - #print(f'{s}Stereo Done. ({t4 - t3:.3f}s)') - - - diff --git a/ultralytics-main/stereo/stereoconfig_040_2.py b/ultralytics-main/stereo/stereoconfig_040_2.py deleted file mode 100644 index 4148d73..0000000 --- a/ultralytics-main/stereo/stereoconfig_040_2.py +++ /dev/null @@ -1,42 +0,0 @@ -import numpy as np - - -####################仅仅是一个示例################################### - - -# 双目相机参数 -class stereoCamera(object): - def __init__(self): - # 左相机内参 - self.cam_matrix_left = np.array([[1060.3700, 0, 1124.9100], - [0, 1059.7600, 623.3810], - [0, 0, 1] - ]) - # 右相机内参 - self.cam_matrix_right = np.array([[1049.2200, 0, 1124.6899], - [0, 1049.0800, 619.5950], - [0, 0, 1] - ]) - - # 左右相机畸变系数:[k1, k2, p1, p2, k3] - self.distortion_l = np.array([[-0.0424, 0.0126, -0.0002, 0.0003, -0.0060]]) - self.distortion_r = np.array([[-0.0411, 0.0089, -0.0002, 0.0003, -0.0060]]) - - # 旋转矩阵 - self.R = np.array([[1.0000, -0.0006, 0.0028], - [0.0006, 1.0000, -0.0003], - [-0.0028, 0.0003, 1.0000] - ]) - - # 平移矩阵 - self.T = np.array([[119.7550], [-0.1684], [0.4651]]) - - # 焦距 - self.focal_length = 859.367 # 默认值，一般取立体校正后的重投影矩阵Q中的 Q[2,3] - - # 基线距离 - self.baseline = 119.9578 # 单位：mm， 为平移向量的第一个参数（取绝对值） - - - - diff --git a/ultralytics-main/ultralytics/__init__.py b/ultralytics-main/ultralytics/__init__.py deleted file mode 100644 index 1a38daf..0000000 --- a/ultralytics-main/ultralytics/__init__.py +++ /dev/null @@ -1,26 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -__version__ = "8.1.30" - -from ultralytics.data.explorer.explorer import Explorer -from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld -from ultralytics.models.fastsam import FastSAM -from ultralytics.models.nas import NAS -from ultralytics.utils import ASSETS, SETTINGS as settings -from ultralytics.utils.checks import check_yolo as checks -from ultralytics.utils.downloads import download - -__all__ = ( - "__version__", - "ASSETS", - "YOLO", - "YOLOWorld", - "NAS", - "SAM", - "FastSAM", - "RTDETR", - "checks", - "download", - "settings", - "Explorer", -) diff --git a/ultralytics-main/ultralytics/bus.jpg b/ultralytics-main/ultralytics/bus.jpg deleted file mode 100644 index b43e311..0000000 Binary files a/ultralytics-main/ultralytics/bus.jpg and /dev/null differ diff --git a/ultralytics-main/ultralytics/cfg/__init__.py b/ultralytics-main/ultralytics/cfg/__init__.py deleted file mode 100644 index d9d7375..0000000 --- a/ultralytics-main/ultralytics/cfg/__init__.py +++ /dev/null @@ -1,587 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import shutil -import subprocess -import sys -from pathlib import Path -from types import SimpleNamespace -from typing import Dict, List, Union - -from ultralytics.utils import ( - ASSETS, - DEFAULT_CFG, - DEFAULT_CFG_DICT, - DEFAULT_CFG_PATH, - LOGGER, - RANK, - ROOT, - RUNS_DIR, - SETTINGS, - SETTINGS_YAML, - TESTS_RUNNING, - IterableSimpleNamespace, - __version__, - checks, - colorstr, - deprecation_warn, - yaml_load, - yaml_print, -) - -# Define valid tasks and modes -MODES = "train", "val", "predict", "export", "track", "benchmark" -TASKS = "detect", "segment", "classify", "pose", "obb" -TASK2DATA = { - "detect": "coco8.yaml", - "segment": "coco8-seg.yaml", - "classify": "imagenet10", - "pose": "coco8-pose.yaml", - "obb": "dota8.yaml", -} -TASK2MODEL = { - "detect": "yolov8n.pt", - "segment": "yolov8n-seg.pt", - "classify": "yolov8n-cls.pt", - "pose": "yolov8n-pose.pt", - "obb": "yolov8n-obb.pt", -} -TASK2METRIC = { - "detect": "metrics/mAP50-95(B)", - "segment": "metrics/mAP50-95(M)", - "classify": "metrics/accuracy_top1", - "pose": "metrics/mAP50-95(P)", - "obb": "metrics/mAP50-95(B)", -} - -CLI_HELP_MSG = f""" - Arguments received: {str(['yolo'] + sys.argv[1:])}. Ultralytics 'yolo' commands use the following syntax: - - yolo TASK MODE ARGS - - Where TASK (optional) is one of {TASKS} - MODE (required) is one of {MODES} - ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults. - See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg' - - 1. Train a detection model for 10 epochs with an initial learning_rate of 0.01 - yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 - - 2. Predict a YouTube video using a pretrained segmentation model at image size 320: - yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 - - 3. Val a pretrained detection model at batch-size 1 and image size 640: - yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 - - 4. Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required) - yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128 - - 6. Explore your datasets using semantic search and SQL with a simple GUI powered by Ultralytics Explorer API - yolo explorer - - 5. Run special commands: - yolo help - yolo checks - yolo version - yolo settings - yolo copy-cfg - yolo cfg - - Docs: https://docs.ultralytics.com - Community: https://community.ultralytics.com - GitHub: https://github.com/ultralytics/ultralytics - """ - -# Define keys for arg type checks -CFG_FLOAT_KEYS = "warmup_epochs", "box", "cls", "dfl", "degrees", "shear", "time" -CFG_FRACTION_KEYS = ( - "dropout", - "iou", - "lr0", - "lrf", - "momentum", - "weight_decay", - "warmup_momentum", - "warmup_bias_lr", - "label_smoothing", - "hsv_h", - "hsv_s", - "hsv_v", - "translate", - "scale", - "perspective", - "flipud", - "fliplr", - "mosaic", - "mixup", - "copy_paste", - "conf", - "iou", - "fraction", -) # fraction floats 0.0 - 1.0 -CFG_INT_KEYS = ( - "epochs", - "patience", - "batch", - "workers", - "seed", - "close_mosaic", - "mask_ratio", - "max_det", - "vid_stride", - "line_width", - "workspace", - "nbs", - "save_period", -) -CFG_BOOL_KEYS = ( - "save", - "exist_ok", - "verbose", - "deterministic", - "single_cls", - "rect", - "cos_lr", - "overlap_mask", - "val", - "save_json", - "save_hybrid", - "half", - "dnn", - "plots", - "show", - "save_txt", - "save_conf", - "save_crop", - "save_frames", - "show_labels", - "show_conf", - "visualize", - "augment", - "agnostic_nms", - "retina_masks", - "show_boxes", - "keras", - "optimize", - "int8", - "dynamic", - "simplify", - "nms", - "profile", - "multi_scale", -) - - -def cfg2dict(cfg): - """ - Convert a configuration object to a dictionary, whether it is a file path, a string, or a SimpleNamespace object. - - Args: - cfg (str | Path | dict | SimpleNamespace): Configuration object to be converted to a dictionary. - - Returns: - cfg (dict): Configuration object in dictionary format. - """ - if isinstance(cfg, (str, Path)): - cfg = yaml_load(cfg) # load dict - elif isinstance(cfg, SimpleNamespace): - cfg = vars(cfg) # convert to dict - return cfg - - -def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, overrides: Dict = None): - """ - Load and merge configuration data from a file or dictionary. - - Args: - cfg (str | Path | Dict | SimpleNamespace): Configuration data. - overrides (str | Dict | optional): Overrides in the form of a file name or a dictionary. Default is None. - - Returns: - (SimpleNamespace): Training arguments namespace. - """ - cfg = cfg2dict(cfg) - - # Merge overrides - if overrides: - overrides = cfg2dict(overrides) - if "save_dir" not in cfg: - overrides.pop("save_dir", None) # special override keys to ignore - check_dict_alignment(cfg, overrides) - cfg = {**cfg, **overrides} # merge cfg and overrides dicts (prefer overrides) - - # Special handling for numeric project/name - for k in "project", "name": - if k in cfg and isinstance(cfg[k], (int, float)): - cfg[k] = str(cfg[k]) - if cfg.get("name") == "model": # assign model to 'name' arg - cfg["name"] = cfg.get("model", "").split(".")[0] - LOGGER.warning(f"WARNING ⚠️ 'name=model' automatically updated to 'name={cfg['name']}'.") - - # Type and Value checks - for k, v in cfg.items(): - if v is not None: # None values may be from optional args - if k in CFG_FLOAT_KEYS and not isinstance(v, (int, float)): - raise TypeError( - f"'{k}={v}' is of invalid type {type(v).__name__}. " - f"Valid '{k}' types are int (i.e. '{k}=0') or float (i.e. '{k}=0.5')" - ) - elif k in CFG_FRACTION_KEYS: - if not isinstance(v, (int, float)): - raise TypeError( - f"'{k}={v}' is of invalid type {type(v).__name__}. " - f"Valid '{k}' types are int (i.e. '{k}=0') or float (i.e. '{k}=0.5')" - ) - if not (0.0 <= v <= 1.0): - raise ValueError(f"'{k}={v}' is an invalid value. " f"Valid '{k}' values are between 0.0 and 1.0.") - elif k in CFG_INT_KEYS and not isinstance(v, int): - raise TypeError( - f"'{k}={v}' is of invalid type {type(v).__name__}. " f"'{k}' must be an int (i.e. '{k}=8')" - ) - elif k in CFG_BOOL_KEYS and not isinstance(v, bool): - raise TypeError( - f"'{k}={v}' is of invalid type {type(v).__name__}. " - f"'{k}' must be a bool (i.e. '{k}=True' or '{k}=False')" - ) - - # Return instance - return IterableSimpleNamespace(**cfg) - - -def get_save_dir(args, name=None): - """Return save_dir as created from train/val/predict arguments.""" - - if getattr(args, "save_dir", None): - save_dir = args.save_dir - else: - from ultralytics.utils.files import increment_path - - project = args.project or (ROOT.parent / "tests/tmp/runs" if TESTS_RUNNING else RUNS_DIR) / args.task - name = name or args.name or f"{args.mode}" - save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in (-1, 0) else True) - - return Path(save_dir) - - -def _handle_deprecation(custom): - """Hardcoded function to handle deprecated config keys.""" - - for key in custom.copy().keys(): - if key == "boxes": - deprecation_warn(key, "show_boxes") - custom["show_boxes"] = custom.pop("boxes") - if key == "hide_labels": - deprecation_warn(key, "show_labels") - custom["show_labels"] = custom.pop("hide_labels") == "False" - if key == "hide_conf": - deprecation_warn(key, "show_conf") - custom["show_conf"] = custom.pop("hide_conf") == "False" - if key == "line_thickness": - deprecation_warn(key, "line_width") - custom["line_width"] = custom.pop("line_thickness") - - return custom - - -def check_dict_alignment(base: Dict, custom: Dict, e=None): - """ - This function checks for any mismatched keys between a custom configuration list and a base configuration list. If - any mismatched keys are found, the function prints out similar keys from the base list and exits the program. - - Args: - custom (dict): a dictionary of custom configuration options - base (dict): a dictionary of base configuration options - e (Error, optional): An optional error that is passed by the calling function. - """ - custom = _handle_deprecation(custom) - base_keys, custom_keys = (set(x.keys()) for x in (base, custom)) - mismatched = [k for k in custom_keys if k not in base_keys] - if mismatched: - from difflib import get_close_matches - - string = "" - for x in mismatched: - matches = get_close_matches(x, base_keys) # key list - matches = [f"{k}={base[k]}" if base.get(k) is not None else k for k in matches] - match_str = f"Similar arguments are i.e. {matches}." if matches else "" - string += f"'{colorstr('red', 'bold', x)}' is not a valid YOLO argument. {match_str}\n" - raise SyntaxError(string + CLI_HELP_MSG) from e - - -def merge_equals_args(args: List[str]) -> List[str]: - """ - Merges arguments around isolated '=' args in a list of strings. The function considers cases where the first - argument ends with '=' or the second starts with '=', as well as when the middle one is an equals sign. - - Args: - args (List[str]): A list of strings where each element is an argument. - - Returns: - (List[str]): A list of strings where the arguments around isolated '=' are merged. - """ - new_args = [] - for i, arg in enumerate(args): - if arg == "=" and 0 < i < len(args) - 1: # merge ['arg', '=', 'val'] - new_args[-1] += f"={args[i + 1]}" - del args[i + 1] - elif arg.endswith("=") and i < len(args) - 1 and "=" not in args[i + 1]: # merge ['arg=', 'val'] - new_args.append(f"{arg}{args[i + 1]}") - del args[i + 1] - elif arg.startswith("=") and i > 0: # merge ['arg', '=val'] - new_args[-1] += arg - else: - new_args.append(arg) - return new_args - - -def handle_yolo_hub(args: List[str]) -> None: - """ - Handle Ultralytics HUB command-line interface (CLI) commands. - - This function processes Ultralytics HUB CLI commands such as login and logout. - It should be called when executing a script with arguments related to HUB authentication. - - Args: - args (List[str]): A list of command line arguments - - Example: - ```bash - python my_script.py hub login your_api_key - ``` - """ - from ultralytics import hub - - if args[0] == "login": - key = args[1] if len(args) > 1 else "" - # Log in to Ultralytics HUB using the provided API key - hub.login(key) - elif args[0] == "logout": - # Log out from Ultralytics HUB - hub.logout() - - -def handle_yolo_settings(args: List[str]) -> None: - """ - Handle YOLO settings command-line interface (CLI) commands. - - This function processes YOLO settings CLI commands such as reset. - It should be called when executing a script with arguments related to YOLO settings management. - - Args: - args (List[str]): A list of command line arguments for YOLO settings management. - - Example: - ```bash - python my_script.py yolo settings reset - ``` - """ - url = "https://docs.ultralytics.com/quickstart/#ultralytics-settings" # help URL - try: - if any(args): - if args[0] == "reset": - SETTINGS_YAML.unlink() # delete the settings file - SETTINGS.reset() # create new settings - LOGGER.info("Settings reset successfully") # inform the user that settings have been reset - else: # save a new setting - new = dict(parse_key_value_pair(a) for a in args) - check_dict_alignment(SETTINGS, new) - SETTINGS.update(new) - - LOGGER.info(f"💡 Learn about settings at {url}") - yaml_print(SETTINGS_YAML) # print the current settings - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.") - - -def handle_explorer(): - """Open the Ultralytics Explorer GUI.""" - checks.check_requirements("streamlit") - LOGGER.info("💡 Loading Explorer dashboard...") - subprocess.run(["streamlit", "run", ROOT / "data/explorer/gui/dash.py", "--server.maxMessageSize", "2048"]) - - -def parse_key_value_pair(pair): - """Parse one 'key=value' pair and return key and value.""" - k, v = pair.split("=", 1) # split on first '=' sign - k, v = k.strip(), v.strip() # remove spaces - assert v, f"missing '{k}' value" - return k, smart_value(v) - - -def smart_value(v): - """Convert a string to an underlying type such as int, float, bool, etc.""" - v_lower = v.lower() - if v_lower == "none": - return None - elif v_lower == "true": - return True - elif v_lower == "false": - return False - else: - with contextlib.suppress(Exception): - return eval(v) - return v - - -def entrypoint(debug=""): - """ - This function is the ultralytics package entrypoint, it's responsible for parsing the command line arguments passed - to the package. - - This function allows for: - - passing mandatory YOLO args as a list of strings - - specifying the task to be performed, either 'detect', 'segment' or 'classify' - - specifying the mode, either 'train', 'val', 'test', or 'predict' - - running special modes like 'checks' - - passing overrides to the package's configuration - - It uses the package's default cfg and initializes it using the passed overrides. - Then it calls the CLI function with the composed cfg - """ - args = (debug.split(" ") if debug else sys.argv)[1:] - if not args: # no arguments passed - LOGGER.info(CLI_HELP_MSG) - return - - special = { - "help": lambda: LOGGER.info(CLI_HELP_MSG), - "checks": checks.collect_system_info, - "version": lambda: LOGGER.info(__version__), - "settings": lambda: handle_yolo_settings(args[1:]), - "cfg": lambda: yaml_print(DEFAULT_CFG_PATH), - "hub": lambda: handle_yolo_hub(args[1:]), - "login": lambda: handle_yolo_hub(args), - "copy-cfg": copy_default_cfg, - "explorer": lambda: handle_explorer(), - } - full_args_dict = {**DEFAULT_CFG_DICT, **{k: None for k in TASKS}, **{k: None for k in MODES}, **special} - - # Define common misuses of special commands, i.e. -h, -help, --help - special.update({k[0]: v for k, v in special.items()}) # singular - special.update({k[:-1]: v for k, v in special.items() if len(k) > 1 and k.endswith("s")}) # singular - special = {**special, **{f"-{k}": v for k, v in special.items()}, **{f"--{k}": v for k, v in special.items()}} - - overrides = {} # basic overrides, i.e. imgsz=320 - for a in merge_equals_args(args): # merge spaces around '=' sign - if a.startswith("--"): - LOGGER.warning(f"WARNING ⚠️ '{a}' does not require leading dashes '--', updating to '{a[2:]}'.") - a = a[2:] - if a.endswith(","): - LOGGER.warning(f"WARNING ⚠️ '{a}' does not require trailing comma ',', updating to '{a[:-1]}'.") - a = a[:-1] - if "=" in a: - try: - k, v = parse_key_value_pair(a) - if k == "cfg" and v is not None: # custom.yaml passed - LOGGER.info(f"Overriding {DEFAULT_CFG_PATH} with {v}") - overrides = {k: val for k, val in yaml_load(checks.check_yaml(v)).items() if k != "cfg"} - else: - overrides[k] = v - except (NameError, SyntaxError, ValueError, AssertionError) as e: - check_dict_alignment(full_args_dict, {a: ""}, e) - - elif a in TASKS: - overrides["task"] = a - elif a in MODES: - overrides["mode"] = a - elif a.lower() in special: - special[a.lower()]() - return - elif a in DEFAULT_CFG_DICT and isinstance(DEFAULT_CFG_DICT[a], bool): - overrides[a] = True # auto-True for default bool args, i.e. 'yolo show' sets show=True - elif a in DEFAULT_CFG_DICT: - raise SyntaxError( - f"'{colorstr('red', 'bold', a)}' is a valid YOLO argument but is missing an '=' sign " - f"to set its value, i.e. try '{a}={DEFAULT_CFG_DICT[a]}'\n{CLI_HELP_MSG}" - ) - else: - check_dict_alignment(full_args_dict, {a: ""}) - - # Check keys - check_dict_alignment(full_args_dict, overrides) - - # Mode - mode = overrides.get("mode") - if mode is None: - mode = DEFAULT_CFG.mode or "predict" - LOGGER.warning(f"WARNING ⚠️ 'mode' is missing. Valid modes are {MODES}. Using default 'mode={mode}'.") - elif mode not in MODES: - raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {MODES}.\n{CLI_HELP_MSG}") - - # Task - task = overrides.pop("task", None) - if task: - if task not in TASKS: - raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}") - if "model" not in overrides: - overrides["model"] = TASK2MODEL[task] - - # Model - model = overrides.pop("model", DEFAULT_CFG.model) - if model is None: - model = "yolov8n.pt" - LOGGER.warning(f"WARNING ⚠️ 'model' is missing. Using default 'model={model}'.") - overrides["model"] = model - stem = Path(model).stem.lower() - if "rtdetr" in stem: # guess architecture - from ultralytics import RTDETR - - model = RTDETR(model) # no task argument - elif "fastsam" in stem: - from ultralytics import FastSAM - - model = FastSAM(model) - elif "sam" in stem: - from ultralytics import SAM - - model = SAM(model) - else: - from ultralytics import YOLO - - model = YOLO(model, task=task) - if isinstance(overrides.get("pretrained"), str): - model.load(overrides["pretrained"]) - - # Task Update - if task != model.task: - if task: - LOGGER.warning( - f"WARNING ⚠️ conflicting 'task={task}' passed with 'task={model.task}' model. " - f"Ignoring 'task={task}' and updating to 'task={model.task}' to match model." - ) - task = model.task - - # Mode - if mode in ("predict", "track") and "source" not in overrides: - overrides["source"] = DEFAULT_CFG.source or ASSETS - LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using default 'source={overrides['source']}'.") - elif mode in ("train", "val"): - if "data" not in overrides and "resume" not in overrides: - overrides["data"] = DEFAULT_CFG.data or TASK2DATA.get(task or DEFAULT_CFG.task, DEFAULT_CFG.data) - LOGGER.warning(f"WARNING ⚠️ 'data' is missing. Using default 'data={overrides['data']}'.") - elif mode == "export": - if "format" not in overrides: - overrides["format"] = DEFAULT_CFG.format or "torchscript" - LOGGER.warning(f"WARNING ⚠️ 'format' is missing. Using default 'format={overrides['format']}'.") - - # Run command in python - getattr(model, mode)(**overrides) # default args from model - - # Show help - LOGGER.info(f"💡 Learn more at https://docs.ultralytics.com/modes/{mode}") - - -# Special modes -------------------------------------------------------------------------------------------------------- -def copy_default_cfg(): - """Copy and create a new default configuration file with '_copy' appended to its name.""" - new_file = Path.cwd() / DEFAULT_CFG_PATH.name.replace(".yaml", "_copy.yaml") - shutil.copy2(DEFAULT_CFG_PATH, new_file) - LOGGER.info( - f"{DEFAULT_CFG_PATH} copied to {new_file}\n" - f"Example YOLO command with this new custom cfg:\n yolo cfg='{new_file}' imgsz=320 batch=8" - ) - - -if __name__ == "__main__": - # Example: entrypoint(debug='yolo predict model=yolov8n.pt') - entrypoint(debug="") diff --git a/ultralytics-main/ultralytics/cfg/default.yaml b/ultralytics-main/ultralytics/cfg/default.yaml deleted file mode 100644 index 5ddd257..0000000 --- a/ultralytics-main/ultralytics/cfg/default.yaml +++ /dev/null @@ -1,125 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Default training settings and hyperparameters for medium-augmentation COCO training - -task: detect # (str) YOLO task, i.e. detect, segment, classify, pose -mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark - -# Train settings ------------------------------------------------------------------------------------------------------- -model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml -data: # (str, optional) path to data file, i.e. coco128.yaml -epochs: 100 # (int) number of epochs to train for -time: # (float, optional) number of hours to train for, overrides epochs if supplied -patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training -batch: 16 # (int) number of images per batch (-1 for AutoBatch) -imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes -save: True # (bool) save train checkpoints and predict results -save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1) -cache: False # (bool) True/ram, disk or False. Use cache for data loading -device: # (int | str | list, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu -workers: 8 # (int) number of worker threads for data loading (per RANK if DDP) -project: # (str, optional) project name -name: # (str, optional) experiment name, results saved to 'project/name' directory -exist_ok: False # (bool) whether to overwrite existing experiment -pretrained: True # (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str) -optimizer: auto # (str) optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto] -verbose: True # (bool) whether to print verbose output -seed: 0 # (int) random seed for reproducibility -deterministic: True # (bool) whether to enable deterministic mode -single_cls: False # (bool) train multi-class data as single-class -rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val' -cos_lr: False # (bool) use cosine learning rate scheduler -close_mosaic: 10 # (int) disable mosaic augmentation for final epochs (0 to disable) -resume: False # (bool) resume training from last checkpoint -amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check -fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set) -profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers -freeze: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training -multi_scale: False # (bool) Whether to use multiscale during training -# Segmentation -overlap_mask: True # (bool) masks should overlap during training (segment train only) -mask_ratio: 4 # (int) mask downsample ratio (segment train only) -# Classification -dropout: 0.0 # (float) use dropout regularization (classify train only) - -# Val/Test settings ---------------------------------------------------------------------------------------------------- -val: True # (bool) validate/test during training -split: val # (str) dataset split to use for validation, i.e. 'val', 'test' or 'train' -save_json: False # (bool) save results to JSON file -save_hybrid: False # (bool) save hybrid version of labels (labels + additional predictions) -conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val) -iou: 0.7 # (float) intersection over union (IoU) threshold for NMS -max_det: 300 # (int) maximum number of detections per image -half: False # (bool) use half precision (FP16) -dnn: False # (bool) use OpenCV DNN for ONNX inference -plots: True # (bool) save plots and images during train/val - -# Predict settings ----------------------------------------------------------------------------------------------------- -source: # (str, optional) source directory for images or videos -vid_stride: 1 # (int) video frame-rate stride -stream_buffer: False # (bool) buffer all streaming frames (True) or return the most recent frame (False) -visualize: False # (bool) visualize model features -augment: False # (bool) apply image augmentation to prediction sources -agnostic_nms: False # (bool) class-agnostic NMS -classes: # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3] -retina_masks: False # (bool) use high-resolution segmentation masks -embed: # (list[int], optional) return feature vectors/embeddings from given layers - -# Visualize settings --------------------------------------------------------------------------------------------------- -show: False # (bool) show predicted images and videos if environment allows -save_frames: False # (bool) save predicted individual video frames -save_txt: False # (bool) save results as .txt file -save_conf: False # (bool) save results with confidence scores -save_crop: False # (bool) save cropped images with results -show_labels: True # (bool) show prediction labels, i.e. 'person' -show_conf: True # (bool) show prediction confidence, i.e. '0.99' -show_boxes: True # (bool) show prediction boxes -line_width: # (int, optional) line width of the bounding boxes. Scaled to image size if None. - -# Export settings ------------------------------------------------------------------------------------------------------ -format: torchscript # (str) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats -keras: False # (bool) use Kera=s -optimize: False # (bool) TorchScript: optimize for mobile -int8: False # (bool) CoreML/TF INT8 quantization -dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes -simplify: False # (bool) ONNX: simplify model -opset: # (int, optional) ONNX: opset version -workspace: 4 # (int) TensorRT: workspace size (GB) -nms: False # (bool) CoreML: add NMS - -# Hyperparameters ------------------------------------------------------------------------------------------------------ -lr0: 0.01 # (float) initial learning rate (i.e. SGD=1E-2, Adam=1E-3) -lrf: 0.01 # (float) final learning rate (lr0 * lrf) -momentum: 0.937 # (float) SGD momentum/Adam beta1 -weight_decay: 0.0005 # (float) optimizer weight decay 5e-4 -warmup_epochs: 3.0 # (float) warmup epochs (fractions ok) -warmup_momentum: 0.8 # (float) warmup initial momentum -warmup_bias_lr: 0.1 # (float) warmup initial bias lr -box: 7.5 # (float) box loss gain -cls: 0.5 # (float) cls loss gain (scale with pixels) -dfl: 1.5 # (float) dfl loss gain -pose: 12.0 # (float) pose loss gain -kobj: 1.0 # (float) keypoint obj loss gain -label_smoothing: 0.0 # (float) label smoothing (fraction) -nbs: 64 # (int) nominal batch size -hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction) -hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction) -hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction) -degrees: 0.0 # (float) image rotation (+/- deg) -translate: 0.1 # (float) image translation (+/- fraction) -scale: 0.5 # (float) image scale (+/- gain) -shear: 0.0 # (float) image shear (+/- deg) -perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001 -flipud: 0.0 # (float) image flip up-down (probability) -fliplr: 0.5 # (float) image flip left-right (probability) -mosaic: 1.0 # (float) image mosaic (probability) -mixup: 0.0 # (float) image mixup (probability) -copy_paste: 0.0 # (float) segment copy-paste (probability) -auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix) -erasing: 0.4 # (float) probability of random erasing during classification training (0-1) -crop_fraction: 1.0 # (float) image crop fraction for classification evaluation/inference (0-1) - -# Custom config.yaml --------------------------------------------------------------------------------------------------- -cfg: # (str, optional) for overriding defaults.yaml - -# Tracker settings ------------------------------------------------------------------------------------------------------ -tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml] diff --git a/ultralytics-main/ultralytics/cfg/models/README.md b/ultralytics-main/ultralytics/cfg/models/README.md deleted file mode 100644 index c022fb5..0000000 --- a/ultralytics-main/ultralytics/cfg/models/README.md +++ /dev/null @@ -1,40 +0,0 @@ -## Models - -Welcome to the Ultralytics Models directory! Here you will find a wide variety of pre-configured model configuration files (`*.yaml`s) that can be used to create custom YOLO models. The models in this directory have been expertly crafted and fine-tuned by the Ultralytics team to provide the best performance for a wide range of object detection and image segmentation tasks. - -These model configurations cover a wide range of scenarios, from simple object detection to more complex tasks like instance segmentation and object tracking. They are also designed to run efficiently on a variety of hardware platforms, from CPUs to GPUs. Whether you are a seasoned machine learning practitioner or just getting started with YOLO, this directory provides a great starting point for your custom model development needs. - -To get started, simply browse through the models in this directory and find one that best suits your needs. Once you've selected a model, you can use the provided `*.yaml` file to train and deploy your custom YOLO model with ease. See full details at the Ultralytics [Docs](https://docs.ultralytics.com/models), and if you need help or have any questions, feel free to reach out to the Ultralytics team for support. So, don't wait, start creating your custom YOLO model now! - -### Usage - -Model `*.yaml` files may be used directly in the Command Line Interface (CLI) with a `yolo` command: - -```bash -yolo task=detect mode=train model=yolov8n.yaml data=coco128.yaml epochs=100 -``` - -They may also be used directly in a Python environment, and accepts the same [arguments](https://docs.ultralytics.com/usage/cfg/) as in the CLI example above: - -```python -from ultralytics import YOLO - -model = YOLO("model.yaml") # build a YOLOv8n model from scratch -# YOLO("model.pt") use pre-trained model if available -model.info() # display model information -model.train(data="coco128.yaml", epochs=100) # train the model -``` - -## Pre-trained Model Architectures - -Ultralytics supports many model architectures. Visit https://docs.ultralytics.com/models to view detailed information and usage. Any of these models can be used by loading their configs or pretrained checkpoints if available. - -## Contribute New Models - -Have you trained a new YOLO variant or achieved state-of-the-art performance with specific tuning? We'd love to showcase your work in our Models section! Contributions from the community in the form of new models, architectures, or optimizations are highly valued and can significantly enrich our repository. - -By contributing to this section, you're helping us offer a wider array of model choices and configurations to the community. It's a fantastic way to share your knowledge and expertise while making the Ultralytics YOLO ecosystem even more versatile. - -To get started, please consult our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for step-by-step instructions on how to submit a Pull Request (PR) 🛠️. Your contributions are eagerly awaited! - -Let's join hands to extend the range and capabilities of the Ultralytics YOLO models 🙏! diff --git a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml b/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml deleted file mode 100644 index c6eb0b3..0000000 --- a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml +++ /dev/null @@ -1,50 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - l: [1.00, 1.00, 1024] - -backbone: - # [from, repeats, module, args] - - [-1, 1, HGStem, [32, 48]] # 0-P2/4 - - [-1, 6, HGBlock, [48, 128, 3]] # stage 1 - - - [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8 - - [-1, 6, HGBlock, [96, 512, 3]] # stage 2 - - - [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P3/16 - - [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut - - [-1, 6, HGBlock, [192, 1024, 5, True, True]] - - [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3 - - - [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P4/32 - - [-1, 6, HGBlock, [384, 2048, 5, True, False]] # stage 4 - -head: - - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2 - - [-1, 1, AIFI, [1024, 8]] - - [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1 - - [[-2, -1], 1, Concat, [1]] - - [-1, 3, RepC3, [256]] # 16, fpn_blocks.0 - - [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0 - - [[-2, -1], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1 - - - [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0 - - [[-1, 17], 1, Concat, [1]] # cat Y4 - - [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0 - - - [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1 - - [[-1, 12], 1, Concat, [1]] # cat Y5 - - [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1 - - - [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml b/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml deleted file mode 100644 index a68bb5d..0000000 --- a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml +++ /dev/null @@ -1,42 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# RT-DETR-ResNet101 object detection model with P3-P5 outputs. - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - l: [1.00, 1.00, 1024] - -backbone: - # [from, repeats, module, args] - - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0 - - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1 - - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2 - - [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3 - - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4 - -head: - - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5 - - [-1, 1, AIFI, [1024, 8]] - - [-1, 1, Conv, [256, 1, 1]] # 7 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9 - - [[-2, -1], 1, Concat, [1]] - - [-1, 3, RepC3, [256]] # 11 - - [-1, 1, Conv, [256, 1, 1]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 - - [[-2, -1], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1 - - - [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0 - - [[-1, 12], 1, Concat, [1]] # cat Y4 - - [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0 - - - [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1 - - [[-1, 7], 1, Concat, [1]] # cat Y5 - - [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1 - - - [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml b/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml deleted file mode 100644 index 7145910..0000000 --- a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml +++ /dev/null @@ -1,42 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# RT-DETR-ResNet50 object detection model with P3-P5 outputs. - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - l: [1.00, 1.00, 1024] - -backbone: - # [from, repeats, module, args] - - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0 - - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1 - - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2 - - [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3 - - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4 - -head: - - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5 - - [-1, 1, AIFI, [1024, 8]] - - [-1, 1, Conv, [256, 1, 1]] # 7 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9 - - [[-2, -1], 1, Concat, [1]] - - [-1, 3, RepC3, [256]] # 11 - - [-1, 1, Conv, [256, 1, 1]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 - - [[-2, -1], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1 - - - [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0 - - [[-1, 12], 1, Concat, [1]] # cat Y4 - - [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0 - - - [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1 - - [[-1, 7], 1, Concat, [1]] # cat Y5 - - [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1 - - - [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml b/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml deleted file mode 100644 index 0e819b0..0000000 --- a/ultralytics-main/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml +++ /dev/null @@ -1,54 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# RT-DETR-x object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - x: [1.00, 1.00, 2048] - -backbone: - # [from, repeats, module, args] - - [-1, 1, HGStem, [32, 64]] # 0-P2/4 - - [-1, 6, HGBlock, [64, 128, 3]] # stage 1 - - - [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8 - - [-1, 6, HGBlock, [128, 512, 3]] - - [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2 - - - [-1, 1, DWConv, [512, 3, 2, 1, False]] # 5-P3/16 - - [-1, 6, HGBlock, [256, 1024, 5, True, False]] # cm, c2, k, light, shortcut - - [-1, 6, HGBlock, [256, 1024, 5, True, True]] - - [-1, 6, HGBlock, [256, 1024, 5, True, True]] - - [-1, 6, HGBlock, [256, 1024, 5, True, True]] - - [-1, 6, HGBlock, [256, 1024, 5, True, True]] # 10-stage 3 - - - [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 11-P4/32 - - [-1, 6, HGBlock, [512, 2048, 5, True, False]] - - [-1, 6, HGBlock, [512, 2048, 5, True, True]] # 13-stage 4 - -head: - - [-1, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 14 input_proj.2 - - [-1, 1, AIFI, [2048, 8]] - - [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [10, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 18 input_proj.1 - - [[-2, -1], 1, Concat, [1]] - - [-1, 3, RepC3, [384]] # 20, fpn_blocks.0 - - [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [4, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 23 input_proj.0 - - [[-2, -1], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1 - - - [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0 - - [[-1, 21], 1, Concat, [1]] # cat Y4 - - [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0 - - - [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1 - - [[-1, 16], 1, Concat, [1]] # cat Y5 - - [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1 - - - [[25, 28, 31], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v3/yolov3-spp.yaml b/ultralytics-main/ultralytics/cfg/models/v3/yolov3-spp.yaml deleted file mode 100644 index 6724f4e..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v3/yolov3-spp.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv3-SPP object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3 - -# Parameters -nc: 80 # number of classes -depth_multiple: 1.0 # model depth multiple -width_multiple: 1.0 # layer channel multiple - -# darknet53 backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [32, 3, 1]] # 0 - - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2 - - [-1, 1, Bottleneck, [64]] - - [-1, 1, Conv, [128, 3, 2]] # 3-P2/4 - - [-1, 2, Bottleneck, [128]] - - [-1, 1, Conv, [256, 3, 2]] # 5-P3/8 - - [-1, 8, Bottleneck, [256]] - - [-1, 1, Conv, [512, 3, 2]] # 7-P4/16 - - [-1, 8, Bottleneck, [512]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32 - - [-1, 4, Bottleneck, [1024]] # 10 - -# YOLOv3-SPP head -head: - - [-1, 1, Bottleneck, [1024, False]] - - [-1, 1, SPP, [512, [5, 9, 13]]] - - [-1, 1, Conv, [1024, 3, 1]] - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large) - - - [-2, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, Bottleneck, [512, False]] - - [-1, 1, Bottleneck, [512, False]] - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium) - - - [-2, 1, Conv, [128, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P3 - - [-1, 1, Bottleneck, [256, False]] - - [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small) - - - [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v3/yolov3-tiny.yaml b/ultralytics-main/ultralytics/cfg/models/v3/yolov3-tiny.yaml deleted file mode 100644 index f3fe257..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v3/yolov3-tiny.yaml +++ /dev/null @@ -1,37 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv3-tiny object detection model with P4-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3 - -# Parameters -nc: 80 # number of classes -depth_multiple: 1.0 # model depth multiple -width_multiple: 1.0 # layer channel multiple - -# YOLOv3-tiny backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [16, 3, 1]] # 0 - - [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 1-P1/2 - - [-1, 1, Conv, [32, 3, 1]] - - [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 3-P2/4 - - [-1, 1, Conv, [64, 3, 1]] - - [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 5-P3/8 - - [-1, 1, Conv, [128, 3, 1]] - - [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 7-P4/16 - - [-1, 1, Conv, [256, 3, 1]] - - [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 9-P5/32 - - [-1, 1, Conv, [512, 3, 1]] - - [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]] # 11 - - [-1, 1, nn.MaxPool2d, [2, 1, 0]] # 12 - -# YOLOv3-tiny head -head: - - [-1, 1, Conv, [1024, 3, 1]] - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, Conv, [512, 3, 1]] # 15 (P5/32-large) - - - [-2, 1, Conv, [128, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, Conv, [256, 3, 1]] # 19 (P4/16-medium) - - - [[19, 15], 1, Detect, [nc]] # Detect(P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v3/yolov3.yaml b/ultralytics-main/ultralytics/cfg/models/v3/yolov3.yaml deleted file mode 100644 index 716866a..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v3/yolov3.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv3 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3 - -# Parameters -nc: 80 # number of classes -depth_multiple: 1.0 # model depth multiple -width_multiple: 1.0 # layer channel multiple - -# darknet53 backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [32, 3, 1]] # 0 - - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2 - - [-1, 1, Bottleneck, [64]] - - [-1, 1, Conv, [128, 3, 2]] # 3-P2/4 - - [-1, 2, Bottleneck, [128]] - - [-1, 1, Conv, [256, 3, 2]] # 5-P3/8 - - [-1, 8, Bottleneck, [256]] - - [-1, 1, Conv, [512, 3, 2]] # 7-P4/16 - - [-1, 8, Bottleneck, [512]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32 - - [-1, 4, Bottleneck, [1024]] # 10 - -# YOLOv3 head -head: - - [-1, 1, Bottleneck, [1024, False]] - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, Conv, [1024, 3, 1]] - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large) - - - [-2, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, Bottleneck, [512, False]] - - [-1, 1, Bottleneck, [512, False]] - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium) - - - [-2, 1, Conv, [128, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P3 - - [-1, 1, Bottleneck, [256, False]] - - [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small) - - - [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v5/yolov5-p6.yaml b/ultralytics-main/ultralytics/cfg/models/v5/yolov5-p6.yaml deleted file mode 100644 index 2fd3ac7..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v5/yolov5-p6.yaml +++ /dev/null @@ -1,59 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv5 object detection model with P3-P6 outputs. For details see https://docs.ultralytics.com/models/yolov5 - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will call yolov5-p6.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 1024] - l: [1.00, 1.00, 1024] - x: [1.33, 1.25, 1024] - -# YOLOv5 v6.0 backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3, [128]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3, [256]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 9, C3, [512]] - - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 - - [-1, 3, C3, [768]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 - - [-1, 3, C3, [1024]] - - [-1, 1, SPPF, [1024, 5]] # 11 - -# YOLOv5 v6.0 head -head: - - [-1, 1, Conv, [768, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P5 - - [-1, 3, C3, [768, False]] # 15 - - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3, [512, False]] # 19 - - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3, [256, False]] # 23 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 20], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3, [512, False]] # 26 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 16], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3, [768, False]] # 29 (P5/32-large) - - - [-1, 1, Conv, [768, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P6 - - [-1, 3, C3, [1024, False]] # 32 (P6/64-xlarge) - - - [[23, 26, 29, 32], 1, Detect, [nc]] # Detect(P3, P4, P5, P6) diff --git a/ultralytics-main/ultralytics/cfg/models/v5/yolov5.yaml b/ultralytics-main/ultralytics/cfg/models/v5/yolov5.yaml deleted file mode 100644 index 8fdc79e..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v5/yolov5.yaml +++ /dev/null @@ -1,48 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv5 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov5 - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 1024] - l: [1.00, 1.00, 1024] - x: [1.33, 1.25, 1024] - -# YOLOv5 v6.0 backbone -backbone: - # [from, number, module, args] - - [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3, [128]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3, [256]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 9, C3, [512]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C3, [1024]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv5 v6.0 head -head: - - [-1, 1, Conv, [512, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3, [512, False]] # 13 - - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3, [256, False]] # 17 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3, [512, False]] # 20 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 10], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3, [1024, False]] # 23 (P5/32-large) - - - [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v6/yolov6.yaml b/ultralytics-main/ultralytics/cfg/models/v6/yolov6.yaml deleted file mode 100644 index f39dfb4..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v6/yolov6.yaml +++ /dev/null @@ -1,53 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv6 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/models/yolov6 - -# Parameters -nc: 80 # number of classes -activation: nn.ReLU() # (optional) model default activation function -scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv6-3.0s backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 6, Conv, [128, 3, 1]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 12, Conv, [256, 3, 1]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 18, Conv, [512, 3, 1]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 6, Conv, [1024, 3, 1]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv6-3.0s head -head: - - [-1, 1, Conv, [256, 1, 1]] - - [-1, 1, nn.ConvTranspose2d, [256, 2, 2, 0]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, Conv, [256, 3, 1]] - - [-1, 9, Conv, [256, 3, 1]] # 14 - - - [-1, 1, Conv, [128, 1, 1]] - - [-1, 1, nn.ConvTranspose2d, [128, 2, 2, 0]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 1, Conv, [128, 3, 1]] - - [-1, 9, Conv, [128, 3, 1]] # 19 - - - [-1, 1, Conv, [128, 3, 2]] - - [[-1, 15], 1, Concat, [1]] # cat head P4 - - [-1, 1, Conv, [256, 3, 1]] - - [-1, 9, Conv, [256, 3, 1]] # 23 - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 10], 1, Concat, [1]] # cat head P5 - - [-1, 1, Conv, [512, 3, 1]] - - [-1, 9, Conv, [512, 3, 1]] # 27 - - - [[19, 23, 27], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml deleted file mode 100644 index 6867f88..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml +++ /dev/null @@ -1,25 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify - -# Parameters -nc: 1000 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 1024] - l: [1.00, 1.00, 1024] - x: [1.00, 1.25, 1024] - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2 - - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4 - - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8 - - [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3-P4/16 - - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32 - -# YOLOv8.0n head -head: - - [-1, 1, Classify, [nc]] # Classify diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml deleted file mode 100644 index 8ffd111..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml +++ /dev/null @@ -1,25 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify - -# Parameters -nc: 1000 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 1024] - l: [1.00, 1.00, 1024] - x: [1.00, 1.25, 1024] - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2 - - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4 - - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8 - - [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3-P4/16 - - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32 - -# YOLOv8.0n head -head: - - [-1, 1, Classify, [nc]] # Classify diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls.yaml deleted file mode 100644 index 180fc65..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-cls.yaml +++ /dev/null @@ -1,29 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify - -# Parameters -nc: 1000 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 1024] - l: [1.00, 1.00, 1024] - x: [1.00, 1.25, 1024] - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - -# YOLOv8.0n head -head: - - [-1, 1, Classify, [nc]] # Classify diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml deleted file mode 100644 index aee2093..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml +++ /dev/null @@ -1,54 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p2 summary: 491 layers, 2033944 parameters, 2033928 gradients, 13.8 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p2 summary: 491 layers, 5562080 parameters, 5562064 gradients, 25.1 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m-ghost-p2 summary: 731 layers, 9031728 parameters, 9031712 gradients, 42.8 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l-ghost-p2 summary: 971 layers, 12214448 parameters, 12214432 gradients, 69.1 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x-ghost-p2 summary: 971 layers, 18664776 parameters, 18664760 gradients, 103.3 GFLOPs - -# YOLOv8.0-ghost backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3Ghost, [128, True]] - - [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3Ghost, [256, True]] - - [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C3Ghost, [512, True]] - - [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C3Ghost, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0-ghost-p2 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3Ghost, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3Ghost, [256]] # 15 (P3/8-small) - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 2], 1, Concat, [1]] # cat backbone P2 - - [-1, 3, C3Ghost, [128]] # 18 (P2/4-xsmall) - - - [-1, 1, GhostConv, [128, 3, 2]] - - [[-1, 15], 1, Concat, [1]] # cat head P3 - - [-1, 3, C3Ghost, [256]] # 21 (P3/8-small) - - - [-1, 1, GhostConv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3Ghost, [512]] # 24 (P4/16-medium) - - - [-1, 1, GhostConv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3Ghost, [1024]] # 27 (P5/32-large) - - - [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml deleted file mode 100644 index b35f4cd..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml +++ /dev/null @@ -1,56 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p6 summary: 529 layers, 2901100 parameters, 2901084 gradients, 5.8 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p6 summary: 529 layers, 9520008 parameters, 9519992 gradients, 16.4 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m-ghost-p6 summary: 789 layers, 18002904 parameters, 18002888 gradients, 34.4 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l-ghost-p6 summary: 1049 layers, 21227584 parameters, 21227568 gradients, 55.3 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x-ghost-p6 summary: 1049 layers, 33057852 parameters, 33057836 gradients, 85.7 GFLOPs - -# YOLOv8.0-ghost backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3Ghost, [128, True]] - - [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3Ghost, [256, True]] - - [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C3Ghost, [512, True]] - - [-1, 1, GhostConv, [768, 3, 2]] # 7-P5/32 - - [-1, 3, C3Ghost, [768, True]] - - [-1, 1, GhostConv, [1024, 3, 2]] # 9-P6/64 - - [-1, 3, C3Ghost, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 11 - -# YOLOv8.0-ghost-p6 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P5 - - [-1, 3, C3Ghost, [768]] # 14 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3Ghost, [512]] # 17 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3Ghost, [256]] # 20 (P3/8-small) - - - [-1, 1, GhostConv, [256, 3, 2]] - - [[-1, 17], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3Ghost, [512]] # 23 (P4/16-medium) - - - [-1, 1, GhostConv, [512, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3Ghost, [768]] # 26 (P5/32-large) - - - [-1, 1, GhostConv, [768, 3, 2]] - - [[-1, 11], 1, Concat, [1]] # cat head P6 - - [-1, 3, C3Ghost, [1024]] # 29 (P6/64-xlarge) - - - [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost.yaml deleted file mode 100644 index adc1802..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-ghost.yaml +++ /dev/null @@ -1,47 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect -# Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2 - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n-ghost summary: 403 layers, 1865316 parameters, 1865300 gradients, 5.8 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s-ghost summary: 403 layers, 5960072 parameters, 5960056 gradients, 16.4 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m-ghost summary: 603 layers, 10336312 parameters, 10336296 gradients, 32.7 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l-ghost summary: 803 layers, 14277872 parameters, 14277856 gradients, 53.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x-ghost summary: 803 layers, 22229308 parameters, 22229292 gradients, 83.3 GFLOPs - -# YOLOv8.0n-ghost backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C3Ghost, [128, True]] - - [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C3Ghost, [256, True]] - - [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C3Ghost, [512, True]] - - [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C3Ghost, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C3Ghost, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C3Ghost, [256]] # 15 (P3/8-small) - - - [-1, 1, GhostConv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C3Ghost, [512]] # 18 (P4/16-medium) - - - [-1, 1, GhostConv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C3Ghost, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-obb.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-obb.yaml deleted file mode 100644 index 7a7f60c..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-obb.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 Oriented Bounding Boxes (OBB) model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, OBB, [nc, 1]] # OBB(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p2.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p2.yaml deleted file mode 100644 index 5392774..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p2.yaml +++ /dev/null @@ -1,54 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0 backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0-p2 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 2], 1, Concat, [1]] # cat backbone P2 - - [-1, 3, C2f, [128]] # 18 (P2/4-xsmall) - - - [-1, 1, Conv, [128, 3, 2]] - - [[-1, 15], 1, Concat, [1]] # cat head P3 - - [-1, 3, C2f, [256]] # 21 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 24 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 27 (P5/32-large) - - - [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p6.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p6.yaml deleted file mode 100644 index 2d6d5f9..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-p6.yaml +++ /dev/null @@ -1,56 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0x6 backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [768, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 11 - -# YOLOv8.0x6 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P5 - - [-1, 3, C2, [768, False]] # 14 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2, [512, False]] # 17 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2, [256, False]] # 20 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 17], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2, [512, False]] # 23 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2, [768, False]] # 26 (P5/32-large) - - - [-1, 1, Conv, [768, 3, 2]] - - [[-1, 11], 1, Concat, [1]] # cat head P6 - - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge) - - - [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose-p6.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose-p6.yaml deleted file mode 100644 index 60007ac..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose-p6.yaml +++ /dev/null @@ -1,57 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-pose-p6 keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose - -# Parameters -nc: 1 # number of classes -kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) -scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0x6 backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [768, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 11 - -# YOLOv8.0x6 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P5 - - [-1, 3, C2, [768, False]] # 14 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2, [512, False]] # 17 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2, [256, False]] # 20 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 17], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2, [512, False]] # 23 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2, [768, False]] # 26 (P5/32-large) - - - [-1, 1, Conv, [768, 3, 2]] - - [[-1, 11], 1, Concat, [1]] # cat head P6 - - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge) - - - [[20, 23, 26, 29], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5, P6) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose.yaml deleted file mode 100644 index 60388ef..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-pose.yaml +++ /dev/null @@ -1,47 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-pose keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose - -# Parameters -nc: 1 # number of classes -kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) -scales: # model compound scaling constants, i.e. 'model=yolov8n-pose.yaml' will call yolov8-pose.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-rtdetr.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-rtdetr.yaml deleted file mode 100644 index 27b790b..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-rtdetr.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml deleted file mode 100644 index 78c0444..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml +++ /dev/null @@ -1,56 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-seg-p6 instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-seg-p6.yaml' will call yolov8-seg-p6.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0x6 backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [768, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [768, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 11 - -# YOLOv8.0x6 head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 8], 1, Concat, [1]] # cat backbone P5 - - [-1, 3, C2, [768, False]] # 14 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2, [512, False]] # 17 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2, [256, False]] # 20 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 17], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2, [512, False]] # 23 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 14], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2, [768, False]] # 26 (P5/32-large) - - - [-1, 1, Conv, [768, 3, 2]] - - [[-1, 11], 1, Concat, [1]] # cat head P6 - - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge) - - - [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Pose(P3, P4, P5, P6) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg.yaml deleted file mode 100644 index 700b795..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-seg.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n-seg.yaml' will call yolov8-seg.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] - s: [0.33, 0.50, 1024] - m: [0.67, 0.75, 768] - l: [1.00, 1.00, 512] - x: [1.00, 1.25, 512] - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-world.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-world.yaml deleted file mode 100644 index c21a7f0..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-world.yaml +++ /dev/null @@ -1,48 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-World object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2fAttn, [512, 256, 8]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small) - - - [[15, 12, 9], 1, ImagePoolingAttn, [256]] # 16 (P3/8-small) - - - [15, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2fAttn, [512, 256, 8]] # 19 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2fAttn, [1024, 512, 16]] # 22 (P5/32-large) - - - [[15, 19, 22], 1, WorldDetect, [nc, 512, False]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-worldv2.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8-worldv2.yaml deleted file mode 100644 index 322b97d..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8-worldv2.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8-World-v2 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 80 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2fAttn, [512, 256, 8]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small) - - - [15, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2fAttn, [512, 256, 8]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2fAttn, [1024, 512, 16]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, WorldDetect, [nc, 512, True]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v8/yolov8.yaml b/ultralytics-main/ultralytics/cfg/models/v8/yolov8.yaml deleted file mode 100644 index 167b180..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v8/yolov8.yaml +++ /dev/null @@ -1,46 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect - -# Parameters -nc: 2 # number of classes -scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' - # [depth, width, max_channels] - n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs - s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs - m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs - l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs - x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs - -# YOLOv8.0n backbone -backbone: - # [from, repeats, module, args] - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 3, C2f, [128, True]] - - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - - [-1, 6, C2f, [256, True]] - - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - - [-1, 6, C2f, [512, True]] - - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - - [-1, 3, C2f, [1024, True]] - - [-1, 1, SPPF, [1024, 5]] # 9 - -# YOLOv8.0n head -head: - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 3, C2f, [512]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 3, C2f, [256]] # 15 (P3/8-small) - - - [-1, 1, Conv, [256, 3, 2]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - - - [-1, 1, Conv, [512, 3, 2]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v9/yolov9c.yaml b/ultralytics-main/ultralytics/cfg/models/v9/yolov9c.yaml deleted file mode 100644 index 66c02d6..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v9/yolov9c.yaml +++ /dev/null @@ -1,36 +0,0 @@ -# YOLOv9 - -# parameters -nc: 80 # number of classes - -# gelan backbone -backbone: - - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - - [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]] # 2 - - [-1, 1, ADown, [256]] # 3-P3/8 - - [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]] # 4 - - [-1, 1, ADown, [512]] # 5-P4/16 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 6 - - [-1, 1, ADown, [512]] # 7-P5/32 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 8 - - [-1, 1, SPPELAN, [512, 256]] # 9 - -head: - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 12 - - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - - [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]] # 15 (P3/8-small) - - - [-1, 1, ADown, [256]] - - [[-1, 12], 1, Concat, [1]] # cat head P4 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 18 (P4/16-medium) - - - [-1, 1, ADown, [512]] - - [[-1, 9], 1, Concat, [1]] # cat head P5 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 21 (P5/32-large) - - - [[15, 18, 21], 1, Detect, [nc]] # DDetect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/models/v9/yolov9e.yaml b/ultralytics-main/ultralytics/cfg/models/v9/yolov9e.yaml deleted file mode 100644 index 8e15a42..0000000 --- a/ultralytics-main/ultralytics/cfg/models/v9/yolov9e.yaml +++ /dev/null @@ -1,60 +0,0 @@ -# YOLOv9 - -# parameters -nc: 80 # number of classes - -# gelan backbone -backbone: - - [-1, 1, Silence, []] - - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2 - - [-1, 1, Conv, [128, 3, 2]] # 2-P2/4 - - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 3 - - [-1, 1, ADown, [256]] # 4-P3/8 - - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 5 - - [-1, 1, ADown, [512]] # 6-P4/16 - - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 7 - - [-1, 1, ADown, [1024]] # 8-P5/32 - - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 9 - - - [1, 1, CBLinear, [[64]]] # 10 - - [3, 1, CBLinear, [[64, 128]]] # 11 - - [5, 1, CBLinear, [[64, 128, 256]]] # 12 - - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13 - - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14 - - - [0, 1, Conv, [64, 3, 2]] # 15-P1/2 - - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16 - - [-1, 1, Conv, [128, 3, 2]] # 17-P2/4 - - [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18 - - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 19 - - [-1, 1, ADown, [256]] # 20-P3/8 - - [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21 - - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 22 - - [-1, 1, ADown, [512]] # 23-P4/16 - - [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24 - - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 25 - - [-1, 1, ADown, [1024]] # 26-P5/32 - - [[14, -1], 1, CBFuse, [[4]]] # 27 - - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 28 - - [-1, 1, SPPELAN, [512, 256]] # 29 - -# gelan head -head: - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 25], 1, Concat, [1]] # cat backbone P4 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 32 - - - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - - [[-1, 22], 1, Concat, [1]] # cat backbone P3 - - [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]] # 35 (P3/8-small) - - - [-1, 1, ADown, [256]] - - [[-1, 32], 1, Concat, [1]] # cat head P4 - - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 38 (P4/16-medium) - - - [-1, 1, ADown, [512]] - - [[-1, 29], 1, Concat, [1]] # cat head P5 - - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]] # 41 (P5/32-large) - - # detect - - [[35, 38, 41], 1, Detect, [nc]] # Detect(P3, P4, P5) diff --git a/ultralytics-main/ultralytics/cfg/trackers/botsort.yaml b/ultralytics-main/ultralytics/cfg/trackers/botsort.yaml deleted file mode 100644 index 0c66dc6..0000000 --- a/ultralytics-main/ultralytics/cfg/trackers/botsort.yaml +++ /dev/null @@ -1,18 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT - -tracker_type: botsort # tracker type, ['botsort', 'bytetrack'] -track_high_thresh: 0.5 # threshold for the first association -track_low_thresh: 0.1 # threshold for the second association -new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks -track_buffer: 30 # buffer to calculate the time when to remove tracks -match_thresh: 0.8 # threshold for matching tracks -# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now) -# mot20: False # for tracker evaluation(not used for now) - -# BoT-SORT settings -gmc_method: sparseOptFlow # method of global motion compensation -# ReID model related thresh (not supported yet) -proximity_thresh: 0.5 -appearance_thresh: 0.25 -with_reid: False diff --git a/ultralytics-main/ultralytics/cfg/trackers/bytetrack.yaml b/ultralytics-main/ultralytics/cfg/trackers/bytetrack.yaml deleted file mode 100644 index 29d352c..0000000 --- a/ultralytics-main/ultralytics/cfg/trackers/bytetrack.yaml +++ /dev/null @@ -1,11 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack - -tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack'] -track_high_thresh: 0.5 # threshold for the first association -track_low_thresh: 0.1 # threshold for the second association -new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks -track_buffer: 30 # buffer to calculate the time when to remove tracks -match_thresh: 0.8 # threshold for matching tracks -# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now) -# mot20: False # for tracker evaluation(not used for now) diff --git a/ultralytics-main/ultralytics/data/__init__.py b/ultralytics-main/ultralytics/data/__init__.py deleted file mode 100644 index 9f91ce9..0000000 --- a/ultralytics-main/ultralytics/data/__init__.py +++ /dev/null @@ -1,15 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .base import BaseDataset -from .build import build_dataloader, build_yolo_dataset, load_inference_source -from .dataset import ClassificationDataset, SemanticDataset, YOLODataset - -__all__ = ( - "BaseDataset", - "ClassificationDataset", - "SemanticDataset", - "YOLODataset", - "build_yolo_dataset", - "build_dataloader", - "load_inference_source", -) diff --git a/ultralytics-main/ultralytics/data/annotator.py b/ultralytics-main/ultralytics/data/annotator.py deleted file mode 100644 index b5b899c..0000000 --- a/ultralytics-main/ultralytics/data/annotator.py +++ /dev/null @@ -1,50 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from pathlib import Path - -from ultralytics import SAM, YOLO - - -def auto_annotate(data, det_model="yolov8x.pt", sam_model="sam_b.pt", device="", output_dir=None): - """ - Automatically annotates images using a YOLO object detection model and a SAM segmentation model. - - Args: - data (str): Path to a folder containing images to be annotated. - det_model (str, optional): Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'. - sam_model (str, optional): Pre-trained SAM segmentation model. Defaults to 'sam_b.pt'. - device (str, optional): Device to run the models on. Defaults to an empty string (CPU or GPU, if available). - output_dir (str | None | optional): Directory to save the annotated results. - Defaults to a 'labels' folder in the same directory as 'data'. - - Example: - ```python - from ultralytics.data.annotator import auto_annotate - - auto_annotate(data='ultralytics/assets', det_model='yolov8n.pt', sam_model='mobile_sam.pt') - ``` - """ - det_model = YOLO(det_model) - sam_model = SAM(sam_model) - - data = Path(data) - if not output_dir: - output_dir = data.parent / f"{data.stem}_auto_annotate_labels" - Path(output_dir).mkdir(exist_ok=True, parents=True) - - det_results = det_model(data, stream=True, device=device) - - for result in det_results: - class_ids = result.boxes.cls.int().tolist() # noqa - if len(class_ids): - boxes = result.boxes.xyxy # Boxes object for bbox outputs - sam_results = sam_model(result.orig_img, bboxes=boxes, verbose=False, save=False, device=device) - segments = sam_results[0].masks.xyn # noqa - - with open(f"{Path(output_dir) / Path(result.path).stem}.txt", "w") as f: - for i in range(len(segments)): - s = segments[i] - if len(s) == 0: - continue - segment = map(str, segments[i].reshape(-1).tolist()) - f.write(f"{class_ids[i]} " + " ".join(segment) + "\n") diff --git a/ultralytics-main/ultralytics/data/augment.py b/ultralytics-main/ultralytics/data/augment.py deleted file mode 100644 index a16f60b..0000000 --- a/ultralytics-main/ultralytics/data/augment.py +++ /dev/null @@ -1,1250 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math -import random -from copy import deepcopy - -import cv2 -import numpy as np -import torch -import torchvision.transforms as T - -from ultralytics.utils import LOGGER, colorstr -from ultralytics.utils.checks import check_version -from ultralytics.utils.instance import Instances -from ultralytics.utils.metrics import bbox_ioa -from ultralytics.utils.ops import segment2box, xyxyxyxy2xywhr -from ultralytics.utils.torch_utils import TORCHVISION_0_10, TORCHVISION_0_11, TORCHVISION_0_13 -from .utils import polygons2masks, polygons2masks_overlap - -DEFAULT_MEAN = (0.0, 0.0, 0.0) -DEFAULT_STD = (1.0, 1.0, 1.0) -DEFAULT_CROP_FTACTION = 1.0 - - -# TODO: we might need a BaseTransform to make all these augments be compatible with both classification and semantic -class BaseTransform: - """ - Base class for image transformations. - - This is a generic transformation class that can be extended for specific image processing needs. - The class is designed to be compatible with both classification and semantic segmentation tasks. - - Methods: - __init__: Initializes the BaseTransform object. - apply_image: Applies image transformation to labels. - apply_instances: Applies transformations to object instances in labels. - apply_semantic: Applies semantic segmentation to an image. - __call__: Applies all label transformations to an image, instances, and semantic masks. - """ - - def __init__(self) -> None: - """Initializes the BaseTransform object.""" - pass - - def apply_image(self, labels): - """Applies image transformations to labels.""" - pass - - def apply_instances(self, labels): - """Applies transformations to object instances in labels.""" - pass - - def apply_semantic(self, labels): - """Applies semantic segmentation to an image.""" - pass - - def __call__(self, labels): - """Applies all label transformations to an image, instances, and semantic masks.""" - self.apply_image(labels) - self.apply_instances(labels) - self.apply_semantic(labels) - - -class Compose: - """Class for composing multiple image transformations.""" - - def __init__(self, transforms): - """Initializes the Compose object with a list of transforms.""" - self.transforms = transforms - - def __call__(self, data): - """Applies a series of transformations to input data.""" - for t in self.transforms: - data = t(data) - return data - - def append(self, transform): - """Appends a new transform to the existing list of transforms.""" - self.transforms.append(transform) - - def tolist(self): - """Converts the list of transforms to a standard Python list.""" - return self.transforms - - def __repr__(self): - """Returns a string representation of the object.""" - return f"{self.__class__.__name__}({', '.join([f'{t}' for t in self.transforms])})" - - -class BaseMixTransform: - """ - Class for base mix (MixUp/Mosaic) transformations. - - This implementation is from mmyolo. - """ - - def __init__(self, dataset, pre_transform=None, p=0.0) -> None: - """Initializes the BaseMixTransform object with dataset, pre_transform, and probability.""" - self.dataset = dataset - self.pre_transform = pre_transform - self.p = p - - def __call__(self, labels): - """Applies pre-processing transforms and mixup/mosaic transforms to labels data.""" - if random.uniform(0, 1) > self.p: - return labels - - # Get index of one or three other images - indexes = self.get_indexes() - if isinstance(indexes, int): - indexes = [indexes] - - # Get images information will be used for Mosaic or MixUp - mix_labels = [self.dataset.get_image_and_label(i) for i in indexes] - - if self.pre_transform is not None: - for i, data in enumerate(mix_labels): - mix_labels[i] = self.pre_transform(data) - labels["mix_labels"] = mix_labels - - # Mosaic or MixUp - labels = self._mix_transform(labels) - labels.pop("mix_labels", None) - return labels - - def _mix_transform(self, labels): - """Applies MixUp or Mosaic augmentation to the label dictionary.""" - raise NotImplementedError - - def get_indexes(self): - """Gets a list of shuffled indexes for mosaic augmentation.""" - raise NotImplementedError - - -class Mosaic(BaseMixTransform): - """ - Mosaic augmentation. - - This class performs mosaic augmentation by combining multiple (4 or 9) images into a single mosaic image. - The augmentation is applied to a dataset with a given probability. - - Attributes: - dataset: The dataset on which the mosaic augmentation is applied. - imgsz (int, optional): Image size (height and width) after mosaic pipeline of a single image. Default to 640. - p (float, optional): Probability of applying the mosaic augmentation. Must be in the range 0-1. Default to 1.0. - n (int, optional): The grid size, either 4 (for 2x2) or 9 (for 3x3). - """ - - def __init__(self, dataset, imgsz=640, p=1.0, n=4): - """Initializes the object with a dataset, image size, probability, and border.""" - assert 0 <= p <= 1.0, f"The probability should be in range [0, 1], but got {p}." - assert n in (4, 9), "grid must be equal to 4 or 9." - super().__init__(dataset=dataset, p=p) - self.dataset = dataset - self.imgsz = imgsz - self.border = (-imgsz // 2, -imgsz // 2) # width, height - self.n = n - - def get_indexes(self, buffer=True): - """Return a list of random indexes from the dataset.""" - if buffer: # select images from buffer - return random.choices(list(self.dataset.buffer), k=self.n - 1) - else: # select any images - return [random.randint(0, len(self.dataset) - 1) for _ in range(self.n - 1)] - - def _mix_transform(self, labels): - """Apply mixup transformation to the input image and labels.""" - assert labels.get("rect_shape", None) is None, "rect and mosaic are mutually exclusive." - assert len(labels.get("mix_labels", [])), "There are no other images for mosaic augment." - return ( - self._mosaic3(labels) if self.n == 3 else self._mosaic4(labels) if self.n == 4 else self._mosaic9(labels) - ) # This code is modified for mosaic3 method. - - def _mosaic3(self, labels): - """Create a 1x3 image mosaic.""" - mosaic_labels = [] - s = self.imgsz - for i in range(3): - labels_patch = labels if i == 0 else labels["mix_labels"][i - 1] - # Load image - img = labels_patch["img"] - h, w = labels_patch.pop("resized_shape") - - # Place img in img3 - if i == 0: # center - img3 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 3 tiles - h0, w0 = h, w - c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates - elif i == 1: # right - c = s + w0, s, s + w0 + w, s + h - elif i == 2: # left - c = s - w, s + h0 - h, s, s + h0 - - padw, padh = c[:2] - x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords - - img3[y1:y2, x1:x2] = img[y1 - padh :, x1 - padw :] # img3[ymin:ymax, xmin:xmax] - # hp, wp = h, w # height, width previous for next iteration - - # Labels assuming imgsz*2 mosaic size - labels_patch = self._update_labels(labels_patch, padw + self.border[0], padh + self.border[1]) - mosaic_labels.append(labels_patch) - final_labels = self._cat_labels(mosaic_labels) - - final_labels["img"] = img3[-self.border[0] : self.border[0], -self.border[1] : self.border[1]] - return final_labels - - def _mosaic4(self, labels): - """Create a 2x2 image mosaic.""" - mosaic_labels = [] - s = self.imgsz - yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.border) # mosaic center x, y - for i in range(4): - labels_patch = labels if i == 0 else labels["mix_labels"][i - 1] - # Load image - img = labels_patch["img"] - h, w = labels_patch.pop("resized_shape") - - # Place img in img4 - if i == 0: # top left - img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) - x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) - elif i == 1: # top right - x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc - x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h - elif i == 2: # bottom left - x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) - x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) - elif i == 3: # bottom right - x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) - x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) - - img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - padw = x1a - x1b - padh = y1a - y1b - - labels_patch = self._update_labels(labels_patch, padw, padh) - mosaic_labels.append(labels_patch) - final_labels = self._cat_labels(mosaic_labels) - final_labels["img"] = img4 - return final_labels - - def _mosaic9(self, labels): - """Create a 3x3 image mosaic.""" - mosaic_labels = [] - s = self.imgsz - hp, wp = -1, -1 # height, width previous - for i in range(9): - labels_patch = labels if i == 0 else labels["mix_labels"][i - 1] - # Load image - img = labels_patch["img"] - h, w = labels_patch.pop("resized_shape") - - # Place img in img9 - if i == 0: # center - img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - h0, w0 = h, w - c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates - elif i == 1: # top - c = s, s - h, s + w, s - elif i == 2: # top right - c = s + wp, s - h, s + wp + w, s - elif i == 3: # right - c = s + w0, s, s + w0 + w, s + h - elif i == 4: # bottom right - c = s + w0, s + hp, s + w0 + w, s + hp + h - elif i == 5: # bottom - c = s + w0 - w, s + h0, s + w0, s + h0 + h - elif i == 6: # bottom left - c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h - elif i == 7: # left - c = s - w, s + h0 - h, s, s + h0 - elif i == 8: # top left - c = s - w, s + h0 - hp - h, s, s + h0 - hp - - padw, padh = c[:2] - x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords - - # Image - img9[y1:y2, x1:x2] = img[y1 - padh :, x1 - padw :] # img9[ymin:ymax, xmin:xmax] - hp, wp = h, w # height, width previous for next iteration - - # Labels assuming imgsz*2 mosaic size - labels_patch = self._update_labels(labels_patch, padw + self.border[0], padh + self.border[1]) - mosaic_labels.append(labels_patch) - final_labels = self._cat_labels(mosaic_labels) - - final_labels["img"] = img9[-self.border[0] : self.border[0], -self.border[1] : self.border[1]] - return final_labels - - @staticmethod - def _update_labels(labels, padw, padh): - """Update labels.""" - nh, nw = labels["img"].shape[:2] - labels["instances"].convert_bbox(format="xyxy") - labels["instances"].denormalize(nw, nh) - labels["instances"].add_padding(padw, padh) - return labels - - def _cat_labels(self, mosaic_labels): - """Return labels with mosaic border instances clipped.""" - if len(mosaic_labels) == 0: - return {} - cls = [] - instances = [] - imgsz = self.imgsz * 2 # mosaic imgsz - for labels in mosaic_labels: - cls.append(labels["cls"]) - instances.append(labels["instances"]) - # Final labels - final_labels = { - "im_file": mosaic_labels[0]["im_file"], - "ori_shape": mosaic_labels[0]["ori_shape"], - "resized_shape": (imgsz, imgsz), - "cls": np.concatenate(cls, 0), - "instances": Instances.concatenate(instances, axis=0), - "mosaic_border": self.border, - } - final_labels["instances"].clip(imgsz, imgsz) - good = final_labels["instances"].remove_zero_area_boxes() - final_labels["cls"] = final_labels["cls"][good] - return final_labels - - -class MixUp(BaseMixTransform): - """Class for applying MixUp augmentation to the dataset.""" - - def __init__(self, dataset, pre_transform=None, p=0.0) -> None: - """Initializes MixUp object with dataset, pre_transform, and probability of applying MixUp.""" - super().__init__(dataset=dataset, pre_transform=pre_transform, p=p) - - def get_indexes(self): - """Get a random index from the dataset.""" - return random.randint(0, len(self.dataset) - 1) - - def _mix_transform(self, labels): - """Applies MixUp augmentation as per https://arxiv.org/pdf/1710.09412.pdf.""" - r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 - labels2 = labels["mix_labels"][0] - labels["img"] = (labels["img"] * r + labels2["img"] * (1 - r)).astype(np.uint8) - labels["instances"] = Instances.concatenate([labels["instances"], labels2["instances"]], axis=0) - labels["cls"] = np.concatenate([labels["cls"], labels2["cls"]], 0) - return labels - - -class RandomPerspective: - """ - Implements random perspective and affine transformations on images and corresponding bounding boxes, segments, and - keypoints. These transformations include rotation, translation, scaling, and shearing. The class also offers the - option to apply these transformations conditionally with a specified probability. - - Attributes: - degrees (float): Degree range for random rotations. - translate (float): Fraction of total width and height for random translation. - scale (float): Scaling factor interval, e.g., a scale factor of 0.1 allows a resize between 90%-110%. - shear (float): Shear intensity (angle in degrees). - perspective (float): Perspective distortion factor. - border (tuple): Tuple specifying mosaic border. - pre_transform (callable): A function/transform to apply to the image before starting the random transformation. - - Methods: - affine_transform(img, border): Applies a series of affine transformations to the image. - apply_bboxes(bboxes, M): Transforms bounding boxes using the calculated affine matrix. - apply_segments(segments, M): Transforms segments and generates new bounding boxes. - apply_keypoints(keypoints, M): Transforms keypoints. - __call__(labels): Main method to apply transformations to both images and their corresponding annotations. - box_candidates(box1, box2): Filters out bounding boxes that don't meet certain criteria post-transformation. - """ - - def __init__( - self, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, border=(0, 0), pre_transform=None - ): - """Initializes RandomPerspective object with transformation parameters.""" - - self.degrees = degrees - self.translate = translate - self.scale = scale - self.shear = shear - self.perspective = perspective - self.border = border # mosaic border - self.pre_transform = pre_transform - - def affine_transform(self, img, border): - """ - Applies a sequence of affine transformations centered around the image center. - - Args: - img (ndarray): Input image. - border (tuple): Border dimensions. - - Returns: - img (ndarray): Transformed image. - M (ndarray): Transformation matrix. - s (float): Scale factor. - """ - - # Center - C = np.eye(3, dtype=np.float32) - - C[0, 2] = -img.shape[1] / 2 # x translation (pixels) - C[1, 2] = -img.shape[0] / 2 # y translation (pixels) - - # Perspective - P = np.eye(3, dtype=np.float32) - P[2, 0] = random.uniform(-self.perspective, self.perspective) # x perspective (about y) - P[2, 1] = random.uniform(-self.perspective, self.perspective) # y perspective (about x) - - # Rotation and Scale - R = np.eye(3, dtype=np.float32) - a = random.uniform(-self.degrees, self.degrees) - # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations - s = random.uniform(1 - self.scale, 1 + self.scale) - # s = 2 ** random.uniform(-scale, scale) - R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) - - # Shear - S = np.eye(3, dtype=np.float32) - S[0, 1] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180) # x shear (deg) - S[1, 0] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180) # y shear (deg) - - # Translation - T = np.eye(3, dtype=np.float32) - T[0, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[0] # x translation (pixels) - T[1, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[1] # y translation (pixels) - - # Combined rotation matrix - M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT - # Affine image - if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed - if self.perspective: - img = cv2.warpPerspective(img, M, dsize=self.size, borderValue=(114, 114, 114)) - else: # affine - img = cv2.warpAffine(img, M[:2], dsize=self.size, borderValue=(114, 114, 114)) - return img, M, s - - def apply_bboxes(self, bboxes, M): - """ - Apply affine to bboxes only. - - Args: - bboxes (ndarray): list of bboxes, xyxy format, with shape (num_bboxes, 4). - M (ndarray): affine matrix. - - Returns: - new_bboxes (ndarray): bboxes after affine, [num_bboxes, 4]. - """ - n = len(bboxes) - if n == 0: - return bboxes - - xy = np.ones((n * 4, 3), dtype=bboxes.dtype) - xy[:, :2] = bboxes[:, [0, 1, 2, 3, 0, 3, 2, 1]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 - xy = xy @ M.T # transform - xy = (xy[:, :2] / xy[:, 2:3] if self.perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine - - # Create new boxes - x = xy[:, [0, 2, 4, 6]] - y = xy[:, [1, 3, 5, 7]] - return np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1)), dtype=bboxes.dtype).reshape(4, n).T - - def apply_segments(self, segments, M): - """ - Apply affine to segments and generate new bboxes from segments. - - Args: - segments (ndarray): list of segments, [num_samples, 500, 2]. - M (ndarray): affine matrix. - - Returns: - new_segments (ndarray): list of segments after affine, [num_samples, 500, 2]. - new_bboxes (ndarray): bboxes after affine, [N, 4]. - """ - n, num = segments.shape[:2] - if n == 0: - return [], segments - - xy = np.ones((n * num, 3), dtype=segments.dtype) - segments = segments.reshape(-1, 2) - xy[:, :2] = segments - xy = xy @ M.T # transform - xy = xy[:, :2] / xy[:, 2:3] - segments = xy.reshape(n, -1, 2) - bboxes = np.stack([segment2box(xy, self.size[0], self.size[1]) for xy in segments], 0) - segments[..., 0] = segments[..., 0].clip(bboxes[:, 0:1], bboxes[:, 2:3]) - segments[..., 1] = segments[..., 1].clip(bboxes[:, 1:2], bboxes[:, 3:4]) - return bboxes, segments - - def apply_keypoints(self, keypoints, M): - """ - Apply affine to keypoints. - - Args: - keypoints (ndarray): keypoints, [N, 17, 3]. - M (ndarray): affine matrix. - - Returns: - new_keypoints (ndarray): keypoints after affine, [N, 17, 3]. - """ - n, nkpt = keypoints.shape[:2] - if n == 0: - return keypoints - xy = np.ones((n * nkpt, 3), dtype=keypoints.dtype) - visible = keypoints[..., 2].reshape(n * nkpt, 1) - xy[:, :2] = keypoints[..., :2].reshape(n * nkpt, 2) - xy = xy @ M.T # transform - xy = xy[:, :2] / xy[:, 2:3] # perspective rescale or affine - out_mask = (xy[:, 0] < 0) | (xy[:, 1] < 0) | (xy[:, 0] > self.size[0]) | (xy[:, 1] > self.size[1]) - visible[out_mask] = 0 - return np.concatenate([xy, visible], axis=-1).reshape(n, nkpt, 3) - - def __call__(self, labels): - """ - Affine images and targets. - - Args: - labels (dict): a dict of `bboxes`, `segments`, `keypoints`. - """ - if self.pre_transform and "mosaic_border" not in labels: - labels = self.pre_transform(labels) - labels.pop("ratio_pad", None) # do not need ratio pad - - img = labels["img"] - cls = labels["cls"] - instances = labels.pop("instances") - # Make sure the coord formats are right - instances.convert_bbox(format="xyxy") - instances.denormalize(*img.shape[:2][::-1]) - - border = labels.pop("mosaic_border", self.border) - self.size = img.shape[1] + border[1] * 2, img.shape[0] + border[0] * 2 # w, h - # M is affine matrix - # Scale for func:`box_candidates` - img, M, scale = self.affine_transform(img, border) - - bboxes = self.apply_bboxes(instances.bboxes, M) - - segments = instances.segments - keypoints = instances.keypoints - # Update bboxes if there are segments. - if len(segments): - bboxes, segments = self.apply_segments(segments, M) - - if keypoints is not None: - keypoints = self.apply_keypoints(keypoints, M) - new_instances = Instances(bboxes, segments, keypoints, bbox_format="xyxy", normalized=False) - # Clip - new_instances.clip(*self.size) - - # Filter instances - instances.scale(scale_w=scale, scale_h=scale, bbox_only=True) - # Make the bboxes have the same scale with new_bboxes - i = self.box_candidates( - box1=instances.bboxes.T, box2=new_instances.bboxes.T, area_thr=0.01 if len(segments) else 0.10 - ) - labels["instances"] = new_instances[i] - labels["cls"] = cls[i] - labels["img"] = img - labels["resized_shape"] = img.shape[:2] - return labels - - def box_candidates(self, box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): - """ - Compute box candidates based on a set of thresholds. This method compares the characteristics of the boxes - before and after augmentation to decide whether a box is a candidate for further processing. - - Args: - box1 (numpy.ndarray): The 4,n bounding box before augmentation, represented as [x1, y1, x2, y2]. - box2 (numpy.ndarray): The 4,n bounding box after augmentation, represented as [x1, y1, x2, y2]. - wh_thr (float, optional): The width and height threshold in pixels. Default is 2. - ar_thr (float, optional): The aspect ratio threshold. Default is 100. - area_thr (float, optional): The area ratio threshold. Default is 0.1. - eps (float, optional): A small epsilon value to prevent division by zero. Default is 1e-16. - - Returns: - (numpy.ndarray): A boolean array indicating which boxes are candidates based on the given thresholds. - """ - w1, h1 = box1[2] - box1[0], box1[3] - box1[1] - w2, h2 = box2[2] - box2[0], box2[3] - box2[1] - ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio - return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates - - -class RandomHSV: - """ - This class is responsible for performing random adjustments to the Hue, Saturation, and Value (HSV) channels of an - image. - - The adjustments are random but within limits set by hgain, sgain, and vgain. - """ - - def __init__(self, hgain=0.5, sgain=0.5, vgain=0.5) -> None: - """ - Initialize RandomHSV class with gains for each HSV channel. - - Args: - hgain (float, optional): Maximum variation for hue. Default is 0.5. - sgain (float, optional): Maximum variation for saturation. Default is 0.5. - vgain (float, optional): Maximum variation for value. Default is 0.5. - """ - self.hgain = hgain - self.sgain = sgain - self.vgain = vgain - - def __call__(self, labels): - """ - Applies random HSV augmentation to an image within the predefined limits. - - The modified image replaces the original image in the input 'labels' dict. - """ - img = labels["img"] - if self.hgain or self.sgain or self.vgain: - r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain] + 1 # random gains - hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV)) - dtype = img.dtype # uint8 - - x = np.arange(0, 256, dtype=r.dtype) - lut_hue = ((x * r[0]) % 180).astype(dtype) - lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) - lut_val = np.clip(x * r[2], 0, 255).astype(dtype) - - im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) - cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=img) # no return needed - return labels - - -class RandomFlip: - """ - Applies a random horizontal or vertical flip to an image with a given probability. - - Also updates any instances (bounding boxes, keypoints, etc.) accordingly. - """ - - def __init__(self, p=0.5, direction="horizontal", flip_idx=None) -> None: - """ - Initializes the RandomFlip class with probability and direction. - - Args: - p (float, optional): The probability of applying the flip. Must be between 0 and 1. Default is 0.5. - direction (str, optional): The direction to apply the flip. Must be 'horizontal' or 'vertical'. - Default is 'horizontal'. - flip_idx (array-like, optional): Index mapping for flipping keypoints, if any. - """ - assert direction in ["horizontal", "vertical"], f"Support direction `horizontal` or `vertical`, got {direction}" - assert 0 <= p <= 1.0 - - self.p = p - self.direction = direction - self.flip_idx = flip_idx - - def __call__(self, labels): - """ - Applies random flip to an image and updates any instances like bounding boxes or keypoints accordingly. - - Args: - labels (dict): A dictionary containing the keys 'img' and 'instances'. 'img' is the image to be flipped. - 'instances' is an object containing bounding boxes and optionally keypoints. - - Returns: - (dict): The same dict with the flipped image and updated instances under the 'img' and 'instances' keys. - """ - img = labels["img"] - instances = labels.pop("instances") - instances.convert_bbox(format="xywh") - h, w = img.shape[:2] - h = 1 if instances.normalized else h - w = 1 if instances.normalized else w - - # Flip up-down - if self.direction == "vertical" and random.random() < self.p: - img = np.flipud(img) - instances.flipud(h) - if self.direction == "horizontal" and random.random() < self.p: - img = np.fliplr(img) - instances.fliplr(w) - # For keypoints - if self.flip_idx is not None and instances.keypoints is not None: - instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :]) - labels["img"] = np.ascontiguousarray(img) - labels["instances"] = instances - return labels - - -class LetterBox: - """Resize image and padding for detection, instance segmentation, pose.""" - - def __init__(self, new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, center=True, stride=32): - """Initialize LetterBox object with specific parameters.""" - self.new_shape = new_shape - self.auto = auto - self.scaleFill = scaleFill - self.scaleup = scaleup - self.stride = stride - self.center = center # Put the image in the middle or top-left - - def __call__(self, labels=None, image=None): - """Return updated labels and image with added border.""" - if labels is None: - labels = {} - img = labels.get("img") if image is None else image - shape = img.shape[:2] # current shape [height, width] - new_shape = labels.pop("rect_shape", self.new_shape) - if isinstance(new_shape, int): - new_shape = (new_shape, new_shape) - - # Scale ratio (new / old) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - if not self.scaleup: # only scale down, do not scale up (for better val mAP) - r = min(r, 1.0) - - # Compute padding - ratio = r, r # width, height ratios - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding - if self.auto: # minimum rectangle - dw, dh = np.mod(dw, self.stride), np.mod(dh, self.stride) # wh padding - elif self.scaleFill: # stretch - dw, dh = 0.0, 0.0 - new_unpad = (new_shape[1], new_shape[0]) - ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios - - if self.center: - dw /= 2 # divide padding into 2 sides - dh /= 2 - - if shape[::-1] != new_unpad: # resize - img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(dh - 0.1)) if self.center else 0, int(round(dh + 0.1)) - left, right = int(round(dw - 0.1)) if self.center else 0, int(round(dw + 0.1)) - img = cv2.copyMakeBorder( - img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114) - ) # add border - if labels.get("ratio_pad"): - labels["ratio_pad"] = (labels["ratio_pad"], (left, top)) # for evaluation - - if len(labels): - labels = self._update_labels(labels, ratio, dw, dh) - labels["img"] = img - labels["resized_shape"] = new_shape - return labels - else: - return img - - def _update_labels(self, labels, ratio, padw, padh): - """Update labels.""" - labels["instances"].convert_bbox(format="xyxy") - labels["instances"].denormalize(*labels["img"].shape[:2][::-1]) - labels["instances"].scale(*ratio) - labels["instances"].add_padding(padw, padh) - return labels - - -class CopyPaste: - """ - Implements the Copy-Paste augmentation as described in the paper https://arxiv.org/abs/2012.07177. This class is - responsible for applying the Copy-Paste augmentation on images and their corresponding instances. - """ - - def __init__(self, p=0.5) -> None: - """ - Initializes the CopyPaste class with a given probability. - - Args: - p (float, optional): The probability of applying the Copy-Paste augmentation. Must be between 0 and 1. - Default is 0.5. - """ - self.p = p - - def __call__(self, labels): - """ - Applies the Copy-Paste augmentation to the given image and instances. - - Args: - labels (dict): A dictionary containing: - - 'img': The image to augment. - - 'cls': Class labels associated with the instances. - - 'instances': Object containing bounding boxes, and optionally, keypoints and segments. - - Returns: - (dict): Dict with augmented image and updated instances under the 'img', 'cls', and 'instances' keys. - - Notes: - 1. Instances are expected to have 'segments' as one of their attributes for this augmentation to work. - 2. This method modifies the input dictionary 'labels' in place. - """ - im = labels["img"] - cls = labels["cls"] - h, w = im.shape[:2] - instances = labels.pop("instances") - instances.convert_bbox(format="xyxy") - instances.denormalize(w, h) - if self.p and len(instances.segments): - n = len(instances) - _, w, _ = im.shape # height, width, channels - im_new = np.zeros(im.shape, np.uint8) - - # Calculate ioa first then select indexes randomly - ins_flip = deepcopy(instances) - ins_flip.fliplr(w) - - ioa = bbox_ioa(ins_flip.bboxes, instances.bboxes) # intersection over area, (N, M) - indexes = np.nonzero((ioa < 0.30).all(1))[0] # (N, ) - n = len(indexes) - for j in random.sample(list(indexes), k=round(self.p * n)): - cls = np.concatenate((cls, cls[[j]]), axis=0) - instances = Instances.concatenate((instances, ins_flip[[j]]), axis=0) - cv2.drawContours(im_new, instances.segments[[j]].astype(np.int32), -1, (1, 1, 1), cv2.FILLED) - - result = cv2.flip(im, 1) # augment segments (flip left-right) - i = cv2.flip(im_new, 1).astype(bool) - im[i] = result[i] - - labels["img"] = im - labels["cls"] = cls - labels["instances"] = instances - return labels - - -class Albumentations: - """ - Albumentations transformations. - - Optional, uninstall package to disable. Applies Blur, Median Blur, convert to grayscale, Contrast Limited Adaptive - Histogram Equalization, random change of brightness and contrast, RandomGamma and lowering of image quality by - compression. - """ - - def __init__(self, p=1.0): - """Initialize the transform object for YOLO bbox formatted params.""" - self.p = p - self.transform = None - prefix = colorstr("albumentations: ") - try: - import albumentations as A - - check_version(A.__version__, "1.0.3", hard=True) # version requirement - - # Transforms - T = [ - A.Blur(p=0.01), - A.MedianBlur(p=0.01), - A.ToGray(p=0.01), - A.CLAHE(p=0.01), - A.RandomBrightnessContrast(p=0.0), - A.RandomGamma(p=0.0), - A.ImageCompression(quality_lower=75, p=0.0), - ] - self.transform = A.Compose(T, bbox_params=A.BboxParams(format="yolo", label_fields=["class_labels"])) - - LOGGER.info(prefix + ", ".join(f"{x}".replace("always_apply=False, ", "") for x in T if x.p)) - except ImportError: # package not installed, skip - pass - except Exception as e: - LOGGER.info(f"{prefix}{e}") - - def __call__(self, labels): - """Generates object detections and returns a dictionary with detection results.""" - im = labels["img"] - cls = labels["cls"] - if len(cls): - labels["instances"].convert_bbox("xywh") - labels["instances"].normalize(*im.shape[:2][::-1]) - bboxes = labels["instances"].bboxes - # TODO: add supports of segments and keypoints - if self.transform and random.random() < self.p: - new = self.transform(image=im, bboxes=bboxes, class_labels=cls) # transformed - if len(new["class_labels"]) > 0: # skip update if no bbox in new im - labels["img"] = new["image"] - labels["cls"] = np.array(new["class_labels"]) - bboxes = np.array(new["bboxes"], dtype=np.float32) - labels["instances"].update(bboxes=bboxes) - return labels - - -# TODO: technically this is not an augmentation, maybe we should put this to another files -class Format: - """ - Formats image annotations for object detection, instance segmentation, and pose estimation tasks. The class - standardizes the image and instance annotations to be used by the `collate_fn` in PyTorch DataLoader. - - Attributes: - bbox_format (str): Format for bounding boxes. Default is 'xywh'. - normalize (bool): Whether to normalize bounding boxes. Default is True. - return_mask (bool): Return instance masks for segmentation. Default is False. - return_keypoint (bool): Return keypoints for pose estimation. Default is False. - mask_ratio (int): Downsample ratio for masks. Default is 4. - mask_overlap (bool): Whether to overlap masks. Default is True. - batch_idx (bool): Keep batch indexes. Default is True. - """ - - def __init__( - self, - bbox_format="xywh", - normalize=True, - return_mask=False, - return_keypoint=False, - return_obb=False, - mask_ratio=4, - mask_overlap=True, - batch_idx=True, - ): - """Initializes the Format class with given parameters.""" - self.bbox_format = bbox_format - self.normalize = normalize - self.return_mask = return_mask # set False when training detection only - self.return_keypoint = return_keypoint - self.return_obb = return_obb - self.mask_ratio = mask_ratio - self.mask_overlap = mask_overlap - self.batch_idx = batch_idx # keep the batch indexes - - def __call__(self, labels): - """Return formatted image, classes, bounding boxes & keypoints to be used by 'collate_fn'.""" - img = labels.pop("img") - h, w = img.shape[:2] - cls = labels.pop("cls") - instances = labels.pop("instances") - instances.convert_bbox(format=self.bbox_format) - instances.denormalize(w, h) - nl = len(instances) - - if self.return_mask: - if nl: - masks, instances, cls = self._format_segments(instances, cls, w, h) - masks = torch.from_numpy(masks) - else: - masks = torch.zeros( - 1 if self.mask_overlap else nl, img.shape[0] // self.mask_ratio, img.shape[1] // self.mask_ratio - ) - labels["masks"] = masks - if self.normalize: - instances.normalize(w, h) - labels["img"] = self._format_img(img) - labels["cls"] = torch.from_numpy(cls) if nl else torch.zeros(nl) - labels["bboxes"] = torch.from_numpy(instances.bboxes) if nl else torch.zeros((nl, 4)) - if self.return_keypoint: - labels["keypoints"] = torch.from_numpy(instances.keypoints) - if self.return_obb: - labels["bboxes"] = ( - xyxyxyxy2xywhr(torch.from_numpy(instances.segments)) if len(instances.segments) else torch.zeros((0, 5)) - ) - # Then we can use collate_fn - if self.batch_idx: - labels["batch_idx"] = torch.zeros(nl) - return labels - - def _format_img(self, img): - """Format the image for YOLO from Numpy array to PyTorch tensor.""" - if len(img.shape) < 3: - img = np.expand_dims(img, -1) - img = np.ascontiguousarray(img.transpose(2, 0, 1)[::-1]) - img = torch.from_numpy(img) - return img - - def _format_segments(self, instances, cls, w, h): - """Convert polygon points to bitmap.""" - segments = instances.segments - if self.mask_overlap: - masks, sorted_idx = polygons2masks_overlap((h, w), segments, downsample_ratio=self.mask_ratio) - masks = masks[None] # (640, 640) -> (1, 640, 640) - instances = instances[sorted_idx] - cls = cls[sorted_idx] - else: - masks = polygons2masks((h, w), segments, color=1, downsample_ratio=self.mask_ratio) - - return masks, instances, cls - - -def v8_transforms(dataset, imgsz, hyp, stretch=False): - """Convert images to a size suitable for YOLOv8 training.""" - pre_transform = Compose( - [ - Mosaic(dataset, imgsz=imgsz, p=hyp.mosaic), - CopyPaste(p=hyp.copy_paste), - RandomPerspective( - degrees=hyp.degrees, - translate=hyp.translate, - scale=hyp.scale, - shear=hyp.shear, - perspective=hyp.perspective, - pre_transform=None if stretch else LetterBox(new_shape=(imgsz, imgsz)), - ), - ] - ) - flip_idx = dataset.data.get("flip_idx", []) # for keypoints augmentation - if dataset.use_keypoints: - kpt_shape = dataset.data.get("kpt_shape", None) - if len(flip_idx) == 0 and hyp.fliplr > 0.0: - hyp.fliplr = 0.0 - LOGGER.warning("WARNING ⚠️ No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'") - elif flip_idx and (len(flip_idx) != kpt_shape[0]): - raise ValueError(f"data.yaml flip_idx={flip_idx} length must be equal to kpt_shape[0]={kpt_shape[0]}") - - return Compose( - [ - pre_transform, - MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup), - Albumentations(p=1.0), - RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v), - RandomFlip(direction="vertical", p=hyp.flipud), - RandomFlip(direction="horizontal", p=hyp.fliplr, flip_idx=flip_idx), - ] - ) # transforms - - -# Classification augmentations ----------------------------------------------------------------------------------------- -def classify_transforms( - size=224, - mean=DEFAULT_MEAN, - std=DEFAULT_STD, - interpolation: T.InterpolationMode = T.InterpolationMode.BILINEAR, - crop_fraction: float = DEFAULT_CROP_FTACTION, -): - """ - Classification transforms for evaluation/inference. Inspired by timm/data/transforms_factory.py. - - Args: - size (int): image size - mean (tuple): mean values of RGB channels - std (tuple): std values of RGB channels - interpolation (T.InterpolationMode): interpolation mode. default is T.InterpolationMode.BILINEAR. - crop_fraction (float): fraction of image to crop. default is 1.0. - - Returns: - (T.Compose): torchvision transforms - """ - - if isinstance(size, (tuple, list)): - assert len(size) == 2 - scale_size = tuple(math.floor(x / crop_fraction) for x in size) - else: - scale_size = math.floor(size / crop_fraction) - scale_size = (scale_size, scale_size) - - # aspect ratio is preserved, crops center within image, no borders are added, image is lost - if scale_size[0] == scale_size[1]: - # simple case, use torchvision built-in Resize w/ shortest edge mode (scalar size arg) - tfl = [T.Resize(scale_size[0], interpolation=interpolation)] - else: - # resize shortest edge to matching target dim for non-square target - tfl = [T.Resize(scale_size)] - tfl += [T.CenterCrop(size)] - - tfl += [ - T.ToTensor(), - T.Normalize( - mean=torch.tensor(mean), - std=torch.tensor(std), - ), - ] - - return T.Compose(tfl) - - -# Classification augmentations train --------------------------------------------------------------------------------------- -def classify_augmentations( - size=224, - mean=DEFAULT_MEAN, - std=DEFAULT_STD, - scale=None, - ratio=None, - hflip=0.5, - vflip=0.0, - auto_augment=None, - hsv_h=0.015, # image HSV-Hue augmentation (fraction) - hsv_s=0.4, # image HSV-Saturation augmentation (fraction) - hsv_v=0.4, # image HSV-Value augmentation (fraction) - force_color_jitter=False, - erasing=0.0, - interpolation: T.InterpolationMode = T.InterpolationMode.BILINEAR, -): - """ - Classification transforms with augmentation for training. Inspired by timm/data/transforms_factory.py. - - Args: - size (int): image size - scale (tuple): scale range of the image. default is (0.08, 1.0) - ratio (tuple): aspect ratio range of the image. default is (3./4., 4./3.) - mean (tuple): mean values of RGB channels - std (tuple): std values of RGB channels - hflip (float): probability of horizontal flip - vflip (float): probability of vertical flip - auto_augment (str): auto augmentation policy. can be 'randaugment', 'augmix', 'autoaugment' or None. - hsv_h (float): image HSV-Hue augmentation (fraction) - hsv_s (float): image HSV-Saturation augmentation (fraction) - hsv_v (float): image HSV-Value augmentation (fraction) - force_color_jitter (bool): force to apply color jitter even if auto augment is enabled - erasing (float): probability of random erasing - interpolation (T.InterpolationMode): interpolation mode. default is T.InterpolationMode.BILINEAR. - - Returns: - (T.Compose): torchvision transforms - """ - # Transforms to apply if albumentations not installed - if not isinstance(size, int): - raise TypeError(f"classify_transforms() size {size} must be integer, not (list, tuple)") - scale = tuple(scale or (0.08, 1.0)) # default imagenet scale range - ratio = tuple(ratio or (3.0 / 4.0, 4.0 / 3.0)) # default imagenet ratio range - primary_tfl = [T.RandomResizedCrop(size, scale=scale, ratio=ratio, interpolation=interpolation)] - if hflip > 0.0: - primary_tfl += [T.RandomHorizontalFlip(p=hflip)] - if vflip > 0.0: - primary_tfl += [T.RandomVerticalFlip(p=vflip)] - - secondary_tfl = [] - disable_color_jitter = False - if auto_augment: - assert isinstance(auto_augment, str) - # color jitter is typically disabled if AA/RA on, - # this allows override without breaking old hparm cfgs - disable_color_jitter = not force_color_jitter - - if auto_augment == "randaugment": - if TORCHVISION_0_11: - secondary_tfl += [T.RandAugment(interpolation=interpolation)] - else: - LOGGER.warning('"auto_augment=randaugment" requires torchvision >= 0.11.0. Disabling it.') - - elif auto_augment == "augmix": - if TORCHVISION_0_13: - secondary_tfl += [T.AugMix(interpolation=interpolation)] - else: - LOGGER.warning('"auto_augment=augmix" requires torchvision >= 0.13.0. Disabling it.') - - elif auto_augment == "autoaugment": - if TORCHVISION_0_10: - secondary_tfl += [T.AutoAugment(interpolation=interpolation)] - else: - LOGGER.warning('"auto_augment=autoaugment" requires torchvision >= 0.10.0. Disabling it.') - - else: - raise ValueError( - f'Invalid auto_augment policy: {auto_augment}. Should be one of "randaugment", ' - f'"augmix", "autoaugment" or None' - ) - - if not disable_color_jitter: - secondary_tfl += [T.ColorJitter(brightness=hsv_v, contrast=hsv_v, saturation=hsv_s, hue=hsv_h)] - - final_tfl = [ - T.ToTensor(), - T.Normalize(mean=torch.tensor(mean), std=torch.tensor(std)), - T.RandomErasing(p=erasing, inplace=True), - ] - - return T.Compose(primary_tfl + secondary_tfl + final_tfl) - - -# NOTE: keep this class for backward compatibility -class ClassifyLetterBox: - """ - YOLOv8 LetterBox class for image preprocessing, designed to be part of a transformation pipeline, e.g., - T.Compose([LetterBox(size), ToTensor()]). - - Attributes: - h (int): Target height of the image. - w (int): Target width of the image. - auto (bool): If True, automatically solves for short side using stride. - stride (int): The stride value, used when 'auto' is True. - """ - - def __init__(self, size=(640, 640), auto=False, stride=32): - """ - Initializes the ClassifyLetterBox class with a target size, auto-flag, and stride. - - Args: - size (Union[int, Tuple[int, int]]): The target dimensions (height, width) for the letterbox. - auto (bool): If True, automatically calculates the short side based on stride. - stride (int): The stride value, used when 'auto' is True. - """ - super().__init__() - self.h, self.w = (size, size) if isinstance(size, int) else size - self.auto = auto # pass max size integer, automatically solve for short side using stride - self.stride = stride # used with auto - - def __call__(self, im): - """ - Resizes the image and pads it with a letterbox method. - - Args: - im (numpy.ndarray): The input image as a numpy array of shape HWC. - - Returns: - (numpy.ndarray): The letterboxed and resized image as a numpy array. - """ - imh, imw = im.shape[:2] - r = min(self.h / imh, self.w / imw) # ratio of new/old dimensions - h, w = round(imh * r), round(imw * r) # resized image dimensions - - # Calculate padding dimensions - hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else (self.h, self.w) - top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1) - - # Create padded image - im_out = np.full((hs, ws, 3), 114, dtype=im.dtype) - im_out[top : top + h, left : left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR) - return im_out - - -# NOTE: keep this class for backward compatibility -class CenterCrop: - """YOLOv8 CenterCrop class for image preprocessing, designed to be part of a transformation pipeline, e.g., - T.Compose([CenterCrop(size), ToTensor()]). - """ - - def __init__(self, size=640): - """Converts an image from numpy array to PyTorch tensor.""" - super().__init__() - self.h, self.w = (size, size) if isinstance(size, int) else size - - def __call__(self, im): - """ - Resizes and crops the center of the image using a letterbox method. - - Args: - im (numpy.ndarray): The input image as a numpy array of shape HWC. - - Returns: - (numpy.ndarray): The center-cropped and resized image as a numpy array. - """ - imh, imw = im.shape[:2] - m = min(imh, imw) # min dimension - top, left = (imh - m) // 2, (imw - m) // 2 - return cv2.resize(im[top : top + m, left : left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR) - - -# NOTE: keep this class for backward compatibility -class ToTensor: - """YOLOv8 ToTensor class for image preprocessing, i.e., T.Compose([LetterBox(size), ToTensor()]).""" - - def __init__(self, half=False): - """Initialize YOLOv8 ToTensor object with optional half-precision support.""" - super().__init__() - self.half = half - - def __call__(self, im): - """ - Transforms an image from a numpy array to a PyTorch tensor, applying optional half-precision and normalization. - - Args: - im (numpy.ndarray): Input image as a numpy array with shape (H, W, C) in BGR order. - - Returns: - (torch.Tensor): The transformed image as a PyTorch tensor in float32 or float16, normalized to [0, 1]. - """ - im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1]) # HWC to CHW -> BGR to RGB -> contiguous - im = torch.from_numpy(im) # to torch - im = im.half() if self.half else im.float() # uint8 to fp16/32 - im /= 255.0 # 0-255 to 0.0-1.0 - return im diff --git a/ultralytics-main/ultralytics/data/base.py b/ultralytics-main/ultralytics/data/base.py deleted file mode 100644 index 6af8d3c..0000000 --- a/ultralytics-main/ultralytics/data/base.py +++ /dev/null @@ -1,311 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import glob -import math -import os -import random -from copy import deepcopy -from multiprocessing.pool import ThreadPool -from pathlib import Path -from typing import Optional - -import cv2 -import numpy as np -import psutil -from torch.utils.data import Dataset - -from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM -from .utils import HELP_URL, IMG_FORMATS - - -class BaseDataset(Dataset): - """ - Base dataset class for loading and processing image data. - - Args: - img_path (str): Path to the folder containing images. - imgsz (int, optional): Image size. Defaults to 640. - cache (bool, optional): Cache images to RAM or disk during training. Defaults to False. - augment (bool, optional): If True, data augmentation is applied. Defaults to True. - hyp (dict, optional): Hyperparameters to apply data augmentation. Defaults to None. - prefix (str, optional): Prefix to print in log messages. Defaults to ''. - rect (bool, optional): If True, rectangular training is used. Defaults to False. - batch_size (int, optional): Size of batches. Defaults to None. - stride (int, optional): Stride. Defaults to 32. - pad (float, optional): Padding. Defaults to 0.0. - single_cls (bool, optional): If True, single class training is used. Defaults to False. - classes (list): List of included classes. Default is None. - fraction (float): Fraction of dataset to utilize. Default is 1.0 (use all data). - - Attributes: - im_files (list): List of image file paths. - labels (list): List of label data dictionaries. - ni (int): Number of images in the dataset. - ims (list): List of loaded images. - npy_files (list): List of numpy file paths. - transforms (callable): Image transformation function. - """ - - def __init__( - self, - img_path, - imgsz=640, - cache=False, - augment=True, - hyp=DEFAULT_CFG, - prefix="", - rect=False, - batch_size=16, - stride=32, - pad=0.5, - single_cls=False, - classes=None, - fraction=1.0, - ): - """Initialize BaseDataset with given configuration and options.""" - super().__init__() - self.img_path = img_path - self.imgsz = imgsz - self.augment = augment - self.single_cls = single_cls - self.prefix = prefix - self.fraction = fraction - self.im_files = self.get_img_files(self.img_path) - self.labels = self.get_labels() - self.update_labels(include_class=classes) # single_cls and include_class - self.ni = len(self.labels) # number of images - self.rect = rect - self.batch_size = batch_size - self.stride = stride - self.pad = pad - if self.rect: - assert self.batch_size is not None - self.set_rectangle() - - # Buffer thread for mosaic images - self.buffer = [] # buffer size = batch size - self.max_buffer_length = min((self.ni, self.batch_size * 8, 1000)) if self.augment else 0 - - # Cache images - if cache == "ram" and not self.check_cache_ram(): - cache = False - self.ims, self.im_hw0, self.im_hw = [None] * self.ni, [None] * self.ni, [None] * self.ni - self.npy_files = [Path(f).with_suffix(".npy") for f in self.im_files] - if cache: - self.cache_images(cache) - - # Transforms - self.transforms = self.build_transforms(hyp=hyp) - - def get_img_files(self, img_path): - """Read image files.""" - try: - f = [] # image files - for p in img_path if isinstance(img_path, list) else [img_path]: - p = Path(p) # os-agnostic - if p.is_dir(): # dir - f += glob.glob(str(p / "**" / "*.*"), recursive=True) - # F = list(p.rglob('*.*')) # pathlib - elif p.is_file(): # file - with open(p) as t: - t = t.read().strip().splitlines() - parent = str(p.parent) + os.sep - f += [x.replace("./", parent) if x.startswith("./") else x for x in t] # local to global path - # F += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib) - else: - raise FileNotFoundError(f"{self.prefix}{p} does not exist") - im_files = sorted(x.replace("/", os.sep) for x in f if x.split(".")[-1].lower() in IMG_FORMATS) - # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib - assert im_files, f"{self.prefix}No images found in {img_path}" - except Exception as e: - raise FileNotFoundError(f"{self.prefix}Error loading data from {img_path}\n{HELP_URL}") from e - if self.fraction < 1: - # im_files = im_files[: round(len(im_files) * self.fraction)] - num_elements_to_select = round(len(im_files) * self.fraction) - im_files = random.sample(im_files, num_elements_to_select) - return im_files - - def update_labels(self, include_class: Optional[list]): - """Update labels to include only these classes (optional).""" - include_class_array = np.array(include_class).reshape(1, -1) - for i in range(len(self.labels)): - if include_class is not None: - cls = self.labels[i]["cls"] - bboxes = self.labels[i]["bboxes"] - segments = self.labels[i]["segments"] - keypoints = self.labels[i]["keypoints"] - j = (cls == include_class_array).any(1) - self.labels[i]["cls"] = cls[j] - self.labels[i]["bboxes"] = bboxes[j] - if segments: - self.labels[i]["segments"] = [segments[si] for si, idx in enumerate(j) if idx] - if keypoints is not None: - self.labels[i]["keypoints"] = keypoints[j] - if self.single_cls: - self.labels[i]["cls"][:, 0] = 0 - - def load_image(self, i, rect_mode=True): - """Loads 1 image from dataset index 'i', returns (im, resized hw).""" - im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i] - if im is None: # not cached in RAM - if fn.exists(): # load npy - try: - im = np.load(fn) - except Exception as e: - LOGGER.warning(f"{self.prefix}WARNING ⚠️ Removing corrupt *.npy image file {fn} due to: {e}") - Path(fn).unlink(missing_ok=True) - im = cv2.imread(f) # BGR - else: # read image - im = cv2.imread(f) # BGR - if im is None: - raise FileNotFoundError(f"Image Not Found {f}") - - h0, w0 = im.shape[:2] # orig hw - if rect_mode: # resize long side to imgsz while maintaining aspect ratio - r = self.imgsz / max(h0, w0) # ratio - if r != 1: # if sizes are not equal - w, h = (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz)) - im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR) - elif not (h0 == w0 == self.imgsz): # resize by stretching image to square imgsz - im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR) - - # Add to buffer if training with augmentations - if self.augment: - self.ims[i], self.im_hw0[i], self.im_hw[i] = im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized - self.buffer.append(i) - if len(self.buffer) >= self.max_buffer_length: - j = self.buffer.pop(0) - self.ims[j], self.im_hw0[j], self.im_hw[j] = None, None, None - - return im, (h0, w0), im.shape[:2] - - return self.ims[i], self.im_hw0[i], self.im_hw[i] - - def cache_images(self, cache): - """Cache images to memory or disk.""" - b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes - fcn = self.cache_images_to_disk if cache == "disk" else self.load_image - with ThreadPool(NUM_THREADS) as pool: - results = pool.imap(fcn, range(self.ni)) - pbar = TQDM(enumerate(results), total=self.ni, disable=LOCAL_RANK > 0) - for i, x in pbar: - if cache == "disk": - b += self.npy_files[i].stat().st_size - else: # 'ram' - self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i) - b += self.ims[i].nbytes - pbar.desc = f"{self.prefix}Caching images ({b / gb:.1f}GB {cache})" - pbar.close() - - def cache_images_to_disk(self, i): - """Saves an image as an *.npy file for faster loading.""" - f = self.npy_files[i] - if not f.exists(): - np.save(f.as_posix(), cv2.imread(self.im_files[i]), allow_pickle=False) - - def check_cache_ram(self, safety_margin=0.5): - """Check image caching requirements vs available memory.""" - b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes - n = min(self.ni, 30) # extrapolate from 30 random images - for _ in range(n): - im = cv2.imread(random.choice(self.im_files)) # sample image - ratio = self.imgsz / max(im.shape[0], im.shape[1]) # max(h, w) # ratio - b += im.nbytes * ratio**2 - mem_required = b * self.ni / n * (1 + safety_margin) # GB required to cache dataset into RAM - mem = psutil.virtual_memory() - cache = mem_required < mem.available # to cache or not to cache, that is the question - if not cache: - LOGGER.info( - f'{self.prefix}{mem_required / gb:.1f}GB RAM required to cache images ' - f'with {int(safety_margin * 100)}% safety margin but only ' - f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, ' - f"{'caching images ✅' if cache else 'not caching images ⚠️'}" - ) - return cache - - def set_rectangle(self): - """Sets the shape of bounding boxes for YOLO detections as rectangles.""" - bi = np.floor(np.arange(self.ni) / self.batch_size).astype(int) # batch index - nb = bi[-1] + 1 # number of batches - - s = np.array([x.pop("shape") for x in self.labels]) # hw - ar = s[:, 0] / s[:, 1] # aspect ratio - irect = ar.argsort() - self.im_files = [self.im_files[i] for i in irect] - self.labels = [self.labels[i] for i in irect] - ar = ar[irect] - - # Set training image shapes - shapes = [[1, 1]] * nb - for i in range(nb): - ari = ar[bi == i] - mini, maxi = ari.min(), ari.max() - if maxi < 1: - shapes[i] = [maxi, 1] - elif mini > 1: - shapes[i] = [1, 1 / mini] - - self.batch_shapes = np.ceil(np.array(shapes) * self.imgsz / self.stride + self.pad).astype(int) * self.stride - self.batch = bi # batch index of image - - def __getitem__(self, index): - """Returns transformed label information for given index.""" - return self.transforms(self.get_image_and_label(index)) - - def get_image_and_label(self, index): - """Get and return label information from the dataset.""" - label = deepcopy(self.labels[index]) # requires deepcopy() https://github.com/ultralytics/ultralytics/pull/1948 - label.pop("shape", None) # shape is for rect, remove it - label["img"], label["ori_shape"], label["resized_shape"] = self.load_image(index) - label["ratio_pad"] = ( - label["resized_shape"][0] / label["ori_shape"][0], - label["resized_shape"][1] / label["ori_shape"][1], - ) # for evaluation - if self.rect: - label["rect_shape"] = self.batch_shapes[self.batch[index]] - return self.update_labels_info(label) - - def __len__(self): - """Returns the length of the labels list for the dataset.""" - return len(self.labels) - - def update_labels_info(self, label): - """Custom your label format here.""" - return label - - def build_transforms(self, hyp=None): - """ - Users can customize augmentations here. - - Example: - ```python - if self.augment: - # Training transforms - return Compose([]) - else: - # Val transforms - return Compose([]) - ``` - """ - raise NotImplementedError - - def get_labels(self): - """ - Users can customize their own format here. - - Note: - Ensure output is a dictionary with the following keys: - ```python - dict( - im_file=im_file, - shape=shape, # format: (height, width) - cls=cls, - bboxes=bboxes, # xywh - segments=segments, # xy - keypoints=keypoints, # xy - normalized=True, # or False - bbox_format="xyxy", # or xywh, ltwh - ) - ``` - """ - raise NotImplementedError diff --git a/ultralytics-main/ultralytics/data/build.py b/ultralytics-main/ultralytics/data/build.py deleted file mode 100644 index 37c5fa4..0000000 --- a/ultralytics-main/ultralytics/data/build.py +++ /dev/null @@ -1,186 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import os -import random -from pathlib import Path - -import numpy as np -import torch -from PIL import Image -from torch.utils.data import dataloader, distributed - -from ultralytics.data.loaders import ( - LOADERS, - LoadImagesAndVideos, - LoadPilAndNumpy, - LoadScreenshots, - LoadStreams, - LoadTensor, - SourceTypes, - autocast_list, -) -from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS -from ultralytics.utils import RANK, colorstr -from ultralytics.utils.checks import check_file -from .dataset import YOLODataset -from .utils import PIN_MEMORY - - -class InfiniteDataLoader(dataloader.DataLoader): - """ - Dataloader that reuses workers. - - Uses same syntax as vanilla DataLoader. - """ - - def __init__(self, *args, **kwargs): - """Dataloader that infinitely recycles workers, inherits from DataLoader.""" - super().__init__(*args, **kwargs) - object.__setattr__(self, "batch_sampler", _RepeatSampler(self.batch_sampler)) - self.iterator = super().__iter__() - - def __len__(self): - """Returns the length of the batch sampler's sampler.""" - return len(self.batch_sampler.sampler) - - def __iter__(self): - """Creates a sampler that repeats indefinitely.""" - for _ in range(len(self)): - yield next(self.iterator) - - def reset(self): - """ - Reset iterator. - - This is useful when we want to modify settings of dataset while training. - """ - self.iterator = self._get_iterator() - - -class _RepeatSampler: - """ - Sampler that repeats forever. - - Args: - sampler (Dataset.sampler): The sampler to repeat. - """ - - def __init__(self, sampler): - """Initializes an object that repeats a given sampler indefinitely.""" - self.sampler = sampler - - def __iter__(self): - """Iterates over the 'sampler' and yields its contents.""" - while True: - yield from iter(self.sampler) - - -def seed_worker(worker_id): # noqa - """Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader.""" - worker_seed = torch.initial_seed() % 2**32 - np.random.seed(worker_seed) - random.seed(worker_seed) - - -def build_yolo_dataset(cfg, img_path, batch, data, mode="train", rect=False, stride=32): - """Build YOLO Dataset.""" - return YOLODataset( - img_path=img_path, - imgsz=cfg.imgsz, - batch_size=batch, - augment=mode == "train", # augmentation - hyp=cfg, # TODO: probably add a get_hyps_from_cfg function - rect=cfg.rect or rect, # rectangular batches - cache=cfg.cache or None, - single_cls=cfg.single_cls or False, - stride=int(stride), - pad=0.0 if mode == "train" else 0.5, - prefix=colorstr(f"{mode}: "), - task=cfg.task, - classes=cfg.classes, - data=data, - fraction=cfg.fraction if mode == "train" else 1.0, - ) - - -def build_dataloader(dataset, batch, workers, shuffle=True, rank=-1): - """Return an InfiniteDataLoader or DataLoader for training or validation set.""" - batch = min(batch, len(dataset)) - nd = torch.cuda.device_count() # number of CUDA devices - nw = min([os.cpu_count() // max(nd, 1), workers]) # number of workers - sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle) - generator = torch.Generator() - generator.manual_seed(6148914691236517205 + RANK) - return InfiniteDataLoader( - dataset=dataset, - batch_size=batch, - shuffle=shuffle and sampler is None, - num_workers=nw, - sampler=sampler, - pin_memory=PIN_MEMORY, - collate_fn=getattr(dataset, "collate_fn", None), - worker_init_fn=seed_worker, - generator=generator, - ) - - -def check_source(source): - """Check source type and return corresponding flag values.""" - webcam, screenshot, from_img, in_memory, tensor = False, False, False, False, False - if isinstance(source, (str, int, Path)): # int for local usb camera - source = str(source) - is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) - is_url = source.lower().startswith(("https://", "http://", "rtsp://", "rtmp://", "tcp://")) - webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file) - screenshot = source.lower() == "screen" - if is_url and is_file: - source = check_file(source) # download - elif isinstance(source, LOADERS): - in_memory = True - elif isinstance(source, (list, tuple)): - source = autocast_list(source) # convert all list elements to PIL or np arrays - from_img = True - elif isinstance(source, (Image.Image, np.ndarray)): - from_img = True - elif isinstance(source, torch.Tensor): - tensor = True - else: - raise TypeError("Unsupported image type. For supported types see https://docs.ultralytics.com/modes/predict") - - return source, webcam, screenshot, from_img, in_memory, tensor - - -def load_inference_source(source=None, batch=1, vid_stride=1, buffer=False): - """ - Loads an inference source for object detection and applies necessary transformations. - - Args: - source (str, Path, Tensor, PIL.Image, np.ndarray): The input source for inference. - batch (int, optional): Batch size for dataloaders. Default is 1. - vid_stride (int, optional): The frame interval for video sources. Default is 1. - buffer (bool, optional): Determined whether stream frames will be buffered. Default is False. - - Returns: - dataset (Dataset): A dataset object for the specified input source. - """ - source, stream, screenshot, from_img, in_memory, tensor = check_source(source) - source_type = source.source_type if in_memory else SourceTypes(stream, screenshot, from_img, tensor) - - # Dataloader - if tensor: - dataset = LoadTensor(source) - elif in_memory: - dataset = source - elif stream: - dataset = LoadStreams(source, vid_stride=vid_stride, buffer=buffer) - elif screenshot: - dataset = LoadScreenshots(source) - elif from_img: - dataset = LoadPilAndNumpy(source) - else: - dataset = LoadImagesAndVideos(source, batch=batch, vid_stride=vid_stride) - - # Attach source types to the dataset - setattr(dataset, "source_type", source_type) - - return dataset diff --git a/ultralytics-main/ultralytics/data/converter.py b/ultralytics-main/ultralytics/data/converter.py deleted file mode 100644 index eff4dac..0000000 --- a/ultralytics-main/ultralytics/data/converter.py +++ /dev/null @@ -1,542 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import json -from collections import defaultdict -from pathlib import Path - -import cv2 -import numpy as np - -from ultralytics.utils import LOGGER, TQDM -from ultralytics.utils.files import increment_path - - -def coco91_to_coco80_class(): - """ - Converts 91-index COCO class IDs to 80-index COCO class IDs. - - Returns: - (list): A list of 91 class IDs where the index represents the 80-index class ID and the value is the - corresponding 91-index class ID. - """ - return [ - 0, - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - None, - 11, - 12, - 13, - 14, - 15, - 16, - 17, - 18, - 19, - 20, - 21, - 22, - 23, - None, - 24, - 25, - None, - None, - 26, - 27, - 28, - 29, - 30, - 31, - 32, - 33, - 34, - 35, - 36, - 37, - 38, - 39, - None, - 40, - 41, - 42, - 43, - 44, - 45, - 46, - 47, - 48, - 49, - 50, - 51, - 52, - 53, - 54, - 55, - 56, - 57, - 58, - 59, - None, - 60, - None, - None, - 61, - None, - 62, - 63, - 64, - 65, - 66, - 67, - 68, - 69, - 70, - 71, - 72, - None, - 73, - 74, - 75, - 76, - 77, - 78, - 79, - None, - ] - - -def coco80_to_coco91_class(): - """ - Converts 80-index (val2014) to 91-index (paper). - For details see https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/. - - Example: - ```python - import numpy as np - - a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n') - b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n') - x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco - x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet - ``` - """ - return [ - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - 11, - 13, - 14, - 15, - 16, - 17, - 18, - 19, - 20, - 21, - 22, - 23, - 24, - 25, - 27, - 28, - 31, - 32, - 33, - 34, - 35, - 36, - 37, - 38, - 39, - 40, - 41, - 42, - 43, - 44, - 46, - 47, - 48, - 49, - 50, - 51, - 52, - 53, - 54, - 55, - 56, - 57, - 58, - 59, - 60, - 61, - 62, - 63, - 64, - 65, - 67, - 70, - 72, - 73, - 74, - 75, - 76, - 77, - 78, - 79, - 80, - 81, - 82, - 84, - 85, - 86, - 87, - 88, - 89, - 90, - ] - - -def convert_coco( - labels_dir="../coco/annotations/", - save_dir="coco_converted/", - use_segments=False, - use_keypoints=False, - cls91to80=True, -): - """ - Converts COCO dataset annotations to a YOLO annotation format suitable for training YOLO models. - - Args: - labels_dir (str, optional): Path to directory containing COCO dataset annotation files. - save_dir (str, optional): Path to directory to save results to. - use_segments (bool, optional): Whether to include segmentation masks in the output. - use_keypoints (bool, optional): Whether to include keypoint annotations in the output. - cls91to80 (bool, optional): Whether to map 91 COCO class IDs to the corresponding 80 COCO class IDs. - - Example: - ```python - from ultralytics.data.converter import convert_coco - - convert_coco('../datasets/coco/annotations/', use_segments=True, use_keypoints=False, cls91to80=True) - ``` - - Output: - Generates output files in the specified output directory. - """ - - # Create dataset directory - save_dir = increment_path(save_dir) # increment if save directory already exists - for p in save_dir / "labels", save_dir / "images": - p.mkdir(parents=True, exist_ok=True) # make dir - - # Convert classes - coco80 = coco91_to_coco80_class() - - # Import json - for json_file in sorted(Path(labels_dir).resolve().glob("*.json")): - fn = Path(save_dir) / "labels" / json_file.stem.replace("instances_", "") # folder name - fn.mkdir(parents=True, exist_ok=True) - with open(json_file) as f: - data = json.load(f) - - # Create image dict - images = {f'{x["id"]:d}': x for x in data["images"]} - # Create image-annotations dict - imgToAnns = defaultdict(list) - for ann in data["annotations"]: - imgToAnns[ann["image_id"]].append(ann) - - # Write labels file - for img_id, anns in TQDM(imgToAnns.items(), desc=f"Annotations {json_file}"): - img = images[f"{img_id:d}"] - h, w, f = img["height"], img["width"], img["file_name"] - - bboxes = [] - segments = [] - keypoints = [] - for ann in anns: - if ann["iscrowd"]: - continue - # The COCO box format is [top left x, top left y, width, height] - box = np.array(ann["bbox"], dtype=np.float64) - box[:2] += box[2:] / 2 # xy top-left corner to center - box[[0, 2]] /= w # normalize x - box[[1, 3]] /= h # normalize y - if box[2] <= 0 or box[3] <= 0: # if w <= 0 and h <= 0 - continue - - cls = coco80[ann["category_id"] - 1] if cls91to80 else ann["category_id"] - 1 # class - box = [cls] + box.tolist() - if box not in bboxes: - bboxes.append(box) - if use_segments and ann.get("segmentation") is not None: - if len(ann["segmentation"]) == 0: - segments.append([]) - continue - elif len(ann["segmentation"]) > 1: - s = merge_multi_segment(ann["segmentation"]) - s = (np.concatenate(s, axis=0) / np.array([w, h])).reshape(-1).tolist() - else: - s = [j for i in ann["segmentation"] for j in i] # all segments concatenated - s = (np.array(s).reshape(-1, 2) / np.array([w, h])).reshape(-1).tolist() - s = [cls] + s - segments.append(s) - if use_keypoints and ann.get("keypoints") is not None: - keypoints.append( - box + (np.array(ann["keypoints"]).reshape(-1, 3) / np.array([w, h, 1])).reshape(-1).tolist() - ) - - # Write - with open((fn / f).with_suffix(".txt"), "a") as file: - for i in range(len(bboxes)): - if use_keypoints: - line = (*(keypoints[i]),) # cls, box, keypoints - else: - line = ( - *(segments[i] if use_segments and len(segments[i]) > 0 else bboxes[i]), - ) # cls, box or segments - file.write(("%g " * len(line)).rstrip() % line + "\n") - - LOGGER.info(f"COCO data converted successfully.\nResults saved to {save_dir.resolve()}") - - -def convert_dota_to_yolo_obb(dota_root_path: str): - """ - Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format. - - The function processes images in the 'train' and 'val' folders of the DOTA dataset. For each image, it reads the - associated label from the original labels directory and writes new labels in YOLO OBB format to a new directory. - - Args: - dota_root_path (str): The root directory path of the DOTA dataset. - - Example: - ```python - from ultralytics.data.converter import convert_dota_to_yolo_obb - - convert_dota_to_yolo_obb('path/to/DOTA') - ``` - - Notes: - The directory structure assumed for the DOTA dataset: - - - DOTA - ├─ images - │ ├─ train - │ └─ val - └─ labels - ├─ train_original - └─ val_original - - After execution, the function will organize the labels into: - - - DOTA - └─ labels - ├─ train - └─ val - """ - dota_root_path = Path(dota_root_path) - - # Class names to indices mapping - class_mapping = { - "plane": 0, - "ship": 1, - "storage-tank": 2, - "baseball-diamond": 3, - "tennis-court": 4, - "basketball-court": 5, - "ground-track-field": 6, - "harbor": 7, - "bridge": 8, - "large-vehicle": 9, - "small-vehicle": 10, - "helicopter": 11, - "roundabout": 12, - "soccer-ball-field": 13, - "swimming-pool": 14, - "container-crane": 15, - "airport": 16, - "helipad": 17, - } - - def convert_label(image_name, image_width, image_height, orig_label_dir, save_dir): - """Converts a single image's DOTA annotation to YOLO OBB format and saves it to a specified directory.""" - orig_label_path = orig_label_dir / f"{image_name}.txt" - save_path = save_dir / f"{image_name}.txt" - - with orig_label_path.open("r") as f, save_path.open("w") as g: - lines = f.readlines() - for line in lines: - parts = line.strip().split() - if len(parts) < 9: - continue - class_name = parts[8] - class_idx = class_mapping[class_name] - coords = [float(p) for p in parts[:8]] - normalized_coords = [ - coords[i] / image_width if i % 2 == 0 else coords[i] / image_height for i in range(8) - ] - formatted_coords = ["{:.6g}".format(coord) for coord in normalized_coords] - g.write(f"{class_idx} {' '.join(formatted_coords)}\n") - - for phase in ["train", "val"]: - image_dir = dota_root_path / "images" / phase - orig_label_dir = dota_root_path / "labels" / f"{phase}_original" - save_dir = dota_root_path / "labels" / phase - - save_dir.mkdir(parents=True, exist_ok=True) - - image_paths = list(image_dir.iterdir()) - for image_path in TQDM(image_paths, desc=f"Processing {phase} images"): - if image_path.suffix != ".png": - continue - image_name_without_ext = image_path.stem - img = cv2.imread(str(image_path)) - h, w = img.shape[:2] - convert_label(image_name_without_ext, w, h, orig_label_dir, save_dir) - - -def min_index(arr1, arr2): - """ - Find a pair of indexes with the shortest distance between two arrays of 2D points. - - Args: - arr1 (np.ndarray): A NumPy array of shape (N, 2) representing N 2D points. - arr2 (np.ndarray): A NumPy array of shape (M, 2) representing M 2D points. - - Returns: - (tuple): A tuple containing the indexes of the points with the shortest distance in arr1 and arr2 respectively. - """ - dis = ((arr1[:, None, :] - arr2[None, :, :]) ** 2).sum(-1) - return np.unravel_index(np.argmin(dis, axis=None), dis.shape) - - -def merge_multi_segment(segments): - """ - Merge multiple segments into one list by connecting the coordinates with the minimum distance between each segment. - This function connects these coordinates with a thin line to merge all segments into one. - - Args: - segments (List[List]): Original segmentations in COCO's JSON file. - Each element is a list of coordinates, like [segmentation1, segmentation2,...]. - - Returns: - s (List[np.ndarray]): A list of connected segments represented as NumPy arrays. - """ - s = [] - segments = [np.array(i).reshape(-1, 2) for i in segments] - idx_list = [[] for _ in range(len(segments))] - - # Record the indexes with min distance between each segment - for i in range(1, len(segments)): - idx1, idx2 = min_index(segments[i - 1], segments[i]) - idx_list[i - 1].append(idx1) - idx_list[i].append(idx2) - - # Use two round to connect all the segments - for k in range(2): - # Forward connection - if k == 0: - for i, idx in enumerate(idx_list): - # Middle segments have two indexes, reverse the index of middle segments - if len(idx) == 2 and idx[0] > idx[1]: - idx = idx[::-1] - segments[i] = segments[i][::-1, :] - - segments[i] = np.roll(segments[i], -idx[0], axis=0) - segments[i] = np.concatenate([segments[i], segments[i][:1]]) - # Deal with the first segment and the last one - if i in [0, len(idx_list) - 1]: - s.append(segments[i]) - else: - idx = [0, idx[1] - idx[0]] - s.append(segments[i][idx[0] : idx[1] + 1]) - - else: - for i in range(len(idx_list) - 1, -1, -1): - if i not in [0, len(idx_list) - 1]: - idx = idx_list[i] - nidx = abs(idx[1] - idx[0]) - s.append(segments[i][nidx:]) - return s - - -def yolo_bbox2segment(im_dir, save_dir=None, sam_model="sam_b.pt"): - """ - Converts existing object detection dataset (bounding boxes) to segmentation dataset or oriented bounding box (OBB) - in YOLO format. Generates segmentation data using SAM auto-annotator as needed. - - Args: - im_dir (str | Path): Path to image directory to convert. - save_dir (str | Path): Path to save the generated labels, labels will be saved - into `labels-segment` in the same directory level of `im_dir` if save_dir is None. Default: None. - sam_model (str): Segmentation model to use for intermediate segmentation data; optional. - - Notes: - The input directory structure assumed for dataset: - - - im_dir - ├─ 001.jpg - ├─ .. - └─ NNN.jpg - - labels - ├─ 001.txt - ├─ .. - └─ NNN.txt - """ - from ultralytics.data import YOLODataset - from ultralytics.utils.ops import xywh2xyxy - from ultralytics.utils import LOGGER - from ultralytics import SAM - from tqdm import tqdm - - # NOTE: add placeholder to pass class index check - dataset = YOLODataset(im_dir, data=dict(names=list(range(1000)))) - if len(dataset.labels[0]["segments"]) > 0: # if it's segment data - LOGGER.info("Segmentation labels detected, no need to generate new ones!") - return - - LOGGER.info("Detection labels detected, generating segment labels by SAM model!") - sam_model = SAM(sam_model) - for l in tqdm(dataset.labels, total=len(dataset.labels), desc="Generating segment labels"): - h, w = l["shape"] - boxes = l["bboxes"] - if len(boxes) == 0: # skip empty labels - continue - boxes[:, [0, 2]] *= w - boxes[:, [1, 3]] *= h - im = cv2.imread(l["im_file"]) - sam_results = sam_model(im, bboxes=xywh2xyxy(boxes), verbose=False, save=False) - l["segments"] = sam_results[0].masks.xyn - - save_dir = Path(save_dir) if save_dir else Path(im_dir).parent / "labels-segment" - save_dir.mkdir(parents=True, exist_ok=True) - for l in dataset.labels: - texts = [] - lb_name = Path(l["im_file"]).with_suffix(".txt").name - txt_file = save_dir / lb_name - cls = l["cls"] - for i, s in enumerate(l["segments"]): - line = (int(cls[i]), *s.reshape(-1)) - texts.append(("%g " * len(line)).rstrip() % line) - if texts: - with open(txt_file, "a") as f: - f.writelines(text + "\n" for text in texts) - LOGGER.info(f"Generated segment labels saved in {save_dir}") diff --git a/ultralytics-main/ultralytics/data/dataset.py b/ultralytics-main/ultralytics/data/dataset.py deleted file mode 100644 index f358b9b..0000000 --- a/ultralytics-main/ultralytics/data/dataset.py +++ /dev/null @@ -1,382 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -import contextlib -from itertools import repeat -from multiprocessing.pool import ThreadPool -from pathlib import Path - -import cv2 -import numpy as np -import torch -import torchvision -from PIL import Image - -from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM, colorstr, is_dir_writeable -from ultralytics.utils.ops import resample_segments -from .augment import Compose, Format, Instances, LetterBox, classify_augmentations, classify_transforms, v8_transforms -from .base import BaseDataset -from .utils import HELP_URL, LOGGER, get_hash, img2label_paths, verify_image, verify_image_label - -# Ultralytics dataset *.cache version, >= 1.0.0 for YOLOv8 -DATASET_CACHE_VERSION = "1.0.3" - - -class YOLODataset(BaseDataset): - """ - Dataset class for loading object detection and/or segmentation labels in YOLO format. - - Args: - data (dict, optional): A dataset YAML dictionary. Defaults to None. - task (str): An explicit arg to point current task, Defaults to 'detect'. - - Returns: - (torch.utils.data.Dataset): A PyTorch dataset object that can be used for training an object detection model. - """ - - def __init__(self, *args, data=None, task="detect", **kwargs): - """Initializes the YOLODataset with optional configurations for segments and keypoints.""" - self.use_segments = task == "segment" - self.use_keypoints = task == "pose" - self.use_obb = task == "obb" - self.data = data - assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints." - super().__init__(*args, **kwargs) - - def cache_labels(self, path=Path("./labels.cache")): - """ - Cache dataset labels, check images and read shapes. - - Args: - path (Path): Path where to save the cache file. Default is Path('./labels.cache'). - - Returns: - (dict): labels. - """ - x = {"labels": []} - nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages - desc = f"{self.prefix}Scanning {path.parent / path.stem}..." - total = len(self.im_files) - nkpt, ndim = self.data.get("kpt_shape", (0, 0)) - if self.use_keypoints and (nkpt <= 0 or ndim not in (2, 3)): - raise ValueError( - "'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of " - "keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'" - ) - with ThreadPool(NUM_THREADS) as pool: - results = pool.imap( - func=verify_image_label, - iterable=zip( - self.im_files, - self.label_files, - repeat(self.prefix), - repeat(self.use_keypoints), - repeat(len(self.data["names"])), - repeat(nkpt), - repeat(ndim), - ), - ) - pbar = TQDM(results, desc=desc, total=total) - for im_file, lb, shape, segments, keypoint, nm_f, nf_f, ne_f, nc_f, msg in pbar: - nm += nm_f - nf += nf_f - ne += ne_f - nc += nc_f - if im_file: - x["labels"].append( - dict( - im_file=im_file, - shape=shape, - cls=lb[:, 0:1], # n, 1 - bboxes=lb[:, 1:], # n, 4 - segments=segments, - keypoints=keypoint, - normalized=True, - bbox_format="xywh", - ) - ) - if msg: - msgs.append(msg) - pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt" - pbar.close() - - if msgs: - LOGGER.info("\n".join(msgs)) - if nf == 0: - LOGGER.warning(f"{self.prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}") - x["hash"] = get_hash(self.label_files + self.im_files) - x["results"] = nf, nm, ne, nc, len(self.im_files) - x["msgs"] = msgs # warnings - save_dataset_cache_file(self.prefix, path, x) - return x - - def get_labels(self): - """Returns dictionary of labels for YOLO training.""" - self.label_files = img2label_paths(self.im_files) - cache_path = Path(self.label_files[0]).parent.with_suffix(".cache") - try: - cache, exists = load_dataset_cache_file(cache_path), True # attempt to load a *.cache file - assert cache["version"] == DATASET_CACHE_VERSION # matches current version - assert cache["hash"] == get_hash(self.label_files + self.im_files) # identical hash - except (FileNotFoundError, AssertionError, AttributeError): - cache, exists = self.cache_labels(cache_path), False # run cache ops - - # Display cache - nf, nm, ne, nc, n = cache.pop("results") # found, missing, empty, corrupt, total - if exists and LOCAL_RANK in (-1, 0): - d = f"Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt" - TQDM(None, desc=self.prefix + d, total=n, initial=n) # display results - if cache["msgs"]: - LOGGER.info("\n".join(cache["msgs"])) # display warnings - - # Read cache - [cache.pop(k) for k in ("hash", "version", "msgs")] # remove items - labels = cache["labels"] - if not labels: - LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}") - self.im_files = [lb["im_file"] for lb in labels] # update im_files - - # Check if the dataset is all boxes or all segments - lengths = ((len(lb["cls"]), len(lb["bboxes"]), len(lb["segments"])) for lb in labels) - len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths)) - if len_segments and len_boxes != len_segments: - LOGGER.warning( - f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, " - f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. " - "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset." - ) - for lb in labels: - lb["segments"] = [] - if len_cls == 0: - LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}") - return labels - - def build_transforms(self, hyp=None): - """Builds and appends transforms to the list.""" - if self.augment: - hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0 - hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0 - transforms = v8_transforms(self, self.imgsz, hyp) - else: - transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)]) - transforms.append( - Format( - bbox_format="xywh", - normalize=True, - return_mask=self.use_segments, - return_keypoint=self.use_keypoints, - return_obb=self.use_obb, - batch_idx=True, - mask_ratio=hyp.mask_ratio, - mask_overlap=hyp.overlap_mask, - ) - ) - return transforms - - def close_mosaic(self, hyp): - """Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations.""" - hyp.mosaic = 0.0 # set mosaic ratio=0.0 - hyp.copy_paste = 0.0 # keep the same behavior as previous v8 close-mosaic - hyp.mixup = 0.0 # keep the same behavior as previous v8 close-mosaic - self.transforms = self.build_transforms(hyp) - - def update_labels_info(self, label): - """ - Custom your label format here. - - Note: - cls is not with bboxes now, classification and semantic segmentation need an independent cls label - Can also support classification and semantic segmentation by adding or removing dict keys there. - """ - bboxes = label.pop("bboxes") - segments = label.pop("segments", []) - keypoints = label.pop("keypoints", None) - bbox_format = label.pop("bbox_format") - normalized = label.pop("normalized") - - # NOTE: do NOT resample oriented boxes - segment_resamples = 100 if self.use_obb else 1000 - if len(segments) > 0: - # list[np.array(1000, 2)] * num_samples - # (N, 1000, 2) - segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0) - else: - segments = np.zeros((0, segment_resamples, 2), dtype=np.float32) - label["instances"] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized) - return label - - @staticmethod - def collate_fn(batch): - """Collates data samples into batches.""" - new_batch = {} - keys = batch[0].keys() - values = list(zip(*[list(b.values()) for b in batch])) - for i, k in enumerate(keys): - value = values[i] - if k == "img": - value = torch.stack(value, 0) - if k in ["masks", "keypoints", "bboxes", "cls", "segments", "obb"]: - value = torch.cat(value, 0) - new_batch[k] = value - new_batch["batch_idx"] = list(new_batch["batch_idx"]) - for i in range(len(new_batch["batch_idx"])): - new_batch["batch_idx"][i] += i # add target image index for build_targets() - new_batch["batch_idx"] = torch.cat(new_batch["batch_idx"], 0) - return new_batch - - -# Classification dataloaders ------------------------------------------------------------------------------------------- -class ClassificationDataset(torchvision.datasets.ImageFolder): - """ - Extends torchvision ImageFolder to support YOLO classification tasks, offering functionalities like image - augmentation, caching, and verification. It's designed to efficiently handle large datasets for training deep - learning models, with optional image transformations and caching mechanisms to speed up training. - - This class allows for augmentations using both torchvision and Albumentations libraries, and supports caching images - in RAM or on disk to reduce IO overhead during training. Additionally, it implements a robust verification process - to ensure data integrity and consistency. - - Attributes: - cache_ram (bool): Indicates if caching in RAM is enabled. - cache_disk (bool): Indicates if caching on disk is enabled. - samples (list): A list of tuples, each containing the path to an image, its class index, path to its .npy cache - file (if caching on disk), and optionally the loaded image array (if caching in RAM). - torch_transforms (callable): PyTorch transforms to be applied to the images. - """ - - def __init__(self, root, args, augment=False, prefix=""): - """ - Initialize YOLO object with root, image size, augmentations, and cache settings. - - Args: - root (str): Path to the dataset directory where images are stored in a class-specific folder structure. - args (Namespace): Configuration containing dataset-related settings such as image size, augmentation - parameters, and cache settings. It includes attributes like `imgsz` (image size), `fraction` (fraction - of data to use), `scale`, `fliplr`, `flipud`, `cache` (disk or RAM caching for faster training), - `auto_augment`, `hsv_h`, `hsv_s`, `hsv_v`, and `crop_fraction`. - augment (bool, optional): Whether to apply augmentations to the dataset. Default is False. - prefix (str, optional): Prefix for logging and cache filenames, aiding in dataset identification and - debugging. Default is an empty string. - """ - super().__init__(root=root) - if augment and args.fraction < 1.0: # reduce training fraction - self.samples = self.samples[: round(len(self.samples) * args.fraction)] - self.prefix = colorstr(f"{prefix}: ") if prefix else "" - self.cache_ram = args.cache is True or args.cache == "ram" # cache images into RAM - self.cache_disk = args.cache == "disk" # cache images on hard drive as uncompressed *.npy files - self.samples = self.verify_images() # filter out bad images - self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples] # file, index, npy, im - scale = (1.0 - args.scale, 1.0) # (0.08, 1.0) - self.torch_transforms = ( - classify_augmentations( - size=args.imgsz, - scale=scale, - hflip=args.fliplr, - vflip=args.flipud, - erasing=args.erasing, - auto_augment=args.auto_augment, - hsv_h=args.hsv_h, - hsv_s=args.hsv_s, - hsv_v=args.hsv_v, - ) - if augment - else classify_transforms(size=args.imgsz, crop_fraction=args.crop_fraction) - ) - - def __getitem__(self, i): - """Returns subset of data and targets corresponding to given indices.""" - f, j, fn, im = self.samples[i] # filename, index, filename.with_suffix('.npy'), image - if self.cache_ram and im is None: - im = self.samples[i][3] = cv2.imread(f) - elif self.cache_disk: - if not fn.exists(): # load npy - np.save(fn.as_posix(), cv2.imread(f), allow_pickle=False) - im = np.load(fn) - else: # read image - im = cv2.imread(f) # BGR - # Convert NumPy array to PIL image - im = Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB)) - sample = self.torch_transforms(im) - return {"img": sample, "cls": j} - - def __len__(self) -> int: - """Return the total number of samples in the dataset.""" - return len(self.samples) - - def verify_images(self): - """Verify all images in dataset.""" - desc = f"{self.prefix}Scanning {self.root}..." - path = Path(self.root).with_suffix(".cache") # *.cache file path - - with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError): - cache = load_dataset_cache_file(path) # attempt to load a *.cache file - assert cache["version"] == DATASET_CACHE_VERSION # matches current version - assert cache["hash"] == get_hash([x[0] for x in self.samples]) # identical hash - nf, nc, n, samples = cache.pop("results") # found, missing, empty, corrupt, total - if LOCAL_RANK in (-1, 0): - d = f"{desc} {nf} images, {nc} corrupt" - TQDM(None, desc=d, total=n, initial=n) - if cache["msgs"]: - LOGGER.info("\n".join(cache["msgs"])) # display warnings - return samples - - # Run scan if *.cache retrieval failed - nf, nc, msgs, samples, x = 0, 0, [], [], {} - with ThreadPool(NUM_THREADS) as pool: - results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix))) - pbar = TQDM(results, desc=desc, total=len(self.samples)) - for sample, nf_f, nc_f, msg in pbar: - if nf_f: - samples.append(sample) - if msg: - msgs.append(msg) - nf += nf_f - nc += nc_f - pbar.desc = f"{desc} {nf} images, {nc} corrupt" - pbar.close() - if msgs: - LOGGER.info("\n".join(msgs)) - x["hash"] = get_hash([x[0] for x in self.samples]) - x["results"] = nf, nc, len(samples), samples - x["msgs"] = msgs # warnings - save_dataset_cache_file(self.prefix, path, x) - return samples - - -def load_dataset_cache_file(path): - """Load an Ultralytics *.cache dictionary from path.""" - import gc - - gc.disable() # reduce pickle load time https://github.com/ultralytics/ultralytics/pull/1585 - cache = np.load(str(path), allow_pickle=True).item() # load dict - gc.enable() - return cache - - -def save_dataset_cache_file(prefix, path, x): - """Save an Ultralytics dataset *.cache dictionary x to path.""" - x["version"] = DATASET_CACHE_VERSION # add cache version - if is_dir_writeable(path.parent): - if path.exists(): - path.unlink() # remove *.cache file if exists - np.save(str(path), x) # save cache for next time - path.with_suffix(".cache.npy").rename(path) # remove .npy suffix - LOGGER.info(f"{prefix}New cache created: {path}") - else: - LOGGER.warning(f"{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable, cache not saved.") - - -# TODO: support semantic segmentation -class SemanticDataset(BaseDataset): - """ - Semantic Segmentation Dataset. - - This class is responsible for handling datasets used for semantic segmentation tasks. It inherits functionalities - from the BaseDataset class. - - Note: - This class is currently a placeholder and needs to be populated with methods and attributes for supporting - semantic segmentation tasks. - """ - - def __init__(self): - """Initialize a SemanticDataset object.""" - super().__init__() diff --git a/ultralytics-main/ultralytics/data/explorer/__init__.py b/ultralytics-main/ultralytics/data/explorer/__init__.py deleted file mode 100644 index ce594dc..0000000 --- a/ultralytics-main/ultralytics/data/explorer/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .utils import plot_query_result - -__all__ = ["plot_query_result"] diff --git a/ultralytics-main/ultralytics/data/explorer/explorer.py b/ultralytics-main/ultralytics/data/explorer/explorer.py deleted file mode 100644 index d21a5c2..0000000 --- a/ultralytics-main/ultralytics/data/explorer/explorer.py +++ /dev/null @@ -1,472 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from io import BytesIO -from pathlib import Path -from typing import Any, List, Tuple, Union - -import cv2 -import numpy as np -import torch -from PIL import Image -from matplotlib import pyplot as plt -from pandas import DataFrame -from tqdm import tqdm - -from ultralytics.data.augment import Format -from ultralytics.data.dataset import YOLODataset -from ultralytics.data.utils import check_det_dataset -from ultralytics.models.yolo.model import YOLO -from ultralytics.utils import LOGGER, IterableSimpleNamespace, checks, USER_CONFIG_DIR -from .utils import get_sim_index_schema, get_table_schema, plot_query_result, prompt_sql_query, sanitize_batch - - -class ExplorerDataset(YOLODataset): - def __init__(self, *args, data: dict = None, **kwargs) -> None: - super().__init__(*args, data=data, **kwargs) - - def load_image(self, i: int) -> Union[Tuple[np.ndarray, Tuple[int, int], Tuple[int, int]], Tuple[None, None, None]]: - """Loads 1 image from dataset index 'i' without any resize ops.""" - im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i] - if im is None: # not cached in RAM - if fn.exists(): # load npy - im = np.load(fn) - else: # read image - im = cv2.imread(f) # BGR - if im is None: - raise FileNotFoundError(f"Image Not Found {f}") - h0, w0 = im.shape[:2] # orig hw - return im, (h0, w0), im.shape[:2] - - return self.ims[i], self.im_hw0[i], self.im_hw[i] - - def build_transforms(self, hyp: IterableSimpleNamespace = None): - """Creates transforms for dataset images without resizing.""" - return Format( - bbox_format="xyxy", - normalize=False, - return_mask=self.use_segments, - return_keypoint=self.use_keypoints, - batch_idx=True, - mask_ratio=hyp.mask_ratio, - mask_overlap=hyp.overlap_mask, - ) - - -class Explorer: - def __init__( - self, - data: Union[str, Path] = "coco128.yaml", - model: str = "yolov8n.pt", - uri: str = USER_CONFIG_DIR / "explorer", - ) -> None: - # Note duckdb==0.10.0 bug https://github.com/ultralytics/ultralytics/pull/8181 - checks.check_requirements(["lancedb>=0.4.3", "duckdb<=0.9.2"]) - import lancedb - - self.connection = lancedb.connect(uri) - self.table_name = Path(data).name.lower() + "_" + model.lower() - self.sim_idx_base_name = ( - f"{self.table_name}_sim_idx".lower() - ) # Use this name and append thres and top_k to reuse the table - self.model = YOLO(model) - self.data = data # None - self.choice_set = None - - self.table = None - self.progress = 0 - - def create_embeddings_table(self, force: bool = False, split: str = "train") -> None: - """ - Create LanceDB table containing the embeddings of the images in the dataset. The table will be reused if it - already exists. Pass force=True to overwrite the existing table. - - Args: - force (bool): Whether to overwrite the existing table or not. Defaults to False. - split (str): Split of the dataset to use. Defaults to 'train'. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - ``` - """ - if self.table is not None and not force: - LOGGER.info("Table already exists. Reusing it. Pass force=True to overwrite it.") - return - if self.table_name in self.connection.table_names() and not force: - LOGGER.info(f"Table {self.table_name} already exists. Reusing it. Pass force=True to overwrite it.") - self.table = self.connection.open_table(self.table_name) - self.progress = 1 - return - if self.data is None: - raise ValueError("Data must be provided to create embeddings table") - - data_info = check_det_dataset(self.data) - if split not in data_info: - raise ValueError( - f"Split {split} is not found in the dataset. Available keys in the dataset are {list(data_info.keys())}" - ) - - choice_set = data_info[split] - choice_set = choice_set if isinstance(choice_set, list) else [choice_set] - self.choice_set = choice_set - dataset = ExplorerDataset(img_path=choice_set, data=data_info, augment=False, cache=False, task=self.model.task) - - # Create the table schema - batch = dataset[0] - vector_size = self.model.embed(batch["im_file"], verbose=False)[0].shape[0] - table = self.connection.create_table(self.table_name, schema=get_table_schema(vector_size), mode="overwrite") - table.add( - self._yield_batches( - dataset, - data_info, - self.model, - exclude_keys=["img", "ratio_pad", "resized_shape", "ori_shape", "batch_idx"], - ) - ) - - self.table = table - - def _yield_batches(self, dataset: ExplorerDataset, data_info: dict, model: YOLO, exclude_keys: List[str]): - """Generates batches of data for embedding, excluding specified keys.""" - for i in tqdm(range(len(dataset))): - self.progress = float(i + 1) / len(dataset) - batch = dataset[i] - for k in exclude_keys: - batch.pop(k, None) - batch = sanitize_batch(batch, data_info) - batch["vector"] = model.embed(batch["im_file"], verbose=False)[0].detach().tolist() - yield [batch] - - def query( - self, imgs: Union[str, np.ndarray, List[str], List[np.ndarray]] = None, limit: int = 25 - ) -> Any: # pyarrow.Table - """ - Query the table for similar images. Accepts a single image or a list of images. - - Args: - imgs (str or list): Path to the image or a list of paths to the images. - limit (int): Number of results to return. - - Returns: - (pyarrow.Table): An arrow table containing the results. Supports converting to: - - pandas dataframe: `result.to_pandas()` - - dict of lists: `result.to_pydict()` - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - similar = exp.query(img='https://ultralytics.com/images/zidane.jpg') - ``` - """ - if self.table is None: - raise ValueError("Table is not created. Please create the table first.") - if isinstance(imgs, str): - imgs = [imgs] - assert isinstance(imgs, list), f"img must be a string or a list of strings. Got {type(imgs)}" - embeds = self.model.embed(imgs) - # Get avg if multiple images are passed (len > 1) - embeds = torch.mean(torch.stack(embeds), 0).cpu().numpy() if len(embeds) > 1 else embeds[0].cpu().numpy() - return self.table.search(embeds).limit(limit).to_arrow() - - def sql_query( - self, query: str, return_type: str = "pandas" - ) -> Union[DataFrame, Any, None]: # pandas.dataframe or pyarrow.Table - """ - Run a SQL-Like query on the table. Utilizes LanceDB predicate pushdown. - - Args: - query (str): SQL query to run. - return_type (str): Type of the result to return. Can be either 'pandas' or 'arrow'. Defaults to 'pandas'. - - Returns: - (pyarrow.Table): An arrow table containing the results. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - query = "SELECT * FROM 'table' WHERE labels LIKE '%person%'" - result = exp.sql_query(query) - ``` - """ - assert return_type in { - "pandas", - "arrow", - }, f"Return type should be either `pandas` or `arrow`, but got {return_type}" - import duckdb - - if self.table is None: - raise ValueError("Table is not created. Please create the table first.") - - # Note: using filter pushdown would be a better long term solution. Temporarily using duckdb for this. - table = self.table.to_arrow() # noqa NOTE: Don't comment this. This line is used by DuckDB - if not query.startswith("SELECT") and not query.startswith("WHERE"): - raise ValueError( - f"Query must start with SELECT or WHERE. You can either pass the entire query or just the WHERE clause. found {query}" - ) - if query.startswith("WHERE"): - query = f"SELECT * FROM 'table' {query}" - LOGGER.info(f"Running query: {query}") - - rs = duckdb.sql(query) - if return_type == "arrow": - return rs.arrow() - elif return_type == "pandas": - return rs.df() - - def plot_sql_query(self, query: str, labels: bool = True) -> Image.Image: - """ - Plot the results of a SQL-Like query on the table. - Args: - query (str): SQL query to run. - labels (bool): Whether to plot the labels or not. - - Returns: - (PIL.Image): Image containing the plot. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - query = "SELECT * FROM 'table' WHERE labels LIKE '%person%'" - result = exp.plot_sql_query(query) - ``` - """ - result = self.sql_query(query, return_type="arrow") - if len(result) == 0: - LOGGER.info("No results found.") - return None - img = plot_query_result(result, plot_labels=labels) - return Image.fromarray(img) - - def get_similar( - self, - img: Union[str, np.ndarray, List[str], List[np.ndarray]] = None, - idx: Union[int, List[int]] = None, - limit: int = 25, - return_type: str = "pandas", - ) -> Union[DataFrame, Any]: # pandas.dataframe or pyarrow.Table - """ - Query the table for similar images. Accepts a single image or a list of images. - - Args: - img (str or list): Path to the image or a list of paths to the images. - idx (int or list): Index of the image in the table or a list of indexes. - limit (int): Number of results to return. Defaults to 25. - return_type (str): Type of the result to return. Can be either 'pandas' or 'arrow'. Defaults to 'pandas'. - - Returns: - (pandas.DataFrame): A dataframe containing the results. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - similar = exp.get_similar(img='https://ultralytics.com/images/zidane.jpg') - ``` - """ - assert return_type in { - "pandas", - "arrow", - }, f"Return type should be either `pandas` or `arrow`, but got {return_type}" - img = self._check_imgs_or_idxs(img, idx) - similar = self.query(img, limit=limit) - - if return_type == "arrow": - return similar - elif return_type == "pandas": - return similar.to_pandas() - - def plot_similar( - self, - img: Union[str, np.ndarray, List[str], List[np.ndarray]] = None, - idx: Union[int, List[int]] = None, - limit: int = 25, - labels: bool = True, - ) -> Image.Image: - """ - Plot the similar images. Accepts images or indexes. - - Args: - img (str or list): Path to the image or a list of paths to the images. - idx (int or list): Index of the image in the table or a list of indexes. - labels (bool): Whether to plot the labels or not. - limit (int): Number of results to return. Defaults to 25. - - Returns: - (PIL.Image): Image containing the plot. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - similar = exp.plot_similar(img='https://ultralytics.com/images/zidane.jpg') - ``` - """ - similar = self.get_similar(img, idx, limit, return_type="arrow") - if len(similar) == 0: - LOGGER.info("No results found.") - return None - img = plot_query_result(similar, plot_labels=labels) - return Image.fromarray(img) - - def similarity_index(self, max_dist: float = 0.2, top_k: float = None, force: bool = False) -> DataFrame: - """ - Calculate the similarity index of all the images in the table. Here, the index will contain the data points that - are max_dist or closer to the image in the embedding space at a given index. - - Args: - max_dist (float): maximum L2 distance between the embeddings to consider. Defaults to 0.2. - top_k (float): Percentage of the closest data points to consider when counting. Used to apply limit when running - vector search. Defaults: None. - force (bool): Whether to overwrite the existing similarity index or not. Defaults to True. - - Returns: - (pandas.DataFrame): A dataframe containing the similarity index. Each row corresponds to an image, and columns - include indices of similar images and their respective distances. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - sim_idx = exp.similarity_index() - ``` - """ - if self.table is None: - raise ValueError("Table is not created. Please create the table first.") - sim_idx_table_name = f"{self.sim_idx_base_name}_thres_{max_dist}_top_{top_k}".lower() - if sim_idx_table_name in self.connection.table_names() and not force: - LOGGER.info("Similarity matrix already exists. Reusing it. Pass force=True to overwrite it.") - return self.connection.open_table(sim_idx_table_name).to_pandas() - - if top_k and not (1.0 >= top_k >= 0.0): - raise ValueError(f"top_k must be between 0.0 and 1.0. Got {top_k}") - if max_dist < 0.0: - raise ValueError(f"max_dist must be greater than 0. Got {max_dist}") - - top_k = int(top_k * len(self.table)) if top_k else len(self.table) - top_k = max(top_k, 1) - features = self.table.to_lance().to_table(columns=["vector", "im_file"]).to_pydict() - im_files = features["im_file"] - embeddings = features["vector"] - - sim_table = self.connection.create_table(sim_idx_table_name, schema=get_sim_index_schema(), mode="overwrite") - - def _yield_sim_idx(): - """Generates a dataframe with similarity indices and distances for images.""" - for i in tqdm(range(len(embeddings))): - sim_idx = self.table.search(embeddings[i]).limit(top_k).to_pandas().query(f"_distance <= {max_dist}") - yield [ - { - "idx": i, - "im_file": im_files[i], - "count": len(sim_idx), - "sim_im_files": sim_idx["im_file"].tolist(), - } - ] - - sim_table.add(_yield_sim_idx()) - self.sim_index = sim_table - return sim_table.to_pandas() - - def plot_similarity_index(self, max_dist: float = 0.2, top_k: float = None, force: bool = False) -> Image: - """ - Plot the similarity index of all the images in the table. Here, the index will contain the data points that are - max_dist or closer to the image in the embedding space at a given index. - - Args: - max_dist (float): maximum L2 distance between the embeddings to consider. Defaults to 0.2. - top_k (float): Percentage of closest data points to consider when counting. Used to apply limit when - running vector search. Defaults to 0.01. - force (bool): Whether to overwrite the existing similarity index or not. Defaults to True. - - Returns: - (PIL.Image): Image containing the plot. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - - similarity_idx_plot = exp.plot_similarity_index() - similarity_idx_plot.show() # view image preview - similarity_idx_plot.save('path/to/save/similarity_index_plot.png') # save contents to file - ``` - """ - sim_idx = self.similarity_index(max_dist=max_dist, top_k=top_k, force=force) - sim_count = sim_idx["count"].tolist() - sim_count = np.array(sim_count) - - indices = np.arange(len(sim_count)) - - # Create the bar plot - plt.bar(indices, sim_count) - - # Customize the plot (optional) - plt.xlabel("data idx") - plt.ylabel("Count") - plt.title("Similarity Count") - buffer = BytesIO() - plt.savefig(buffer, format="png") - buffer.seek(0) - - # Use Pillow to open the image from the buffer - return Image.fromarray(np.array(Image.open(buffer))) - - def _check_imgs_or_idxs( - self, img: Union[str, np.ndarray, List[str], List[np.ndarray], None], idx: Union[None, int, List[int]] - ) -> List[np.ndarray]: - if img is None and idx is None: - raise ValueError("Either img or idx must be provided.") - if img is not None and idx is not None: - raise ValueError("Only one of img or idx must be provided.") - if idx is not None: - idx = idx if isinstance(idx, list) else [idx] - img = self.table.to_lance().take(idx, columns=["im_file"]).to_pydict()["im_file"] - - return img if isinstance(img, list) else [img] - - def ask_ai(self, query): - """ - Ask AI a question. - - Args: - query (str): Question to ask. - - Returns: - (pandas.DataFrame): A dataframe containing filtered results to the SQL query. - - Example: - ```python - exp = Explorer() - exp.create_embeddings_table() - answer = exp.ask_ai('Show images with 1 person and 2 dogs') - ``` - """ - result = prompt_sql_query(query) - try: - df = self.sql_query(result) - except Exception as e: - LOGGER.error("AI generated query is not valid. Please try again with a different prompt") - LOGGER.error(e) - return None - return df - - def visualize(self, result): - """ - Visualize the results of a query. TODO. - - Args: - result (pyarrow.Table): Table containing the results of a query. - """ - pass - - def generate_report(self, result): - """ - Generate a report of the dataset. - - TODO - """ - pass diff --git a/ultralytics-main/ultralytics/data/explorer/gui/__init__.py b/ultralytics-main/ultralytics/data/explorer/gui/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/data/explorer/gui/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/data/explorer/gui/dash.py b/ultralytics-main/ultralytics/data/explorer/gui/dash.py deleted file mode 100644 index b082d49..0000000 --- a/ultralytics-main/ultralytics/data/explorer/gui/dash.py +++ /dev/null @@ -1,268 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import time -from threading import Thread - -import pandas as pd - -from ultralytics import Explorer -from ultralytics.utils import ROOT, SETTINGS -from ultralytics.utils.checks import check_requirements - -check_requirements(("streamlit>=1.29.0", "streamlit-select>=0.3")) - -import streamlit as st -from streamlit_select import image_select - - -def _get_explorer(): - """Initializes and returns an instance of the Explorer class.""" - exp = Explorer(data=st.session_state.get("dataset"), model=st.session_state.get("model")) - thread = Thread( - target=exp.create_embeddings_table, kwargs={"force": st.session_state.get("force_recreate_embeddings")} - ) - thread.start() - progress_bar = st.progress(0, text="Creating embeddings table...") - while exp.progress < 1: - time.sleep(0.1) - progress_bar.progress(exp.progress, text=f"Progress: {exp.progress * 100}%") - thread.join() - st.session_state["explorer"] = exp - progress_bar.empty() - - -def init_explorer_form(): - """Initializes an Explorer instance and creates embeddings table with progress tracking.""" - datasets = ROOT / "cfg" / "datasets" - ds = [d.name for d in datasets.glob("*.yaml")] - models = [ - "yolov8n.pt", - "yolov8s.pt", - "yolov8m.pt", - "yolov8l.pt", - "yolov8x.pt", - "yolov8n-seg.pt", - "yolov8s-seg.pt", - "yolov8m-seg.pt", - "yolov8l-seg.pt", - "yolov8x-seg.pt", - "yolov8n-pose.pt", - "yolov8s-pose.pt", - "yolov8m-pose.pt", - "yolov8l-pose.pt", - "yolov8x-pose.pt", - ] - with st.form(key="explorer_init_form"): - col1, col2 = st.columns(2) - with col1: - st.selectbox("Select dataset", ds, key="dataset", index=ds.index("coco128.yaml")) - with col2: - st.selectbox("Select model", models, key="model") - st.checkbox("Force recreate embeddings", key="force_recreate_embeddings") - - st.form_submit_button("Explore", on_click=_get_explorer) - - -def query_form(): - """Sets up a form in Streamlit to initialize Explorer with dataset and model selection.""" - with st.form("query_form"): - col1, col2 = st.columns([0.8, 0.2]) - with col1: - st.text_input( - "Query", - "WHERE labels LIKE '%person%' AND labels LIKE '%dog%'", - label_visibility="collapsed", - key="query", - ) - with col2: - st.form_submit_button("Query", on_click=run_sql_query) - - -def ai_query_form(): - """Sets up a Streamlit form for user input to initialize Explorer with dataset and model selection.""" - with st.form("ai_query_form"): - col1, col2 = st.columns([0.8, 0.2]) - with col1: - st.text_input("Query", "Show images with 1 person and 1 dog", label_visibility="collapsed", key="ai_query") - with col2: - st.form_submit_button("Ask AI", on_click=run_ai_query) - - -def find_similar_imgs(imgs): - """Initializes a Streamlit form for AI-based image querying with custom input.""" - exp = st.session_state["explorer"] - similar = exp.get_similar(img=imgs, limit=st.session_state.get("limit"), return_type="arrow") - paths = similar.to_pydict()["im_file"] - st.session_state["imgs"] = paths - st.session_state["res"] = similar - - -def similarity_form(selected_imgs): - """Initializes a form for AI-based image querying with custom input in Streamlit.""" - st.write("Similarity Search") - with st.form("similarity_form"): - subcol1, subcol2 = st.columns([1, 1]) - with subcol1: - st.number_input( - "limit", min_value=None, max_value=None, value=25, label_visibility="collapsed", key="limit" - ) - - with subcol2: - disabled = not len(selected_imgs) - st.write("Selected: ", len(selected_imgs)) - st.form_submit_button( - "Search", - disabled=disabled, - on_click=find_similar_imgs, - args=(selected_imgs,), - ) - if disabled: - st.error("Select at least one image to search.") - - -# def persist_reset_form(): -# with st.form("persist_reset"): -# col1, col2 = st.columns([1, 1]) -# with col1: -# st.form_submit_button("Reset", on_click=reset) -# -# with col2: -# st.form_submit_button("Persist", on_click=update_state, args=("PERSISTING", True)) - - -def run_sql_query(): - """Executes an SQL query and returns the results.""" - st.session_state["error"] = None - query = st.session_state.get("query") - if query.rstrip().lstrip(): - exp = st.session_state["explorer"] - res = exp.sql_query(query, return_type="arrow") - st.session_state["imgs"] = res.to_pydict()["im_file"] - st.session_state["res"] = res - - -def run_ai_query(): - """Execute SQL query and update session state with query results.""" - if not SETTINGS["openai_api_key"]: - st.session_state["error"] = ( - 'OpenAI API key not found in settings. Please run yolo settings openai_api_key="..."' - ) - return - st.session_state["error"] = None - query = st.session_state.get("ai_query") - if query.rstrip().lstrip(): - exp = st.session_state["explorer"] - res = exp.ask_ai(query) - if not isinstance(res, pd.DataFrame) or res.empty: - st.session_state["error"] = "No results found using AI generated query. Try another query or rerun it." - return - st.session_state["imgs"] = res["im_file"].to_list() - st.session_state["res"] = res - - -def reset_explorer(): - """Resets the explorer to its initial state by clearing session variables.""" - st.session_state["explorer"] = None - st.session_state["imgs"] = None - st.session_state["error"] = None - - -def utralytics_explorer_docs_callback(): - """Resets the explorer to its initial state by clearing session variables.""" - with st.container(border=True): - st.image( - "https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Original.svg", - width=100, - ) - st.markdown( - "

This demo is built using Ultralytics Explorer API. Visit API docs to try examples & learn more

", - unsafe_allow_html=True, - help=None, - ) - st.link_button("Ultrlaytics Explorer API", "https://docs.ultralytics.com/datasets/explorer/") - - -def layout(): - """Resets explorer session variables and provides documentation with a link to API docs.""" - st.set_page_config(layout="wide", initial_sidebar_state="collapsed") - st.markdown("

Ultralytics Explorer Demo

", unsafe_allow_html=True) - - if st.session_state.get("explorer") is None: - init_explorer_form() - return - - st.button(":arrow_backward: Select Dataset", on_click=reset_explorer) - exp = st.session_state.get("explorer") - col1, col2 = st.columns([0.75, 0.25], gap="small") - imgs = [] - if st.session_state.get("error"): - st.error(st.session_state["error"]) - else: - if st.session_state.get("imgs"): - imgs = st.session_state.get("imgs") - else: - imgs = exp.table.to_lance().to_table(columns=["im_file"]).to_pydict()["im_file"] - st.session_state["res"] = exp.table.to_arrow() - total_imgs, selected_imgs = len(imgs), [] - with col1: - subcol1, subcol2, subcol3, subcol4, subcol5 = st.columns(5) - with subcol1: - st.write("Max Images Displayed:") - with subcol2: - num = st.number_input( - "Max Images Displayed", - min_value=0, - max_value=total_imgs, - value=min(500, total_imgs), - key="num_imgs_displayed", - label_visibility="collapsed", - ) - with subcol3: - st.write("Start Index:") - with subcol4: - start_idx = st.number_input( - "Start Index", - min_value=0, - max_value=total_imgs, - value=0, - key="start_index", - label_visibility="collapsed", - ) - with subcol5: - reset = st.button("Reset", use_container_width=False, key="reset") - if reset: - st.session_state["imgs"] = None - st.experimental_rerun() - - query_form() - ai_query_form() - if total_imgs: - labels, boxes, masks, kpts, classes = None, None, None, None, None - task = exp.model.task - if st.session_state.get("display_labels"): - labels = st.session_state.get("res").to_pydict()["labels"][start_idx : start_idx + num] - boxes = st.session_state.get("res").to_pydict()["bboxes"][start_idx : start_idx + num] - masks = st.session_state.get("res").to_pydict()["masks"][start_idx : start_idx + num] - kpts = st.session_state.get("res").to_pydict()["keypoints"][start_idx : start_idx + num] - classes = st.session_state.get("res").to_pydict()["cls"][start_idx : start_idx + num] - imgs_displayed = imgs[start_idx : start_idx + num] - selected_imgs = image_select( - f"Total samples: {total_imgs}", - images=imgs_displayed, - use_container_width=False, - # indices=[i for i in range(num)] if select_all else None, - labels=labels, - classes=classes, - bboxes=boxes, - masks=masks if task == "segment" else None, - kpts=kpts if task == "pose" else None, - ) - - with col2: - similarity_form(selected_imgs) - display_labels = st.checkbox("Labels", value=False, key="display_labels") - utralytics_explorer_docs_callback() - - -if __name__ == "__main__": - layout() diff --git a/ultralytics-main/ultralytics/data/explorer/utils.py b/ultralytics-main/ultralytics/data/explorer/utils.py deleted file mode 100644 index d1c4b9b..0000000 --- a/ultralytics-main/ultralytics/data/explorer/utils.py +++ /dev/null @@ -1,166 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import getpass -from typing import List - -import cv2 -import numpy as np -import pandas as pd - -from ultralytics.data.augment import LetterBox -from ultralytics.utils import LOGGER as logger -from ultralytics.utils import SETTINGS -from ultralytics.utils.checks import check_requirements -from ultralytics.utils.ops import xyxy2xywh -from ultralytics.utils.plotting import plot_images - - -def get_table_schema(vector_size): - """Extracts and returns the schema of a database table.""" - from lancedb.pydantic import LanceModel, Vector - - class Schema(LanceModel): - im_file: str - labels: List[str] - cls: List[int] - bboxes: List[List[float]] - masks: List[List[List[int]]] - keypoints: List[List[List[float]]] - vector: Vector(vector_size) - - return Schema - - -def get_sim_index_schema(): - """Returns a LanceModel schema for a database table with specified vector size.""" - from lancedb.pydantic import LanceModel - - class Schema(LanceModel): - idx: int - im_file: str - count: int - sim_im_files: List[str] - - return Schema - - -def sanitize_batch(batch, dataset_info): - """Sanitizes input batch for inference, ensuring correct format and dimensions.""" - batch["cls"] = batch["cls"].flatten().int().tolist() - box_cls_pair = sorted(zip(batch["bboxes"].tolist(), batch["cls"]), key=lambda x: x[1]) - batch["bboxes"] = [box for box, _ in box_cls_pair] - batch["cls"] = [cls for _, cls in box_cls_pair] - batch["labels"] = [dataset_info["names"][i] for i in batch["cls"]] - batch["masks"] = batch["masks"].tolist() if "masks" in batch else [[[]]] - batch["keypoints"] = batch["keypoints"].tolist() if "keypoints" in batch else [[[]]] - return batch - - -def plot_query_result(similar_set, plot_labels=True): - """ - Plot images from the similar set. - - Args: - similar_set (list): Pyarrow or pandas object containing the similar data points - plot_labels (bool): Whether to plot labels or not - """ - similar_set = ( - similar_set.to_dict(orient="list") if isinstance(similar_set, pd.DataFrame) else similar_set.to_pydict() - ) - empty_masks = [[[]]] - empty_boxes = [[]] - images = similar_set.get("im_file", []) - bboxes = similar_set.get("bboxes", []) if similar_set.get("bboxes") is not empty_boxes else [] - masks = similar_set.get("masks") if similar_set.get("masks")[0] != empty_masks else [] - kpts = similar_set.get("keypoints") if similar_set.get("keypoints")[0] != empty_masks else [] - cls = similar_set.get("cls", []) - - plot_size = 640 - imgs, batch_idx, plot_boxes, plot_masks, plot_kpts = [], [], [], [], [] - for i, imf in enumerate(images): - im = cv2.imread(imf) - im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB) - h, w = im.shape[:2] - r = min(plot_size / h, plot_size / w) - imgs.append(LetterBox(plot_size, center=False)(image=im).transpose(2, 0, 1)) - if plot_labels: - if len(bboxes) > i and len(bboxes[i]) > 0: - box = np.array(bboxes[i], dtype=np.float32) - box[:, [0, 2]] *= r - box[:, [1, 3]] *= r - plot_boxes.append(box) - if len(masks) > i and len(masks[i]) > 0: - mask = np.array(masks[i], dtype=np.uint8)[0] - plot_masks.append(LetterBox(plot_size, center=False)(image=mask)) - if len(kpts) > i and kpts[i] is not None: - kpt = np.array(kpts[i], dtype=np.float32) - kpt[:, :, :2] *= r - plot_kpts.append(kpt) - batch_idx.append(np.ones(len(np.array(bboxes[i], dtype=np.float32))) * i) - imgs = np.stack(imgs, axis=0) - masks = np.stack(plot_masks, axis=0) if plot_masks else np.zeros(0, dtype=np.uint8) - kpts = np.concatenate(plot_kpts, axis=0) if plot_kpts else np.zeros((0, 51), dtype=np.float32) - boxes = xyxy2xywh(np.concatenate(plot_boxes, axis=0)) if plot_boxes else np.zeros(0, dtype=np.float32) - batch_idx = np.concatenate(batch_idx, axis=0) - cls = np.concatenate([np.array(c, dtype=np.int32) for c in cls], axis=0) - - return plot_images( - imgs, batch_idx, cls, bboxes=boxes, masks=masks, kpts=kpts, max_subplots=len(images), save=False, threaded=False - ) - - -def prompt_sql_query(query): - """Plots images with optional labels from a similar data set.""" - check_requirements("openai>=1.6.1") - from openai import OpenAI - - if not SETTINGS["openai_api_key"]: - logger.warning("OpenAI API key not found in settings. Please enter your API key below.") - openai_api_key = getpass.getpass("OpenAI API key: ") - SETTINGS.update({"openai_api_key": openai_api_key}) - openai = OpenAI(api_key=SETTINGS["openai_api_key"]) - - messages = [ - { - "role": "system", - "content": """ - You are a helpful data scientist proficient in SQL. You need to output exactly one SQL query based on - the following schema and a user request. You only need to output the format with fixed selection - statement that selects everything from "'table'", like `SELECT * from 'table'` - - Schema: - im_file: string not null - labels: list not null - child 0, item: string - cls: list not null - child 0, item: int64 - bboxes: list> not null - child 0, item: list - child 0, item: double - masks: list>> not null - child 0, item: list> - child 0, item: list - child 0, item: int64 - keypoints: list>> not null - child 0, item: list> - child 0, item: list - child 0, item: double - vector: fixed_size_list[256] not null - child 0, item: float - - Some details about the schema: - - the "labels" column contains the string values like 'person' and 'dog' for the respective objects - in each image - - the "cls" column contains the integer values on these classes that map them the labels - - Example of a correct query: - request - Get all data points that contain 2 or more people and at least one dog - correct query- - SELECT * FROM 'table' WHERE ARRAY_LENGTH(cls) >= 2 AND ARRAY_LENGTH(FILTER(labels, x -> x = 'person')) >= 2 AND ARRAY_LENGTH(FILTER(labels, x -> x = 'dog')) >= 1; - """, - }, - {"role": "user", "content": f"{query}"}, - ] - - response = openai.chat.completions.create(model="gpt-3.5-turbo", messages=messages) - return response.choices[0].message.content diff --git a/ultralytics-main/ultralytics/data/loaders.py b/ultralytics-main/ultralytics/data/loaders.py deleted file mode 100644 index 4b89770..0000000 --- a/ultralytics-main/ultralytics/data/loaders.py +++ /dev/null @@ -1,555 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import glob -import math -import os -import time -from dataclasses import dataclass -from pathlib import Path -from threading import Thread -from urllib.parse import urlparse - -import cv2 -import numpy as np -import requests -import torch -from PIL import Image - -from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS -from ultralytics.utils import LOGGER, is_colab, is_kaggle, ops -from ultralytics.utils.checks import check_requirements - - -@dataclass -class SourceTypes: - """Class to represent various types of input sources for predictions.""" - - stream: bool = False - screenshot: bool = False - from_img: bool = False - tensor: bool = False - - -class LoadStreams: - """ - Stream Loader for various types of video streams, Supports RTSP, RTMP, HTTP, and TCP streams. - - Attributes: - sources (str): The source input paths or URLs for the video streams. - vid_stride (int): Video frame-rate stride, defaults to 1. - buffer (bool): Whether to buffer input streams, defaults to False. - running (bool): Flag to indicate if the streaming thread is running. - mode (str): Set to 'stream' indicating real-time capture. - imgs (list): List of image frames for each stream. - fps (list): List of FPS for each stream. - frames (list): List of total frames for each stream. - threads (list): List of threads for each stream. - shape (list): List of shapes for each stream. - caps (list): List of cv2.VideoCapture objects for each stream. - bs (int): Batch size for processing. - - Methods: - __init__: Initialize the stream loader. - update: Read stream frames in daemon thread. - close: Close stream loader and release resources. - __iter__: Returns an iterator object for the class. - __next__: Returns source paths, transformed, and original images for processing. - __len__: Return the length of the sources object. - - Example: - ```bash - yolo predict source='rtsp://example.com/media.mp4' - ``` - """ - - def __init__(self, sources="file.streams", vid_stride=1, buffer=False): - """Initialize instance variables and check for consistent input stream shapes.""" - torch.backends.cudnn.benchmark = True # faster for fixed-size inference - self.buffer = buffer # buffer input streams - self.running = True # running flag for Thread - self.mode = "stream" - self.vid_stride = vid_stride # video frame-rate stride - - sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources] - n = len(sources) - self.bs = n - self.fps = [0] * n # frames per second - self.frames = [0] * n - self.threads = [None] * n - self.caps = [None] * n # video capture objects - self.imgs = [[] for _ in range(n)] # images - self.shape = [[] for _ in range(n)] # image shapes - self.sources = [ops.clean_str(x) for x in sources] # clean source names for later - for i, s in enumerate(sources): # index, source - # Start thread to read frames from video stream - st = f"{i + 1}/{n}: {s}... " - if urlparse(s).hostname in ("www.youtube.com", "youtube.com", "youtu.be"): # if source is YouTube video - # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/LNwODJXcvt4' - s = get_best_youtube_url(s) - s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam - if s == 0 and (is_colab() or is_kaggle()): - raise NotImplementedError( - "'source=0' webcam not supported in Colab and Kaggle notebooks. " - "Try running 'source=0' in a local environment." - ) - self.caps[i] = cv2.VideoCapture(s) # store video capture object - if not self.caps[i].isOpened(): - raise ConnectionError(f"{st}Failed to open {s}") - w = int(self.caps[i].get(cv2.CAP_PROP_FRAME_WIDTH)) - h = int(self.caps[i].get(cv2.CAP_PROP_FRAME_HEIGHT)) - fps = self.caps[i].get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan - self.frames[i] = max(int(self.caps[i].get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float( - "inf" - ) # infinite stream fallback - self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback - - success, im = self.caps[i].read() # guarantee first frame - if not success or im is None: - raise ConnectionError(f"{st}Failed to read images from {s}") - self.imgs[i].append(im) - self.shape[i] = im.shape - self.threads[i] = Thread(target=self.update, args=([i, self.caps[i], s]), daemon=True) - LOGGER.info(f"{st}Success ✅ ({self.frames[i]} frames of shape {w}x{h} at {self.fps[i]:.2f} FPS)") - self.threads[i].start() - LOGGER.info("") # newline - - def update(self, i, cap, stream): - """Read stream `i` frames in daemon thread.""" - n, f = 0, self.frames[i] # frame number, frame array - while self.running and cap.isOpened() and n < (f - 1): - if len(self.imgs[i]) < 30: # keep a <=30-image buffer - n += 1 - cap.grab() # .read() = .grab() followed by .retrieve() - if n % self.vid_stride == 0: - success, im = cap.retrieve() - if not success: - im = np.zeros(self.shape[i], dtype=np.uint8) - LOGGER.warning("WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.") - cap.open(stream) # re-open stream if signal was lost - if self.buffer: - self.imgs[i].append(im) - else: - self.imgs[i] = [im] - else: - time.sleep(0.01) # wait until the buffer is empty - - def close(self): - """Close stream loader and release resources.""" - self.running = False # stop flag for Thread - for thread in self.threads: - if thread.is_alive(): - thread.join(timeout=5) # Add timeout - for cap in self.caps: # Iterate through the stored VideoCapture objects - try: - cap.release() # release video capture - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ Could not release VideoCapture object: {e}") - cv2.destroyAllWindows() - - def __iter__(self): - """Iterates through YOLO image feed and re-opens unresponsive streams.""" - self.count = -1 - return self - - def __next__(self): - """Returns source paths, transformed and original images for processing.""" - self.count += 1 - - images = [] - for i, x in enumerate(self.imgs): - # Wait until a frame is available in each buffer - while not x: - if not self.threads[i].is_alive() or cv2.waitKey(1) == ord("q"): # q to quit - self.close() - raise StopIteration - time.sleep(1 / min(self.fps)) - x = self.imgs[i] - if not x: - LOGGER.warning(f"WARNING ⚠️ Waiting for stream {i}") - - # Get and remove the first frame from imgs buffer - if self.buffer: - images.append(x.pop(0)) - - # Get the last frame, and clear the rest from the imgs buffer - else: - images.append(x.pop(-1) if x else np.zeros(self.shape[i], dtype=np.uint8)) - x.clear() - - return self.sources, images, [""] * self.bs - - def __len__(self): - """Return the length of the sources object.""" - return self.bs # 1E12 frames = 32 streams at 30 FPS for 30 years - - -class LoadScreenshots: - """ - YOLOv8 screenshot dataloader. - - This class manages the loading of screenshot images for processing with YOLOv8. - Suitable for use with `yolo predict source=screen`. - - Attributes: - source (str): The source input indicating which screen to capture. - screen (int): The screen number to capture. - left (int): The left coordinate for screen capture area. - top (int): The top coordinate for screen capture area. - width (int): The width of the screen capture area. - height (int): The height of the screen capture area. - mode (str): Set to 'stream' indicating real-time capture. - frame (int): Counter for captured frames. - sct (mss.mss): Screen capture object from `mss` library. - bs (int): Batch size, set to 1. - monitor (dict): Monitor configuration details. - - Methods: - __iter__: Returns an iterator object. - __next__: Captures the next screenshot and returns it. - """ - - def __init__(self, source): - """Source = [screen_number left top width height] (pixels).""" - check_requirements("mss") - import mss # noqa - - source, *params = source.split() - self.screen, left, top, width, height = 0, None, None, None, None # default to full screen 0 - if len(params) == 1: - self.screen = int(params[0]) - elif len(params) == 4: - left, top, width, height = (int(x) for x in params) - elif len(params) == 5: - self.screen, left, top, width, height = (int(x) for x in params) - self.mode = "stream" - self.frame = 0 - self.sct = mss.mss() - self.bs = 1 - self.fps = 30 - - # Parse monitor shape - monitor = self.sct.monitors[self.screen] - self.top = monitor["top"] if top is None else (monitor["top"] + top) - self.left = monitor["left"] if left is None else (monitor["left"] + left) - self.width = width or monitor["width"] - self.height = height or monitor["height"] - self.monitor = {"left": self.left, "top": self.top, "width": self.width, "height": self.height} - - def __iter__(self): - """Returns an iterator of the object.""" - return self - - def __next__(self): - """mss screen capture: get raw pixels from the screen as np array.""" - im0 = np.asarray(self.sct.grab(self.monitor))[:, :, :3] # BGRA to BGR - s = f"screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: " - - self.frame += 1 - return [str(self.screen)], [im0], [s] # screen, img, string - - -class LoadImagesAndVideos: - """ - YOLOv8 image/video dataloader. - - This class manages the loading and pre-processing of image and video data for YOLOv8. It supports loading from - various formats, including single image files, video files, and lists of image and video paths. - - Attributes: - files (list): List of image and video file paths. - nf (int): Total number of files (images and videos). - video_flag (list): Flags indicating whether a file is a video (True) or an image (False). - mode (str): Current mode, 'image' or 'video'. - vid_stride (int): Stride for video frame-rate, defaults to 1. - bs (int): Batch size, set to 1 for this class. - cap (cv2.VideoCapture): Video capture object for OpenCV. - frame (int): Frame counter for video. - frames (int): Total number of frames in the video. - count (int): Counter for iteration, initialized at 0 during `__iter__()`. - - Methods: - _new_video(path): Create a new cv2.VideoCapture object for a given video path. - """ - - def __init__(self, path, batch=1, vid_stride=1): - """Initialize the Dataloader and raise FileNotFoundError if file not found.""" - parent = None - if isinstance(path, str) and Path(path).suffix == ".txt": # *.txt file with img/vid/dir on each line - parent = Path(path).parent - path = Path(path).read_text().splitlines() # list of sources - files = [] - for p in sorted(path) if isinstance(path, (list, tuple)) else [path]: - a = str(Path(p).absolute()) # do not use .resolve() https://github.com/ultralytics/ultralytics/issues/2912 - if "*" in a: - files.extend(sorted(glob.glob(a, recursive=True))) # glob - elif os.path.isdir(a): - files.extend(sorted(glob.glob(os.path.join(a, "*.*")))) # dir - elif os.path.isfile(a): - files.append(a) # files (absolute or relative to CWD) - elif parent and (parent / p).is_file(): - files.append(str((parent / p).absolute())) # files (relative to *.txt file parent) - else: - raise FileNotFoundError(f"{p} does not exist") - - images = [x for x in files if x.split(".")[-1].lower() in IMG_FORMATS] - videos = [x for x in files if x.split(".")[-1].lower() in VID_FORMATS] - ni, nv = len(images), len(videos) - - self.files = images + videos - self.nf = ni + nv # number of files - self.ni = ni # number of images - self.video_flag = [False] * ni + [True] * nv - self.mode = "image" - self.vid_stride = vid_stride # video frame-rate stride - self.bs = batch - if any(videos): - self._new_video(videos[0]) # new video - else: - self.cap = None - if self.nf == 0: - raise FileNotFoundError( - f"No images or videos found in {p}. " - f"Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}" - ) - - def __iter__(self): - """Returns an iterator object for VideoStream or ImageFolder.""" - self.count = 0 - return self - - def __next__(self): - """Returns the next batch of images or video frames along with their paths and metadata.""" - paths, imgs, info = [], [], [] - while len(imgs) < self.bs: - if self.count >= self.nf: # end of file list - if len(imgs) > 0: - return paths, imgs, info # return last partial batch - else: - raise StopIteration - - path = self.files[self.count] - if self.video_flag[self.count]: - self.mode = "video" - if not self.cap or not self.cap.isOpened(): - self._new_video(path) - - for _ in range(self.vid_stride): - success = self.cap.grab() - if not success: - break # end of video or failure - - if success: - success, im0 = self.cap.retrieve() - if success: - self.frame += 1 - paths.append(path) - imgs.append(im0) - info.append(f"video {self.count + 1}/{self.nf} (frame {self.frame}/{self.frames}) {path}: ") - if self.frame == self.frames: # end of video - self.count += 1 - self.cap.release() - else: - # Move to the next file if the current video ended or failed to open - self.count += 1 - if self.cap: - self.cap.release() - if self.count < self.nf: - self._new_video(self.files[self.count]) - else: - self.mode = "image" - im0 = cv2.imread(path) # BGR - if im0 is None: - raise FileNotFoundError(f"Image Not Found {path}") - paths.append(path) - imgs.append(im0) - info.append(f"image {self.count + 1}/{self.nf} {path}: ") - self.count += 1 # move to the next file - if self.count >= self.ni: # end of image list - break - - return paths, imgs, info - - def _new_video(self, path): - """Creates a new video capture object for the given path.""" - self.frame = 0 - self.cap = cv2.VideoCapture(path) - self.fps = int(self.cap.get(cv2.CAP_PROP_FPS)) - if not self.cap.isOpened(): - raise FileNotFoundError(f"Failed to open video {path}") - self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride) - - def __len__(self): - """Returns the number of batches in the object.""" - return math.ceil(self.nf / self.bs) # number of files - - -class LoadPilAndNumpy: - """ - Load images from PIL and Numpy arrays for batch processing. - - This class is designed to manage loading and pre-processing of image data from both PIL and Numpy formats. - It performs basic validation and format conversion to ensure that the images are in the required format for - downstream processing. - - Attributes: - paths (list): List of image paths or autogenerated filenames. - im0 (list): List of images stored as Numpy arrays. - mode (str): Type of data being processed, defaults to 'image'. - bs (int): Batch size, equivalent to the length of `im0`. - - Methods: - _single_check(im): Validate and format a single image to a Numpy array. - """ - - def __init__(self, im0): - """Initialize PIL and Numpy Dataloader.""" - if not isinstance(im0, list): - im0 = [im0] - self.paths = [getattr(im, "filename", f"image{i}.jpg") for i, im in enumerate(im0)] - self.im0 = [self._single_check(im) for im in im0] - self.mode = "image" - self.bs = len(self.im0) - - @staticmethod - def _single_check(im): - """Validate and format an image to numpy array.""" - assert isinstance(im, (Image.Image, np.ndarray)), f"Expected PIL/np.ndarray image type, but got {type(im)}" - if isinstance(im, Image.Image): - if im.mode != "RGB": - im = im.convert("RGB") - im = np.asarray(im)[:, :, ::-1] - im = np.ascontiguousarray(im) # contiguous - return im - - def __len__(self): - """Returns the length of the 'im0' attribute.""" - return len(self.im0) - - def __next__(self): - """Returns batch paths, images, processed images, None, ''.""" - if self.count == 1: # loop only once as it's batch inference - raise StopIteration - self.count += 1 - return self.paths, self.im0, [""] * self.bs - - def __iter__(self): - """Enables iteration for class LoadPilAndNumpy.""" - self.count = 0 - return self - - -class LoadTensor: - """ - Load images from torch.Tensor data. - - This class manages the loading and pre-processing of image data from PyTorch tensors for further processing. - - Attributes: - im0 (torch.Tensor): The input tensor containing the image(s). - bs (int): Batch size, inferred from the shape of `im0`. - mode (str): Current mode, set to 'image'. - paths (list): List of image paths or filenames. - count (int): Counter for iteration, initialized at 0 during `__iter__()`. - - Methods: - _single_check(im, stride): Validate and possibly modify the input tensor. - """ - - def __init__(self, im0) -> None: - """Initialize Tensor Dataloader.""" - self.im0 = self._single_check(im0) - self.bs = self.im0.shape[0] - self.mode = "image" - self.paths = [getattr(im, "filename", f"image{i}.jpg") for i, im in enumerate(im0)] - - @staticmethod - def _single_check(im, stride=32): - """Validate and format an image to torch.Tensor.""" - s = ( - f"WARNING ⚠️ torch.Tensor inputs should be BCHW i.e. shape(1, 3, 640, 640) " - f"divisible by stride {stride}. Input shape{tuple(im.shape)} is incompatible." - ) - if len(im.shape) != 4: - if len(im.shape) != 3: - raise ValueError(s) - LOGGER.warning(s) - im = im.unsqueeze(0) - if im.shape[2] % stride or im.shape[3] % stride: - raise ValueError(s) - if im.max() > 1.0 + torch.finfo(im.dtype).eps: # torch.float32 eps is 1.2e-07 - LOGGER.warning( - f"WARNING ⚠️ torch.Tensor inputs should be normalized 0.0-1.0 but max value is {im.max()}. " - f"Dividing input by 255." - ) - im = im.float() / 255.0 - - return im - - def __iter__(self): - """Returns an iterator object.""" - self.count = 0 - return self - - def __next__(self): - """Return next item in the iterator.""" - if self.count == 1: - raise StopIteration - self.count += 1 - return self.paths, self.im0, [""] * self.bs - - def __len__(self): - """Returns the batch size.""" - return self.bs - - -def autocast_list(source): - """Merges a list of source of different types into a list of numpy arrays or PIL images.""" - files = [] - for im in source: - if isinstance(im, (str, Path)): # filename or uri - files.append(Image.open(requests.get(im, stream=True).raw if str(im).startswith("http") else im)) - elif isinstance(im, (Image.Image, np.ndarray)): # PIL or np Image - files.append(im) - else: - raise TypeError( - f"type {type(im).__name__} is not a supported Ultralytics prediction source type. \n" - f"See https://docs.ultralytics.com/modes/predict for supported source types." - ) - - return files - - -def get_best_youtube_url(url, use_pafy=True): - """ - Retrieves the URL of the best quality MP4 video stream from a given YouTube video. - - This function uses the pafy or yt_dlp library to extract the video info from YouTube. It then finds the highest - quality MP4 format that has video codec but no audio codec, and returns the URL of this video stream. - - Args: - url (str): The URL of the YouTube video. - use_pafy (bool): Use the pafy package, default=True, otherwise use yt_dlp package. - - Returns: - (str): The URL of the best quality MP4 video stream, or None if no suitable stream is found. - """ - if use_pafy: - check_requirements(("pafy", "youtube_dl==2020.12.2")) - import pafy # noqa - - return pafy.new(url).getbestvideo(preftype="mp4").url - else: - check_requirements("yt-dlp") - import yt_dlp - - with yt_dlp.YoutubeDL({"quiet": True}) as ydl: - info_dict = ydl.extract_info(url, download=False) # extract info - for f in reversed(info_dict.get("formats", [])): # reversed because best is usually last - # Find a format with video codec, no audio, *.mp4 extension at least 1920x1080 size - good_size = (f.get("width") or 0) >= 1920 or (f.get("height") or 0) >= 1080 - if good_size and f["vcodec"] != "none" and f["acodec"] == "none" and f["ext"] == "mp4": - return f.get("url") - - -# Define constants -LOADERS = (LoadStreams, LoadPilAndNumpy, LoadImagesAndVideos, LoadScreenshots) diff --git a/ultralytics-main/ultralytics/data/scripts/download_weights.sh b/ultralytics-main/ultralytics/data/scripts/download_weights.sh deleted file mode 100644 index 87db31f..0000000 --- a/ultralytics-main/ultralytics/data/scripts/download_weights.sh +++ /dev/null @@ -1,18 +0,0 @@ -#!/bin/bash -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Download latest models from https://github.com/ultralytics/assets/releases -# Example usage: bash ultralytics/data/scripts/download_weights.sh -# parent -# └── weights -# ├── yolov8n.pt ← downloads here -# ├── yolov8s.pt -# └── ... - -python - < gap, f"invalid crop_size gap pair [{crop_size} {gap}]" - step = crop_size - gap - - xn = 1 if w <= crop_size else ceil((w - crop_size) / step + 1) - xs = [step * i for i in range(xn)] - if len(xs) > 1 and xs[-1] + crop_size > w: - xs[-1] = w - crop_size - - yn = 1 if h <= crop_size else ceil((h - crop_size) / step + 1) - ys = [step * i for i in range(yn)] - if len(ys) > 1 and ys[-1] + crop_size > h: - ys[-1] = h - crop_size - - start = np.array(list(itertools.product(xs, ys)), dtype=np.int64) - stop = start + crop_size - windows.append(np.concatenate([start, stop], axis=1)) - windows = np.concatenate(windows, axis=0) - - im_in_wins = windows.copy() - im_in_wins[:, 0::2] = np.clip(im_in_wins[:, 0::2], 0, w) - im_in_wins[:, 1::2] = np.clip(im_in_wins[:, 1::2], 0, h) - im_areas = (im_in_wins[:, 2] - im_in_wins[:, 0]) * (im_in_wins[:, 3] - im_in_wins[:, 1]) - win_areas = (windows[:, 2] - windows[:, 0]) * (windows[:, 3] - windows[:, 1]) - im_rates = im_areas / win_areas - if not (im_rates > im_rate_thr).any(): - max_rate = im_rates.max() - im_rates[abs(im_rates - max_rate) < eps] = 1 - return windows[im_rates > im_rate_thr] - - -def get_window_obj(anno, windows, iof_thr=0.7): - """Get objects for each window.""" - h, w = anno["ori_size"] - label = anno["label"] - if len(label): - label[:, 1::2] *= w - label[:, 2::2] *= h - iofs = bbox_iof(label[:, 1:], windows) - # Unnormalized and misaligned coordinates - return [(label[iofs[:, i] >= iof_thr]) for i in range(len(windows))] # window_anns - else: - return [np.zeros((0, 9), dtype=np.float32) for _ in range(len(windows))] # window_anns - - -def crop_and_save(anno, windows, window_objs, im_dir, lb_dir): - """ - Crop images and save new labels. - - Args: - anno (dict): Annotation dict, including `filepath`, `label`, `ori_size` as its keys. - windows (list): A list of windows coordinates. - window_objs (list): A list of labels inside each window. - im_dir (str): The output directory path of images. - lb_dir (str): The output directory path of labels. - - Notes: - The directory structure assumed for the DOTA dataset: - - data_root - - images - - train - - val - - labels - - train - - val - """ - im = cv2.imread(anno["filepath"]) - name = Path(anno["filepath"]).stem - for i, window in enumerate(windows): - x_start, y_start, x_stop, y_stop = window.tolist() - new_name = f"{name}__{x_stop - x_start}__{x_start}___{y_start}" - patch_im = im[y_start:y_stop, x_start:x_stop] - ph, pw = patch_im.shape[:2] - - cv2.imwrite(str(Path(im_dir) / f"{new_name}.jpg"), patch_im) - label = window_objs[i] - if len(label) == 0: - continue - label[:, 1::2] -= x_start - label[:, 2::2] -= y_start - label[:, 1::2] /= pw - label[:, 2::2] /= ph - - with open(Path(lb_dir) / f"{new_name}.txt", "w") as f: - for lb in label: - formatted_coords = ["{:.6g}".format(coord) for coord in lb[1:]] - f.write(f"{int(lb[0])} {' '.join(formatted_coords)}\n") - - -def split_images_and_labels(data_root, save_dir, split="train", crop_sizes=[1024], gaps=[200]): - """ - Split both images and labels. - - Notes: - The directory structure assumed for the DOTA dataset: - - data_root - - images - - split - - labels - - split - and the output directory structure is: - - save_dir - - images - - split - - labels - - split - """ - im_dir = Path(save_dir) / "images" / split - im_dir.mkdir(parents=True, exist_ok=True) - lb_dir = Path(save_dir) / "labels" / split - lb_dir.mkdir(parents=True, exist_ok=True) - - annos = load_yolo_dota(data_root, split=split) - for anno in tqdm(annos, total=len(annos), desc=split): - windows = get_windows(anno["ori_size"], crop_sizes, gaps) - window_objs = get_window_obj(anno, windows) - crop_and_save(anno, windows, window_objs, str(im_dir), str(lb_dir)) - - -def split_trainval(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]): - """ - Split train and val set of DOTA. - - Notes: - The directory structure assumed for the DOTA dataset: - - data_root - - images - - train - - val - - labels - - train - - val - and the output directory structure is: - - save_dir - - images - - train - - val - - labels - - train - - val - """ - crop_sizes, gaps = [], [] - for r in rates: - crop_sizes.append(int(crop_size / r)) - gaps.append(int(gap / r)) - for split in ["train", "val"]: - split_images_and_labels(data_root, save_dir, split, crop_sizes, gaps) - - -def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]): - """ - Split test set of DOTA, labels are not included within this set. - - Notes: - The directory structure assumed for the DOTA dataset: - - data_root - - images - - test - and the output directory structure is: - - save_dir - - images - - test - """ - crop_sizes, gaps = [], [] - for r in rates: - crop_sizes.append(int(crop_size / r)) - gaps.append(int(gap / r)) - save_dir = Path(save_dir) / "images" / "test" - save_dir.mkdir(parents=True, exist_ok=True) - - im_dir = Path(data_root) / "images" / "test" - assert im_dir.exists(), f"Can't find {im_dir}, please check your data root." - im_files = glob(str(im_dir / "*")) - for im_file in tqdm(im_files, total=len(im_files), desc="test"): - w, h = exif_size(Image.open(im_file)) - windows = get_windows((h, w), crop_sizes=crop_sizes, gaps=gaps) - im = cv2.imread(im_file) - name = Path(im_file).stem - for window in windows: - x_start, y_start, x_stop, y_stop = window.tolist() - new_name = f"{name}__{x_stop - x_start}__{x_start}___{y_start}" - patch_im = im[y_start:y_stop, x_start:x_stop] - cv2.imwrite(str(save_dir / f"{new_name}.jpg"), patch_im) - - -if __name__ == "__main__": - split_trainval(data_root="DOTAv2", save_dir="DOTAv2-split") - split_test(data_root="DOTAv2", save_dir="DOTAv2-split") diff --git a/ultralytics-main/ultralytics/data/utils.py b/ultralytics-main/ultralytics/data/utils.py deleted file mode 100644 index 1ce8127..0000000 --- a/ultralytics-main/ultralytics/data/utils.py +++ /dev/null @@ -1,651 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import hashlib -import json -import os -import random -import subprocess -import time -import zipfile -from multiprocessing.pool import ThreadPool -from pathlib import Path -from tarfile import is_tarfile - -import cv2 -import numpy as np -from PIL import Image, ImageOps - -from ultralytics.nn.autobackend import check_class_names -from ultralytics.utils import ( - DATASETS_DIR, - LOGGER, - NUM_THREADS, - ROOT, - SETTINGS_YAML, - TQDM, - clean_url, - colorstr, - emojis, - yaml_load, - yaml_save, -) -from ultralytics.utils.checks import check_file, check_font, is_ascii -from ultralytics.utils.downloads import download, safe_download, unzip_file -from ultralytics.utils.ops import segments2boxes - -HELP_URL = "See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance." -IMG_FORMATS = "bmp", "dng", "jpeg", "jpg", "mpo", "png", "tif", "tiff", "webp", "pfm" # image suffixes -VID_FORMATS = "asf", "avi", "gif", "m4v", "mkv", "mov", "mp4", "mpeg", "mpg", "ts", "wmv", "webm" # video suffixes -PIN_MEMORY = str(os.getenv("PIN_MEMORY", True)).lower() == "true" # global pin_memory for dataloaders - - -def img2label_paths(img_paths): - """Define label paths as a function of image paths.""" - sa, sb = f"{os.sep}images{os.sep}", f"{os.sep}labels{os.sep}" # /images/, /labels/ substrings - return [sb.join(x.rsplit(sa, 1)).rsplit(".", 1)[0] + ".txt" for x in img_paths] - - -def get_hash(paths): - """Returns a single hash value of a list of paths (files or dirs).""" - size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes - h = hashlib.sha256(str(size).encode()) # hash sizes - h.update("".join(paths).encode()) # hash paths - return h.hexdigest() # return hash - - -def exif_size(img: Image.Image): - """Returns exif-corrected PIL size.""" - s = img.size # (width, height) - if img.format == "JPEG": # only support JPEG images - with contextlib.suppress(Exception): - exif = img.getexif() - if exif: - rotation = exif.get(274, None) # the EXIF key for the orientation tag is 274 - if rotation in [6, 8]: # rotation 270 or 90 - s = s[1], s[0] - return s - - -def verify_image(args): - """Verify one image.""" - (im_file, cls), prefix = args - # Number (found, corrupt), message - nf, nc, msg = 0, 0, "" - try: - im = Image.open(im_file) - im.verify() # PIL verify - shape = exif_size(im) # image size - shape = (shape[1], shape[0]) # hw - assert (shape[0] > 9) & (shape[1] > 9), f"image size {shape} <10 pixels" - assert im.format.lower() in IMG_FORMATS, f"invalid image format {im.format}" - if im.format.lower() in ("jpg", "jpeg"): - with open(im_file, "rb") as f: - f.seek(-2, 2) - if f.read() != b"\xff\xd9": # corrupt JPEG - ImageOps.exif_transpose(Image.open(im_file)).save(im_file, "JPEG", subsampling=0, quality=100) - msg = f"{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved" - nf = 1 - except Exception as e: - nc = 1 - msg = f"{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}" - return (im_file, cls), nf, nc, msg - - -def verify_image_label(args): - """Verify one image-label pair.""" - im_file, lb_file, prefix, keypoint, num_cls, nkpt, ndim = args - # Number (missing, found, empty, corrupt), message, segments, keypoints - nm, nf, ne, nc, msg, segments, keypoints = 0, 0, 0, 0, "", [], None - try: - # Verify images - im = Image.open(im_file) - im.verify() # PIL verify - shape = exif_size(im) # image size - shape = (shape[1], shape[0]) # hw - assert (shape[0] > 9) & (shape[1] > 9), f"image size {shape} <10 pixels" - assert im.format.lower() in IMG_FORMATS, f"invalid image format {im.format}" - if im.format.lower() in ("jpg", "jpeg"): - with open(im_file, "rb") as f: - f.seek(-2, 2) - if f.read() != b"\xff\xd9": # corrupt JPEG - ImageOps.exif_transpose(Image.open(im_file)).save(im_file, "JPEG", subsampling=0, quality=100) - msg = f"{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved" - - # Verify labels - if os.path.isfile(lb_file): - nf = 1 # label found - with open(lb_file) as f: - lb = [x.split() for x in f.read().strip().splitlines() if len(x)] - if any(len(x) > 6 for x in lb) and (not keypoint): # is segment - classes = np.array([x[0] for x in lb], dtype=np.float32) - segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb] # (cls, xy1...) - lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh) - lb = np.array(lb, dtype=np.float32) - nl = len(lb) - if nl: - if keypoint: - assert lb.shape[1] == (5 + nkpt * ndim), f"labels require {(5 + nkpt * ndim)} columns each" - points = lb[:, 5:].reshape(-1, ndim)[:, :2] - else: - assert lb.shape[1] == 5, f"labels require 5 columns, {lb.shape[1]} columns detected" - points = lb[:, 1:] - assert points.max() <= 1, f"non-normalized or out of bounds coordinates {points[points > 1]}" - assert lb.min() >= 0, f"negative label values {lb[lb < 0]}" - - # All labels - max_cls = lb[:, 0].max() # max label count - assert max_cls <= num_cls, ( - f"Label class {int(max_cls)} exceeds dataset class count {num_cls}. " - f"Possible class labels are 0-{num_cls - 1}" - ) - _, i = np.unique(lb, axis=0, return_index=True) - if len(i) < nl: # duplicate row check - lb = lb[i] # remove duplicates - if segments: - segments = [segments[x] for x in i] - msg = f"{prefix}WARNING ⚠️ {im_file}: {nl - len(i)} duplicate labels removed" - else: - ne = 1 # label empty - lb = np.zeros((0, (5 + nkpt * ndim) if keypoint else 5), dtype=np.float32) - else: - nm = 1 # label missing - lb = np.zeros((0, (5 + nkpt * ndim) if keypoints else 5), dtype=np.float32) - if keypoint: - keypoints = lb[:, 5:].reshape(-1, nkpt, ndim) - if ndim == 2: - kpt_mask = np.where((keypoints[..., 0] < 0) | (keypoints[..., 1] < 0), 0.0, 1.0).astype(np.float32) - keypoints = np.concatenate([keypoints, kpt_mask[..., None]], axis=-1) # (nl, nkpt, 3) - lb = lb[:, :5] - return im_file, lb, shape, segments, keypoints, nm, nf, ne, nc, msg - except Exception as e: - nc = 1 - msg = f"{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}" - return [None, None, None, None, None, nm, nf, ne, nc, msg] - - -def polygon2mask(imgsz, polygons, color=1, downsample_ratio=1): - """ - Convert a list of polygons to a binary mask of the specified image size. - - Args: - imgsz (tuple): The size of the image as (height, width). - polygons (list[np.ndarray]): A list of polygons. Each polygon is an array with shape [N, M], where - N is the number of polygons, and M is the number of points such that M % 2 = 0. - color (int, optional): The color value to fill in the polygons on the mask. Defaults to 1. - downsample_ratio (int, optional): Factor by which to downsample the mask. Defaults to 1. - - Returns: - (np.ndarray): A binary mask of the specified image size with the polygons filled in. - """ - mask = np.zeros(imgsz, dtype=np.uint8) - polygons = np.asarray(polygons, dtype=np.int32) - polygons = polygons.reshape((polygons.shape[0], -1, 2)) - cv2.fillPoly(mask, polygons, color=color) - nh, nw = (imgsz[0] // downsample_ratio, imgsz[1] // downsample_ratio) - # Note: fillPoly first then resize is trying to keep the same loss calculation method when mask-ratio=1 - return cv2.resize(mask, (nw, nh)) - - -def polygons2masks(imgsz, polygons, color, downsample_ratio=1): - """ - Convert a list of polygons to a set of binary masks of the specified image size. - - Args: - imgsz (tuple): The size of the image as (height, width). - polygons (list[np.ndarray]): A list of polygons. Each polygon is an array with shape [N, M], where - N is the number of polygons, and M is the number of points such that M % 2 = 0. - color (int): The color value to fill in the polygons on the masks. - downsample_ratio (int, optional): Factor by which to downsample each mask. Defaults to 1. - - Returns: - (np.ndarray): A set of binary masks of the specified image size with the polygons filled in. - """ - return np.array([polygon2mask(imgsz, [x.reshape(-1)], color, downsample_ratio) for x in polygons]) - - -def polygons2masks_overlap(imgsz, segments, downsample_ratio=1): - """Return a (640, 640) overlap mask.""" - masks = np.zeros( - (imgsz[0] // downsample_ratio, imgsz[1] // downsample_ratio), - dtype=np.int32 if len(segments) > 255 else np.uint8, - ) - areas = [] - ms = [] - for si in range(len(segments)): - mask = polygon2mask(imgsz, [segments[si].reshape(-1)], downsample_ratio=downsample_ratio, color=1) - ms.append(mask) - areas.append(mask.sum()) - areas = np.asarray(areas) - index = np.argsort(-areas) - ms = np.array(ms)[index] - for i in range(len(segments)): - mask = ms[i] * (i + 1) - masks = masks + mask - masks = np.clip(masks, a_min=0, a_max=i + 1) - return masks, index - - -def find_dataset_yaml(path: Path) -> Path: - """ - Find and return the YAML file associated with a Detect, Segment or Pose dataset. - - This function searches for a YAML file at the root level of the provided directory first, and if not found, it - performs a recursive search. It prefers YAML files that have the same stem as the provided path. An AssertionError - is raised if no YAML file is found or if multiple YAML files are found. - - Args: - path (Path): The directory path to search for the YAML file. - - Returns: - (Path): The path of the found YAML file. - """ - files = list(path.glob("*.yaml")) or list(path.rglob("*.yaml")) # try root level first and then recursive - assert files, f"No YAML file found in '{path.resolve()}'" - if len(files) > 1: - files = [f for f in files if f.stem == path.stem] # prefer *.yaml files that match - assert len(files) == 1, f"Expected 1 YAML file in '{path.resolve()}', but found {len(files)}.\n{files}" - return files[0] - - -def check_det_dataset(dataset, autodownload=True): - """ - Download, verify, and/or unzip a dataset if not found locally. - - This function checks the availability of a specified dataset, and if not found, it has the option to download and - unzip the dataset. It then reads and parses the accompanying YAML data, ensuring key requirements are met and also - resolves paths related to the dataset. - - Args: - dataset (str): Path to the dataset or dataset descriptor (like a YAML file). - autodownload (bool, optional): Whether to automatically download the dataset if not found. Defaults to True. - - Returns: - (dict): Parsed dataset information and paths. - """ - - file = check_file(dataset) - - # Download (optional) - extract_dir = "" - if zipfile.is_zipfile(file) or is_tarfile(file): - new_dir = safe_download(file, dir=DATASETS_DIR, unzip=True, delete=False) - file = find_dataset_yaml(DATASETS_DIR / new_dir) - extract_dir, autodownload = file.parent, False - - # Read YAML - data = yaml_load(file, append_filename=True) # dictionary - - # Checks - for k in "train", "val": - if k not in data: - if k != "val" or "validation" not in data: - raise SyntaxError( - emojis(f"{dataset} '{k}:' key missing ❌.\n'train' and 'val' are required in all data YAMLs.") - ) - LOGGER.info("WARNING ⚠️ renaming data YAML 'validation' key to 'val' to match YOLO format.") - data["val"] = data.pop("validation") # replace 'validation' key with 'val' key - if "names" not in data and "nc" not in data: - raise SyntaxError(emojis(f"{dataset} key missing ❌.\n either 'names' or 'nc' are required in all data YAMLs.")) - if "names" in data and "nc" in data and len(data["names"]) != data["nc"]: - raise SyntaxError(emojis(f"{dataset} 'names' length {len(data['names'])} and 'nc: {data['nc']}' must match.")) - if "names" not in data: - data["names"] = [f"class_{i}" for i in range(data["nc"])] - else: - data["nc"] = len(data["names"]) - - data["names"] = check_class_names(data["names"]) - - # Resolve paths - path = Path(extract_dir or data.get("path") or Path(data.get("yaml_file", "")).parent) # dataset root - if not path.is_absolute(): - path = (DATASETS_DIR / path).resolve() - - # Set paths - data["path"] = path # download scripts - for k in "train", "val", "test": - if data.get(k): # prepend path - if isinstance(data[k], str): - x = (path / data[k]).resolve() - if not x.exists() and data[k].startswith("../"): - x = (path / data[k][3:]).resolve() - data[k] = str(x) - else: - data[k] = [str((path / x).resolve()) for x in data[k]] - - # Parse YAML - val, s = (data.get(x) for x in ("val", "download")) - if val: - val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path - if not all(x.exists() for x in val): - name = clean_url(dataset) # dataset name with URL auth stripped - m = f"\nDataset '{name}' images not found ⚠️, missing path '{[x for x in val if not x.exists()][0]}'" - if s and autodownload: - LOGGER.warning(m) - else: - m += f"\nNote dataset download directory is '{DATASETS_DIR}'. You can update this in '{SETTINGS_YAML}'" - raise FileNotFoundError(m) - t = time.time() - r = None # success - if s.startswith("http") and s.endswith(".zip"): # URL - safe_download(url=s, dir=DATASETS_DIR, delete=True) - elif s.startswith("bash "): # bash script - LOGGER.info(f"Running {s} ...") - r = os.system(s) - else: # python script - exec(s, {"yaml": data}) - dt = f"({round(time.time() - t, 1)}s)" - s = f"success ✅ {dt}, saved to {colorstr('bold', DATASETS_DIR)}" if r in (0, None) else f"failure {dt} ❌" - LOGGER.info(f"Dataset download {s}\n") - check_font("Arial.ttf" if is_ascii(data["names"]) else "Arial.Unicode.ttf") # download fonts - - return data # dictionary - - -def check_cls_dataset(dataset, split=""): - """ - Checks a classification dataset such as Imagenet. - - This function accepts a `dataset` name and attempts to retrieve the corresponding dataset information. - If the dataset is not found locally, it attempts to download the dataset from the internet and save it locally. - - Args: - dataset (str | Path): The name of the dataset. - split (str, optional): The split of the dataset. Either 'val', 'test', or ''. Defaults to ''. - - Returns: - (dict): A dictionary containing the following keys: - - 'train' (Path): The directory path containing the training set of the dataset. - - 'val' (Path): The directory path containing the validation set of the dataset. - - 'test' (Path): The directory path containing the test set of the dataset. - - 'nc' (int): The number of classes in the dataset. - - 'names' (dict): A dictionary of class names in the dataset. - """ - - # Download (optional if dataset=https://file.zip is passed directly) - if str(dataset).startswith(("http:/", "https:/")): - dataset = safe_download(dataset, dir=DATASETS_DIR, unzip=True, delete=False) - elif Path(dataset).suffix in (".zip", ".tar", ".gz"): - file = check_file(dataset) - dataset = safe_download(file, dir=DATASETS_DIR, unzip=True, delete=False) - - dataset = Path(dataset) - data_dir = (dataset if dataset.is_dir() else (DATASETS_DIR / dataset)).resolve() - if not data_dir.is_dir(): - LOGGER.warning(f"\nDataset not found ⚠️, missing path {data_dir}, attempting download...") - t = time.time() - if str(dataset) == "imagenet": - subprocess.run(f"bash {ROOT / 'data/scripts/get_imagenet.sh'}", shell=True, check=True) - else: - url = f"https://github.com/ultralytics/yolov5/releases/download/v1.0/{dataset}.zip" - download(url, dir=data_dir.parent) - s = f"Dataset download success ✅ ({time.time() - t:.1f}s), saved to {colorstr('bold', data_dir)}\n" - LOGGER.info(s) - train_set = data_dir / "train" - val_set = ( - data_dir / "val" - if (data_dir / "val").exists() - else data_dir / "validation" - if (data_dir / "validation").exists() - else None - ) # data/test or data/val - test_set = data_dir / "test" if (data_dir / "test").exists() else None # data/val or data/test - if split == "val" and not val_set: - LOGGER.warning("WARNING ⚠️ Dataset 'split=val' not found, using 'split=test' instead.") - elif split == "test" and not test_set: - LOGGER.warning("WARNING ⚠️ Dataset 'split=test' not found, using 'split=val' instead.") - - nc = len([x for x in (data_dir / "train").glob("*") if x.is_dir()]) # number of classes - names = [x.name for x in (data_dir / "train").iterdir() if x.is_dir()] # class names list - names = dict(enumerate(sorted(names))) - - # Print to console - for k, v in {"train": train_set, "val": val_set, "test": test_set}.items(): - prefix = f'{colorstr(f"{k}:")} {v}...' - if v is None: - LOGGER.info(prefix) - else: - files = [path for path in v.rglob("*.*") if path.suffix[1:].lower() in IMG_FORMATS] - nf = len(files) # number of files - nd = len({file.parent for file in files}) # number of directories - if nf == 0: - if k == "train": - raise FileNotFoundError(emojis(f"{dataset} '{k}:' no training images found ❌ ")) - else: - LOGGER.warning(f"{prefix} found {nf} images in {nd} classes: WARNING ⚠️ no images found") - elif nd != nc: - LOGGER.warning(f"{prefix} found {nf} images in {nd} classes: ERROR ❌️ requires {nc} classes, not {nd}") - else: - LOGGER.info(f"{prefix} found {nf} images in {nd} classes ✅ ") - - return {"train": train_set, "val": val_set, "test": test_set, "nc": nc, "names": names} - - -class HUBDatasetStats: - """ - A class for generating HUB dataset JSON and `-hub` dataset directory. - - Args: - path (str): Path to data.yaml or data.zip (with data.yaml inside data.zip). Default is 'coco8.yaml'. - task (str): Dataset task. Options are 'detect', 'segment', 'pose', 'classify'. Default is 'detect'. - autodownload (bool): Attempt to download dataset if not found locally. Default is False. - - Example: - Download *.zip files from https://github.com/ultralytics/hub/tree/main/example_datasets - i.e. https://github.com/ultralytics/hub/raw/main/example_datasets/coco8.zip for coco8.zip. - ```python - from ultralytics.data.utils import HUBDatasetStats - - stats = HUBDatasetStats('path/to/coco8.zip', task='detect') # detect dataset - stats = HUBDatasetStats('path/to/coco8-seg.zip', task='segment') # segment dataset - stats = HUBDatasetStats('path/to/coco8-pose.zip', task='pose') # pose dataset - stats = HUBDatasetStats('path/to/imagenet10.zip', task='classify') # classification dataset - - stats.get_json(save=True) - stats.process_images() - ``` - """ - - def __init__(self, path="coco8.yaml", task="detect", autodownload=False): - """Initialize class.""" - path = Path(path).resolve() - LOGGER.info(f"Starting HUB dataset checks for {path}....") - - self.task = task # detect, segment, pose, classify - if self.task == "classify": - unzip_dir = unzip_file(path) - data = check_cls_dataset(unzip_dir) - data["path"] = unzip_dir - else: # detect, segment, pose - _, data_dir, yaml_path = self._unzip(Path(path)) - try: - # Load YAML with checks - data = yaml_load(yaml_path) - data["path"] = "" # strip path since YAML should be in dataset root for all HUB datasets - yaml_save(yaml_path, data) - data = check_det_dataset(yaml_path, autodownload) # dict - data["path"] = data_dir # YAML path should be set to '' (relative) or parent (absolute) - except Exception as e: - raise Exception("error/HUB/dataset_stats/init") from e - - self.hub_dir = Path(f'{data["path"]}-hub') - self.im_dir = self.hub_dir / "images" - self.stats = {"nc": len(data["names"]), "names": list(data["names"].values())} # statistics dictionary - self.data = data - - @staticmethod - def _unzip(path): - """Unzip data.zip.""" - if not str(path).endswith(".zip"): # path is data.yaml - return False, None, path - unzip_dir = unzip_file(path, path=path.parent) - assert unzip_dir.is_dir(), ( - f"Error unzipping {path}, {unzip_dir} not found. " f"path/to/abc.zip MUST unzip to path/to/abc/" - ) - return True, str(unzip_dir), find_dataset_yaml(unzip_dir) # zipped, data_dir, yaml_path - - def _hub_ops(self, f): - """Saves a compressed image for HUB previews.""" - compress_one_image(f, self.im_dir / Path(f).name) # save to dataset-hub - - def get_json(self, save=False, verbose=False): - """Return dataset JSON for Ultralytics HUB.""" - - def _round(labels): - """Update labels to integer class and 4 decimal place floats.""" - if self.task == "detect": - coordinates = labels["bboxes"] - elif self.task == "segment": - coordinates = [x.flatten() for x in labels["segments"]] - elif self.task == "pose": - n = labels["keypoints"].shape[0] - coordinates = np.concatenate((labels["bboxes"], labels["keypoints"].reshape(n, -1)), 1) - else: - raise ValueError("Undefined dataset task.") - zipped = zip(labels["cls"], coordinates) - return [[int(c[0]), *(round(float(x), 4) for x in points)] for c, points in zipped] - - for split in "train", "val", "test": - self.stats[split] = None # predefine - path = self.data.get(split) - - # Check split - if path is None: # no split - continue - files = [f for f in Path(path).rglob("*.*") if f.suffix[1:].lower() in IMG_FORMATS] # image files in split - if not files: # no images - continue - - # Get dataset statistics - if self.task == "classify": - from torchvision.datasets import ImageFolder - - dataset = ImageFolder(self.data[split]) - - x = np.zeros(len(dataset.classes)).astype(int) - for im in dataset.imgs: - x[im[1]] += 1 - - self.stats[split] = { - "instance_stats": {"total": len(dataset), "per_class": x.tolist()}, - "image_stats": {"total": len(dataset), "unlabelled": 0, "per_class": x.tolist()}, - "labels": [{Path(k).name: v} for k, v in dataset.imgs], - } - else: - from ultralytics.data import YOLODataset - - dataset = YOLODataset(img_path=self.data[split], data=self.data, task=self.task) - x = np.array( - [ - np.bincount(label["cls"].astype(int).flatten(), minlength=self.data["nc"]) - for label in TQDM(dataset.labels, total=len(dataset), desc="Statistics") - ] - ) # shape(128x80) - self.stats[split] = { - "instance_stats": {"total": int(x.sum()), "per_class": x.sum(0).tolist()}, - "image_stats": { - "total": len(dataset), - "unlabelled": int(np.all(x == 0, 1).sum()), - "per_class": (x > 0).sum(0).tolist(), - }, - "labels": [{Path(k).name: _round(v)} for k, v in zip(dataset.im_files, dataset.labels)], - } - - # Save, print and return - if save: - self.hub_dir.mkdir(parents=True, exist_ok=True) # makes dataset-hub/ - stats_path = self.hub_dir / "stats.json" - LOGGER.info(f"Saving {stats_path.resolve()}...") - with open(stats_path, "w") as f: - json.dump(self.stats, f) # save stats.json - if verbose: - LOGGER.info(json.dumps(self.stats, indent=2, sort_keys=False)) - return self.stats - - def process_images(self): - """Compress images for Ultralytics HUB.""" - from ultralytics.data import YOLODataset # ClassificationDataset - - self.im_dir.mkdir(parents=True, exist_ok=True) # makes dataset-hub/images/ - for split in "train", "val", "test": - if self.data.get(split) is None: - continue - dataset = YOLODataset(img_path=self.data[split], data=self.data) - with ThreadPool(NUM_THREADS) as pool: - for _ in TQDM(pool.imap(self._hub_ops, dataset.im_files), total=len(dataset), desc=f"{split} images"): - pass - LOGGER.info(f"Done. All images saved to {self.im_dir}") - return self.im_dir - - -def compress_one_image(f, f_new=None, max_dim=1920, quality=50): - """ - Compresses a single image file to reduced size while preserving its aspect ratio and quality using either the Python - Imaging Library (PIL) or OpenCV library. If the input image is smaller than the maximum dimension, it will not be - resized. - - Args: - f (str): The path to the input image file. - f_new (str, optional): The path to the output image file. If not specified, the input file will be overwritten. - max_dim (int, optional): The maximum dimension (width or height) of the output image. Default is 1920 pixels. - quality (int, optional): The image compression quality as a percentage. Default is 50%. - - Example: - ```python - from pathlib import Path - from ultralytics.data.utils import compress_one_image - - for f in Path('path/to/dataset').rglob('*.jpg'): - compress_one_image(f) - ``` - """ - - try: # use PIL - im = Image.open(f) - r = max_dim / max(im.height, im.width) # ratio - if r < 1.0: # image too large - im = im.resize((int(im.width * r), int(im.height * r))) - im.save(f_new or f, "JPEG", quality=quality, optimize=True) # save - except Exception as e: # use OpenCV - LOGGER.info(f"WARNING ⚠️ HUB ops PIL failure {f}: {e}") - im = cv2.imread(f) - im_height, im_width = im.shape[:2] - r = max_dim / max(im_height, im_width) # ratio - if r < 1.0: # image too large - im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA) - cv2.imwrite(str(f_new or f), im) - - -def autosplit(path=DATASETS_DIR / "coco8/images", weights=(0.9, 0.1, 0.0), annotated_only=False): - """ - Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files. - - Args: - path (Path, optional): Path to images directory. Defaults to DATASETS_DIR / 'coco8/images'. - weights (list | tuple, optional): Train, validation, and test split fractions. Defaults to (0.9, 0.1, 0.0). - annotated_only (bool, optional): If True, only images with an associated txt file are used. Defaults to False. - - Example: - ```python - from ultralytics.data.utils import autosplit - - autosplit() - ``` - """ - - path = Path(path) # images dir - files = sorted(x for x in path.rglob("*.*") if x.suffix[1:].lower() in IMG_FORMATS) # image files only - n = len(files) # number of files - random.seed(0) # for reproducibility - indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split - - txt = ["autosplit_train.txt", "autosplit_val.txt", "autosplit_test.txt"] # 3 txt files - for x in txt: - if (path.parent / x).exists(): - (path.parent / x).unlink() # remove existing - - LOGGER.info(f"Autosplitting images from {path}" + ", using *.txt labeled images only" * annotated_only) - for i, img in TQDM(zip(indices, files), total=n): - if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label - with open(path.parent / txt[i], "a") as f: - f.write(f"./{img.relative_to(path.parent).as_posix()}" + "\n") # add image to txt file diff --git a/ultralytics-main/ultralytics/engine/__init__.py b/ultralytics-main/ultralytics/engine/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/engine/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/engine/exporter.py b/ultralytics-main/ultralytics/engine/exporter.py deleted file mode 100644 index 859106a..0000000 --- a/ultralytics-main/ultralytics/engine/exporter.py +++ /dev/null @@ -1,1141 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Export a YOLOv8 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit - -Format | `format=argument` | Model ---- | --- | --- -PyTorch | - | yolov8n.pt -TorchScript | `torchscript` | yolov8n.torchscript -ONNX | `onnx` | yolov8n.onnx -OpenVINO | `openvino` | yolov8n_openvino_model/ -TensorRT | `engine` | yolov8n.engine -CoreML | `coreml` | yolov8n.mlpackage -TensorFlow SavedModel | `saved_model` | yolov8n_saved_model/ -TensorFlow GraphDef | `pb` | yolov8n.pb -TensorFlow Lite | `tflite` | yolov8n.tflite -TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite -TensorFlow.js | `tfjs` | yolov8n_web_model/ -PaddlePaddle | `paddle` | yolov8n_paddle_model/ -NCNN | `ncnn` | yolov8n_ncnn_model/ - -Requirements: - $ pip install "ultralytics[export]" - -Python: - from ultralytics import YOLO - model = YOLO('yolov8n.pt') - results = model.export(format='onnx') - -CLI: - $ yolo mode=export model=yolov8n.pt format=onnx - -Inference: - $ yolo predict model=yolov8n.pt # PyTorch - yolov8n.torchscript # TorchScript - yolov8n.onnx # ONNX Runtime or OpenCV DNN with dnn=True - yolov8n_openvino_model # OpenVINO - yolov8n.engine # TensorRT - yolov8n.mlpackage # CoreML (macOS-only) - yolov8n_saved_model # TensorFlow SavedModel - yolov8n.pb # TensorFlow GraphDef - yolov8n.tflite # TensorFlow Lite - yolov8n_edgetpu.tflite # TensorFlow Edge TPU - yolov8n_paddle_model # PaddlePaddle - yolov8n_ncnn_model # NCNN - -TensorFlow.js: - $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example - $ npm install - $ ln -s ../../yolov5/yolov8n_web_model public/yolov8n_web_model - $ npm start -""" - -import json -import os -import shutil -import subprocess -import time -import warnings -from copy import deepcopy -from datetime import datetime -from pathlib import Path - -import numpy as np -import torch - -from ultralytics.cfg import get_cfg -from ultralytics.data.dataset import YOLODataset -from ultralytics.data.utils import check_det_dataset -from ultralytics.nn.autobackend import check_class_names, default_class_names -from ultralytics.nn.modules import C2f, Detect, RTDETRDecoder -from ultralytics.nn.tasks import DetectionModel, SegmentationModel, WorldModel -from ultralytics.utils import ( - ARM64, - DEFAULT_CFG, - LINUX, - LOGGER, - MACOS, - ROOT, - WINDOWS, - __version__, - callbacks, - colorstr, - get_default_args, - yaml_save, -) -from ultralytics.utils.checks import PYTHON_VERSION, check_imgsz, check_is_path_safe, check_requirements, check_version -from ultralytics.utils.downloads import attempt_download_asset, get_github_assets -from ultralytics.utils.files import file_size, spaces_in_path -from ultralytics.utils.ops import Profile -from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_device, smart_inference_mode - - -def export_formats(): - """YOLOv8 export formats.""" - import pandas - - x = [ - ["PyTorch", "-", ".pt", True, True], - ["TorchScript", "torchscript", ".torchscript", True, True], - ["ONNX", "onnx", ".onnx", True, True], - ["OpenVINO", "openvino", "_openvino_model", True, False], - ["TensorRT", "engine", ".engine", False, True], - ["CoreML", "coreml", ".mlpackage", True, False], - ["TensorFlow SavedModel", "saved_model", "_saved_model", True, True], - ["TensorFlow GraphDef", "pb", ".pb", True, True], - ["TensorFlow Lite", "tflite", ".tflite", True, False], - ["TensorFlow Edge TPU", "edgetpu", "_edgetpu.tflite", True, False], - ["TensorFlow.js", "tfjs", "_web_model", True, False], - ["PaddlePaddle", "paddle", "_paddle_model", True, True], - ["NCNN", "ncnn", "_ncnn_model", True, True], - ] - return pandas.DataFrame(x, columns=["Format", "Argument", "Suffix", "CPU", "GPU"]) - - -def gd_outputs(gd): - """TensorFlow GraphDef model output node names.""" - name_list, input_list = [], [] - for node in gd.node: # tensorflow.core.framework.node_def_pb2.NodeDef - name_list.append(node.name) - input_list.extend(node.input) - return sorted(f"{x}:0" for x in list(set(name_list) - set(input_list)) if not x.startswith("NoOp")) - - -def try_export(inner_func): - """YOLOv8 export decorator, i..e @try_export.""" - inner_args = get_default_args(inner_func) - - def outer_func(*args, **kwargs): - """Export a model.""" - prefix = inner_args["prefix"] - try: - with Profile() as dt: - f, model = inner_func(*args, **kwargs) - LOGGER.info(f"{prefix} export success ✅ {dt.t:.1f}s, saved as '{f}' ({file_size(f):.1f} MB)") - return f, model - except Exception as e: - LOGGER.info(f"{prefix} export failure ❌ {dt.t:.1f}s: {e}") - raise e - - return outer_func - - -class Exporter: - """ - A class for exporting a model. - - Attributes: - args (SimpleNamespace): Configuration for the exporter. - callbacks (list, optional): List of callback functions. Defaults to None. - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """ - Initializes the Exporter class. - - Args: - cfg (str, optional): Path to a configuration file. Defaults to DEFAULT_CFG. - overrides (dict, optional): Configuration overrides. Defaults to None. - _callbacks (dict, optional): Dictionary of callback functions. Defaults to None. - """ - self.args = get_cfg(cfg, overrides) - if self.args.format.lower() in ("coreml", "mlmodel"): # fix attempt for protobuf<3.20.x errors - os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python" # must run before TensorBoard callback - - self.callbacks = _callbacks or callbacks.get_default_callbacks() - callbacks.add_integration_callbacks(self) - - @smart_inference_mode() - def __call__(self, model=None): - """Returns list of exported files/dirs after running callbacks.""" - self.run_callbacks("on_export_start") - t = time.time() - fmt = self.args.format.lower() # to lowercase - if fmt in ("tensorrt", "trt"): # 'engine' aliases - fmt = "engine" - if fmt in ("mlmodel", "mlpackage", "mlprogram", "apple", "ios", "coreml"): # 'coreml' aliases - fmt = "coreml" - fmts = tuple(export_formats()["Argument"][1:]) # available export formats - flags = [x == fmt for x in fmts] - if sum(flags) != 1: - raise ValueError(f"Invalid export format='{fmt}'. Valid formats are {fmts}") - jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, ncnn = flags # export booleans - - # Device - if fmt == "engine" and self.args.device is None: - LOGGER.warning("WARNING ⚠️ TensorRT requires GPU export, automatically assigning device=0") - self.args.device = "0" - self.device = select_device("cpu" if self.args.device is None else self.args.device) - - # Checks - if not hasattr(model, "names"): - model.names = default_class_names() - model.names = check_class_names(model.names) - if self.args.half and onnx and self.device.type == "cpu": - LOGGER.warning("WARNING ⚠️ half=True only compatible with GPU export, i.e. use device=0") - self.args.half = False - assert not self.args.dynamic, "half=True not compatible with dynamic=True, i.e. use only one." - self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2) # check image size - if self.args.optimize: - assert not ncnn, "optimize=True not compatible with format='ncnn', i.e. use optimize=False" - assert self.device.type == "cpu", "optimize=True not compatible with cuda devices, i.e. use device='cpu'" - if edgetpu and not LINUX: - raise SystemError("Edge TPU export only supported on Linux. See https://coral.ai/docs/edgetpu/compiler/") - if isinstance(model, WorldModel): - LOGGER.warning( - "WARNING ⚠️ YOLOWorld (original version) export is not supported to any format.\n" - "WARNING ⚠️ YOLOWorldv2 models (i.e. 'yolov8s-worldv2.pt') only support export to " - "(torchscript, onnx, openvino, engine, coreml) formats. " - "See https://docs.ultralytics.com/models/yolo-world for details." - ) - - # Input - im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device) - file = Path( - getattr(model, "pt_path", None) or getattr(model, "yaml_file", None) or model.yaml.get("yaml_file", "") - ) - if file.suffix in {".yaml", ".yml"}: - file = Path(file.name) - - # Update model - model = deepcopy(model).to(self.device) - for p in model.parameters(): - p.requires_grad = False - model.eval() - model.float() - model = model.fuse() - for m in model.modules(): - if isinstance(m, (Detect, RTDETRDecoder)): # includes all Detect subclasses like Segment, Pose, OBB - m.dynamic = self.args.dynamic - m.export = True - m.format = self.args.format - elif isinstance(m, C2f) and not any((saved_model, pb, tflite, edgetpu, tfjs)): - # EdgeTPU does not support FlexSplitV while split provides cleaner ONNX graph - m.forward = m.forward_split - - y = None - for _ in range(2): - y = model(im) # dry runs - if self.args.half and onnx and self.device.type != "cpu": - im, model = im.half(), model.half() # to FP16 - - # Filter warnings - warnings.filterwarnings("ignore", category=torch.jit.TracerWarning) # suppress TracerWarning - warnings.filterwarnings("ignore", category=UserWarning) # suppress shape prim::Constant missing ONNX warning - warnings.filterwarnings("ignore", category=DeprecationWarning) # suppress CoreML np.bool deprecation warning - - # Assign - self.im = im - self.model = model - self.file = file - self.output_shape = ( - tuple(y.shape) - if isinstance(y, torch.Tensor) - else tuple(tuple(x.shape if isinstance(x, torch.Tensor) else []) for x in y) - ) - self.pretty_name = Path(self.model.yaml.get("yaml_file", self.file)).stem.replace("yolo", "YOLO") - data = model.args["data"] if hasattr(model, "args") and isinstance(model.args, dict) else "" - description = f'Ultralytics {self.pretty_name} model {f"trained on {data}" if data else ""}' - self.metadata = { - "description": description, - "author": "Ultralytics", - "date": datetime.now().isoformat(), - "version": __version__, - "license": "AGPL-3.0 License (https://ultralytics.com/license)", - "docs": "https://docs.ultralytics.com", - "stride": int(max(model.stride)), - "task": model.task, - "batch": self.args.batch, - "imgsz": self.imgsz, - "names": model.names, - } # model metadata - if model.task == "pose": - self.metadata["kpt_shape"] = model.model[-1].kpt_shape - - LOGGER.info( - f"\n{colorstr('PyTorch:')} starting from '{file}' with input shape {tuple(im.shape)} BCHW and " - f'output shape(s) {self.output_shape} ({file_size(file):.1f} MB)' - ) - - # Exports - f = [""] * len(fmts) # exported filenames - if jit or ncnn: # TorchScript - f[0], _ = self.export_torchscript() - if engine: # TensorRT required before ONNX - f[1], _ = self.export_engine() - if onnx: # ONNX - f[2], _ = self.export_onnx() - if xml: # OpenVINO - f[3], _ = self.export_openvino() - if coreml: # CoreML - f[4], _ = self.export_coreml() - if any((saved_model, pb, tflite, edgetpu, tfjs)): # TensorFlow formats - self.args.int8 |= edgetpu - f[5], keras_model = self.export_saved_model() - if pb or tfjs: # pb prerequisite to tfjs - f[6], _ = self.export_pb(keras_model=keras_model) - if tflite: - f[7], _ = self.export_tflite(keras_model=keras_model, nms=False, agnostic_nms=self.args.agnostic_nms) - if edgetpu: - f[8], _ = self.export_edgetpu(tflite_model=Path(f[5]) / f"{self.file.stem}_full_integer_quant.tflite") - if tfjs: - f[9], _ = self.export_tfjs() - if paddle: # PaddlePaddle - f[10], _ = self.export_paddle() - if ncnn: # NCNN - f[11], _ = self.export_ncnn() - - # Finish - f = [str(x) for x in f if x] # filter out '' and None - if any(f): - f = str(Path(f[-1])) - square = self.imgsz[0] == self.imgsz[1] - s = ( - "" - if square - else f"WARNING ⚠️ non-PyTorch val requires square images, 'imgsz={self.imgsz}' will not " - f"work. Use export 'imgsz={max(self.imgsz)}' if val is required." - ) - imgsz = self.imgsz[0] if square else str(self.imgsz)[1:-1].replace(" ", "") - predict_data = f"data={data}" if model.task == "segment" and fmt == "pb" else "" - q = "int8" if self.args.int8 else "half" if self.args.half else "" # quantization - LOGGER.info( - f'\nExport complete ({time.time() - t:.1f}s)' - f"\nResults saved to {colorstr('bold', file.parent.resolve())}" - f'\nPredict: yolo predict task={model.task} model={f} imgsz={imgsz} {q} {predict_data}' - f'\nValidate: yolo val task={model.task} model={f} imgsz={imgsz} data={data} {q} {s}' - f'\nVisualize: https://netron.app' - ) - - self.run_callbacks("on_export_end") - return f # return list of exported files/dirs - - @try_export - def export_torchscript(self, prefix=colorstr("TorchScript:")): - """YOLOv8 TorchScript model export.""" - LOGGER.info(f"\n{prefix} starting export with torch {torch.__version__}...") - f = self.file.with_suffix(".torchscript") - - ts = torch.jit.trace(self.model, self.im, strict=False) - extra_files = {"config.txt": json.dumps(self.metadata)} # torch._C.ExtraFilesMap() - if self.args.optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html - LOGGER.info(f"{prefix} optimizing for mobile...") - from torch.utils.mobile_optimizer import optimize_for_mobile - - optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files) - else: - ts.save(str(f), _extra_files=extra_files) - return f, None - - @try_export - def export_onnx(self, prefix=colorstr("ONNX:")): - """YOLOv8 ONNX export.""" - requirements = ["onnx>=1.12.0"] - if self.args.simplify: - requirements += ["onnxsim>=0.4.33", "onnxruntime-gpu" if torch.cuda.is_available() else "onnxruntime"] - if ARM64: - check_requirements("cmake") # 'cmake' is needed to build onnxsim on aarch64 - check_requirements(requirements) - import onnx # noqa - - opset_version = self.args.opset or get_latest_opset() - LOGGER.info(f"\n{prefix} starting export with onnx {onnx.__version__} opset {opset_version}...") - f = str(self.file.with_suffix(".onnx")) - - output_names = ["output0", "output1"] if isinstance(self.model, SegmentationModel) else ["output0"] - dynamic = self.args.dynamic - if dynamic: - dynamic = {"images": {0: "batch", 2: "height", 3: "width"}} # shape(1,3,640,640) - if isinstance(self.model, SegmentationModel): - dynamic["output0"] = {0: "batch", 2: "anchors"} # shape(1, 116, 8400) - dynamic["output1"] = {0: "batch", 2: "mask_height", 3: "mask_width"} # shape(1,32,160,160) - elif isinstance(self.model, DetectionModel): - dynamic["output0"] = {0: "batch", 2: "anchors"} # shape(1, 84, 8400) - - torch.onnx.export( - self.model.cpu() if dynamic else self.model, # dynamic=True only compatible with cpu - self.im.cpu() if dynamic else self.im, - f, - verbose=False, - opset_version=opset_version, - do_constant_folding=True, # WARNING: DNN inference with torch>=1.12 may require do_constant_folding=False - input_names=["images"], - output_names=output_names, - dynamic_axes=dynamic or None, - ) - - # Checks - model_onnx = onnx.load(f) # load onnx model - # onnx.checker.check_model(model_onnx) # check onnx model - - # Simplify - if self.args.simplify: - try: - import onnxsim - - LOGGER.info(f"{prefix} simplifying with onnxsim {onnxsim.__version__}...") - # subprocess.run(f'onnxsim "{f}" "{f}"', shell=True) - model_onnx, check = onnxsim.simplify(model_onnx) - assert check, "Simplified ONNX model could not be validated" - except Exception as e: - LOGGER.info(f"{prefix} simplifier failure: {e}") - - # Metadata - for k, v in self.metadata.items(): - meta = model_onnx.metadata_props.add() - meta.key, meta.value = k, str(v) - - onnx.save(model_onnx, f) - return f, model_onnx - - @try_export - def export_openvino(self, prefix=colorstr("OpenVINO:")): - """YOLOv8 OpenVINO export.""" - check_requirements("openvino>=2024.0.0") # requires openvino: https://pypi.org/project/openvino/ - import openvino as ov - - LOGGER.info(f"\n{prefix} starting export with openvino {ov.__version__}...") - assert TORCH_1_13, f"OpenVINO export requires torch>=1.13.0 but torch=={torch.__version__} is installed" - ov_model = ov.convert_model( - self.model.cpu(), - input=None if self.args.dynamic else [self.im.shape], - example_input=self.im, - ) - - def serialize(ov_model, file): - """Set RT info, serialize and save metadata YAML.""" - ov_model.set_rt_info("YOLOv8", ["model_info", "model_type"]) - ov_model.set_rt_info(True, ["model_info", "reverse_input_channels"]) - ov_model.set_rt_info(114, ["model_info", "pad_value"]) - ov_model.set_rt_info([255.0], ["model_info", "scale_values"]) - ov_model.set_rt_info(self.args.iou, ["model_info", "iou_threshold"]) - ov_model.set_rt_info([v.replace(" ", "_") for v in self.model.names.values()], ["model_info", "labels"]) - if self.model.task != "classify": - ov_model.set_rt_info("fit_to_window_letterbox", ["model_info", "resize_type"]) - - ov.runtime.save_model(ov_model, file, compress_to_fp16=self.args.half) - yaml_save(Path(file).parent / "metadata.yaml", self.metadata) # add metadata.yaml - - if self.args.int8: - fq = str(self.file).replace(self.file.suffix, f"_int8_openvino_model{os.sep}") - fq_ov = str(Path(fq) / self.file.with_suffix(".xml").name) - if not self.args.data: - self.args.data = DEFAULT_CFG.data or "coco128.yaml" - LOGGER.warning( - f"{prefix} WARNING ⚠️ INT8 export requires a missing 'data' arg for calibration. " - f"Using default 'data={self.args.data}'." - ) - check_requirements("nncf>=2.8.0") - import nncf - - def transform_fn(data_item): - """Quantization transform function.""" - assert ( - data_item["img"].dtype == torch.uint8 - ), "Input image must be uint8 for the quantization preprocessing" - im = data_item["img"].numpy().astype(np.float32) / 255.0 # uint8 to fp16/32 and 0 - 255 to 0.0 - 1.0 - return np.expand_dims(im, 0) if im.ndim == 3 else im - - # Generate calibration data for integer quantization - LOGGER.info(f"{prefix} collecting INT8 calibration images from 'data={self.args.data}'") - data = check_det_dataset(self.args.data) - dataset = YOLODataset(data["val"], data=data, imgsz=self.imgsz[0], augment=False) - n = len(dataset) - if n < 300: - LOGGER.warning(f"{prefix} WARNING ⚠️ >300 images recommended for INT8 calibration, found {n} images.") - quantization_dataset = nncf.Dataset(dataset, transform_fn) - - ignored_scope = None - if isinstance(self.model.model[-1], Detect): - # Includes all Detect subclasses like Segment, Pose, OBB, WorldDetect - head_module_name = ".".join(list(self.model.named_modules())[-1][0].split(".")[:2]) - - ignored_scope = nncf.IgnoredScope( # ignore operations - patterns=[ - f".*{head_module_name}/.*/Add", - f".*{head_module_name}/.*/Sub*", - f".*{head_module_name}/.*/Mul*", - f".*{head_module_name}/.*/Div*", - f".*{head_module_name}\\.dfl.*", - ], - types=["Sigmoid"], - ) - - quantized_ov_model = nncf.quantize( - ov_model, quantization_dataset, preset=nncf.QuantizationPreset.MIXED, ignored_scope=ignored_scope - ) - serialize(quantized_ov_model, fq_ov) - return fq, None - - f = str(self.file).replace(self.file.suffix, f"_openvino_model{os.sep}") - f_ov = str(Path(f) / self.file.with_suffix(".xml").name) - - serialize(ov_model, f_ov) - return f, None - - @try_export - def export_paddle(self, prefix=colorstr("PaddlePaddle:")): - """YOLOv8 Paddle export.""" - check_requirements(("paddlepaddle", "x2paddle")) - import x2paddle # noqa - from x2paddle.convert import pytorch2paddle # noqa - - LOGGER.info(f"\n{prefix} starting export with X2Paddle {x2paddle.__version__}...") - f = str(self.file).replace(self.file.suffix, f"_paddle_model{os.sep}") - - pytorch2paddle(module=self.model, save_dir=f, jit_type="trace", input_examples=[self.im]) # export - yaml_save(Path(f) / "metadata.yaml", self.metadata) # add metadata.yaml - return f, None - - @try_export - def export_ncnn(self, prefix=colorstr("NCNN:")): - """ - YOLOv8 NCNN export using PNNX https://github.com/pnnx/pnnx. - """ - check_requirements("ncnn") - import ncnn # noqa - - LOGGER.info(f"\n{prefix} starting export with NCNN {ncnn.__version__}...") - f = Path(str(self.file).replace(self.file.suffix, f"_ncnn_model{os.sep}")) - f_ts = self.file.with_suffix(".torchscript") - - name = Path("pnnx.exe" if WINDOWS else "pnnx") # PNNX filename - pnnx = name if name.is_file() else ROOT / name - if not pnnx.is_file(): - LOGGER.warning( - f"{prefix} WARNING ⚠️ PNNX not found. Attempting to download binary file from " - "https://github.com/pnnx/pnnx/.\nNote PNNX Binary file must be placed in current working directory " - f"or in {ROOT}. See PNNX repo for full installation instructions." - ) - system = "macos" if MACOS else "windows" if WINDOWS else "linux-aarch64" if ARM64 else "linux" - _, assets = get_github_assets(repo="pnnx/pnnx", retry=True) - if assets: - url = [x for x in assets if f"{system}.zip" in x][0] - else: - url = f"https://github.com/pnnx/pnnx/releases/download/20240226/pnnx-20240226-{system}.zip" - LOGGER.warning(f"{prefix} WARNING ⚠️ PNNX GitHub assets not found, using default {url}") - asset = attempt_download_asset(url, repo="pnnx/pnnx", release="latest") - if check_is_path_safe(Path.cwd(), asset): # avoid path traversal security vulnerability - unzip_dir = Path(asset).with_suffix("") - (unzip_dir / name).rename(pnnx) # move binary to ROOT - shutil.rmtree(unzip_dir) # delete unzip dir - Path(asset).unlink() # delete zip - pnnx.chmod(0o777) # set read, write, and execute permissions for everyone - - ncnn_args = [ - f'ncnnparam={f / "model.ncnn.param"}', - f'ncnnbin={f / "model.ncnn.bin"}', - f'ncnnpy={f / "model_ncnn.py"}', - ] - - pnnx_args = [ - f'pnnxparam={f / "model.pnnx.param"}', - f'pnnxbin={f / "model.pnnx.bin"}', - f'pnnxpy={f / "model_pnnx.py"}', - f'pnnxonnx={f / "model.pnnx.onnx"}', - ] - - cmd = [ - str(pnnx), - str(f_ts), - *ncnn_args, - *pnnx_args, - f"fp16={int(self.args.half)}", - f"device={self.device.type}", - f'inputshape="{[self.args.batch, 3, *self.imgsz]}"', - ] - f.mkdir(exist_ok=True) # make ncnn_model directory - LOGGER.info(f"{prefix} running '{' '.join(cmd)}'") - subprocess.run(cmd, check=True) - - # Remove debug files - pnnx_files = [x.split("=")[-1] for x in pnnx_args] - for f_debug in ("debug.bin", "debug.param", "debug2.bin", "debug2.param", *pnnx_files): - Path(f_debug).unlink(missing_ok=True) - - yaml_save(f / "metadata.yaml", self.metadata) # add metadata.yaml - return str(f), None - - @try_export - def export_coreml(self, prefix=colorstr("CoreML:")): - """YOLOv8 CoreML export.""" - mlmodel = self.args.format.lower() == "mlmodel" # legacy *.mlmodel export format requested - check_requirements("coremltools>=6.0,<=6.2" if mlmodel else "coremltools>=7.0") - import coremltools as ct # noqa - - LOGGER.info(f"\n{prefix} starting export with coremltools {ct.__version__}...") - assert not WINDOWS, "CoreML export is not supported on Windows, please run on macOS or Linux." - f = self.file.with_suffix(".mlmodel" if mlmodel else ".mlpackage") - if f.is_dir(): - shutil.rmtree(f) - - bias = [0.0, 0.0, 0.0] - scale = 1 / 255 - classifier_config = None - if self.model.task == "classify": - classifier_config = ct.ClassifierConfig(list(self.model.names.values())) if self.args.nms else None - model = self.model - elif self.model.task == "detect": - model = IOSDetectModel(self.model, self.im) if self.args.nms else self.model - else: - if self.args.nms: - LOGGER.warning(f"{prefix} WARNING ⚠️ 'nms=True' is only available for Detect models like 'yolov8n.pt'.") - # TODO CoreML Segment and Pose model pipelining - model = self.model - - ts = torch.jit.trace(model.eval(), self.im, strict=False) # TorchScript model - ct_model = ct.convert( - ts, - inputs=[ct.ImageType("image", shape=self.im.shape, scale=scale, bias=bias)], - classifier_config=classifier_config, - convert_to="neuralnetwork" if mlmodel else "mlprogram", - ) - bits, mode = (8, "kmeans") if self.args.int8 else (16, "linear") if self.args.half else (32, None) - if bits < 32: - if "kmeans" in mode: - check_requirements("scikit-learn") # scikit-learn package required for k-means quantization - if mlmodel: - ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode) - elif bits == 8: # mlprogram already quantized to FP16 - import coremltools.optimize.coreml as cto - - op_config = cto.OpPalettizerConfig(mode="kmeans", nbits=bits, weight_threshold=512) - config = cto.OptimizationConfig(global_config=op_config) - ct_model = cto.palettize_weights(ct_model, config=config) - if self.args.nms and self.model.task == "detect": - if mlmodel: - # coremltools<=6.2 NMS export requires Python<3.11 - check_version(PYTHON_VERSION, "<3.11", name="Python ", hard=True) - weights_dir = None - else: - ct_model.save(str(f)) # save otherwise weights_dir does not exist - weights_dir = str(f / "Data/com.apple.CoreML/weights") - ct_model = self._pipeline_coreml(ct_model, weights_dir=weights_dir) - - m = self.metadata # metadata dict - ct_model.short_description = m.pop("description") - ct_model.author = m.pop("author") - ct_model.license = m.pop("license") - ct_model.version = m.pop("version") - ct_model.user_defined_metadata.update({k: str(v) for k, v in m.items()}) - try: - ct_model.save(str(f)) # save *.mlpackage - except Exception as e: - LOGGER.warning( - f"{prefix} WARNING ⚠️ CoreML export to *.mlpackage failed ({e}), reverting to *.mlmodel export. " - f"Known coremltools Python 3.11 and Windows bugs https://github.com/apple/coremltools/issues/1928." - ) - f = f.with_suffix(".mlmodel") - ct_model.save(str(f)) - return f, ct_model - - @try_export - def export_engine(self, prefix=colorstr("TensorRT:")): - """YOLOv8 TensorRT export https://developer.nvidia.com/tensorrt.""" - assert self.im.device.type != "cpu", "export running on CPU but must be on GPU, i.e. use 'device=0'" - f_onnx, _ = self.export_onnx() # run before trt import https://github.com/ultralytics/ultralytics/issues/7016 - - try: - import tensorrt as trt # noqa - except ImportError: - if LINUX: - check_requirements("nvidia-tensorrt", cmds="-U --index-url https://pypi.ngc.nvidia.com") - import tensorrt as trt # noqa - - check_version(trt.__version__, "7.0.0", hard=True) # require tensorrt>=7.0.0 - - self.args.simplify = True - - LOGGER.info(f"\n{prefix} starting export with TensorRT {trt.__version__}...") - assert Path(f_onnx).exists(), f"failed to export ONNX file: {f_onnx}" - f = self.file.with_suffix(".engine") # TensorRT engine file - logger = trt.Logger(trt.Logger.INFO) - if self.args.verbose: - logger.min_severity = trt.Logger.Severity.VERBOSE - - builder = trt.Builder(logger) - config = builder.create_builder_config() - config.max_workspace_size = self.args.workspace * 1 << 30 - # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30) # fix TRT 8.4 deprecation notice - - flag = 1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH) - network = builder.create_network(flag) - parser = trt.OnnxParser(network, logger) - if not parser.parse_from_file(f_onnx): - raise RuntimeError(f"failed to load ONNX file: {f_onnx}") - - inputs = [network.get_input(i) for i in range(network.num_inputs)] - outputs = [network.get_output(i) for i in range(network.num_outputs)] - for inp in inputs: - LOGGER.info(f'{prefix} input "{inp.name}" with shape{inp.shape} {inp.dtype}') - for out in outputs: - LOGGER.info(f'{prefix} output "{out.name}" with shape{out.shape} {out.dtype}') - - if self.args.dynamic: - shape = self.im.shape - if shape[0] <= 1: - LOGGER.warning(f"{prefix} WARNING ⚠️ 'dynamic=True' model requires max batch size, i.e. 'batch=16'") - profile = builder.create_optimization_profile() - for inp in inputs: - profile.set_shape(inp.name, (1, *shape[1:]), (max(1, shape[0] // 2), *shape[1:]), shape) - config.add_optimization_profile(profile) - - LOGGER.info( - f"{prefix} building FP{16 if builder.platform_has_fast_fp16 and self.args.half else 32} engine as {f}" - ) - if builder.platform_has_fast_fp16 and self.args.half: - config.set_flag(trt.BuilderFlag.FP16) - - del self.model - torch.cuda.empty_cache() - - # Write file - with builder.build_engine(network, config) as engine, open(f, "wb") as t: - # Metadata - meta = json.dumps(self.metadata) - t.write(len(meta).to_bytes(4, byteorder="little", signed=True)) - t.write(meta.encode()) - # Model - t.write(engine.serialize()) - - return f, None - - @try_export - def export_saved_model(self, prefix=colorstr("TensorFlow SavedModel:")): - """YOLOv8 TensorFlow SavedModel export.""" - cuda = torch.cuda.is_available() - try: - import tensorflow as tf # noqa - except ImportError: - suffix = "-macos" if MACOS else "-aarch64" if ARM64 else "" if cuda else "-cpu" - version = "" if ARM64 else "<=2.13.1" - check_requirements(f"tensorflow{suffix}{version}") - import tensorflow as tf # noqa - if ARM64: - check_requirements("cmake") # 'cmake' is needed to build onnxsim on aarch64 - check_requirements( - ( - "onnx>=1.12.0", - "onnx2tf>=1.15.4,<=1.17.5", - "sng4onnx>=1.0.1", - "onnxsim>=0.4.33", - "onnx_graphsurgeon>=0.3.26", - "tflite_support", - "flatbuffers>=23.5.26,<100", # update old 'flatbuffers' included inside tensorflow package - "onnxruntime-gpu" if cuda else "onnxruntime", - ), - cmds="--extra-index-url https://pypi.ngc.nvidia.com", - ) # onnx_graphsurgeon only on NVIDIA - - LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...") - check_version( - tf.__version__, - "<=2.13.1", - name="tensorflow", - verbose=True, - msg="https://github.com/ultralytics/ultralytics/issues/5161", - ) - import onnx2tf - - f = Path(str(self.file).replace(self.file.suffix, "_saved_model")) - if f.is_dir(): - shutil.rmtree(f) # delete output folder - - # Pre-download calibration file to fix https://github.com/PINTO0309/onnx2tf/issues/545 - onnx2tf_file = Path("calibration_image_sample_data_20x128x128x3_float32.npy") - if not onnx2tf_file.exists(): - attempt_download_asset(f"{onnx2tf_file}.zip", unzip=True, delete=True) - - # Export to ONNX - self.args.simplify = True - f_onnx, _ = self.export_onnx() - - # Export to TF - tmp_file = f / "tmp_tflite_int8_calibration_images.npy" # int8 calibration images file - np_data = None - if self.args.int8: - verbosity = "info" - if self.args.data: - # Generate calibration data for integer quantization - LOGGER.info(f"{prefix} collecting INT8 calibration images from 'data={self.args.data}'") - data = check_det_dataset(self.args.data) - dataset = YOLODataset(data["val"], data=data, imgsz=self.imgsz[0], augment=False) - images = [] - for i, batch in enumerate(dataset): - if i >= 100: # maximum number of calibration images - break - im = batch["img"].permute(1, 2, 0)[None] # list to nparray, CHW to BHWC - images.append(im) - f.mkdir() - images = torch.cat(images, 0).float() - # mean = images.view(-1, 3).mean(0) # imagenet mean [123.675, 116.28, 103.53] - # std = images.view(-1, 3).std(0) # imagenet std [58.395, 57.12, 57.375] - np.save(str(tmp_file), images.numpy()) # BHWC - np_data = [["images", tmp_file, [[[[0, 0, 0]]]], [[[[255, 255, 255]]]]]] - else: - verbosity = "error" - - LOGGER.info(f"{prefix} starting TFLite export with onnx2tf {onnx2tf.__version__}...") - onnx2tf.convert( - input_onnx_file_path=f_onnx, - output_folder_path=str(f), - not_use_onnxsim=True, - verbosity=verbosity, - output_integer_quantized_tflite=self.args.int8, - quant_type="per-tensor", # "per-tensor" (faster) or "per-channel" (slower but more accurate) - custom_input_op_name_np_data_path=np_data, - ) - yaml_save(f / "metadata.yaml", self.metadata) # add metadata.yaml - - # Remove/rename TFLite models - if self.args.int8: - tmp_file.unlink(missing_ok=True) - for file in f.rglob("*_dynamic_range_quant.tflite"): - file.rename(file.with_name(file.stem.replace("_dynamic_range_quant", "_int8") + file.suffix)) - for file in f.rglob("*_integer_quant_with_int16_act.tflite"): - file.unlink() # delete extra fp16 activation TFLite files - - # Add TFLite metadata - for file in f.rglob("*.tflite"): - f.unlink() if "quant_with_int16_act.tflite" in str(f) else self._add_tflite_metadata(file) - - return str(f), tf.saved_model.load(f, tags=None, options=None) # load saved_model as Keras model - - @try_export - def export_pb(self, keras_model, prefix=colorstr("TensorFlow GraphDef:")): - """YOLOv8 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow.""" - import tensorflow as tf # noqa - from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 # noqa - - LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...") - f = self.file.with_suffix(".pb") - - m = tf.function(lambda x: keras_model(x)) # full model - m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)) - frozen_func = convert_variables_to_constants_v2(m) - frozen_func.graph.as_graph_def() - tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False) - return f, None - - @try_export - def export_tflite(self, keras_model, nms, agnostic_nms, prefix=colorstr("TensorFlow Lite:")): - """YOLOv8 TensorFlow Lite export.""" - import tensorflow as tf # noqa - - LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...") - saved_model = Path(str(self.file).replace(self.file.suffix, "_saved_model")) - if self.args.int8: - f = saved_model / f"{self.file.stem}_int8.tflite" # fp32 in/out - elif self.args.half: - f = saved_model / f"{self.file.stem}_float16.tflite" # fp32 in/out - else: - f = saved_model / f"{self.file.stem}_float32.tflite" - return str(f), None - - @try_export - def export_edgetpu(self, tflite_model="", prefix=colorstr("Edge TPU:")): - """YOLOv8 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/.""" - LOGGER.warning(f"{prefix} WARNING ⚠️ Edge TPU known bug https://github.com/ultralytics/ultralytics/issues/1185") - - cmd = "edgetpu_compiler --version" - help_url = "https://coral.ai/docs/edgetpu/compiler/" - assert LINUX, f"export only supported on Linux. See {help_url}" - if subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, shell=True).returncode != 0: - LOGGER.info(f"\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}") - sudo = subprocess.run("sudo --version >/dev/null", shell=True).returncode == 0 # sudo installed on system - for c in ( - "curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -", - 'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | ' - "sudo tee /etc/apt/sources.list.d/coral-edgetpu.list", - "sudo apt-get update", - "sudo apt-get install edgetpu-compiler", - ): - subprocess.run(c if sudo else c.replace("sudo ", ""), shell=True, check=True) - ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1] - - LOGGER.info(f"\n{prefix} starting export with Edge TPU compiler {ver}...") - f = str(tflite_model).replace(".tflite", "_edgetpu.tflite") # Edge TPU model - - cmd = f'edgetpu_compiler -s -d -k 10 --out_dir "{Path(f).parent}" "{tflite_model}"' - LOGGER.info(f"{prefix} running '{cmd}'") - subprocess.run(cmd, shell=True) - self._add_tflite_metadata(f) - return f, None - - @try_export - def export_tfjs(self, prefix=colorstr("TensorFlow.js:")): - """YOLOv8 TensorFlow.js export.""" - check_requirements("tensorflowjs") - if ARM64: - # Fix error: `np.object` was a deprecated alias for the builtin `object` when exporting to TF.js on ARM64 - check_requirements("numpy==1.23.5") - import tensorflow as tf - import tensorflowjs as tfjs # noqa - - LOGGER.info(f"\n{prefix} starting export with tensorflowjs {tfjs.__version__}...") - f = str(self.file).replace(self.file.suffix, "_web_model") # js dir - f_pb = str(self.file.with_suffix(".pb")) # *.pb path - - gd = tf.Graph().as_graph_def() # TF GraphDef - with open(f_pb, "rb") as file: - gd.ParseFromString(file.read()) - outputs = ",".join(gd_outputs(gd)) - LOGGER.info(f"\n{prefix} output node names: {outputs}") - - quantization = "--quantize_float16" if self.args.half else "--quantize_uint8" if self.args.int8 else "" - with spaces_in_path(f_pb) as fpb_, spaces_in_path(f) as f_: # exporter can not handle spaces in path - cmd = ( - "tensorflowjs_converter " - f'--input_format=tf_frozen_model {quantization} --output_node_names={outputs} "{fpb_}" "{f_}"' - ) - LOGGER.info(f"{prefix} running '{cmd}'") - subprocess.run(cmd, shell=True) - - if " " in f: - LOGGER.warning(f"{prefix} WARNING ⚠️ your model may not work correctly with spaces in path '{f}'.") - - # f_json = Path(f) / 'model.json' # *.json path - # with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order - # subst = re.sub( - # r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, ' - # r'"Identity.?.?": {"name": "Identity.?.?"}, ' - # r'"Identity.?.?": {"name": "Identity.?.?"}, ' - # r'"Identity.?.?": {"name": "Identity.?.?"}}}', - # r'{"outputs": {"Identity": {"name": "Identity"}, ' - # r'"Identity_1": {"name": "Identity_1"}, ' - # r'"Identity_2": {"name": "Identity_2"}, ' - # r'"Identity_3": {"name": "Identity_3"}}}', - # f_json.read_text(), - # ) - # j.write(subst) - yaml_save(Path(f) / "metadata.yaml", self.metadata) # add metadata.yaml - return f, None - - def _add_tflite_metadata(self, file): - """Add metadata to *.tflite models per https://www.tensorflow.org/lite/models/convert/metadata.""" - from tflite_support import flatbuffers # noqa - from tflite_support import metadata as _metadata # noqa - from tflite_support import metadata_schema_py_generated as _metadata_fb # noqa - - # Create model info - model_meta = _metadata_fb.ModelMetadataT() - model_meta.name = self.metadata["description"] - model_meta.version = self.metadata["version"] - model_meta.author = self.metadata["author"] - model_meta.license = self.metadata["license"] - - # Label file - tmp_file = Path(file).parent / "temp_meta.txt" - with open(tmp_file, "w") as f: - f.write(str(self.metadata)) - - label_file = _metadata_fb.AssociatedFileT() - label_file.name = tmp_file.name - label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS - - # Create input info - input_meta = _metadata_fb.TensorMetadataT() - input_meta.name = "image" - input_meta.description = "Input image to be detected." - input_meta.content = _metadata_fb.ContentT() - input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT() - input_meta.content.contentProperties.colorSpace = _metadata_fb.ColorSpaceType.RGB - input_meta.content.contentPropertiesType = _metadata_fb.ContentProperties.ImageProperties - - # Create output info - output1 = _metadata_fb.TensorMetadataT() - output1.name = "output" - output1.description = "Coordinates of detected objects, class labels, and confidence score" - output1.associatedFiles = [label_file] - if self.model.task == "segment": - output2 = _metadata_fb.TensorMetadataT() - output2.name = "output" - output2.description = "Mask protos" - output2.associatedFiles = [label_file] - - # Create subgraph info - subgraph = _metadata_fb.SubGraphMetadataT() - subgraph.inputTensorMetadata = [input_meta] - subgraph.outputTensorMetadata = [output1, output2] if self.model.task == "segment" else [output1] - model_meta.subgraphMetadata = [subgraph] - - b = flatbuffers.Builder(0) - b.Finish(model_meta.Pack(b), _metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER) - metadata_buf = b.Output() - - populator = _metadata.MetadataPopulator.with_model_file(str(file)) - populator.load_metadata_buffer(metadata_buf) - populator.load_associated_files([str(tmp_file)]) - populator.populate() - tmp_file.unlink() - - def _pipeline_coreml(self, model, weights_dir=None, prefix=colorstr("CoreML Pipeline:")): - """YOLOv8 CoreML pipeline.""" - import coremltools as ct # noqa - - LOGGER.info(f"{prefix} starting pipeline with coremltools {ct.__version__}...") - _, _, h, w = list(self.im.shape) # BCHW - - # Output shapes - spec = model.get_spec() - out0, out1 = iter(spec.description.output) - if MACOS: - from PIL import Image - - img = Image.new("RGB", (w, h)) # w=192, h=320 - out = model.predict({"image": img}) - out0_shape = out[out0.name].shape # (3780, 80) - out1_shape = out[out1.name].shape # (3780, 4) - else: # linux and windows can not run model.predict(), get sizes from PyTorch model output y - out0_shape = self.output_shape[2], self.output_shape[1] - 4 # (3780, 80) - out1_shape = self.output_shape[2], 4 # (3780, 4) - - # Checks - names = self.metadata["names"] - nx, ny = spec.description.input[0].type.imageType.width, spec.description.input[0].type.imageType.height - _, nc = out0_shape # number of anchors, number of classes - # _, nc = out0.type.multiArrayType.shape - assert len(names) == nc, f"{len(names)} names found for nc={nc}" # check - - # Define output shapes (missing) - out0.type.multiArrayType.shape[:] = out0_shape # (3780, 80) - out1.type.multiArrayType.shape[:] = out1_shape # (3780, 4) - # spec.neuralNetwork.preprocessing[0].featureName = '0' - - # Flexible input shapes - # from coremltools.models.neural_network import flexible_shape_utils - # s = [] # shapes - # s.append(flexible_shape_utils.NeuralNetworkImageSize(320, 192)) - # s.append(flexible_shape_utils.NeuralNetworkImageSize(640, 384)) # (height, width) - # flexible_shape_utils.add_enumerated_image_sizes(spec, feature_name='image', sizes=s) - # r = flexible_shape_utils.NeuralNetworkImageSizeRange() # shape ranges - # r.add_height_range((192, 640)) - # r.add_width_range((192, 640)) - # flexible_shape_utils.update_image_size_range(spec, feature_name='image', size_range=r) - - # Print - # print(spec.description) - - # Model from spec - model = ct.models.MLModel(spec, weights_dir=weights_dir) - - # 3. Create NMS protobuf - nms_spec = ct.proto.Model_pb2.Model() - nms_spec.specificationVersion = 5 - for i in range(2): - decoder_output = model._spec.description.output[i].SerializeToString() - nms_spec.description.input.add() - nms_spec.description.input[i].ParseFromString(decoder_output) - nms_spec.description.output.add() - nms_spec.description.output[i].ParseFromString(decoder_output) - - nms_spec.description.output[0].name = "confidence" - nms_spec.description.output[1].name = "coordinates" - - output_sizes = [nc, 4] - for i in range(2): - ma_type = nms_spec.description.output[i].type.multiArrayType - ma_type.shapeRange.sizeRanges.add() - ma_type.shapeRange.sizeRanges[0].lowerBound = 0 - ma_type.shapeRange.sizeRanges[0].upperBound = -1 - ma_type.shapeRange.sizeRanges.add() - ma_type.shapeRange.sizeRanges[1].lowerBound = output_sizes[i] - ma_type.shapeRange.sizeRanges[1].upperBound = output_sizes[i] - del ma_type.shape[:] - - nms = nms_spec.nonMaximumSuppression - nms.confidenceInputFeatureName = out0.name # 1x507x80 - nms.coordinatesInputFeatureName = out1.name # 1x507x4 - nms.confidenceOutputFeatureName = "confidence" - nms.coordinatesOutputFeatureName = "coordinates" - nms.iouThresholdInputFeatureName = "iouThreshold" - nms.confidenceThresholdInputFeatureName = "confidenceThreshold" - nms.iouThreshold = 0.45 - nms.confidenceThreshold = 0.25 - nms.pickTop.perClass = True - nms.stringClassLabels.vector.extend(names.values()) - nms_model = ct.models.MLModel(nms_spec) - - # 4. Pipeline models together - pipeline = ct.models.pipeline.Pipeline( - input_features=[ - ("image", ct.models.datatypes.Array(3, ny, nx)), - ("iouThreshold", ct.models.datatypes.Double()), - ("confidenceThreshold", ct.models.datatypes.Double()), - ], - output_features=["confidence", "coordinates"], - ) - pipeline.add_model(model) - pipeline.add_model(nms_model) - - # Correct datatypes - pipeline.spec.description.input[0].ParseFromString(model._spec.description.input[0].SerializeToString()) - pipeline.spec.description.output[0].ParseFromString(nms_model._spec.description.output[0].SerializeToString()) - pipeline.spec.description.output[1].ParseFromString(nms_model._spec.description.output[1].SerializeToString()) - - # Update metadata - pipeline.spec.specificationVersion = 5 - pipeline.spec.description.metadata.userDefined.update( - {"IoU threshold": str(nms.iouThreshold), "Confidence threshold": str(nms.confidenceThreshold)} - ) - - # Save the model - model = ct.models.MLModel(pipeline.spec, weights_dir=weights_dir) - model.input_description["image"] = "Input image" - model.input_description["iouThreshold"] = f"(optional) IoU threshold override (default: {nms.iouThreshold})" - model.input_description["confidenceThreshold"] = ( - f"(optional) Confidence threshold override (default: {nms.confidenceThreshold})" - ) - model.output_description["confidence"] = 'Boxes × Class confidence (see user-defined metadata "classes")' - model.output_description["coordinates"] = "Boxes × [x, y, width, height] (relative to image size)" - LOGGER.info(f"{prefix} pipeline success") - return model - - def add_callback(self, event: str, callback): - """Appends the given callback.""" - self.callbacks[event].append(callback) - - def run_callbacks(self, event: str): - """Execute all callbacks for a given event.""" - for callback in self.callbacks.get(event, []): - callback(self) - - -class IOSDetectModel(torch.nn.Module): - """Wrap an Ultralytics YOLO model for Apple iOS CoreML export.""" - - def __init__(self, model, im): - """Initialize the IOSDetectModel class with a YOLO model and example image.""" - super().__init__() - _, _, h, w = im.shape # batch, channel, height, width - self.model = model - self.nc = len(model.names) # number of classes - if w == h: - self.normalize = 1.0 / w # scalar - else: - self.normalize = torch.tensor([1.0 / w, 1.0 / h, 1.0 / w, 1.0 / h]) # broadcast (slower, smaller) - - def forward(self, x): - """Normalize predictions of object detection model with input size-dependent factors.""" - xywh, cls = self.model(x)[0].transpose(0, 1).split((4, self.nc), 1) - return cls, xywh * self.normalize # confidence (3780, 80), coordinates (3780, 4) diff --git a/ultralytics-main/ultralytics/engine/model.py b/ultralytics-main/ultralytics/engine/model.py deleted file mode 100644 index ace045f..0000000 --- a/ultralytics-main/ultralytics/engine/model.py +++ /dev/null @@ -1,821 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import inspect -import sys -from pathlib import Path -from typing import Union - -import numpy as np -import torch - -from ultralytics.cfg import TASK2DATA, get_cfg, get_save_dir -from ultralytics.hub.utils import HUB_WEB_ROOT -from ultralytics.nn.tasks import attempt_load_one_weight, guess_model_task, nn, yaml_model_load -from ultralytics.utils import ASSETS, DEFAULT_CFG_DICT, LOGGER, RANK, SETTINGS, callbacks, checks, emojis, yaml_load - - -class Model(nn.Module): - """ - A base class for implementing YOLO models, unifying APIs across different model types. - - This class provides a common interface for various operations related to YOLO models, such as training, - validation, prediction, exporting, and benchmarking. It handles different types of models, including those - loaded from local files, Ultralytics HUB, or Triton Server. The class is designed to be flexible and - extendable for different tasks and model configurations. - - Args: - model (Union[str, Path], optional): Path or name of the model to load or create. This can be a local file - path, a model name from Ultralytics HUB, or a Triton Server model. Defaults to 'yolov8n.pt'. - task (Any, optional): The task type associated with the YOLO model. This can be used to specify the model's - application domain, such as object detection, segmentation, etc. Defaults to None. - verbose (bool, optional): If True, enables verbose output during the model's operations. Defaults to False. - - Attributes: - callbacks (dict): A dictionary of callback functions for various events during model operations. - predictor (BasePredictor): The predictor object used for making predictions. - model (nn.Module): The underlying PyTorch model. - trainer (BaseTrainer): The trainer object used for training the model. - ckpt (dict): The checkpoint data if the model is loaded from a *.pt file. - cfg (str): The configuration of the model if loaded from a *.yaml file. - ckpt_path (str): The path to the checkpoint file. - overrides (dict): A dictionary of overrides for model configuration. - metrics (dict): The latest training/validation metrics. - session (HUBTrainingSession): The Ultralytics HUB session, if applicable. - task (str): The type of task the model is intended for. - model_name (str): The name of the model. - - Methods: - __call__: Alias for the predict method, enabling the model instance to be callable. - _new: Initializes a new model based on a configuration file. - _load: Loads a model from a checkpoint file. - _check_is_pytorch_model: Ensures that the model is a PyTorch model. - reset_weights: Resets the model's weights to their initial state. - load: Loads model weights from a specified file. - save: Saves the current state of the model to a file. - info: Logs or returns information about the model. - fuse: Fuses Conv2d and BatchNorm2d layers for optimized inference. - predict: Performs object detection predictions. - track: Performs object tracking. - val: Validates the model on a dataset. - benchmark: Benchmarks the model on various export formats. - export: Exports the model to different formats. - train: Trains the model on a dataset. - tune: Performs hyperparameter tuning. - _apply: Applies a function to the model's tensors. - add_callback: Adds a callback function for an event. - clear_callback: Clears all callbacks for an event. - reset_callbacks: Resets all callbacks to their default functions. - _get_hub_session: Retrieves or creates an Ultralytics HUB session. - is_triton_model: Checks if a model is a Triton Server model. - is_hub_model: Checks if a model is an Ultralytics HUB model. - _reset_ckpt_args: Resets checkpoint arguments when loading a PyTorch model. - _smart_load: Loads the appropriate module based on the model task. - task_map: Provides a mapping from model tasks to corresponding classes. - - Raises: - FileNotFoundError: If the specified model file does not exist or is inaccessible. - ValueError: If the model file or configuration is invalid or unsupported. - ImportError: If required dependencies for specific model types (like HUB SDK) are not installed. - TypeError: If the model is not a PyTorch model when required. - AttributeError: If required attributes or methods are not implemented or available. - NotImplementedError: If a specific model task or mode is not supported. - """ - - def __init__( - self, - model: Union[str, Path] = "yolov8n.pt", - task: str = None, - verbose: bool = False, - ) -> None: - """ - Initializes a new instance of the YOLO model class. - - This constructor sets up the model based on the provided model path or name. It handles various types of model - sources, including local files, Ultralytics HUB models, and Triton Server models. The method initializes several - important attributes of the model and prepares it for operations like training, prediction, or export. - - Args: - model (Union[str, Path], optional): The path or model file to load or create. This can be a local - file path, a model name from Ultralytics HUB, or a Triton Server model. Defaults to 'yolov8n.pt'. - task (Any, optional): The task type associated with the YOLO model, specifying its application domain. - Defaults to None. - verbose (bool, optional): If True, enables verbose output during the model's initialization and subsequent - operations. Defaults to False. - - Raises: - FileNotFoundError: If the specified model file does not exist or is inaccessible. - ValueError: If the model file or configuration is invalid or unsupported. - ImportError: If required dependencies for specific model types (like HUB SDK) are not installed. - """ - super().__init__() - self.callbacks = callbacks.get_default_callbacks() - self.predictor = None # reuse predictor - self.model = None # model object - self.trainer = None # trainer object - self.ckpt = None # if loaded from *.pt - self.cfg = None # if loaded from *.yaml - self.ckpt_path = None - self.overrides = {} # overrides for trainer object - self.metrics = None # validation/training metrics - self.session = None # HUB session - self.task = task # task type - self.model_name = model = str(model).strip() # strip spaces - - # Check if Ultralytics HUB model from https://hub.ultralytics.com - if self.is_hub_model(model): - # Fetch model from HUB - checks.check_requirements("hub-sdk>=0.0.5") - self.session = self._get_hub_session(model) - model = self.session.model_file - - # Check if Triton Server model - elif self.is_triton_model(model): - self.model = model - self.task = task - return - - # Load or create new YOLO model - model = checks.check_model_file_from_stem(model) # add suffix, i.e. yolov8n -> yolov8n.pt - if Path(model).suffix in (".yaml", ".yml"): - self._new(model, task=task, verbose=verbose) - else: - self._load(model, task=task) - - self.model_name = model - - def __call__( - self, - source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None, - stream: bool = False, - **kwargs, - ) -> list: - """ - An alias for the predict method, enabling the model instance to be callable. - - This method simplifies the process of making predictions by allowing the model instance to be called directly - with the required arguments for prediction. - - Args: - source (str | Path | int | PIL.Image | np.ndarray, optional): The source of the image for making - predictions. Accepts various types, including file paths, URLs, PIL images, and numpy arrays. - Defaults to None. - stream (bool, optional): If True, treats the input source as a continuous stream for predictions. - Defaults to False. - **kwargs (any): Additional keyword arguments for configuring the prediction process. - - Returns: - (List[ultralytics.engine.results.Results]): A list of prediction results, encapsulated in the Results class. - """ - return self.predict(source, stream, **kwargs) - - @staticmethod - def _get_hub_session(model: str): - """Creates a session for Hub Training.""" - from ultralytics.hub.session import HUBTrainingSession - - session = HUBTrainingSession(model) - return session if session.client.authenticated else None - - @staticmethod - def is_triton_model(model: str) -> bool: - """Is model a Triton Server URL string, i.e. :////""" - from urllib.parse import urlsplit - - url = urlsplit(model) - return url.netloc and url.path and url.scheme in {"http", "grpc"} - - @staticmethod - def is_hub_model(model: str) -> bool: - """Check if the provided model is a HUB model.""" - return any( - ( - model.startswith(f"{HUB_WEB_ROOT}/models/"), # i.e. https://hub.ultralytics.com/models/MODEL_ID - [len(x) for x in model.split("_")] == [42, 20], # APIKEY_MODELID - len(model) == 20 and not Path(model).exists() and all(x not in model for x in "./\\"), # MODELID - ) - ) - - def _new(self, cfg: str, task=None, model=None, verbose=False) -> None: - """ - Initializes a new model and infers the task type from the model definitions. - - Args: - cfg (str): model configuration file - task (str | None): model task - model (BaseModel): Customized model. - verbose (bool): display model info on load - """ - cfg_dict = yaml_model_load(cfg) - self.cfg = cfg - self.task = task or guess_model_task(cfg_dict) - self.model = (model or self._smart_load("model"))(cfg_dict, verbose=verbose and RANK == -1) # build model - self.overrides["model"] = self.cfg - self.overrides["task"] = self.task - - # Below added to allow export from YAMLs - self.model.args = {**DEFAULT_CFG_DICT, **self.overrides} # combine default and model args (prefer model args) - self.model.task = self.task - - def _load(self, weights: str, task=None) -> None: - """ - Initializes a new model and infers the task type from the model head. - - Args: - weights (str): model checkpoint to be loaded - task (str | None): model task - """ - suffix = Path(weights).suffix - if suffix == ".pt": - self.model, self.ckpt = attempt_load_one_weight(weights) - self.task = self.model.args["task"] - self.overrides = self.model.args = self._reset_ckpt_args(self.model.args) - self.ckpt_path = self.model.pt_path - else: - weights = checks.check_file(weights) - self.model, self.ckpt = weights, None - self.task = task or guess_model_task(weights) - self.ckpt_path = weights - self.overrides["model"] = weights - self.overrides["task"] = self.task - - def _check_is_pytorch_model(self) -> None: - """Raises TypeError is model is not a PyTorch model.""" - pt_str = isinstance(self.model, (str, Path)) and Path(self.model).suffix == ".pt" - pt_module = isinstance(self.model, nn.Module) - if not (pt_module or pt_str): - raise TypeError( - f"model='{self.model}' should be a *.pt PyTorch model to run this method, but is a different format. " - f"PyTorch models can train, val, predict and export, i.e. 'model.train(data=...)', but exported " - f"formats like ONNX, TensorRT etc. only support 'predict' and 'val' modes, " - f"i.e. 'yolo predict model=yolov8n.onnx'.\nTo run CUDA or MPS inference please pass the device " - f"argument directly in your inference command, i.e. 'model.predict(source=..., device=0)'" - ) - - def reset_weights(self) -> "Model": - """ - Resets the model parameters to randomly initialized values, effectively discarding all training information. - - This method iterates through all modules in the model and resets their parameters if they have a - 'reset_parameters' method. It also ensures that all parameters have 'requires_grad' set to True, enabling them - to be updated during training. - - Returns: - self (ultralytics.engine.model.Model): The instance of the class with reset weights. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - for m in self.model.modules(): - if hasattr(m, "reset_parameters"): - m.reset_parameters() - for p in self.model.parameters(): - p.requires_grad = True - return self - - def load(self, weights: Union[str, Path] = "yolov8n.pt") -> "Model": - """ - Loads parameters from the specified weights file into the model. - - This method supports loading weights from a file or directly from a weights object. It matches parameters by - name and shape and transfers them to the model. - - Args: - weights (str | Path): Path to the weights file or a weights object. Defaults to 'yolov8n.pt'. - - Returns: - self (ultralytics.engine.model.Model): The instance of the class with loaded weights. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - if isinstance(weights, (str, Path)): - weights, self.ckpt = attempt_load_one_weight(weights) - self.model.load(weights) - return self - - def save(self, filename: Union[str, Path] = "saved_model.pt", use_dill=True) -> None: - """ - Saves the current model state to a file. - - This method exports the model's checkpoint (ckpt) to the specified filename. - - Args: - filename (str | Path): The name of the file to save the model to. Defaults to 'saved_model.pt'. - use_dill (bool): Whether to try using dill for serialization if available. Defaults to True. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - from ultralytics import __version__ - from datetime import datetime - - updates = { - "date": datetime.now().isoformat(), - "version": __version__, - "license": "AGPL-3.0 License (https://ultralytics.com/license)", - "docs": "https://docs.ultralytics.com", - } - torch.save({**self.ckpt, **updates}, filename, use_dill=use_dill) - - def info(self, detailed: bool = False, verbose: bool = True): - """ - Logs or returns model information. - - This method provides an overview or detailed information about the model, depending on the arguments passed. - It can control the verbosity of the output. - - Args: - detailed (bool): If True, shows detailed information about the model. Defaults to False. - verbose (bool): If True, prints the information. If False, returns the information. Defaults to True. - - Returns: - (list): Various types of information about the model, depending on the 'detailed' and 'verbose' parameters. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - return self.model.info(detailed=detailed, verbose=verbose) - - def fuse(self): - """ - Fuses Conv2d and BatchNorm2d layers in the model. - - This method optimizes the model by fusing Conv2d and BatchNorm2d layers, which can improve inference speed. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - self.model.fuse() - - def embed( - self, - source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None, - stream: bool = False, - **kwargs, - ) -> list: - """ - Generates image embeddings based on the provided source. - - This method is a wrapper around the 'predict()' method, focusing on generating embeddings from an image source. - It allows customization of the embedding process through various keyword arguments. - - Args: - source (str | int | PIL.Image | np.ndarray): The source of the image for generating embeddings. - The source can be a file path, URL, PIL image, numpy array, etc. Defaults to None. - stream (bool): If True, predictions are streamed. Defaults to False. - **kwargs (any): Additional keyword arguments for configuring the embedding process. - - Returns: - (List[torch.Tensor]): A list containing the image embeddings. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - if not kwargs.get("embed"): - kwargs["embed"] = [len(self.model.model) - 2] # embed second-to-last layer if no indices passed - return self.predict(source, stream, **kwargs) - - def predict( - self, - source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None, - stream: bool = False, - predictor=None, - **kwargs, - ) -> list: - """ - Performs predictions on the given image source using the YOLO model. - - This method facilitates the prediction process, allowing various configurations through keyword arguments. - It supports predictions with custom predictors or the default predictor method. The method handles different - types of image sources and can operate in a streaming mode. It also provides support for SAM-type models - through 'prompts'. - - The method sets up a new predictor if not already present and updates its arguments with each call. - It also issues a warning and uses default assets if the 'source' is not provided. The method determines if it - is being called from the command line interface and adjusts its behavior accordingly, including setting defaults - for confidence threshold and saving behavior. - - Args: - source (str | int | PIL.Image | np.ndarray, optional): The source of the image for making predictions. - Accepts various types, including file paths, URLs, PIL images, and numpy arrays. Defaults to ASSETS. - stream (bool, optional): Treats the input source as a continuous stream for predictions. Defaults to False. - predictor (BasePredictor, optional): An instance of a custom predictor class for making predictions. - If None, the method uses a default predictor. Defaults to None. - **kwargs (any): Additional keyword arguments for configuring the prediction process. These arguments allow - for further customization of the prediction behavior. - - Returns: - (List[ultralytics.engine.results.Results]): A list of prediction results, encapsulated in the Results class. - - Raises: - AttributeError: If the predictor is not properly set up. - """ - if source is None: - source = ASSETS - LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using 'source={source}'.") - - is_cli = (sys.argv[0].endswith("yolo") or sys.argv[0].endswith("ultralytics")) and any( - x in sys.argv for x in ("predict", "track", "mode=predict", "mode=track") - ) - - custom = {"conf": 0.25, "batch": 1, "save": is_cli, "mode": "predict"} # method defaults - args = {**self.overrides, **custom, **kwargs} # highest priority args on the right - prompts = args.pop("prompts", None) # for SAM-type models - - if not self.predictor: - self.predictor = predictor or self._smart_load("predictor")(overrides=args, _callbacks=self.callbacks) - self.predictor.setup_model(model=self.model, verbose=is_cli) - else: # only update args if predictor is already setup - self.predictor.args = get_cfg(self.predictor.args, args) - if "project" in args or "name" in args: - self.predictor.save_dir = get_save_dir(self.predictor.args) - if prompts and hasattr(self.predictor, "set_prompts"): # for SAM-type models - self.predictor.set_prompts(prompts) - return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream) - - def track( - self, - source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None, - stream: bool = False, - persist: bool = False, - **kwargs, - ) -> list: - """ - Conducts object tracking on the specified input source using the registered trackers. - - This method performs object tracking using the model's predictors and optionally registered trackers. It is - capable of handling different types of input sources such as file paths or video streams. The method supports - customization of the tracking process through various keyword arguments. It registers trackers if they are not - already present and optionally persists them based on the 'persist' flag. - - The method sets a default confidence threshold specifically for ByteTrack-based tracking, which requires low - confidence predictions as input. The tracking mode is explicitly set in the keyword arguments. - - Args: - source (str, optional): The input source for object tracking. It can be a file path, URL, or video stream. - stream (bool, optional): Treats the input source as a continuous video stream. Defaults to False. - persist (bool, optional): Persists the trackers between different calls to this method. Defaults to False. - **kwargs (any): Additional keyword arguments for configuring the tracking process. These arguments allow - for further customization of the tracking behavior. - - Returns: - (List[ultralytics.engine.results.Results]): A list of tracking results, encapsulated in the Results class. - - Raises: - AttributeError: If the predictor does not have registered trackers. - """ - if not hasattr(self.predictor, "trackers"): - from ultralytics.trackers import register_tracker - - register_tracker(self, persist) - kwargs["conf"] = kwargs.get("conf") or 0.1 # ByteTrack-based method needs low confidence predictions as input - kwargs["batch"] = kwargs.get("batch") or 1 # batch-size 1 for tracking in videos - kwargs["mode"] = "track" - return self.predict(source=source, stream=stream, **kwargs) - - def val( - self, - validator=None, - **kwargs, - ): - """ - Validates the model using a specified dataset and validation configuration. - - This method facilitates the model validation process, allowing for a range of customization through various - settings and configurations. It supports validation with a custom validator or the default validation approach. - The method combines default configurations, method-specific defaults, and user-provided arguments to configure - the validation process. After validation, it updates the model's metrics with the results obtained from the - validator. - - The method supports various arguments that allow customization of the validation process. For a comprehensive - list of all configurable options, users should refer to the 'configuration' section in the documentation. - - Args: - validator (BaseValidator, optional): An instance of a custom validator class for validating the model. If - None, the method uses a default validator. Defaults to None. - **kwargs (any): Arbitrary keyword arguments representing the validation configuration. These arguments are - used to customize various aspects of the validation process. - - Returns: - (dict): Validation metrics obtained from the validation process. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - custom = {"rect": True} # method defaults - args = {**self.overrides, **custom, **kwargs, "mode": "val"} # highest priority args on the right - - validator = (validator or self._smart_load("validator"))(args=args, _callbacks=self.callbacks) - validator(model=self.model) - self.metrics = validator.metrics - return validator.metrics - - def benchmark( - self, - **kwargs, - ): - """ - Benchmarks the model across various export formats to evaluate performance. - - This method assesses the model's performance in different export formats, such as ONNX, TorchScript, etc. - It uses the 'benchmark' function from the ultralytics.utils.benchmarks module. The benchmarking is configured - using a combination of default configuration values, model-specific arguments, method-specific defaults, and - any additional user-provided keyword arguments. - - The method supports various arguments that allow customization of the benchmarking process, such as dataset - choice, image size, precision modes, device selection, and verbosity. For a comprehensive list of all - configurable options, users should refer to the 'configuration' section in the documentation. - - Args: - **kwargs (any): Arbitrary keyword arguments to customize the benchmarking process. These are combined with - default configurations, model-specific arguments, and method defaults. - - Returns: - (dict): A dictionary containing the results of the benchmarking process. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - from ultralytics.utils.benchmarks import benchmark - - custom = {"verbose": False} # method defaults - args = {**DEFAULT_CFG_DICT, **self.model.args, **custom, **kwargs, "mode": "benchmark"} - return benchmark( - model=self, - data=kwargs.get("data"), # if no 'data' argument passed set data=None for default datasets - imgsz=args["imgsz"], - half=args["half"], - int8=args["int8"], - device=args["device"], - verbose=kwargs.get("verbose"), - ) - - def export( - self, - **kwargs, - ): - """ - Exports the model to a different format suitable for deployment. - - This method facilitates the export of the model to various formats (e.g., ONNX, TorchScript) for deployment - purposes. It uses the 'Exporter' class for the export process, combining model-specific overrides, method - defaults, and any additional arguments provided. The combined arguments are used to configure export settings. - - The method supports a wide range of arguments to customize the export process. For a comprehensive list of all - possible arguments, refer to the 'configuration' section in the documentation. - - Args: - **kwargs (any): Arbitrary keyword arguments to customize the export process. These are combined with the - model's overrides and method defaults. - - Returns: - (object): The exported model in the specified format, or an object related to the export process. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - from .exporter import Exporter - - custom = {"imgsz": self.model.args["imgsz"], "batch": 1, "data": None, "verbose": False} # method defaults - args = {**self.overrides, **custom, **kwargs, "mode": "export"} # highest priority args on the right - return Exporter(overrides=args, _callbacks=self.callbacks)(model=self.model) - - def train( - self, - trainer=None, - **kwargs, - ): - """ - Trains the model using the specified dataset and training configuration. - - This method facilitates model training with a range of customizable settings and configurations. It supports - training with a custom trainer or the default training approach defined in the method. The method handles - different scenarios, such as resuming training from a checkpoint, integrating with Ultralytics HUB, and - updating model and configuration after training. - - When using Ultralytics HUB, if the session already has a loaded model, the method prioritizes HUB training - arguments and issues a warning if local arguments are provided. It checks for pip updates and combines default - configurations, method-specific defaults, and user-provided arguments to configure the training process. After - training, it updates the model and its configurations, and optionally attaches metrics. - - Args: - trainer (BaseTrainer, optional): An instance of a custom trainer class for training the model. If None, the - method uses a default trainer. Defaults to None. - **kwargs (any): Arbitrary keyword arguments representing the training configuration. These arguments are - used to customize various aspects of the training process. - - Returns: - (dict | None): Training metrics if available and training is successful; otherwise, None. - - Raises: - AssertionError: If the model is not a PyTorch model. - PermissionError: If there is a permission issue with the HUB session. - ModuleNotFoundError: If the HUB SDK is not installed. - """ - self._check_is_pytorch_model() - if hasattr(self.session, "model") and self.session.model.id: # Ultralytics HUB session with loaded model - if any(kwargs): - LOGGER.warning("WARNING ⚠️ using HUB training arguments, ignoring local training arguments.") - kwargs = self.session.train_args # overwrite kwargs - - checks.check_pip_update_available() - - overrides = yaml_load(checks.check_yaml(kwargs["cfg"])) if kwargs.get("cfg") else self.overrides - custom = {"data": DEFAULT_CFG_DICT["data"] or TASK2DATA[self.task]} # method defaults - args = {**overrides, **custom, **kwargs, "mode": "train"} # highest priority args on the right - if args.get("resume"): - args["resume"] = self.ckpt_path - - self.trainer = (trainer or self._smart_load("trainer"))(overrides=args, _callbacks=self.callbacks) - if not args.get("resume"): # manually set model only if not resuming - self.trainer.model = self.trainer.get_model(weights=self.model if self.ckpt else None, cfg=self.model.yaml) - self.model = self.trainer.model - - if SETTINGS["hub"] is True and not self.session: - # Create a model in HUB - try: - self.session = self._get_hub_session(self.model_name) - if self.session: - self.session.create_model(args) - # Check model was created - if not getattr(self.session.model, "id", None): - self.session = None - except (PermissionError, ModuleNotFoundError): - # Ignore PermissionError and ModuleNotFoundError which indicates hub-sdk not installed - pass - - self.trainer.hub_session = self.session # attach optional HUB session - self.trainer.train() - # Update model and cfg after training - if RANK in (-1, 0): - ckpt = self.trainer.best if self.trainer.best.exists() else self.trainer.last - self.model, _ = attempt_load_one_weight(ckpt) - self.overrides = self.model.args - self.metrics = getattr(self.trainer.validator, "metrics", None) # TODO: no metrics returned by DDP - return self.metrics - - def tune( - self, - use_ray=False, - iterations=10, - *args, - **kwargs, - ): - """ - Conducts hyperparameter tuning for the model, with an option to use Ray Tune. - - This method supports two modes of hyperparameter tuning: using Ray Tune or a custom tuning method. - When Ray Tune is enabled, it leverages the 'run_ray_tune' function from the ultralytics.utils.tuner module. - Otherwise, it uses the internal 'Tuner' class for tuning. The method combines default, overridden, and - custom arguments to configure the tuning process. - - Args: - use_ray (bool): If True, uses Ray Tune for hyperparameter tuning. Defaults to False. - iterations (int): The number of tuning iterations to perform. Defaults to 10. - *args (list): Variable length argument list for additional arguments. - **kwargs (any): Arbitrary keyword arguments. These are combined with the model's overrides and defaults. - - Returns: - (dict): A dictionary containing the results of the hyperparameter search. - - Raises: - AssertionError: If the model is not a PyTorch model. - """ - self._check_is_pytorch_model() - if use_ray: - from ultralytics.utils.tuner import run_ray_tune - - return run_ray_tune(self, max_samples=iterations, *args, **kwargs) - else: - from .tuner import Tuner - - custom = {} # method defaults - args = {**self.overrides, **custom, **kwargs, "mode": "train"} # highest priority args on the right - return Tuner(args=args, _callbacks=self.callbacks)(model=self, iterations=iterations) - - def _apply(self, fn) -> "Model": - """Apply to(), cpu(), cuda(), half(), float() to model tensors that are not parameters or registered buffers.""" - self._check_is_pytorch_model() - self = super()._apply(fn) # noqa - self.predictor = None # reset predictor as device may have changed - self.overrides["device"] = self.device # was str(self.device) i.e. device(type='cuda', index=0) -> 'cuda:0' - return self - - @property - def names(self) -> list: - """ - Retrieves the class names associated with the loaded model. - - This property returns the class names if they are defined in the model. It checks the class names for validity - using the 'check_class_names' function from the ultralytics.nn.autobackend module. - - Returns: - (list | None): The class names of the model if available, otherwise None. - """ - from ultralytics.nn.autobackend import check_class_names - - return check_class_names(self.model.names) if hasattr(self.model, "names") else None - - @property - def device(self) -> torch.device: - """ - Retrieves the device on which the model's parameters are allocated. - - This property is used to determine whether the model's parameters are on CPU or GPU. It only applies to models - that are instances of nn.Module. - - Returns: - (torch.device | None): The device (CPU/GPU) of the model if it is a PyTorch model, otherwise None. - """ - return next(self.model.parameters()).device if isinstance(self.model, nn.Module) else None - - @property - def transforms(self): - """ - Retrieves the transformations applied to the input data of the loaded model. - - This property returns the transformations if they are defined in the model. - - Returns: - (object | None): The transform object of the model if available, otherwise None. - """ - return self.model.transforms if hasattr(self.model, "transforms") else None - - def add_callback(self, event: str, func) -> None: - """ - Adds a callback function for a specified event. - - This method allows the user to register a custom callback function that is triggered on a specific event during - model training or inference. - - Args: - event (str): The name of the event to attach the callback to. - func (callable): The callback function to be registered. - - Raises: - ValueError: If the event name is not recognized. - """ - self.callbacks[event].append(func) - - def clear_callback(self, event: str) -> None: - """ - Clears all callback functions registered for a specified event. - - This method removes all custom and default callback functions associated with the given event. - - Args: - event (str): The name of the event for which to clear the callbacks. - - Raises: - ValueError: If the event name is not recognized. - """ - self.callbacks[event] = [] - - def reset_callbacks(self) -> None: - """ - Resets all callbacks to their default functions. - - This method reinstates the default callback functions for all events, removing any custom callbacks that were - added previously. - """ - for event in callbacks.default_callbacks.keys(): - self.callbacks[event] = [callbacks.default_callbacks[event][0]] - - @staticmethod - def _reset_ckpt_args(args: dict) -> dict: - """Reset arguments when loading a PyTorch model.""" - include = {"imgsz", "data", "task", "single_cls"} # only remember these arguments when loading a PyTorch model - return {k: v for k, v in args.items() if k in include} - - # def __getattr__(self, attr): - # """Raises error if object has no requested attribute.""" - # name = self.__class__.__name__ - # raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}") - - def _smart_load(self, key: str): - """Load model/trainer/validator/predictor.""" - try: - return self.task_map[self.task][key] - except Exception as e: - name = self.__class__.__name__ - mode = inspect.stack()[1][3] # get the function name. - raise NotImplementedError( - emojis(f"WARNING ⚠️ '{name}' model does not support '{mode}' mode for '{self.task}' task yet.") - ) from e - - @property - def task_map(self) -> dict: - """ - Map head to model, trainer, validator, and predictor classes. - - Returns: - task_map (dict): The map of model task to mode classes. - """ - raise NotImplementedError("Please provide task map for your model!") diff --git a/ultralytics-main/ultralytics/engine/predictor.py b/ultralytics-main/ultralytics/engine/predictor.py deleted file mode 100644 index 921f273..0000000 --- a/ultralytics-main/ultralytics/engine/predictor.py +++ /dev/null @@ -1,397 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Run prediction on images, videos, directories, globs, YouTube, webcam, streams, etc. - -Usage - sources: - $ yolo mode=predict model=yolov8n.pt source=0 # webcam - img.jpg # image - vid.mp4 # video - screen # screenshot - path/ # directory - list.txt # list of images - list.streams # list of streams - 'path/*.jpg' # glob - 'https://youtu.be/LNwODJXcvt4' # YouTube - 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP, TCP stream - -Usage - formats: - $ yolo mode=predict model=yolov8n.pt # PyTorch - yolov8n.torchscript # TorchScript - yolov8n.onnx # ONNX Runtime or OpenCV DNN with dnn=True - yolov8n_openvino_model # OpenVINO - yolov8n.engine # TensorRT - yolov8n.mlpackage # CoreML (macOS-only) - yolov8n_saved_model # TensorFlow SavedModel - yolov8n.pb # TensorFlow GraphDef - yolov8n.tflite # TensorFlow Lite - yolov8n_edgetpu.tflite # TensorFlow Edge TPU - yolov8n_paddle_model # PaddlePaddle - yolov8n_ncnn_model # NCNN -""" - -import platform -import re -import threading -from pathlib import Path - -import cv2 -import numpy as np -import torch - -from ultralytics.cfg import get_cfg, get_save_dir -from ultralytics.data import load_inference_source -from ultralytics.data.augment import LetterBox, classify_transforms -from ultralytics.nn.autobackend import AutoBackend -from ultralytics.utils import DEFAULT_CFG, LOGGER, MACOS, WINDOWS, callbacks, colorstr, ops -from ultralytics.utils.checks import check_imgsz, check_imshow -from ultralytics.utils.files import increment_path -from ultralytics.utils.torch_utils import select_device, smart_inference_mode - -STREAM_WARNING = """ -WARNING ⚠️ inference results will accumulate in RAM unless `stream=True` is passed, causing potential out-of-memory -errors for large sources or long-running streams and videos. See https://docs.ultralytics.com/modes/predict/ for help. - -Example: - results = model(source=..., stream=True) # generator of Results objects - for r in results: - boxes = r.boxes # Boxes object for bbox outputs - masks = r.masks # Masks object for segment masks outputs - probs = r.probs # Class probabilities for classification outputs -""" - - -class BasePredictor: - """ - BasePredictor. - - A base class for creating predictors. - - Attributes: - args (SimpleNamespace): Configuration for the predictor. - save_dir (Path): Directory to save results. - done_warmup (bool): Whether the predictor has finished setup. - model (nn.Module): Model used for prediction. - data (dict): Data configuration. - device (torch.device): Device used for prediction. - dataset (Dataset): Dataset used for prediction. - vid_writer (dict): Dictionary of {save_path: video_writer, ...} writer for saving video output. - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """ - Initializes the BasePredictor class. - - Args: - cfg (str, optional): Path to a configuration file. Defaults to DEFAULT_CFG. - overrides (dict, optional): Configuration overrides. Defaults to None. - """ - self.args = get_cfg(cfg, overrides) - self.save_dir = get_save_dir(self.args) - if self.args.conf is None: - self.args.conf = 0.25 # default conf=0.25 - self.done_warmup = False - if self.args.show: - self.args.show = check_imshow(warn=True) - - # Usable if setup is done - self.model = None - self.data = self.args.data # data_dict - self.imgsz = None - self.device = None - self.dataset = None - self.vid_writer = {} # dict of {save_path: video_writer, ...} - self.plotted_img = None - self.source_type = None - self.seen = 0 - self.windows = [] - self.batch = None - self.results = None - self.transforms = None - self.callbacks = _callbacks or callbacks.get_default_callbacks() - self.txt_path = None - self._lock = threading.Lock() # for automatic thread-safe inference - callbacks.add_integration_callbacks(self) - - def preprocess(self, im): - """ - Prepares input image before inference. - - Args: - im (torch.Tensor | List(np.ndarray)): BCHW for tensor, [(HWC) x B] for list. - """ - not_tensor = not isinstance(im, torch.Tensor) - if not_tensor: - im = np.stack(self.pre_transform(im)) - im = im[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW, (n, 3, h, w) - im = np.ascontiguousarray(im) # contiguous - im = torch.from_numpy(im) - - im = im.to(self.device) - im = im.half() if self.model.fp16 else im.float() # uint8 to fp16/32 - if not_tensor: - im /= 255 # 0 - 255 to 0.0 - 1.0 - return im - - def inference(self, im, *args, **kwargs): - """Runs inference on a given image using the specified model and arguments.""" - visualize = ( - increment_path(self.save_dir / Path(self.batch[0][0]).stem, mkdir=True) - if self.args.visualize and (not self.source_type.tensor) - else False - ) - return self.model(im, augment=self.args.augment, visualize=visualize, embed=self.args.embed, *args, **kwargs) - - def pre_transform(self, im): - """ - Pre-transform input image before inference. - - Args: - im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list. - - Returns: - (list): A list of transformed images. - """ - same_shapes = len({x.shape for x in im}) == 1 - letterbox = LetterBox(self.imgsz, auto=same_shapes and self.model.pt, stride=self.model.stride) - return [letterbox(image=x) for x in im] - - def postprocess(self, preds, img, orig_imgs): - """Post-processes predictions for an image and returns them.""" - return preds - - def __call__(self, source=None, model=None, stream=False, *args, **kwargs): - """Performs inference on an image or stream.""" - self.stream = stream - if stream: - return self.stream_inference(source, model, *args, **kwargs) - else: - return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one - - def predict_cli(self, source=None, model=None): - """ - Method used for CLI prediction. - - It uses always generator as outputs as not required by CLI mode. - """ - gen = self.stream_inference(source, model) - for _ in gen: # noqa, running CLI inference without accumulating any outputs (do not modify) - pass - - def setup_source(self, source): - """Sets up source and inference mode.""" - self.imgsz = check_imgsz(self.args.imgsz, stride=self.model.stride, min_dim=2) # check image size - self.transforms = ( - getattr( - self.model.model, - "transforms", - classify_transforms(self.imgsz[0], crop_fraction=self.args.crop_fraction), - ) - if self.args.task == "classify" - else None - ) - self.dataset = load_inference_source( - source=source, - batch=self.args.batch, - vid_stride=self.args.vid_stride, - buffer=self.args.stream_buffer, - ) - self.source_type = self.dataset.source_type - if not getattr(self, "stream", True) and ( - self.source_type.stream - or self.source_type.screenshot - or len(self.dataset) > 1000 # many images - or any(getattr(self.dataset, "video_flag", [False])) - ): # videos - LOGGER.warning(STREAM_WARNING) - self.vid_writer = {} - - @smart_inference_mode() - def stream_inference(self, source=None, model=None, *args, **kwargs): - """Streams real-time inference on camera feed and saves results to file.""" - if self.args.verbose: - LOGGER.info("") - - # Setup model - if not self.model: - self.setup_model(model) - - with self._lock: # for thread-safe inference - # Setup source every time predict is called - self.setup_source(source if source is not None else self.args.source) - - # Check if save_dir/ label file exists - if self.args.save or self.args.save_txt: - (self.save_dir / "labels" if self.args.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True) - - # Warmup model - if not self.done_warmup: - self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz)) - self.done_warmup = True - - self.seen, self.windows, self.batch = 0, [], None - profilers = ( - ops.Profile(device=self.device), - ops.Profile(device=self.device), - ops.Profile(device=self.device), - ) - self.run_callbacks("on_predict_start") - for self.batch in self.dataset: - self.run_callbacks("on_predict_batch_start") - paths, im0s, s = self.batch - - # Preprocess - with profilers[0]: - im = self.preprocess(im0s) - - # Inference - with profilers[1]: - preds = self.inference(im, *args, **kwargs) - if self.args.embed: - yield from [preds] if isinstance(preds, torch.Tensor) else preds # yield embedding tensors - continue - - # Postprocess - with profilers[2]: - self.results = self.postprocess(preds, im, im0s) - self.run_callbacks("on_predict_postprocess_end") - - # Visualize, save, write results - n = len(im0s) - for i in range(n): - self.seen += 1 - self.results[i].speed = { - "preprocess": profilers[0].dt * 1e3 / n, - "inference": profilers[1].dt * 1e3 / n, - "postprocess": profilers[2].dt * 1e3 / n, - } - if self.args.verbose or self.args.save or self.args.save_txt or self.args.show: - s[i] += self.write_results(i, Path(paths[i]), im, s) - - # Print batch results - if self.args.verbose: - LOGGER.info("\n".join(s)) - - self.run_callbacks("on_predict_batch_end") - yield from self.results - - # Release assets - for v in self.vid_writer.values(): - if isinstance(v, cv2.VideoWriter): - v.release() - - # Print final results - if self.args.verbose and self.seen: - t = tuple(x.t / self.seen * 1e3 for x in profilers) # speeds per image - LOGGER.info( - f"Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape " - f"{(min(self.args.batch, self.seen), 3, *im.shape[2:])}" % t - ) - if self.args.save or self.args.save_txt or self.args.save_crop: - nl = len(list(self.save_dir.glob("labels/*.txt"))) # number of labels - s = f"\n{nl} label{'s' * (nl > 1)} saved to {self.save_dir / 'labels'}" if self.args.save_txt else "" - LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}{s}") - self.run_callbacks("on_predict_end") - - def setup_model(self, model, verbose=True): - """Initialize YOLO model with given parameters and set it to evaluation mode.""" - self.model = AutoBackend( - weights=model or self.args.model, - device=select_device(self.args.device, verbose=verbose), - dnn=self.args.dnn, - data=self.args.data, - fp16=self.args.half, - batch=self.args.batch, - fuse=True, - verbose=verbose, - ) - - self.device = self.model.device # update device - self.args.half = self.model.fp16 # update half - self.model.eval() - - def write_results(self, i, p, im, s): - """Write inference results to a file or directory.""" - string = "" # print string - if len(im.shape) == 3: - im = im[None] # expand for batch dim - if self.source_type.stream or self.source_type.from_img or self.source_type.tensor: # batch_size >= 1 - string += f"{i}: " - frame = self.dataset.count - else: - match = re.search(r"frame (\d+)/", s[i]) - frame = int(match.group(1)) if match else None # 0 if frame undetermined - - self.txt_path = self.save_dir / "labels" / (p.stem + ("" if self.dataset.mode == "image" else f"_{frame}")) - string += "%gx%g " % im.shape[2:] - result = self.results[i] - result.save_dir = self.save_dir.__str__() # used in other locations - string += result.verbose() + f"{result.speed['inference']:.1f}ms" - - # Add predictions to image - if self.args.save or self.args.show: - self.plotted_img = result.plot( - line_width=self.args.line_width, - boxes=self.args.show_boxes, - conf=self.args.show_conf, - labels=self.args.show_labels, - im_gpu=None if self.args.retina_masks else im[i], - ) - - # Save results - if self.args.save_txt: - result.save_txt(f"{self.txt_path}.txt", save_conf=self.args.save_conf) - if self.args.save_crop: - result.save_crop(save_dir=self.save_dir / "crops", file_name=self.txt_path.stem) - if self.args.show: - self.show(str(p)) - if self.args.save: - self.save_predicted_images(str(self.save_dir / p.name), frame) - - return string - - def save_predicted_images(self, save_path="", frame=0): - """Save video predictions as mp4 at specified path.""" - im = self.plotted_img - - # Save videos and streams - if self.dataset.mode in {"stream", "video"}: - fps = self.dataset.fps if self.dataset.mode == "video" else 30 - frames_path = f'{save_path.split(".", 1)[0]}_frames/' - if save_path not in self.vid_writer: # new video - if self.args.save_frames: - Path(frames_path).mkdir(parents=True, exist_ok=True) - suffix, fourcc = (".mp4", "avc1") if MACOS else (".avi", "WMV2") if WINDOWS else (".avi", "MJPG") - self.vid_writer[save_path] = cv2.VideoWriter( - filename=str(Path(save_path).with_suffix(suffix)), - fourcc=cv2.VideoWriter_fourcc(*fourcc), - fps=fps, # integer required, floats produce error in MP4 codec - frameSize=(im.shape[1], im.shape[0]), # (width, height) - ) - - # Save video - self.vid_writer[save_path].write(im) - if self.args.save_frames: - cv2.imwrite(f"{frames_path}{frame}.jpg", im) - - # Save images - else: - cv2.imwrite(save_path, im) - - def show(self, p=""): - """Display an image in a window using OpenCV imshow().""" - im = self.plotted_img - if platform.system() == "Linux" and p not in self.windows: - self.windows.append(p) - cv2.namedWindow(p, cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) - cv2.resizeWindow(p, im.shape[1], im.shape[0]) # (width, height) - cv2.imshow(p, im) - cv2.waitKey(300 if self.dataset.mode == "image" else 1) # 1 millisecond - - def run_callbacks(self, event: str): - """Runs all registered callbacks for a specific event.""" - for callback in self.callbacks.get(event, []): - callback(self) - - def add_callback(self, event: str, func): - """Add callback.""" - self.callbacks[event].append(func) diff --git a/ultralytics-main/ultralytics/engine/results.py b/ultralytics-main/ultralytics/engine/results.py deleted file mode 100644 index 96c9449..0000000 --- a/ultralytics-main/ultralytics/engine/results.py +++ /dev/null @@ -1,728 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Ultralytics Results, Boxes and Masks classes for handling inference results. - -Usage: See https://docs.ultralytics.com/modes/predict/ -""" - -from copy import deepcopy -from functools import lru_cache -from pathlib import Path -import numpy as np -import torch -from ultralytics.data.augment import LetterBox -from ultralytics.utils import LOGGER, SimpleClass, ops -from ultralytics.utils.plotting import Annotator, colors, save_one_box -from ultralytics.utils.torch_utils import smart_inference_mode - - -class BaseTensor(SimpleClass): - """Base tensor class with additional methods for easy manipulation and device handling.""" - - def __init__(self, data, orig_shape) -> None: - """ - Initialize BaseTensor with data and original shape. - - Args: - data (torch.Tensor | np.ndarray): Predictions, such as bboxes, masks and keypoints. - orig_shape (tuple): Original shape of image. - """ - assert isinstance(data, (torch.Tensor, np.ndarray)) - self.data = data - self.orig_shape = orig_shape - - @property - def shape(self): - """Return the shape of the data tensor.""" - return self.data.shape - - def cpu(self): - """Return a copy of the tensor on CPU memory.""" - return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.cpu(), self.orig_shape) - - def numpy(self): - """Return a copy of the tensor as a numpy array.""" - return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.numpy(), self.orig_shape) - - def cuda(self): - """Return a copy of the tensor on GPU memory.""" - return self.__class__(torch.as_tensor(self.data).cuda(), self.orig_shape) - - def to(self, *args, **kwargs): - """Return a copy of the tensor with the specified device and dtype.""" - return self.__class__(torch.as_tensor(self.data).to(*args, **kwargs), self.orig_shape) - - def __len__(self): # override len(results) - """Return the length of the data tensor.""" - return len(self.data) - - def __getitem__(self, idx): - """Return a BaseTensor with the specified index of the data tensor.""" - return self.__class__(self.data[idx], self.orig_shape) - - -class Results(SimpleClass): - """ - A class for storing and manipulating inference results. - - Attributes: - orig_img (numpy.ndarray): Original image as a numpy array. - orig_shape (tuple): Original image shape in (height, width) format. - boxes (Boxes, optional): Object containing detection bounding boxes. - masks (Masks, optional): Object containing detection masks. - probs (Probs, optional): Object containing class probabilities for classification tasks. - keypoints (Keypoints, optional): Object containing detected keypoints for each object. - speed (dict): Dictionary of preprocess, inference, and postprocess speeds (ms/image). - names (dict): Dictionary of class names. - path (str): Path to the image file. - - Methods: - update(boxes=None, masks=None, probs=None, obb=None): Updates object attributes with new detection results. - cpu(): Returns a copy of the Results object with all tensors on CPU memory. - numpy(): Returns a copy of the Results object with all tensors as numpy arrays. - cuda(): Returns a copy of the Results object with all tensors on GPU memory. - to(*args, **kwargs): Returns a copy of the Results object with tensors on a specified device and dtype. - new(): Returns a new Results object with the same image, path, and names. - plot(...): Plots detection results on an input image, returning an annotated image. - show(): Show annotated results to screen. - save(filename): Save annotated results to file. - verbose(): Returns a log string for each task, detailing detections and classifications. - save_txt(txt_file, save_conf=False): Saves detection results to a text file. - save_crop(save_dir, file_name=Path("im.jpg")): Saves cropped detection images. - tojson(normalize=False): Converts detection results to JSON format. - """ - - def __init__(self, orig_img, path, names, boxes=None, masks=None, probs=None, keypoints=None, obb=None) -> None: - """ - Initialize the Results class. - - Args: - orig_img (numpy.ndarray): The original image as a numpy array. - path (str): The path to the image file. - names (dict): A dictionary of class names. - boxes (torch.tensor, optional): A 2D tensor of bounding box coordinates for each detection. - masks (torch.tensor, optional): A 3D tensor of detection masks, where each mask is a binary image. - probs (torch.tensor, optional): A 1D tensor of probabilities of each class for classification task. - keypoints (torch.tensor, optional): A 2D tensor of keypoint coordinates for each detection. - obb (torch.tensor, optional): A 2D tensor of oriented bounding box coordinates for each detection. - """ - self.orig_img = orig_img - self.orig_shape = orig_img.shape[:2] - self.boxes = Boxes(boxes, self.orig_shape) if boxes is not None else None # native size boxes - self.masks = Masks(masks, self.orig_shape) if masks is not None else None # native size or imgsz masks - self.probs = Probs(probs) if probs is not None else None - self.keypoints = Keypoints(keypoints, self.orig_shape) if keypoints is not None else None - self.obb = OBB(obb, self.orig_shape) if obb is not None else None - self.speed = {"preprocess": None, "inference": None, "postprocess": None} # milliseconds per image - self.names = names - self.path = path - self.save_dir = None - self._keys = "boxes", "masks", "probs", "keypoints", "obb" - - def __getitem__(self, idx): - """Return a Results object for the specified index.""" - return self._apply("__getitem__", idx) - - def __len__(self): - """Return the number of detections in the Results object.""" - for k in self._keys: - v = getattr(self, k) - if v is not None: - return len(v) - - def update(self, boxes=None, masks=None, probs=None, obb=None): - """Update the boxes, masks, and probs attributes of the Results object.""" - if boxes is not None: - self.boxes = Boxes(ops.clip_boxes(boxes, self.orig_shape), self.orig_shape) - if masks is not None: - self.masks = Masks(masks, self.orig_shape) - if probs is not None: - self.probs = probs - if obb is not None: - self.obb = OBB(obb, self.orig_shape) - - def _apply(self, fn, *args, **kwargs): - """ - Applies a function to all non-empty attributes and returns a new Results object with modified attributes. This - function is internally called by methods like .to(), .cuda(), .cpu(), etc. - - Args: - fn (str): The name of the function to apply. - *args: Variable length argument list to pass to the function. - **kwargs: Arbitrary keyword arguments to pass to the function. - - Returns: - Results: A new Results object with attributes modified by the applied function. - """ - r = self.new() - for k in self._keys: - v = getattr(self, k) - if v is not None: - setattr(r, k, getattr(v, fn)(*args, **kwargs)) - return r - - def cpu(self): - """Return a copy of the Results object with all tensors on CPU memory.""" - return self._apply("cpu") - - def numpy(self): - """Return a copy of the Results object with all tensors as numpy arrays.""" - return self._apply("numpy") - - def cuda(self): - """Return a copy of the Results object with all tensors on GPU memory.""" - return self._apply("cuda") - - def to(self, *args, **kwargs): - """Return a copy of the Results object with tensors on the specified device and dtype.""" - return self._apply("to", *args, **kwargs) - - def new(self): - """Return a new Results object with the same image, path, and names.""" - return Results(orig_img=self.orig_img, path=self.path, names=self.names) - - def plot( - self, - conf=True, - line_width=None, - font_size=None, - font="Arial.ttf", - pil=False, - img=None, - im_gpu=None, - kpt_radius=5, - kpt_line=True, - labels=True, - boxes=True, - masks=True, - probs=True, - show=False, - save=False, - filename=None, - ): - """ - Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image. - - Args: - conf (bool): Whether to plot the detection confidence score. - line_width (float, optional): The line width of the bounding boxes. If None, it is scaled to the image size. - font_size (float, optional): The font size of the text. If None, it is scaled to the image size. - font (str): The font to use for the text. - pil (bool): Whether to return the image as a PIL Image. - img (numpy.ndarray): Plot to another image. if not, plot to original image. - im_gpu (torch.Tensor): Normalized image in gpu with shape (1, 3, 640, 640), for faster mask plotting. - kpt_radius (int, optional): Radius of the drawn keypoints. Default is 5. - kpt_line (bool): Whether to draw lines connecting keypoints. - labels (bool): Whether to plot the label of bounding boxes. - boxes (bool): Whether to plot the bounding boxes. - masks (bool): Whether to plot the masks. - probs (bool): Whether to plot classification probability - show (bool): Whether to display the annotated image directly. - save (bool): Whether to save the annotated image to `filename`. - filename (str): Filename to save image to if save is True. - - Returns: - (numpy.ndarray): A numpy array of the annotated image. - - Example: - ```python - from PIL import Image - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - results = model('bus.jpg') # results list - for r in results: - im_array = r.plot() # plot a BGR numpy array of predictions - im = Image.fromarray(im_array[..., ::-1]) # RGB PIL image - im.show() # show image - im.save('results.jpg') # save image - ``` - """ - if img is None and isinstance(self.orig_img, torch.Tensor): - img = (self.orig_img[0].detach().permute(1, 2, 0).contiguous() * 255).to(torch.uint8).cpu().numpy() - - names = self.names - is_obb = self.obb is not None - pred_boxes, show_boxes = self.obb if is_obb else self.boxes, boxes - pred_masks, show_masks = self.masks, masks - pred_probs, show_probs = self.probs, probs - annotator = Annotator( - deepcopy(self.orig_img if img is None else img), - line_width, - font_size, - font, - pil or (pred_probs is not None and show_probs), # Classify tasks default to pil=True - example=names, - ) - - # Plot Segment results - if pred_masks and show_masks: - if im_gpu is None: - img = LetterBox(pred_masks.shape[1:])(image=annotator.result()) - im_gpu = ( - torch.as_tensor(img, dtype=torch.float16, device=pred_masks.data.device) - .permute(2, 0, 1) - .flip(0) - .contiguous() - / 255 - ) - idx = pred_boxes.cls if pred_boxes else range(len(pred_masks)) - annotator.masks(pred_masks.data, colors=[colors(x, True) for x in idx], im_gpu=im_gpu) - - # Plot Detect results - if pred_boxes is not None and show_boxes: - for d in reversed(pred_boxes): - c, conf, id = int(d.cls), float(d.conf) if conf else None, None if d.id is None else int(d.id.item()) - name = ("" if id is None else f"id:{id} ") + names[c] - label = (f"{name} {conf:.2f}" if conf else name) if labels else None - box = d.xyxyxyxy.reshape(-1, 4, 2).squeeze() if is_obb else d.xyxy.squeeze() - annotator.box_label(box, label, color=colors(c, True), rotated=is_obb) - - # Plot Classify results - if pred_probs is not None and show_probs: - text = ",\n".join(f"{names[j] if names else j} {pred_probs.data[j]:.2f}" for j in pred_probs.top5) - x = round(self.orig_shape[0] * 0.03) - annotator.text([x, x], text, txt_color=(255, 255, 255)) # TODO: allow setting colors - - # Plot Pose results - if self.keypoints is not None: - for k in reversed(self.keypoints.data): - annotator.kpts(k, self.orig_shape, radius=kpt_radius, kpt_line=kpt_line) - - # Show results - if show: - annotator.show(self.path) - - # Save results - if save: - annotator.save(filename) - - return annotator.result() - - def show(self, *args, **kwargs): - """Show annotated results image.""" - self.plot(show=True, *args, **kwargs) - - def save(self, filename=None, *args, **kwargs): - """Save annotated results image.""" - if not filename: - filename = f"results_{Path(self.path).name}" - self.plot(save=True, filename=filename, *args, **kwargs) - return filename - - def verbose(self): - """Return log string for each task.""" - log_string = "" - probs = self.probs - boxes = self.boxes - if len(self) == 0: - return log_string if probs is not None else f"{log_string}(no detections), " - if probs is not None: - log_string += f"{', '.join(f'{self.names[j]} {probs.data[j]:.2f}' for j in probs.top5)}, " - if boxes: - for c in boxes.cls.unique(): - n = (boxes.cls == c).sum() # detections per class - log_string += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " - return log_string - - def save_txt(self, txt_file, save_conf=False): - """ - Save predictions into txt file. - - Args: - txt_file (str): txt file path. - save_conf (bool): save confidence score or not. - """ - is_obb = self.obb is not None - boxes = self.obb if is_obb else self.boxes - masks = self.masks - probs = self.probs - kpts = self.keypoints - texts = [] - if probs is not None: - # Classify - [texts.append(f"{probs.data[j]:.2f} {self.names[j]}") for j in probs.top5] - elif boxes: - # Detect/segment/pose - for j, d in enumerate(boxes): - c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item()) - line = (c, *(d.xyxyxyxyn.view(-1) if is_obb else d.xywhn.view(-1))) - if masks: - seg = masks[j].xyn[0].copy().reshape(-1) # reversed mask.xyn, (n,2) to (n*2) - line = (c, *seg) - if kpts is not None: - kpt = torch.cat((kpts[j].xyn, kpts[j].conf[..., None]), 2) if kpts[j].has_visible else kpts[j].xyn - line += (*kpt.reshape(-1).tolist(),) - line += (conf,) * save_conf + (() if id is None else (id,)) - texts.append(("%g " * len(line)).rstrip() % line) - - if texts: - Path(txt_file).parent.mkdir(parents=True, exist_ok=True) # make directory - with open(txt_file, "a") as f: - f.writelines(text + "\n" for text in texts) - - def save_crop(self, save_dir, file_name=Path("im.jpg")): - """ - Save cropped predictions to `save_dir/cls/file_name.jpg`. - - Args: - save_dir (str | pathlib.Path): Save path. - file_name (str | pathlib.Path): File name. - """ - if self.probs is not None: - LOGGER.warning("WARNING ⚠️ Classify task do not support `save_crop`.") - return - if self.obb is not None: - LOGGER.warning("WARNING ⚠️ OBB task do not support `save_crop`.") - return - for d in self.boxes: - save_one_box( - d.xyxy, - self.orig_img.copy(), - file=Path(save_dir) / self.names[int(d.cls)] / f"{Path(file_name)}.jpg", - BGR=True, - ) - - def tojson(self, normalize=False): - """Convert the object to JSON format.""" - if self.probs is not None: - LOGGER.warning("Warning: Classify task do not support `tojson` yet.") - return - - import json - - # Create list of detection dictionaries - results = [] - data = self.boxes.data.cpu().tolist() - h, w = self.orig_shape if normalize else (1, 1) - for i, row in enumerate(data): # xyxy, track_id if tracking, conf, class_id - box = {"x1": row[0] / w, "y1": row[1] / h, "x2": row[2] / w, "y2": row[3] / h} - conf = row[-2] - class_id = int(row[-1]) - name = self.names[class_id] - result = {"name": name, "class": class_id, "confidence": conf, "box": box} - if self.boxes.is_track: - result["track_id"] = int(row[-3]) # track ID - if self.masks: - x, y = self.masks.xy[i][:, 0], self.masks.xy[i][:, 1] # numpy array - result["segments"] = {"x": (x / w).tolist(), "y": (y / h).tolist()} - if self.keypoints is not None: - x, y, visible = self.keypoints[i].data[0].cpu().unbind(dim=1) # torch Tensor - result["keypoints"] = {"x": (x / w).tolist(), "y": (y / h).tolist(), "visible": visible.tolist()} - results.append(result) - - # Convert detections to JSON - return json.dumps(results, indent=2) - - -class Boxes(BaseTensor): - """ - Manages detection boxes, providing easy access and manipulation of box coordinates, confidence scores, class - identifiers, and optional tracking IDs. Supports multiple formats for box coordinates, including both absolute and - normalized forms. - - Attributes: - data (torch.Tensor): The raw tensor containing detection boxes and their associated data. - orig_shape (tuple): The original image size as a tuple (height, width), used for normalization. - is_track (bool): Indicates whether tracking IDs are included in the box data. - - Properties: - xyxy (torch.Tensor | numpy.ndarray): Boxes in [x1, y1, x2, y2] format. - conf (torch.Tensor | numpy.ndarray): Confidence scores for each box. - cls (torch.Tensor | numpy.ndarray): Class labels for each box. - id (torch.Tensor | numpy.ndarray, optional): Tracking IDs for each box, if available. - xywh (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format, calculated on demand. - xyxyn (torch.Tensor | numpy.ndarray): Normalized [x1, y1, x2, y2] boxes, relative to `orig_shape`. - xywhn (torch.Tensor | numpy.ndarray): Normalized [x, y, width, height] boxes, relative to `orig_shape`. - - Methods: - cpu(): Moves the boxes to CPU memory. - numpy(): Converts the boxes to a numpy array format. - cuda(): Moves the boxes to CUDA (GPU) memory. - to(device, dtype=None): Moves the boxes to the specified device. - """ - - def __init__(self, boxes, orig_shape) -> None: - """ - Initialize the Boxes class. - - Args: - boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes, with - shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values. - If present, the third last column contains track IDs. - orig_shape (tuple): Original image size, in the format (height, width). - """ - if boxes.ndim == 1: - boxes = boxes[None, :] - n = boxes.shape[-1] - assert n in (6, 7), f"expected 6 or 7 values but got {n}" # xyxy, track_id, conf, cls - super().__init__(boxes, orig_shape) - self.is_track = n == 7 - self.orig_shape = orig_shape - - @property - def xyxy(self): - """Return the boxes in xyxy format.""" - return self.data[:, :4] - - @property - def conf(self): - """Return the confidence values of the boxes.""" - return self.data[:, -2] - - @property - def cls(self): - """Return the class values of the boxes.""" - return self.data[:, -1] - - @property - def id(self): - """Return the track IDs of the boxes (if available).""" - return self.data[:, -3] if self.is_track else None - - @property - @lru_cache(maxsize=2) # maxsize 1 should suffice - def xywh(self): - """Return the boxes in xywh format.""" - return ops.xyxy2xywh(self.xyxy) - - @property - @lru_cache(maxsize=2) - def xyxyn(self): - """Return the boxes in xyxy format normalized by original image size.""" - xyxy = self.xyxy.clone() if isinstance(self.xyxy, torch.Tensor) else np.copy(self.xyxy) - xyxy[..., [0, 2]] /= self.orig_shape[1] - xyxy[..., [1, 3]] /= self.orig_shape[0] - return xyxy - - @property - @lru_cache(maxsize=2) - def xywhn(self): - """Return the boxes in xywh format normalized by original image size.""" - xywh = ops.xyxy2xywh(self.xyxy) - xywh[..., [0, 2]] /= self.orig_shape[1] - xywh[..., [1, 3]] /= self.orig_shape[0] - return xywh - - -class Masks(BaseTensor): - """ - A class for storing and manipulating detection masks. - - Attributes: - xy (list): A list of segments in pixel coordinates. - xyn (list): A list of normalized segments. - - Methods: - cpu(): Returns the masks tensor on CPU memory. - numpy(): Returns the masks tensor as a numpy array. - cuda(): Returns the masks tensor on GPU memory. - to(device, dtype): Returns the masks tensor with the specified device and dtype. - """ - - def __init__(self, masks, orig_shape) -> None: - """Initialize the Masks class with the given masks tensor and original image shape.""" - if masks.ndim == 2: - masks = masks[None, :] - super().__init__(masks, orig_shape) - - @property - @lru_cache(maxsize=1) - def xyn(self): - """Return normalized segments.""" - return [ - ops.scale_coords(self.data.shape[1:], x, self.orig_shape, normalize=True) - for x in ops.masks2segments(self.data) - ] - - @property - @lru_cache(maxsize=1) - def xy(self): - """Return segments in pixel coordinates.""" - return [ - ops.scale_coords(self.data.shape[1:], x, self.orig_shape, normalize=False) - for x in ops.masks2segments(self.data) - ] - - -class Keypoints(BaseTensor): - """ - A class for storing and manipulating detection keypoints. - - Attributes: - xy (torch.Tensor): A collection of keypoints containing x, y coordinates for each detection. - xyn (torch.Tensor): A normalized version of xy with coordinates in the range [0, 1]. - conf (torch.Tensor): Confidence values associated with keypoints if available, otherwise None. - - Methods: - cpu(): Returns a copy of the keypoints tensor on CPU memory. - numpy(): Returns a copy of the keypoints tensor as a numpy array. - cuda(): Returns a copy of the keypoints tensor on GPU memory. - to(device, dtype): Returns a copy of the keypoints tensor with the specified device and dtype. - """ - - @smart_inference_mode() # avoid keypoints < conf in-place error - def __init__(self, keypoints, orig_shape) -> None: - """Initializes the Keypoints object with detection keypoints and original image size.""" - if keypoints.ndim == 2: - keypoints = keypoints[None, :] - if keypoints.shape[2] == 3: # x, y, conf - mask = keypoints[..., 2] < 0.5 # points with conf < 0.5 (not visible) - keypoints[..., :2][mask] = 0 - super().__init__(keypoints, orig_shape) - self.has_visible = self.data.shape[-1] == 3 - - @property - @lru_cache(maxsize=1) - def xy(self): - """Returns x, y coordinates of keypoints.""" - return self.data[..., :2] - - @property - @lru_cache(maxsize=1) - def xyn(self): - """Returns normalized x, y coordinates of keypoints.""" - xy = self.xy.clone() if isinstance(self.xy, torch.Tensor) else np.copy(self.xy) - xy[..., 0] /= self.orig_shape[1] - xy[..., 1] /= self.orig_shape[0] - return xy - - @property - @lru_cache(maxsize=1) - def conf(self): - """Returns confidence values of keypoints if available, else None.""" - return self.data[..., 2] if self.has_visible else None - - -class Probs(BaseTensor): - """ - A class for storing and manipulating classification predictions. - - Attributes: - top1 (int): Index of the top 1 class. - top5 (list[int]): Indices of the top 5 classes. - top1conf (torch.Tensor): Confidence of the top 1 class. - top5conf (torch.Tensor): Confidences of the top 5 classes. - - Methods: - cpu(): Returns a copy of the probs tensor on CPU memory. - numpy(): Returns a copy of the probs tensor as a numpy array. - cuda(): Returns a copy of the probs tensor on GPU memory. - to(): Returns a copy of the probs tensor with the specified device and dtype. - """ - - def __init__(self, probs, orig_shape=None) -> None: - """Initialize the Probs class with classification probabilities and optional original shape of the image.""" - super().__init__(probs, orig_shape) - - @property - @lru_cache(maxsize=1) - def top1(self): - """Return the index of top 1.""" - return int(self.data.argmax()) - - @property - @lru_cache(maxsize=1) - def top5(self): - """Return the indices of top 5.""" - return (-self.data).argsort(0)[:5].tolist() # this way works with both torch and numpy. - - @property - @lru_cache(maxsize=1) - def top1conf(self): - """Return the confidence of top 1.""" - return self.data[self.top1] - - @property - @lru_cache(maxsize=1) - def top5conf(self): - """Return the confidences of top 5.""" - return self.data[self.top5] - - -class OBB(BaseTensor): - """ - A class for storing and manipulating Oriented Bounding Boxes (OBB). - - Args: - boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes, - with shape (num_boxes, 7) or (num_boxes, 8). The last two columns contain confidence and class values. - If present, the third last column contains track IDs, and the fifth column from the left contains rotation. - orig_shape (tuple): Original image size, in the format (height, width). - - Attributes: - xywhr (torch.Tensor | numpy.ndarray): The boxes in [x_center, y_center, width, height, rotation] format. - conf (torch.Tensor | numpy.ndarray): The confidence values of the boxes. - cls (torch.Tensor | numpy.ndarray): The class values of the boxes. - id (torch.Tensor | numpy.ndarray): The track IDs of the boxes (if available). - xyxyxyxyn (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format normalized by orig image size. - xyxyxyxy (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format. - xyxy (torch.Tensor | numpy.ndarray): The horizontal boxes in xyxyxyxy format. - data (torch.Tensor): The raw OBB tensor (alias for `boxes`). - - Methods: - cpu(): Move the object to CPU memory. - numpy(): Convert the object to a numpy array. - cuda(): Move the object to CUDA memory. - to(*args, **kwargs): Move the object to the specified device. - """ - - def __init__(self, boxes, orig_shape) -> None: - """Initialize the Boxes class.""" - if boxes.ndim == 1: - boxes = boxes[None, :] - n = boxes.shape[-1] - assert n in (7, 8), f"expected 7 or 8 values but got {n}" # xywh, rotation, track_id, conf, cls - super().__init__(boxes, orig_shape) - self.is_track = n == 8 - self.orig_shape = orig_shape - - @property - def xywhr(self): - """Return the rotated boxes in xywhr format.""" - return self.data[:, :5] - - @property - def conf(self): - """Return the confidence values of the boxes.""" - return self.data[:, -2] - - @property - def cls(self): - """Return the class values of the boxes.""" - return self.data[:, -1] - - @property - def id(self): - """Return the track IDs of the boxes (if available).""" - return self.data[:, -3] if self.is_track else None - - @property - @lru_cache(maxsize=2) - def xyxyxyxy(self): - """Return the boxes in xyxyxyxy format, (N, 4, 2).""" - return ops.xywhr2xyxyxyxy(self.xywhr) - - @property - @lru_cache(maxsize=2) - def xyxyxyxyn(self): - """Return the boxes in xyxyxyxy format, (N, 4, 2).""" - xyxyxyxyn = self.xyxyxyxy.clone() if isinstance(self.xyxyxyxy, torch.Tensor) else np.copy(self.xyxyxyxy) - xyxyxyxyn[..., 0] /= self.orig_shape[1] - xyxyxyxyn[..., 1] /= self.orig_shape[0] - return xyxyxyxyn - - @property - @lru_cache(maxsize=2) - def xyxy(self): - """ - Return the horizontal boxes in xyxy format, (N, 4). - - Accepts both torch and numpy boxes. - """ - x1 = self.xyxyxyxy[..., 0].min(1).values - x2 = self.xyxyxyxy[..., 0].max(1).values - y1 = self.xyxyxyxy[..., 1].min(1).values - y2 = self.xyxyxyxy[..., 1].max(1).values - xyxy = [x1, y1, x2, y2] - return np.stack(xyxy, axis=-1) if isinstance(self.data, np.ndarray) else torch.stack(xyxy, dim=-1) diff --git a/ultralytics-main/ultralytics/engine/trainer.py b/ultralytics-main/ultralytics/engine/trainer.py deleted file mode 100644 index 29d6f1d..0000000 --- a/ultralytics-main/ultralytics/engine/trainer.py +++ /dev/null @@ -1,758 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Train a model on a dataset. - -Usage: - $ yolo mode=train model=yolov8n.pt data=coco128.yaml imgsz=640 epochs=100 batch=16 -""" - -import math -import os -import subprocess -import time -import warnings -from copy import deepcopy -from datetime import datetime, timedelta -from pathlib import Path - -import numpy as np -import torch -from torch import distributed as dist -from torch import nn, optim - -from ultralytics.cfg import get_cfg, get_save_dir -from ultralytics.data.utils import check_cls_dataset, check_det_dataset -from ultralytics.nn.tasks import attempt_load_one_weight, attempt_load_weights -from ultralytics.utils import ( - DEFAULT_CFG, - LOGGER, - RANK, - TQDM, - __version__, - callbacks, - clean_url, - colorstr, - emojis, - yaml_save, -) -from ultralytics.utils.autobatch import check_train_batch_size -from ultralytics.utils.checks import check_amp, check_file, check_imgsz, check_model_file_from_stem, print_args -from ultralytics.utils.dist import ddp_cleanup, generate_ddp_command -from ultralytics.utils.files import get_latest_run -from ultralytics.utils.torch_utils import ( - EarlyStopping, - ModelEMA, - de_parallel, - init_seeds, - one_cycle, - select_device, - strip_optimizer, -) - - -class BaseTrainer: - """ - BaseTrainer. - - A base class for creating trainers. - - Attributes: - args (SimpleNamespace): Configuration for the trainer. - validator (BaseValidator): Validator instance. - model (nn.Module): Model instance. - callbacks (defaultdict): Dictionary of callbacks. - save_dir (Path): Directory to save results. - wdir (Path): Directory to save weights. - last (Path): Path to the last checkpoint. - best (Path): Path to the best checkpoint. - save_period (int): Save checkpoint every x epochs (disabled if < 1). - batch_size (int): Batch size for training. - epochs (int): Number of epochs to train for. - start_epoch (int): Starting epoch for training. - device (torch.device): Device to use for training. - amp (bool): Flag to enable AMP (Automatic Mixed Precision). - scaler (amp.GradScaler): Gradient scaler for AMP. - data (str): Path to data. - trainset (torch.utils.data.Dataset): Training dataset. - testset (torch.utils.data.Dataset): Testing dataset. - ema (nn.Module): EMA (Exponential Moving Average) of the model. - resume (bool): Resume training from a checkpoint. - lf (nn.Module): Loss function. - scheduler (torch.optim.lr_scheduler._LRScheduler): Learning rate scheduler. - best_fitness (float): The best fitness value achieved. - fitness (float): Current fitness value. - loss (float): Current loss value. - tloss (float): Total loss value. - loss_names (list): List of loss names. - csv (Path): Path to results CSV file. - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """ - Initializes the BaseTrainer class. - - Args: - cfg (str, optional): Path to a configuration file. Defaults to DEFAULT_CFG. - overrides (dict, optional): Configuration overrides. Defaults to None. - """ - self.args = get_cfg(cfg, overrides) - self.check_resume(overrides) - self.device = select_device(self.args.device, self.args.batch) - self.validator = None - self.metrics = None - self.plots = {} - init_seeds(self.args.seed + 1 + RANK, deterministic=self.args.deterministic) - - # Dirs - self.save_dir = get_save_dir(self.args) - self.args.name = self.save_dir.name # update name for loggers - self.wdir = self.save_dir / "weights" # weights dir - if RANK in (-1, 0): - self.wdir.mkdir(parents=True, exist_ok=True) # make dir - self.args.save_dir = str(self.save_dir) - yaml_save(self.save_dir / "args.yaml", vars(self.args)) # save run args - self.last, self.best = self.wdir / "last.pt", self.wdir / "best.pt" # checkpoint paths - self.save_period = self.args.save_period - - self.batch_size = self.args.batch - self.epochs = self.args.epochs - self.start_epoch = 0 - if RANK == -1: - print_args(vars(self.args)) - - # Device - if self.device.type in ("cpu", "mps"): - self.args.workers = 0 # faster CPU training as time dominated by inference, not dataloading - - # Model and Dataset - self.model = check_model_file_from_stem(self.args.model) # add suffix, i.e. yolov8n -> yolov8n.pt - try: - if self.args.task == "classify": - self.data = check_cls_dataset(self.args.data) - elif self.args.data.split(".")[-1] in ("yaml", "yml") or self.args.task in ( - "detect", - "segment", - "pose", - "obb", - ): - self.data = check_det_dataset(self.args.data) - if "yaml_file" in self.data: - self.args.data = self.data["yaml_file"] # for validating 'yolo train data=url.zip' usage - except Exception as e: - raise RuntimeError(emojis(f"Dataset '{clean_url(self.args.data)}' error ❌ {e}")) from e - - self.trainset, self.testset = self.get_dataset(self.data) - self.ema = None - - # Optimization utils init - self.lf = None - self.scheduler = None - - # Epoch level metrics - self.best_fitness = None - self.fitness = None - self.loss = None - self.tloss = None - self.loss_names = ["Loss"] - self.csv = self.save_dir / "results.csv" - self.plot_idx = [0, 1, 2] - - # Callbacks - self.callbacks = _callbacks or callbacks.get_default_callbacks() - if RANK in (-1, 0): - callbacks.add_integration_callbacks(self) - - def add_callback(self, event: str, callback): - """Appends the given callback.""" - self.callbacks[event].append(callback) - - def set_callback(self, event: str, callback): - """Overrides the existing callbacks with the given callback.""" - self.callbacks[event] = [callback] - - def run_callbacks(self, event: str): - """Run all existing callbacks associated with a particular event.""" - for callback in self.callbacks.get(event, []): - callback(self) - - def train(self): - """Allow device='', device=None on Multi-GPU systems to default to device=0.""" - if isinstance(self.args.device, str) and len(self.args.device): # i.e. device='0' or device='0,1,2,3' - world_size = len(self.args.device.split(",")) - elif isinstance(self.args.device, (tuple, list)): # i.e. device=[0, 1, 2, 3] (multi-GPU from CLI is list) - world_size = len(self.args.device) - elif torch.cuda.is_available(): # i.e. device=None or device='' or device=number - world_size = 1 # default to device 0 - else: # i.e. device='cpu' or 'mps' - world_size = 0 - - # Run subprocess if DDP training, else train normally - if world_size > 1 and "LOCAL_RANK" not in os.environ: - # Argument checks - if self.args.rect: - LOGGER.warning("WARNING ⚠️ 'rect=True' is incompatible with Multi-GPU training, setting 'rect=False'") - self.args.rect = False - if self.args.batch == -1: - LOGGER.warning( - "WARNING ⚠️ 'batch=-1' for AutoBatch is incompatible with Multi-GPU training, setting " - "default 'batch=16'" - ) - self.args.batch = 16 - - # Command - cmd, file = generate_ddp_command(world_size, self) - try: - LOGGER.info(f'{colorstr("DDP:")} debug command {" ".join(cmd)}') - subprocess.run(cmd, check=True) - except Exception as e: - raise e - finally: - ddp_cleanup(self, str(file)) - - else: - self._do_train(world_size) - - def _setup_scheduler(self): - """Initialize training learning rate scheduler.""" - if self.args.cos_lr: - self.lf = one_cycle(1, self.args.lrf, self.epochs) # cosine 1->hyp['lrf'] - else: - self.lf = lambda x: max(1 - x / self.epochs, 0) * (1.0 - self.args.lrf) + self.args.lrf # linear - self.scheduler = optim.lr_scheduler.LambdaLR(self.optimizer, lr_lambda=self.lf) - - def _setup_ddp(self, world_size): - """Initializes and sets the DistributedDataParallel parameters for training.""" - torch.cuda.set_device(RANK) - self.device = torch.device("cuda", RANK) - # LOGGER.info(f'DDP info: RANK {RANK}, WORLD_SIZE {world_size}, DEVICE {self.device}') - os.environ["NCCL_BLOCKING_WAIT"] = "1" # set to enforce timeout - dist.init_process_group( - "nccl" if dist.is_nccl_available() else "gloo", - timeout=timedelta(seconds=10800), # 3 hours - rank=RANK, - world_size=world_size, - ) - - def _setup_train(self, world_size): - """Builds dataloaders and optimizer on correct rank process.""" - - # Model - self.run_callbacks("on_pretrain_routine_start") - ckpt = self.setup_model() - self.model = self.model.to(self.device) - self.set_model_attributes() - - # Freeze layers - freeze_list = ( - self.args.freeze - if isinstance(self.args.freeze, list) - else range(self.args.freeze) - if isinstance(self.args.freeze, int) - else [] - ) - always_freeze_names = [".dfl"] # always freeze these layers - freeze_layer_names = [f"model.{x}." for x in freeze_list] + always_freeze_names - for k, v in self.model.named_parameters(): - # v.register_hook(lambda x: torch.nan_to_num(x)) # NaN to 0 (commented for erratic training results) - if any(x in k for x in freeze_layer_names): - LOGGER.info(f"Freezing layer '{k}'") - v.requires_grad = False - elif not v.requires_grad and v.dtype.is_floating_point: # only floating point Tensor can require gradients - LOGGER.info( - f"WARNING ⚠️ setting 'requires_grad=True' for frozen layer '{k}'. " - "See ultralytics.engine.trainer for customization of frozen layers." - ) - v.requires_grad = True - - # Check AMP - self.amp = torch.tensor(self.args.amp).to(self.device) # True or False - if self.amp and RANK in (-1, 0): # Single-GPU and DDP - callbacks_backup = callbacks.default_callbacks.copy() # backup callbacks as check_amp() resets them - self.amp = torch.tensor(check_amp(self.model), device=self.device) - callbacks.default_callbacks = callbacks_backup # restore callbacks - if RANK > -1 and world_size > 1: # DDP - dist.broadcast(self.amp, src=0) # broadcast the tensor from rank 0 to all other ranks (returns None) - self.amp = bool(self.amp) # as boolean - self.scaler = torch.cuda.amp.GradScaler(enabled=self.amp) - if world_size > 1: - self.model = nn.parallel.DistributedDataParallel(self.model, device_ids=[RANK]) - - # Check imgsz - gs = max(int(self.model.stride.max() if hasattr(self.model, "stride") else 32), 32) # grid size (max stride) - self.args.imgsz = check_imgsz(self.args.imgsz, stride=gs, floor=gs, max_dim=1) - self.stride = gs # for multiscale training - - # Batch size - if self.batch_size == -1 and RANK == -1: # single-GPU only, estimate best batch size - self.args.batch = self.batch_size = check_train_batch_size(self.model, self.args.imgsz, self.amp) - - # Dataloaders - batch_size = self.batch_size // max(world_size, 1) - self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode="train") - if RANK in (-1, 0): - # Note: When training DOTA dataset, double batch size could get OOM on images with >2000 objects. - self.test_loader = self.get_dataloader( - self.testset, batch_size=batch_size if self.args.task == "obb" else batch_size * 2, rank=-1, mode="val" - ) - self.validator = self.get_validator() - metric_keys = self.validator.metrics.keys + self.label_loss_items(prefix="val") - self.metrics = dict(zip(metric_keys, [0] * len(metric_keys))) - self.ema = ModelEMA(self.model) - if self.args.plots: - self.plot_training_labels() - - # Optimizer - self.accumulate = max(round(self.args.nbs / self.batch_size), 1) # accumulate loss before optimizing - weight_decay = self.args.weight_decay * self.batch_size * self.accumulate / self.args.nbs # scale weight_decay - iterations = math.ceil(len(self.train_loader.dataset) / max(self.batch_size, self.args.nbs)) * self.epochs - self.optimizer = self.build_optimizer( - model=self.model, - name=self.args.optimizer, - lr=self.args.lr0, - momentum=self.args.momentum, - decay=weight_decay, - iterations=iterations, - ) - # Scheduler - self._setup_scheduler() - self.stopper, self.stop = EarlyStopping(patience=self.args.patience), False - self.resume_training(ckpt) - self.scheduler.last_epoch = self.start_epoch - 1 # do not move - self.run_callbacks("on_pretrain_routine_end") - - def _do_train(self, world_size=1): - """Train completed, evaluate and plot if specified by arguments.""" - if world_size > 1: - self._setup_ddp(world_size) - self._setup_train(world_size) - - nb = len(self.train_loader) # number of batches - nw = max(round(self.args.warmup_epochs * nb), 100) if self.args.warmup_epochs > 0 else -1 # warmup iterations - last_opt_step = -1 - self.epoch_time = None - self.epoch_time_start = time.time() - self.train_time_start = time.time() - self.run_callbacks("on_train_start") - LOGGER.info( - f'Image sizes {self.args.imgsz} train, {self.args.imgsz} val\n' - f'Using {self.train_loader.num_workers * (world_size or 1)} dataloader workers\n' - f"Logging results to {colorstr('bold', self.save_dir)}\n" - f'Starting training for ' + (f"{self.args.time} hours..." if self.args.time else f"{self.epochs} epochs...") - ) - if self.args.close_mosaic: - base_idx = (self.epochs - self.args.close_mosaic) * nb - self.plot_idx.extend([base_idx, base_idx + 1, base_idx + 2]) - epoch = self.start_epoch - while True: - self.epoch = epoch - self.run_callbacks("on_train_epoch_start") - self.model.train() - if RANK != -1: - self.train_loader.sampler.set_epoch(epoch) - pbar = enumerate(self.train_loader) - # Update dataloader attributes (optional) - if epoch == (self.epochs - self.args.close_mosaic): - self._close_dataloader_mosaic() - self.train_loader.reset() - - if RANK in (-1, 0): - LOGGER.info(self.progress_string()) - pbar = TQDM(enumerate(self.train_loader), total=nb) - self.tloss = None - self.optimizer.zero_grad() - for i, batch in pbar: - self.run_callbacks("on_train_batch_start") - # Warmup - ni = i + nb * epoch - if ni <= nw: - xi = [0, nw] # x interp - self.accumulate = max(1, int(np.interp(ni, xi, [1, self.args.nbs / self.batch_size]).round())) - for j, x in enumerate(self.optimizer.param_groups): - # Bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0 - x["lr"] = np.interp( - ni, xi, [self.args.warmup_bias_lr if j == 0 else 0.0, x["initial_lr"] * self.lf(epoch)] - ) - if "momentum" in x: - x["momentum"] = np.interp(ni, xi, [self.args.warmup_momentum, self.args.momentum]) - - # Forward - with torch.cuda.amp.autocast(self.amp): - batch = self.preprocess_batch(batch) - self.loss, self.loss_items = self.model(batch) - if RANK != -1: - self.loss *= world_size - self.tloss = ( - (self.tloss * i + self.loss_items) / (i + 1) if self.tloss is not None else self.loss_items - ) - - # Backward - self.scaler.scale(self.loss).backward() - - # Optimize - https://pytorch.org/docs/master/notes/amp_examples.html - if ni - last_opt_step >= self.accumulate: - self.optimizer_step() - last_opt_step = ni - - # Timed stopping - if self.args.time: - self.stop = (time.time() - self.train_time_start) > (self.args.time * 3600) - if RANK != -1: # if DDP training - broadcast_list = [self.stop if RANK == 0 else None] - dist.broadcast_object_list(broadcast_list, 0) # broadcast 'stop' to all ranks - self.stop = broadcast_list[0] - if self.stop: # training time exceeded - break - - # Log - mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G" # (GB) - loss_len = self.tloss.shape[0] if len(self.tloss.shape) else 1 - losses = self.tloss if loss_len > 1 else torch.unsqueeze(self.tloss, 0) - if RANK in (-1, 0): - pbar.set_description( - ("%11s" * 2 + "%11.4g" * (2 + loss_len)) - % (f"{epoch + 1}/{self.epochs}", mem, *losses, batch["cls"].shape[0], batch["img"].shape[-1]) - ) - self.run_callbacks("on_batch_end") - if self.args.plots and ni in self.plot_idx: - self.plot_training_samples(batch, ni) - - self.run_callbacks("on_train_batch_end") - - self.lr = {f"lr/pg{ir}": x["lr"] for ir, x in enumerate(self.optimizer.param_groups)} # for loggers - self.run_callbacks("on_train_epoch_end") - if RANK in (-1, 0): - final_epoch = epoch + 1 == self.epochs - self.ema.update_attr(self.model, include=["yaml", "nc", "args", "names", "stride", "class_weights"]) - - # Validation - if self.args.val or final_epoch or self.stopper.possible_stop or self.stop: - self.metrics, self.fitness = self.validate() - self.save_metrics(metrics={**self.label_loss_items(self.tloss), **self.metrics, **self.lr}) - self.stop |= self.stopper(epoch + 1, self.fitness) or final_epoch - if self.args.time: - self.stop |= (time.time() - self.train_time_start) > (self.args.time * 3600) - - # Save model - if self.args.save or final_epoch: - self.save_model() - self.run_callbacks("on_model_save") - - # Scheduler - t = time.time() - self.epoch_time = t - self.epoch_time_start - self.epoch_time_start = t - with warnings.catch_warnings(): - warnings.simplefilter("ignore") # suppress 'Detected lr_scheduler.step() before optimizer.step()' - if self.args.time: - mean_epoch_time = (t - self.train_time_start) / (epoch - self.start_epoch + 1) - self.epochs = self.args.epochs = math.ceil(self.args.time * 3600 / mean_epoch_time) - self._setup_scheduler() - self.scheduler.last_epoch = self.epoch # do not move - self.stop |= epoch >= self.epochs # stop if exceeded epochs - self.scheduler.step() - self.run_callbacks("on_fit_epoch_end") - torch.cuda.empty_cache() # clear GPU memory at end of epoch, may help reduce CUDA out of memory errors - - # Early Stopping - if RANK != -1: # if DDP training - broadcast_list = [self.stop if RANK == 0 else None] - dist.broadcast_object_list(broadcast_list, 0) # broadcast 'stop' to all ranks - self.stop = broadcast_list[0] - if self.stop: - break # must break all DDP ranks - epoch += 1 - - if RANK in (-1, 0): - # Do final val with best.pt - LOGGER.info( - f"\n{epoch - self.start_epoch + 1} epochs completed in " - f"{(time.time() - self.train_time_start) / 3600:.3f} hours." - ) - self.final_eval() - if self.args.plots: - self.plot_metrics() - self.run_callbacks("on_train_end") - torch.cuda.empty_cache() - self.run_callbacks("teardown") - - def save_model(self): - """Save model training checkpoints with additional metadata.""" - import pandas as pd # scope for faster startup - - metrics = {**self.metrics, **{"fitness": self.fitness}} - results = {k.strip(): v for k, v in pd.read_csv(self.csv).to_dict(orient="list").items()} - ckpt = { - "epoch": self.epoch, - "best_fitness": self.best_fitness, - "model": deepcopy(de_parallel(self.model)).half(), - "ema": deepcopy(self.ema.ema).half(), - "updates": self.ema.updates, - "optimizer": self.optimizer.state_dict(), - "train_args": vars(self.args), # save as dict - "train_metrics": metrics, - "train_results": results, - "date": datetime.now().isoformat(), - "version": __version__, - "license": "AGPL-3.0 (https://ultralytics.com/license)", - "docs": "https://docs.ultralytics.com", - } - - # Save last and best - torch.save(ckpt, self.last) - if self.best_fitness == self.fitness: - torch.save(ckpt, self.best) - if (self.save_period > 0) and (self.epoch > 0) and (self.epoch % self.save_period == 0): - torch.save(ckpt, self.wdir / f"epoch{self.epoch}.pt") - - @staticmethod - def get_dataset(data): - """ - Get train, val path from data dict if it exists. - - Returns None if data format is not recognized. - """ - return data["train"], data.get("val") or data.get("test") - - def setup_model(self): - """Load/create/download model for any task.""" - if isinstance(self.model, torch.nn.Module): # if model is loaded beforehand. No setup needed - return - - model, weights = self.model, None - ckpt = None - if str(model).endswith(".pt"): - weights, ckpt = attempt_load_one_weight(model) - cfg = ckpt["model"].yaml - else: - cfg = model - self.model = self.get_model(cfg=cfg, weights=weights, verbose=RANK == -1) # calls Model(cfg, weights) - return ckpt - - def optimizer_step(self): - """Perform a single step of the training optimizer with gradient clipping and EMA update.""" - self.scaler.unscale_(self.optimizer) # unscale gradients - torch.nn.utils.clip_grad_norm_(self.model.parameters(), max_norm=10.0) # clip gradients - self.scaler.step(self.optimizer) - self.scaler.update() - self.optimizer.zero_grad() - if self.ema: - self.ema.update(self.model) - - def preprocess_batch(self, batch): - """Allows custom preprocessing model inputs and ground truths depending on task type.""" - return batch - - def validate(self): - """ - Runs validation on test set using self.validator. - - The returned dict is expected to contain "fitness" key. - """ - metrics = self.validator(self) - fitness = metrics.pop("fitness", -self.loss.detach().cpu().numpy()) # use loss as fitness measure if not found - if not self.best_fitness or self.best_fitness < fitness: - self.best_fitness = fitness - return metrics, fitness - - def get_model(self, cfg=None, weights=None, verbose=True): - """Get model and raise NotImplementedError for loading cfg files.""" - raise NotImplementedError("This task trainer doesn't support loading cfg files") - - def get_validator(self): - """Returns a NotImplementedError when the get_validator function is called.""" - raise NotImplementedError("get_validator function not implemented in trainer") - - def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"): - """Returns dataloader derived from torch.data.Dataloader.""" - raise NotImplementedError("get_dataloader function not implemented in trainer") - - def build_dataset(self, img_path, mode="train", batch=None): - """Build dataset.""" - raise NotImplementedError("build_dataset function not implemented in trainer") - - def label_loss_items(self, loss_items=None, prefix="train"): - """ - Returns a loss dict with labelled training loss items tensor. - - Note: - This is not needed for classification but necessary for segmentation & detection - """ - return {"loss": loss_items} if loss_items is not None else ["loss"] - - def set_model_attributes(self): - """To set or update model parameters before training.""" - self.model.names = self.data["names"] - - def build_targets(self, preds, targets): - """Builds target tensors for training YOLO model.""" - pass - - def progress_string(self): - """Returns a string describing training progress.""" - return "" - - # TODO: may need to put these following functions into callback - def plot_training_samples(self, batch, ni): - """Plots training samples during YOLO training.""" - pass - - def plot_training_labels(self): - """Plots training labels for YOLO model.""" - pass - - def save_metrics(self, metrics): - """Saves training metrics to a CSV file.""" - keys, vals = list(metrics.keys()), list(metrics.values()) - n = len(metrics) + 1 # number of cols - s = "" if self.csv.exists() else (("%23s," * n % tuple(["epoch"] + keys)).rstrip(",") + "\n") # header - with open(self.csv, "a") as f: - f.write(s + ("%23.5g," * n % tuple([self.epoch + 1] + vals)).rstrip(",") + "\n") - - def plot_metrics(self): - """Plot and display metrics visually.""" - pass - - def on_plot(self, name, data=None): - """Registers plots (e.g. to be consumed in callbacks)""" - path = Path(name) - self.plots[path] = {"data": data, "timestamp": time.time()} - - def final_eval(self): - """Performs final evaluation and validation for object detection YOLO model.""" - for f in self.last, self.best: - if f.exists(): - strip_optimizer(f) # strip optimizers - if f is self.best: - LOGGER.info(f"\nValidating {f}...") - self.validator.args.plots = self.args.plots - self.metrics = self.validator(model=f) - self.metrics.pop("fitness", None) - self.run_callbacks("on_fit_epoch_end") - - def check_resume(self, overrides): - """Check if resume checkpoint exists and update arguments accordingly.""" - resume = self.args.resume - if resume: - try: - exists = isinstance(resume, (str, Path)) and Path(resume).exists() - last = Path(check_file(resume) if exists else get_latest_run()) - - # Check that resume data YAML exists, otherwise strip to force re-download of dataset - ckpt_args = attempt_load_weights(last).args - if not Path(ckpt_args["data"]).exists(): - ckpt_args["data"] = self.args.data - - resume = True - self.args = get_cfg(ckpt_args) - self.args.model = str(last) # reinstate model - for k in "imgsz", "batch": # allow arg updates to reduce memory on resume if crashed due to CUDA OOM - if k in overrides: - setattr(self.args, k, overrides[k]) - - except Exception as e: - raise FileNotFoundError( - "Resume checkpoint not found. Please pass a valid checkpoint to resume from, " - "i.e. 'yolo train resume model=path/to/last.pt'" - ) from e - self.resume = resume - - def resume_training(self, ckpt): - """Resume YOLO training from given epoch and best fitness.""" - if ckpt is None: - return - best_fitness = 0.0 - start_epoch = ckpt["epoch"] + 1 - if ckpt["optimizer"] is not None: - self.optimizer.load_state_dict(ckpt["optimizer"]) # optimizer - best_fitness = ckpt["best_fitness"] - if self.ema and ckpt.get("ema"): - self.ema.ema.load_state_dict(ckpt["ema"].float().state_dict()) # EMA - self.ema.updates = ckpt["updates"] - if self.resume: - assert start_epoch > 0, ( - f"{self.args.model} training to {self.epochs} epochs is finished, nothing to resume.\n" - f"Start a new training without resuming, i.e. 'yolo train model={self.args.model}'" - ) - LOGGER.info( - f"Resuming training from {self.args.model} from epoch {start_epoch + 1} to {self.epochs} total epochs" - ) - if self.epochs < start_epoch: - LOGGER.info( - f"{self.model} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {self.epochs} more epochs." - ) - self.epochs += ckpt["epoch"] # finetune additional epochs - self.best_fitness = best_fitness - self.start_epoch = start_epoch - if start_epoch > (self.epochs - self.args.close_mosaic): - self._close_dataloader_mosaic() - - def _close_dataloader_mosaic(self): - """Update dataloaders to stop using mosaic augmentation.""" - if hasattr(self.train_loader.dataset, "mosaic"): - self.train_loader.dataset.mosaic = False - if hasattr(self.train_loader.dataset, "close_mosaic"): - LOGGER.info("Closing dataloader mosaic") - self.train_loader.dataset.close_mosaic(hyp=self.args) - - def build_optimizer(self, model, name="auto", lr=0.001, momentum=0.9, decay=1e-5, iterations=1e5): - """ - Constructs an optimizer for the given model, based on the specified optimizer name, learning rate, momentum, - weight decay, and number of iterations. - - Args: - model (torch.nn.Module): The model for which to build an optimizer. - name (str, optional): The name of the optimizer to use. If 'auto', the optimizer is selected - based on the number of iterations. Default: 'auto'. - lr (float, optional): The learning rate for the optimizer. Default: 0.001. - momentum (float, optional): The momentum factor for the optimizer. Default: 0.9. - decay (float, optional): The weight decay for the optimizer. Default: 1e-5. - iterations (float, optional): The number of iterations, which determines the optimizer if - name is 'auto'. Default: 1e5. - - Returns: - (torch.optim.Optimizer): The constructed optimizer. - """ - - g = [], [], [] # optimizer parameter groups - bn = tuple(v for k, v in nn.__dict__.items() if "Norm" in k) # normalization layers, i.e. BatchNorm2d() - if name == "auto": - LOGGER.info( - f"{colorstr('optimizer:')} 'optimizer=auto' found, " - f"ignoring 'lr0={self.args.lr0}' and 'momentum={self.args.momentum}' and " - f"determining best 'optimizer', 'lr0' and 'momentum' automatically... " - ) - nc = getattr(model, "nc", 10) # number of classes - lr_fit = round(0.002 * 5 / (4 + nc), 6) # lr0 fit equation to 6 decimal places - name, lr, momentum = ("SGD", 0.01, 0.9) if iterations > 10000 else ("AdamW", lr_fit, 0.9) - self.args.warmup_bias_lr = 0.0 # no higher than 0.01 for Adam - - for module_name, module in model.named_modules(): - for param_name, param in module.named_parameters(recurse=False): - fullname = f"{module_name}.{param_name}" if module_name else param_name - if "bias" in fullname: # bias (no decay) - g[2].append(param) - elif isinstance(module, bn): # weight (no decay) - g[1].append(param) - else: # weight (with decay) - g[0].append(param) - - if name in ("Adam", "Adamax", "AdamW", "NAdam", "RAdam"): - optimizer = getattr(optim, name, optim.Adam)(g[2], lr=lr, betas=(momentum, 0.999), weight_decay=0.0) - elif name == "RMSProp": - optimizer = optim.RMSprop(g[2], lr=lr, momentum=momentum) - elif name == "SGD": - optimizer = optim.SGD(g[2], lr=lr, momentum=momentum, nesterov=True) - else: - raise NotImplementedError( - f"Optimizer '{name}' not found in list of available optimizers " - f"[Adam, AdamW, NAdam, RAdam, RMSProp, SGD, auto]." - "To request support for addition optimizers please visit https://github.com/ultralytics/ultralytics." - ) - - optimizer.add_param_group({"params": g[0], "weight_decay": decay}) # add g0 with weight_decay - optimizer.add_param_group({"params": g[1], "weight_decay": 0.0}) # add g1 (BatchNorm2d weights) - LOGGER.info( - f"{colorstr('optimizer:')} {type(optimizer).__name__}(lr={lr}, momentum={momentum}) with parameter groups " - f'{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias(decay=0.0)' - ) - return optimizer diff --git a/ultralytics-main/ultralytics/engine/tuner.py b/ultralytics-main/ultralytics/engine/tuner.py deleted file mode 100644 index a009e73..0000000 --- a/ultralytics-main/ultralytics/engine/tuner.py +++ /dev/null @@ -1,241 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -This module provides functionalities for hyperparameter tuning of the Ultralytics YOLO models for object detection, -instance segmentation, image classification, pose estimation, and multi-object tracking. - -Hyperparameter tuning is the process of systematically searching for the optimal set of hyperparameters -that yield the best model performance. This is particularly crucial in deep learning models like YOLO, -where small changes in hyperparameters can lead to significant differences in model accuracy and efficiency. - -Example: - Tune hyperparameters for YOLOv8n on COCO8 at imgsz=640 and epochs=30 for 300 tuning iterations. - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - model.tune(data='coco8.yaml', epochs=10, iterations=300, optimizer='AdamW', plots=False, save=False, val=False) - ``` -""" - -import random -import shutil -import subprocess -import time - -import numpy as np -import torch - -from ultralytics.cfg import get_cfg, get_save_dir -from ultralytics.utils import DEFAULT_CFG, LOGGER, callbacks, colorstr, remove_colorstr, yaml_print, yaml_save -from ultralytics.utils.plotting import plot_tune_results - - -class Tuner: - """ - Class responsible for hyperparameter tuning of YOLO models. - - The class evolves YOLO model hyperparameters over a given number of iterations - by mutating them according to the search space and retraining the model to evaluate their performance. - - Attributes: - space (dict): Hyperparameter search space containing bounds and scaling factors for mutation. - tune_dir (Path): Directory where evolution logs and results will be saved. - tune_csv (Path): Path to the CSV file where evolution logs are saved. - - Methods: - _mutate(hyp: dict) -> dict: - Mutates the given hyperparameters within the bounds specified in `self.space`. - - __call__(): - Executes the hyperparameter evolution across multiple iterations. - - Example: - Tune hyperparameters for YOLOv8n on COCO8 at imgsz=640 and epochs=30 for 300 tuning iterations. - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - model.tune(data='coco8.yaml', epochs=10, iterations=300, optimizer='AdamW', plots=False, save=False, val=False) - ``` - - Tune with custom search space. - ```python - from ultralytics import YOLO - - model = YOLO('yolov8n.pt') - model.tune(space={key1: val1, key2: val2}) # custom search space dictionary - ``` - """ - - def __init__(self, args=DEFAULT_CFG, _callbacks=None): - """ - Initialize the Tuner with configurations. - - Args: - args (dict, optional): Configuration for hyperparameter evolution. - """ - self.space = args.pop("space", None) or { # key: (min, max, gain(optional)) - # 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']), - "lr0": (1e-5, 1e-1), # initial learning rate (i.e. SGD=1E-2, Adam=1E-3) - "lrf": (0.0001, 0.1), # final OneCycleLR learning rate (lr0 * lrf) - "momentum": (0.7, 0.98, 0.3), # SGD momentum/Adam beta1 - "weight_decay": (0.0, 0.001), # optimizer weight decay 5e-4 - "warmup_epochs": (0.0, 5.0), # warmup epochs (fractions ok) - "warmup_momentum": (0.0, 0.95), # warmup initial momentum - "box": (1.0, 20.0), # box loss gain - "cls": (0.2, 4.0), # cls loss gain (scale with pixels) - "dfl": (0.4, 6.0), # dfl loss gain - "hsv_h": (0.0, 0.1), # image HSV-Hue augmentation (fraction) - "hsv_s": (0.0, 0.9), # image HSV-Saturation augmentation (fraction) - "hsv_v": (0.0, 0.9), # image HSV-Value augmentation (fraction) - "degrees": (0.0, 45.0), # image rotation (+/- deg) - "translate": (0.0, 0.9), # image translation (+/- fraction) - "scale": (0.0, 0.95), # image scale (+/- gain) - "shear": (0.0, 10.0), # image shear (+/- deg) - "perspective": (0.0, 0.001), # image perspective (+/- fraction), range 0-0.001 - "flipud": (0.0, 1.0), # image flip up-down (probability) - "fliplr": (0.0, 1.0), # image flip left-right (probability) - "mosaic": (0.0, 1.0), # image mixup (probability) - "mixup": (0.0, 1.0), # image mixup (probability) - "copy_paste": (0.0, 1.0), # segment copy-paste (probability) - } - self.args = get_cfg(overrides=args) - self.tune_dir = get_save_dir(self.args, name="tune") - self.tune_csv = self.tune_dir / "tune_results.csv" - self.callbacks = _callbacks or callbacks.get_default_callbacks() - self.prefix = colorstr("Tuner: ") - callbacks.add_integration_callbacks(self) - LOGGER.info( - f"{self.prefix}Initialized Tuner instance with 'tune_dir={self.tune_dir}'\n" - f"{self.prefix}💡 Learn about tuning at https://docs.ultralytics.com/guides/hyperparameter-tuning" - ) - - def _mutate(self, parent="single", n=5, mutation=0.8, sigma=0.2): - """ - Mutates the hyperparameters based on bounds and scaling factors specified in `self.space`. - - Args: - parent (str): Parent selection method: 'single' or 'weighted'. - n (int): Number of parents to consider. - mutation (float): Probability of a parameter mutation in any given iteration. - sigma (float): Standard deviation for Gaussian random number generator. - - Returns: - (dict): A dictionary containing mutated hyperparameters. - """ - if self.tune_csv.exists(): # if CSV file exists: select best hyps and mutate - # Select parent(s) - x = np.loadtxt(self.tune_csv, ndmin=2, delimiter=",", skiprows=1) - fitness = x[:, 0] # first column - n = min(n, len(x)) # number of previous results to consider - x = x[np.argsort(-fitness)][:n] # top n mutations - w = x[:, 0] - x[:, 0].min() + 1e-6 # weights (sum > 0) - if parent == "single" or len(x) == 1: - # x = x[random.randint(0, n - 1)] # random selection - x = x[random.choices(range(n), weights=w)[0]] # weighted selection - elif parent == "weighted": - x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination - - # Mutate - r = np.random # method - r.seed(int(time.time())) - g = np.array([v[2] if len(v) == 3 else 1.0 for k, v in self.space.items()]) # gains 0-1 - ng = len(self.space) - v = np.ones(ng) - while all(v == 1): # mutate until a change occurs (prevent duplicates) - v = (g * (r.random(ng) < mutation) * r.randn(ng) * r.random() * sigma + 1).clip(0.3, 3.0) - hyp = {k: float(x[i + 1] * v[i]) for i, k in enumerate(self.space.keys())} - else: - hyp = {k: getattr(self.args, k) for k in self.space.keys()} - - # Constrain to limits - for k, v in self.space.items(): - hyp[k] = max(hyp[k], v[0]) # lower limit - hyp[k] = min(hyp[k], v[1]) # upper limit - hyp[k] = round(hyp[k], 5) # significant digits - - return hyp - - def __call__(self, model=None, iterations=10, cleanup=True): - """ - Executes the hyperparameter evolution process when the Tuner instance is called. - - This method iterates through the number of iterations, performing the following steps in each iteration: - 1. Load the existing hyperparameters or initialize new ones. - 2. Mutate the hyperparameters using the `mutate` method. - 3. Train a YOLO model with the mutated hyperparameters. - 4. Log the fitness score and mutated hyperparameters to a CSV file. - - Args: - model (Model): A pre-initialized YOLO model to be used for training. - iterations (int): The number of generations to run the evolution for. - cleanup (bool): Whether to delete iteration weights to reduce storage space used during tuning. - - Note: - The method utilizes the `self.tune_csv` Path object to read and log hyperparameters and fitness scores. - Ensure this path is set correctly in the Tuner instance. - """ - - t0 = time.time() - best_save_dir, best_metrics = None, None - (self.tune_dir / "weights").mkdir(parents=True, exist_ok=True) - for i in range(iterations): - # Mutate hyperparameters - mutated_hyp = self._mutate() - LOGGER.info(f"{self.prefix}Starting iteration {i + 1}/{iterations} with hyperparameters: {mutated_hyp}") - - metrics = {} - train_args = {**vars(self.args), **mutated_hyp} - save_dir = get_save_dir(get_cfg(train_args)) - weights_dir = save_dir / "weights" - try: - # Train YOLO model with mutated hyperparameters (run in subprocess to avoid dataloader hang) - cmd = ["yolo", "train", *(f"{k}={v}" for k, v in train_args.items())] - return_code = subprocess.run(cmd, check=True).returncode - ckpt_file = weights_dir / ("best.pt" if (weights_dir / "best.pt").exists() else "last.pt") - metrics = torch.load(ckpt_file)["train_metrics"] - assert return_code == 0, "training failed" - - except Exception as e: - LOGGER.warning(f"WARNING ❌️ training failure for hyperparameter tuning iteration {i + 1}\n{e}") - - # Save results and mutated_hyp to CSV - fitness = metrics.get("fitness", 0.0) - log_row = [round(fitness, 5)] + [mutated_hyp[k] for k in self.space.keys()] - headers = "" if self.tune_csv.exists() else (",".join(["fitness"] + list(self.space.keys())) + "\n") - with open(self.tune_csv, "a") as f: - f.write(headers + ",".join(map(str, log_row)) + "\n") - - # Get best results - x = np.loadtxt(self.tune_csv, ndmin=2, delimiter=",", skiprows=1) - fitness = x[:, 0] # first column - best_idx = fitness.argmax() - best_is_current = best_idx == i - if best_is_current: - best_save_dir = save_dir - best_metrics = {k: round(v, 5) for k, v in metrics.items()} - for ckpt in weights_dir.glob("*.pt"): - shutil.copy2(ckpt, self.tune_dir / "weights") - elif cleanup: - shutil.rmtree(ckpt_file.parent) # remove iteration weights/ dir to reduce storage space - - # Plot tune results - plot_tune_results(self.tune_csv) - - # Save and print tune results - header = ( - f'{self.prefix}{i + 1}/{iterations} iterations complete ✅ ({time.time() - t0:.2f}s)\n' - f'{self.prefix}Results saved to {colorstr("bold", self.tune_dir)}\n' - f'{self.prefix}Best fitness={fitness[best_idx]} observed at iteration {best_idx + 1}\n' - f'{self.prefix}Best fitness metrics are {best_metrics}\n' - f'{self.prefix}Best fitness model is {best_save_dir}\n' - f'{self.prefix}Best fitness hyperparameters are printed below.\n' - ) - LOGGER.info("\n" + header) - data = {k: float(x[best_idx, i + 1]) for i, k in enumerate(self.space.keys())} - yaml_save( - self.tune_dir / "best_hyperparameters.yaml", - data=data, - header=remove_colorstr(header.replace(self.prefix, "# ")) + "\n", - ) - yaml_print(self.tune_dir / "best_hyperparameters.yaml") diff --git a/ultralytics-main/ultralytics/engine/validator.py b/ultralytics-main/ultralytics/engine/validator.py deleted file mode 100644 index 17666e3..0000000 --- a/ultralytics-main/ultralytics/engine/validator.py +++ /dev/null @@ -1,338 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Check a model's accuracy on a test or val split of a dataset. - -Usage: - $ yolo mode=val model=yolov8n.pt data=coco128.yaml imgsz=640 - -Usage - formats: - $ yolo mode=val model=yolov8n.pt # PyTorch - yolov8n.torchscript # TorchScript - yolov8n.onnx # ONNX Runtime or OpenCV DNN with dnn=True - yolov8n_openvino_model # OpenVINO - yolov8n.engine # TensorRT - yolov8n.mlpackage # CoreML (macOS-only) - yolov8n_saved_model # TensorFlow SavedModel - yolov8n.pb # TensorFlow GraphDef - yolov8n.tflite # TensorFlow Lite - yolov8n_edgetpu.tflite # TensorFlow Edge TPU - yolov8n_paddle_model # PaddlePaddle - yolov8n_ncnn_model # NCNN -""" - -import json -import time -from pathlib import Path - -import numpy as np -import torch - -from ultralytics.cfg import get_cfg, get_save_dir -from ultralytics.data.utils import check_cls_dataset, check_det_dataset -from ultralytics.nn.autobackend import AutoBackend -from ultralytics.utils import LOGGER, TQDM, callbacks, colorstr, emojis -from ultralytics.utils.checks import check_imgsz -from ultralytics.utils.ops import Profile -from ultralytics.utils.torch_utils import de_parallel, select_device, smart_inference_mode - - -class BaseValidator: - """ - BaseValidator. - - A base class for creating validators. - - Attributes: - args (SimpleNamespace): Configuration for the validator. - dataloader (DataLoader): Dataloader to use for validation. - pbar (tqdm): Progress bar to update during validation. - model (nn.Module): Model to validate. - data (dict): Data dictionary. - device (torch.device): Device to use for validation. - batch_i (int): Current batch index. - training (bool): Whether the model is in training mode. - names (dict): Class names. - seen: Records the number of images seen so far during validation. - stats: Placeholder for statistics during validation. - confusion_matrix: Placeholder for a confusion matrix. - nc: Number of classes. - iouv: (torch.Tensor): IoU thresholds from 0.50 to 0.95 in spaces of 0.05. - jdict (dict): Dictionary to store JSON validation results. - speed (dict): Dictionary with keys 'preprocess', 'inference', 'loss', 'postprocess' and their respective - batch processing times in milliseconds. - save_dir (Path): Directory to save results. - plots (dict): Dictionary to store plots for visualization. - callbacks (dict): Dictionary to store various callback functions. - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """ - Initializes a BaseValidator instance. - - Args: - dataloader (torch.utils.data.DataLoader): Dataloader to be used for validation. - save_dir (Path, optional): Directory to save results. - pbar (tqdm.tqdm): Progress bar for displaying progress. - args (SimpleNamespace): Configuration for the validator. - _callbacks (dict): Dictionary to store various callback functions. - """ - self.args = get_cfg(overrides=args) - self.dataloader = dataloader - self.pbar = pbar - self.stride = None - self.data = None - self.device = None - self.batch_i = None - self.training = True - self.names = None - self.seen = None - self.stats = None - self.confusion_matrix = None - self.nc = None - self.iouv = None - self.jdict = None - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - - self.save_dir = save_dir or get_save_dir(self.args) - (self.save_dir / "labels" if self.args.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True) - if self.args.conf is None: - self.args.conf = 0.001 # default conf=0.001 - self.args.imgsz = check_imgsz(self.args.imgsz, max_dim=1) - - self.plots = {} - self.callbacks = _callbacks or callbacks.get_default_callbacks() - - @smart_inference_mode() - def __call__(self, trainer=None, model=None): - """Supports validation of a pre-trained model if passed or a model being trained if trainer is passed (trainer - gets priority). - """ - self.training = trainer is not None - augment = self.args.augment and (not self.training) - if self.training: - self.device = trainer.device - self.data = trainer.data - self.args.half = self.device.type != "cpu" # force FP16 val during training - model = trainer.ema.ema or trainer.model - model = model.half() if self.args.half else model.float() - # self.model = model - self.loss = torch.zeros_like(trainer.loss_items, device=trainer.device) - self.args.plots &= trainer.stopper.possible_stop or (trainer.epoch == trainer.epochs - 1) - model.eval() - else: - callbacks.add_integration_callbacks(self) - model = AutoBackend( - weights=model or self.args.model, - device=select_device(self.args.device, self.args.batch), - dnn=self.args.dnn, - data=self.args.data, - fp16=self.args.half, - ) - # self.model = model - self.device = model.device # update device - self.args.half = model.fp16 # update half - stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine - imgsz = check_imgsz(self.args.imgsz, stride=stride) - if engine: - self.args.batch = model.batch_size - elif not pt and not jit: - self.args.batch = 1 # export.py models default to batch-size 1 - LOGGER.info(f"Forcing batch=1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models") - - if str(self.args.data).split(".")[-1] in ("yaml", "yml"): - self.data = check_det_dataset(self.args.data) - elif self.args.task == "classify": - self.data = check_cls_dataset(self.args.data, split=self.args.split) - else: - raise FileNotFoundError(emojis(f"Dataset '{self.args.data}' for task={self.args.task} not found ❌")) - - if self.device.type in ("cpu", "mps"): - self.args.workers = 0 # faster CPU val as time dominated by inference, not dataloading - if not pt: - self.args.rect = False - self.stride = model.stride # used in get_dataloader() for padding - self.dataloader = self.dataloader or self.get_dataloader(self.data.get(self.args.split), self.args.batch) - - model.eval() - model.warmup(imgsz=(1 if pt else self.args.batch, 3, imgsz, imgsz)) # warmup - - self.run_callbacks("on_val_start") - dt = ( - Profile(device=self.device), - Profile(device=self.device), - Profile(device=self.device), - Profile(device=self.device), - ) - bar = TQDM(self.dataloader, desc=self.get_desc(), total=len(self.dataloader)) - self.init_metrics(de_parallel(model)) - self.jdict = [] # empty before each val - for batch_i, batch in enumerate(bar): - self.run_callbacks("on_val_batch_start") - self.batch_i = batch_i - # Preprocess - with dt[0]: - batch = self.preprocess(batch) - - # Inference - with dt[1]: - preds = model(batch["img"], augment=augment) - - # Loss - with dt[2]: - if self.training: - self.loss += model.loss(batch, preds)[1] - - # Postprocess - with dt[3]: - preds = self.postprocess(preds) - - self.update_metrics(preds, batch) - if self.args.plots and batch_i < 3: - self.plot_val_samples(batch, batch_i) - self.plot_predictions(batch, preds, batch_i) - - self.run_callbacks("on_val_batch_end") - stats = self.get_stats() - self.check_stats(stats) - self.speed = dict(zip(self.speed.keys(), (x.t / len(self.dataloader.dataset) * 1e3 for x in dt))) - self.finalize_metrics() - self.print_results() - self.run_callbacks("on_val_end") - if self.training: - model.float() - results = {**stats, **trainer.label_loss_items(self.loss.cpu() / len(self.dataloader), prefix="val")} - return {k: round(float(v), 5) for k, v in results.items()} # return results as 5 decimal place floats - else: - LOGGER.info( - "Speed: %.1fms preprocess, %.1fms inference, %.1fms loss, %.1fms postprocess per image" - % tuple(self.speed.values()) - ) - if self.args.save_json and self.jdict: - with open(str(self.save_dir / "predictions.json"), "w") as f: - LOGGER.info(f"Saving {f.name}...") - json.dump(self.jdict, f) # flatten and save - stats = self.eval_json(stats) # update stats - if self.args.plots or self.args.save_json: - LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}") - return stats - - def match_predictions(self, pred_classes, true_classes, iou, use_scipy=False): - """ - Matches predictions to ground truth objects (pred_classes, true_classes) using IoU. - - Args: - pred_classes (torch.Tensor): Predicted class indices of shape(N,). - true_classes (torch.Tensor): Target class indices of shape(M,). - iou (torch.Tensor): An NxM tensor containing the pairwise IoU values for predictions and ground of truth - use_scipy (bool): Whether to use scipy for matching (more precise). - - Returns: - (torch.Tensor): Correct tensor of shape(N,10) for 10 IoU thresholds. - """ - # Dx10 matrix, where D - detections, 10 - IoU thresholds - correct = np.zeros((pred_classes.shape[0], self.iouv.shape[0])).astype(bool) - # LxD matrix where L - labels (rows), D - detections (columns) - correct_class = true_classes[:, None] == pred_classes - iou = iou * correct_class # zero out the wrong classes - iou = iou.cpu().numpy() - for i, threshold in enumerate(self.iouv.cpu().tolist()): - if use_scipy: - # WARNING: known issue that reduces mAP in https://github.com/ultralytics/ultralytics/pull/4708 - import scipy # scope import to avoid importing for all commands - - cost_matrix = iou * (iou >= threshold) - if cost_matrix.any(): - labels_idx, detections_idx = scipy.optimize.linear_sum_assignment(cost_matrix, maximize=True) - valid = cost_matrix[labels_idx, detections_idx] > 0 - if valid.any(): - correct[detections_idx[valid], i] = True - else: - matches = np.nonzero(iou >= threshold) # IoU > threshold and classes match - matches = np.array(matches).T - if matches.shape[0]: - if matches.shape[0] > 1: - matches = matches[iou[matches[:, 0], matches[:, 1]].argsort()[::-1]] - matches = matches[np.unique(matches[:, 1], return_index=True)[1]] - # matches = matches[matches[:, 2].argsort()[::-1]] - matches = matches[np.unique(matches[:, 0], return_index=True)[1]] - correct[matches[:, 1].astype(int), i] = True - return torch.tensor(correct, dtype=torch.bool, device=pred_classes.device) - - def add_callback(self, event: str, callback): - """Appends the given callback.""" - self.callbacks[event].append(callback) - - def run_callbacks(self, event: str): - """Runs all callbacks associated with a specified event.""" - for callback in self.callbacks.get(event, []): - callback(self) - - def get_dataloader(self, dataset_path, batch_size): - """Get data loader from dataset path and batch size.""" - raise NotImplementedError("get_dataloader function not implemented for this validator") - - def build_dataset(self, img_path): - """Build dataset.""" - raise NotImplementedError("build_dataset function not implemented in validator") - - def preprocess(self, batch): - """Preprocesses an input batch.""" - return batch - - def postprocess(self, preds): - """Describes and summarizes the purpose of 'postprocess()' but no details mentioned.""" - return preds - - def init_metrics(self, model): - """Initialize performance metrics for the YOLO model.""" - pass - - def update_metrics(self, preds, batch): - """Updates metrics based on predictions and batch.""" - pass - - def finalize_metrics(self, *args, **kwargs): - """Finalizes and returns all metrics.""" - pass - - def get_stats(self): - """Returns statistics about the model's performance.""" - return {} - - def check_stats(self, stats): - """Checks statistics.""" - pass - - def print_results(self): - """Prints the results of the model's predictions.""" - pass - - def get_desc(self): - """Get description of the YOLO model.""" - pass - - @property - def metric_keys(self): - """Returns the metric keys used in YOLO training/validation.""" - return [] - - def on_plot(self, name, data=None): - """Registers plots (e.g. to be consumed in callbacks)""" - self.plots[Path(name)] = {"data": data, "timestamp": time.time()} - - # TODO: may need to put these following functions into callback - def plot_val_samples(self, batch, ni): - """Plots validation samples during training.""" - pass - - def plot_predictions(self, batch, preds, ni): - """Plots YOLO model predictions on batch images.""" - pass - - def pred_to_json(self, preds, batch): - """Convert predictions to JSON format.""" - pass - - def eval_json(self, stats): - """Evaluate and return JSON format of prediction statistics.""" - pass diff --git a/ultralytics-main/ultralytics/hub/__init__.py b/ultralytics-main/ultralytics/hub/__init__.py deleted file mode 100644 index b46bea4..0000000 --- a/ultralytics-main/ultralytics/hub/__init__.py +++ /dev/null @@ -1,128 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import requests - -from ultralytics.data.utils import HUBDatasetStats -from ultralytics.hub.auth import Auth -from ultralytics.hub.utils import HUB_API_ROOT, HUB_WEB_ROOT, PREFIX -from ultralytics.utils import LOGGER, SETTINGS, checks - - -def login(api_key: str = None, save=True) -> bool: - """ - Log in to the Ultralytics HUB API using the provided API key. - - The session is not stored; a new session is created when needed using the saved SETTINGS or the HUB_API_KEY - environment variable if successfully authenticated. - - Args: - api_key (str, optional): API key to use for authentication. - If not provided, it will be retrieved from SETTINGS or HUB_API_KEY environment variable. - save (bool, optional): Whether to save the API key to SETTINGS if authentication is successful. - - Returns: - (bool): True if authentication is successful, False otherwise. - """ - checks.check_requirements("hub-sdk>=0.0.2") - from hub_sdk import HUBClient - - api_key_url = f"{HUB_WEB_ROOT}/settings?tab=api+keys" # set the redirect URL - saved_key = SETTINGS.get("api_key") - active_key = api_key or saved_key - credentials = {"api_key": active_key} if active_key and active_key != "" else None # set credentials - - client = HUBClient(credentials) # initialize HUBClient - - if client.authenticated: - # Successfully authenticated with HUB - - if save and client.api_key != saved_key: - SETTINGS.update({"api_key": client.api_key}) # update settings with valid API key - - # Set message based on whether key was provided or retrieved from settings - log_message = ( - "New authentication successful ✅" if client.api_key == api_key or not credentials else "Authenticated ✅" - ) - LOGGER.info(f"{PREFIX}{log_message}") - - return True - else: - # Failed to authenticate with HUB - LOGGER.info(f"{PREFIX}Get API key from {api_key_url} and then run 'yolo hub login API_KEY'") - return False - - -def logout(): - """ - Log out of Ultralytics HUB by removing the API key from the settings file. To log in again, use 'yolo hub login'. - - Example: - ```python - from ultralytics import hub - - hub.logout() - ``` - """ - SETTINGS["api_key"] = "" - SETTINGS.save() - LOGGER.info(f"{PREFIX}logged out ✅. To log in again, use 'yolo hub login'.") - - -def reset_model(model_id=""): - """Reset a trained model to an untrained state.""" - r = requests.post(f"{HUB_API_ROOT}/model-reset", json={"modelId": model_id}, headers={"x-api-key": Auth().api_key}) - if r.status_code == 200: - LOGGER.info(f"{PREFIX}Model reset successfully") - return - LOGGER.warning(f"{PREFIX}Model reset failure {r.status_code} {r.reason}") - - -def export_fmts_hub(): - """Returns a list of HUB-supported export formats.""" - from ultralytics.engine.exporter import export_formats - - return list(export_formats()["Argument"][1:]) + ["ultralytics_tflite", "ultralytics_coreml"] - - -def export_model(model_id="", format="torchscript"): - """Export a model to all formats.""" - assert format in export_fmts_hub(), f"Unsupported export format '{format}', valid formats are {export_fmts_hub()}" - r = requests.post( - f"{HUB_API_ROOT}/v1/models/{model_id}/export", json={"format": format}, headers={"x-api-key": Auth().api_key} - ) - assert r.status_code == 200, f"{PREFIX}{format} export failure {r.status_code} {r.reason}" - LOGGER.info(f"{PREFIX}{format} export started ✅") - - -def get_export(model_id="", format="torchscript"): - """Get an exported model dictionary with download URL.""" - assert format in export_fmts_hub(), f"Unsupported export format '{format}', valid formats are {export_fmts_hub()}" - r = requests.post( - f"{HUB_API_ROOT}/get-export", - json={"apiKey": Auth().api_key, "modelId": model_id, "format": format}, - headers={"x-api-key": Auth().api_key}, - ) - assert r.status_code == 200, f"{PREFIX}{format} get_export failure {r.status_code} {r.reason}" - return r.json() - - -def check_dataset(path="", task="detect"): - """ - Function for error-checking HUB dataset Zip file before upload. It checks a dataset for errors before it is uploaded - to the HUB. Usage examples are given below. - - Args: - path (str, optional): Path to data.zip (with data.yaml inside data.zip). Defaults to ''. - task (str, optional): Dataset task. Options are 'detect', 'segment', 'pose', 'classify'. Defaults to 'detect'. - - Example: - ```python - from ultralytics.hub import check_dataset - - check_dataset('path/to/coco8.zip', task='detect') # detect dataset - check_dataset('path/to/coco8-seg.zip', task='segment') # segment dataset - check_dataset('path/to/coco8-pose.zip', task='pose') # pose dataset - ``` - """ - HUBDatasetStats(path=path, task=task).get_json() - LOGGER.info(f"Checks completed correctly ✅. Upload this dataset to {HUB_WEB_ROOT}/datasets/.") diff --git a/ultralytics-main/ultralytics/hub/auth.py b/ultralytics-main/ultralytics/hub/auth.py deleted file mode 100644 index 6ede303..0000000 --- a/ultralytics-main/ultralytics/hub/auth.py +++ /dev/null @@ -1,136 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import requests - -from ultralytics.hub.utils import HUB_API_ROOT, HUB_WEB_ROOT, PREFIX, request_with_credentials -from ultralytics.utils import LOGGER, SETTINGS, emojis, is_colab - -API_KEY_URL = f"{HUB_WEB_ROOT}/settings?tab=api+keys" - - -class Auth: - """ - Manages authentication processes including API key handling, cookie-based authentication, and header generation. - - The class supports different methods of authentication: - 1. Directly using an API key. - 2. Authenticating using browser cookies (specifically in Google Colab). - 3. Prompting the user to enter an API key. - - Attributes: - id_token (str or bool): Token used for identity verification, initialized as False. - api_key (str or bool): API key for authentication, initialized as False. - model_key (bool): Placeholder for model key, initialized as False. - """ - - id_token = api_key = model_key = False - - def __init__(self, api_key="", verbose=False): - """ - Initialize the Auth class with an optional API key. - - Args: - api_key (str, optional): May be an API key or a combination API key and model ID, i.e. key_id - """ - # Split the input API key in case it contains a combined key_model and keep only the API key part - api_key = api_key.split("_")[0] - - # Set API key attribute as value passed or SETTINGS API key if none passed - self.api_key = api_key or SETTINGS.get("api_key", "") - - # If an API key is provided - if self.api_key: - # If the provided API key matches the API key in the SETTINGS - if self.api_key == SETTINGS.get("api_key"): - # Log that the user is already logged in - if verbose: - LOGGER.info(f"{PREFIX}Authenticated ✅") - return - else: - # Attempt to authenticate with the provided API key - success = self.authenticate() - # If the API key is not provided and the environment is a Google Colab notebook - elif is_colab(): - # Attempt to authenticate using browser cookies - success = self.auth_with_cookies() - else: - # Request an API key - success = self.request_api_key() - - # Update SETTINGS with the new API key after successful authentication - if success: - SETTINGS.update({"api_key": self.api_key}) - # Log that the new login was successful - if verbose: - LOGGER.info(f"{PREFIX}New authentication successful ✅") - elif verbose: - LOGGER.info(f"{PREFIX}Get API key from {API_KEY_URL} and then run 'yolo hub login API_KEY'") - - def request_api_key(self, max_attempts=3): - """ - Prompt the user to input their API key. - - Returns the model ID. - """ - import getpass - - for attempts in range(max_attempts): - LOGGER.info(f"{PREFIX}Login. Attempt {attempts + 1} of {max_attempts}") - input_key = getpass.getpass(f"Enter API key from {API_KEY_URL} ") - self.api_key = input_key.split("_")[0] # remove model id if present - if self.authenticate(): - return True - raise ConnectionError(emojis(f"{PREFIX}Failed to authenticate ❌")) - - def authenticate(self) -> bool: - """ - Attempt to authenticate with the server using either id_token or API key. - - Returns: - (bool): True if authentication is successful, False otherwise. - """ - try: - if header := self.get_auth_header(): - r = requests.post(f"{HUB_API_ROOT}/v1/auth", headers=header) - if not r.json().get("success", False): - raise ConnectionError("Unable to authenticate.") - return True - raise ConnectionError("User has not authenticated locally.") - except ConnectionError: - self.id_token = self.api_key = False # reset invalid - LOGGER.warning(f"{PREFIX}Invalid API key ⚠️") - return False - - def auth_with_cookies(self) -> bool: - """ - Attempt to fetch authentication via cookies and set id_token. User must be logged in to HUB and running in a - supported browser. - - Returns: - (bool): True if authentication is successful, False otherwise. - """ - if not is_colab(): - return False # Currently only works with Colab - try: - authn = request_with_credentials(f"{HUB_API_ROOT}/v1/auth/auto") - if authn.get("success", False): - self.id_token = authn.get("data", {}).get("idToken", None) - self.authenticate() - return True - raise ConnectionError("Unable to fetch browser authentication details.") - except ConnectionError: - self.id_token = False # reset invalid - return False - - def get_auth_header(self): - """ - Get the authentication header for making API requests. - - Returns: - (dict): The authentication header if id_token or API key is set, None otherwise. - """ - if self.id_token: - return {"authorization": f"Bearer {self.id_token}"} - elif self.api_key: - return {"x-api-key": self.api_key} - # else returns None diff --git a/ultralytics-main/ultralytics/hub/session.py b/ultralytics-main/ultralytics/hub/session.py deleted file mode 100644 index ebde7aa..0000000 --- a/ultralytics-main/ultralytics/hub/session.py +++ /dev/null @@ -1,355 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import threading -import time -from http import HTTPStatus -from pathlib import Path - -import requests - -from ultralytics.hub.utils import HUB_WEB_ROOT, HELP_MSG, PREFIX, TQDM -from ultralytics.utils import LOGGER, SETTINGS, __version__, checks, emojis, is_colab -from ultralytics.utils.errors import HUBModelError - -AGENT_NAME = f"python-{__version__}-colab" if is_colab() else f"python-{__version__}-local" - - -class HUBTrainingSession: - """ - HUB training session for Ultralytics HUB YOLO models. Handles model initialization, heartbeats, and checkpointing. - - Attributes: - agent_id (str): Identifier for the instance communicating with the server. - model_id (str): Identifier for the YOLO model being trained. - model_url (str): URL for the model in Ultralytics HUB. - api_url (str): API URL for the model in Ultralytics HUB. - auth_header (dict): Authentication header for the Ultralytics HUB API requests. - rate_limits (dict): Rate limits for different API calls (in seconds). - timers (dict): Timers for rate limiting. - metrics_queue (dict): Queue for the model's metrics. - model (dict): Model data fetched from Ultralytics HUB. - alive (bool): Indicates if the heartbeat loop is active. - """ - - def __init__(self, identifier): - """ - Initialize the HUBTrainingSession with the provided model identifier. - - Args: - identifier (str): Model identifier used to initialize the HUB training session. - It can be a URL string or a model key with specific format. - - Raises: - ValueError: If the provided model identifier is invalid. - ConnectionError: If connecting with global API key is not supported. - ModuleNotFoundError: If hub-sdk package is not installed. - """ - from hub_sdk import HUBClient - - self.rate_limits = { - "metrics": 3.0, - "ckpt": 900.0, - "heartbeat": 300.0, - } # rate limits (seconds) - self.metrics_queue = {} # holds metrics for each epoch until upload - self.metrics_upload_failed_queue = {} # holds metrics for each epoch if upload failed - self.timers = {} # holds timers in ultralytics/utils/callbacks/hub.py - - # Parse input - api_key, model_id, self.filename = self._parse_identifier(identifier) - - # Get credentials - active_key = api_key or SETTINGS.get("api_key") - credentials = {"api_key": active_key} if active_key else None # set credentials - - # Initialize client - self.client = HUBClient(credentials) - - if model_id: - self.load_model(model_id) # load existing model - else: - self.model = self.client.model() # load empty model - - def load_model(self, model_id): - """Loads an existing model from Ultralytics HUB using the provided model identifier.""" - self.model = self.client.model(model_id) - if not self.model.data: # then model does not exist - raise ValueError(emojis("❌ The specified HUB model does not exist")) # TODO: improve error handling - - self.model_url = f"{HUB_WEB_ROOT}/models/{self.model.id}" - - self._set_train_args() - - # Start heartbeats for HUB to monitor agent - self.model.start_heartbeat(self.rate_limits["heartbeat"]) - LOGGER.info(f"{PREFIX}View model at {self.model_url} 🚀") - - def create_model(self, model_args): - """Initializes a HUB training session with the specified model identifier.""" - payload = { - "config": { - "batchSize": model_args.get("batch", -1), - "epochs": model_args.get("epochs", 300), - "imageSize": model_args.get("imgsz", 640), - "patience": model_args.get("patience", 100), - "device": model_args.get("device", ""), - "cache": model_args.get("cache", "ram"), - }, - "dataset": {"name": model_args.get("data")}, - "lineage": { - "architecture": { - "name": self.filename.replace(".pt", "").replace(".yaml", ""), - }, - "parent": {}, - }, - "meta": {"name": self.filename}, - } - - if self.filename.endswith(".pt"): - payload["lineage"]["parent"]["name"] = self.filename - - self.model.create_model(payload) - - # Model could not be created - # TODO: improve error handling - if not self.model.id: - return - - self.model_url = f"{HUB_WEB_ROOT}/models/{self.model.id}" - - # Start heartbeats for HUB to monitor agent - self.model.start_heartbeat(self.rate_limits["heartbeat"]) - - LOGGER.info(f"{PREFIX}View model at {self.model_url} 🚀") - - def _parse_identifier(self, identifier): - """ - Parses the given identifier to determine the type of identifier and extract relevant components. - - The method supports different identifier formats: - - A HUB URL, which starts with HUB_WEB_ROOT followed by '/models/' - - An identifier containing an API key and a model ID separated by an underscore - - An identifier that is solely a model ID of a fixed length - - A local filename that ends with '.pt' or '.yaml' - - Args: - identifier (str): The identifier string to be parsed. - - Returns: - (tuple): A tuple containing the API key, model ID, and filename as applicable. - - Raises: - HUBModelError: If the identifier format is not recognized. - """ - - # Initialize variables - api_key, model_id, filename = None, None, None - - # Check if identifier is a HUB URL - if identifier.startswith(f"{HUB_WEB_ROOT}/models/"): - # Extract the model_id after the HUB_WEB_ROOT URL - model_id = identifier.split(f"{HUB_WEB_ROOT}/models/")[-1] - else: - # Split the identifier based on underscores only if it's not a HUB URL - parts = identifier.split("_") - - # Check if identifier is in the format of API key and model ID - if len(parts) == 2 and len(parts[0]) == 42 and len(parts[1]) == 20: - api_key, model_id = parts - # Check if identifier is a single model ID - elif len(parts) == 1 and len(parts[0]) == 20: - model_id = parts[0] - # Check if identifier is a local filename - elif identifier.endswith(".pt") or identifier.endswith(".yaml"): - filename = identifier - else: - raise HUBModelError( - f"model='{identifier}' could not be parsed. Check format is correct. " - f"Supported formats are Ultralytics HUB URL, apiKey_modelId, modelId, local pt or yaml file." - ) - - return api_key, model_id, filename - - def _set_train_args(self): - """ - Initializes training arguments and creates a model entry on the Ultralytics HUB. - - This method sets up training arguments based on the model's state and updates them with any additional - arguments provided. It handles different states of the model, such as whether it's resumable, pretrained, - or requires specific file setup. - - Raises: - ValueError: If the model is already trained, if required dataset information is missing, or if there are - issues with the provided training arguments. - """ - if self.model.is_trained(): - raise ValueError(emojis(f"Model is already trained and uploaded to {self.model_url} 🚀")) - - if self.model.is_resumable(): - # Model has saved weights - self.train_args = {"data": self.model.get_dataset_url(), "resume": True} - self.model_file = self.model.get_weights_url("last") - else: - # Model has no saved weights - self.train_args = self.model.data.get("train_args") # new response - - # Set the model file as either a *.pt or *.yaml file - self.model_file = ( - self.model.get_weights_url("parent") if self.model.is_pretrained() else self.model.get_architecture() - ) - - if "data" not in self.train_args: - # RF bug - datasets are sometimes not exported - raise ValueError("Dataset may still be processing. Please wait a minute and try again.") - - self.model_file = checks.check_yolov5u_filename(self.model_file, verbose=False) # YOLOv5->YOLOv5u - self.model_id = self.model.id - - def request_queue( - self, - request_func, - retry=3, - timeout=30, - thread=True, - verbose=True, - progress_total=None, - *args, - **kwargs, - ): - def retry_request(): - """Attempts to call `request_func` with retries, timeout, and optional threading.""" - t0 = time.time() # Record the start time for the timeout - for i in range(retry + 1): - if (time.time() - t0) > timeout: - LOGGER.warning(f"{PREFIX}Timeout for request reached. {HELP_MSG}") - break # Timeout reached, exit loop - - response = request_func(*args, **kwargs) - if response is None: - LOGGER.warning(f"{PREFIX}Received no response from the request. {HELP_MSG}") - time.sleep(2**i) # Exponential backoff before retrying - continue # Skip further processing and retry - - if progress_total: - self._show_upload_progress(progress_total, response) - - if HTTPStatus.OK <= response.status_code < HTTPStatus.MULTIPLE_CHOICES: - # if request related to metrics upload - if kwargs.get("metrics"): - self.metrics_upload_failed_queue = {} - return response # Success, no need to retry - - if i == 0: - # Initial attempt, check status code and provide messages - message = self._get_failure_message(response, retry, timeout) - - if verbose: - LOGGER.warning(f"{PREFIX}{message} {HELP_MSG} ({response.status_code})") - - if not self._should_retry(response.status_code): - LOGGER.warning(f"{PREFIX}Request failed. {HELP_MSG} ({response.status_code}") - break # Not an error that should be retried, exit loop - - time.sleep(2**i) # Exponential backoff for retries - - # if request related to metrics upload and exceed retries - if response is None and kwargs.get("metrics"): - self.metrics_upload_failed_queue.update(kwargs.get("metrics", None)) - - return response - - if thread: - # Start a new thread to run the retry_request function - threading.Thread(target=retry_request, daemon=True).start() - else: - # If running in the main thread, call retry_request directly - return retry_request() - - def _should_retry(self, status_code): - """Determines if a request should be retried based on the HTTP status code.""" - retry_codes = { - HTTPStatus.REQUEST_TIMEOUT, - HTTPStatus.BAD_GATEWAY, - HTTPStatus.GATEWAY_TIMEOUT, - } - return status_code in retry_codes - - def _get_failure_message(self, response: requests.Response, retry: int, timeout: int): - """ - Generate a retry message based on the response status code. - - Args: - response: The HTTP response object. - retry: The number of retry attempts allowed. - timeout: The maximum timeout duration. - - Returns: - (str): The retry message. - """ - if self._should_retry(response.status_code): - return f"Retrying {retry}x for {timeout}s." if retry else "" - elif response.status_code == HTTPStatus.TOO_MANY_REQUESTS: # rate limit - headers = response.headers - return ( - f"Rate limit reached ({headers['X-RateLimit-Remaining']}/{headers['X-RateLimit-Limit']}). " - f"Please retry after {headers['Retry-After']}s." - ) - else: - try: - return response.json().get("message", "No JSON message.") - except AttributeError: - return "Unable to read JSON." - - def upload_metrics(self): - """Upload model metrics to Ultralytics HUB.""" - return self.request_queue(self.model.upload_metrics, metrics=self.metrics_queue.copy(), thread=True) - - def upload_model( - self, - epoch: int, - weights: str, - is_best: bool = False, - map: float = 0.0, - final: bool = False, - ) -> None: - """ - Upload a model checkpoint to Ultralytics HUB. - - Args: - epoch (int): The current training epoch. - weights (str): Path to the model weights file. - is_best (bool): Indicates if the current model is the best one so far. - map (float): Mean average precision of the model. - final (bool): Indicates if the model is the final model after training. - """ - if Path(weights).is_file(): - progress_total = Path(weights).stat().st_size if final else None # Only show progress if final - self.request_queue( - self.model.upload_model, - epoch=epoch, - weights=weights, - is_best=is_best, - map=map, - final=final, - retry=10, - timeout=3600, - thread=not final, - progress_total=progress_total, - ) - else: - LOGGER.warning(f"{PREFIX}WARNING ⚠️ Model upload issue. Missing model {weights}.") - - def _show_upload_progress(self, content_length: int, response: requests.Response) -> None: - """ - Display a progress bar to track the upload progress of a file download. - - Args: - content_length (int): The total size of the content to be downloaded in bytes. - response (requests.Response): The response object from the file download request. - - Returns: - None - """ - with TQDM(total=content_length, unit="B", unit_scale=True, unit_divisor=1024) as pbar: - for data in response.iter_content(chunk_size=1024): - pbar.update(len(data)) diff --git a/ultralytics-main/ultralytics/hub/utils.py b/ultralytics-main/ultralytics/hub/utils.py deleted file mode 100644 index 5c00076..0000000 --- a/ultralytics-main/ultralytics/hub/utils.py +++ /dev/null @@ -1,247 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import os -import platform -import random -import sys -import threading -import time -from pathlib import Path - -import requests - -from ultralytics.utils import ( - ENVIRONMENT, - LOGGER, - ONLINE, - RANK, - SETTINGS, - TESTS_RUNNING, - TQDM, - TryExcept, - __version__, - colorstr, - get_git_origin_url, - is_colab, - is_git_dir, - is_pip_package, -) -from ultralytics.utils.downloads import GITHUB_ASSETS_NAMES - -HUB_API_ROOT = os.environ.get("ULTRALYTICS_HUB_API", "https://api.ultralytics.com") -HUB_WEB_ROOT = os.environ.get("ULTRALYTICS_HUB_WEB", "https://hub.ultralytics.com") - -PREFIX = colorstr("Ultralytics HUB: ") -HELP_MSG = "If this issue persists please visit https://github.com/ultralytics/hub/issues for assistance." - - -def request_with_credentials(url: str) -> any: - """ - Make an AJAX request with cookies attached in a Google Colab environment. - - Args: - url (str): The URL to make the request to. - - Returns: - (any): The response data from the AJAX request. - - Raises: - OSError: If the function is not run in a Google Colab environment. - """ - if not is_colab(): - raise OSError("request_with_credentials() must run in a Colab environment") - from google.colab import output # noqa - from IPython import display # noqa - - display.display( - display.Javascript( - """ - window._hub_tmp = new Promise((resolve, reject) => { - const timeout = setTimeout(() => reject("Failed authenticating existing browser session"), 5000) - fetch("%s", { - method: 'POST', - credentials: 'include' - }) - .then((response) => resolve(response.json())) - .then((json) => { - clearTimeout(timeout); - }).catch((err) => { - clearTimeout(timeout); - reject(err); - }); - }); - """ - % url - ) - ) - return output.eval_js("_hub_tmp") - - -def requests_with_progress(method, url, **kwargs): - """ - Make an HTTP request using the specified method and URL, with an optional progress bar. - - Args: - method (str): The HTTP method to use (e.g. 'GET', 'POST'). - url (str): The URL to send the request to. - **kwargs (any): Additional keyword arguments to pass to the underlying `requests.request` function. - - Returns: - (requests.Response): The response object from the HTTP request. - - Note: - - If 'progress' is set to True, the progress bar will display the download progress for responses with a known - content length. - - If 'progress' is a number then progress bar will display assuming content length = progress. - """ - progress = kwargs.pop("progress", False) - if not progress: - return requests.request(method, url, **kwargs) - response = requests.request(method, url, stream=True, **kwargs) - total = int(response.headers.get("content-length", 0) if isinstance(progress, bool) else progress) # total size - try: - pbar = TQDM(total=total, unit="B", unit_scale=True, unit_divisor=1024) - for data in response.iter_content(chunk_size=1024): - pbar.update(len(data)) - pbar.close() - except requests.exceptions.ChunkedEncodingError: # avoid 'Connection broken: IncompleteRead' warnings - response.close() - return response - - -def smart_request(method, url, retry=3, timeout=30, thread=True, code=-1, verbose=True, progress=False, **kwargs): - """ - Makes an HTTP request using the 'requests' library, with exponential backoff retries up to a specified timeout. - - Args: - method (str): The HTTP method to use for the request. Choices are 'post' and 'get'. - url (str): The URL to make the request to. - retry (int, optional): Number of retries to attempt before giving up. Default is 3. - timeout (int, optional): Timeout in seconds after which the function will give up retrying. Default is 30. - thread (bool, optional): Whether to execute the request in a separate daemon thread. Default is True. - code (int, optional): An identifier for the request, used for logging purposes. Default is -1. - verbose (bool, optional): A flag to determine whether to print out to console or not. Default is True. - progress (bool, optional): Whether to show a progress bar during the request. Default is False. - **kwargs (any): Keyword arguments to be passed to the requests function specified in method. - - Returns: - (requests.Response): The HTTP response object. If the request is executed in a separate thread, returns None. - """ - retry_codes = (408, 500) # retry only these codes - - @TryExcept(verbose=verbose) - def func(func_method, func_url, **func_kwargs): - """Make HTTP requests with retries and timeouts, with optional progress tracking.""" - r = None # response - t0 = time.time() # initial time for timer - for i in range(retry + 1): - if (time.time() - t0) > timeout: - break - r = requests_with_progress(func_method, func_url, **func_kwargs) # i.e. get(url, data, json, files) - if r.status_code < 300: # return codes in the 2xx range are generally considered "good" or "successful" - break - try: - m = r.json().get("message", "No JSON message.") - except AttributeError: - m = "Unable to read JSON." - if i == 0: - if r.status_code in retry_codes: - m += f" Retrying {retry}x for {timeout}s." if retry else "" - elif r.status_code == 429: # rate limit - h = r.headers # response headers - m = ( - f"Rate limit reached ({h['X-RateLimit-Remaining']}/{h['X-RateLimit-Limit']}). " - f"Please retry after {h['Retry-After']}s." - ) - if verbose: - LOGGER.warning(f"{PREFIX}{m} {HELP_MSG} ({r.status_code} #{code})") - if r.status_code not in retry_codes: - return r - time.sleep(2**i) # exponential standoff - return r - - args = method, url - kwargs["progress"] = progress - if thread: - threading.Thread(target=func, args=args, kwargs=kwargs, daemon=True).start() - else: - return func(*args, **kwargs) - - -class Events: - """ - A class for collecting anonymous event analytics. Event analytics are enabled when sync=True in settings and - disabled when sync=False. Run 'yolo settings' to see and update settings YAML file. - - Attributes: - url (str): The URL to send anonymous events. - rate_limit (float): The rate limit in seconds for sending events. - metadata (dict): A dictionary containing metadata about the environment. - enabled (bool): A flag to enable or disable Events based on certain conditions. - """ - - url = "https://www.google-analytics.com/mp/collect?measurement_id=G-X8NCJYTQXM&api_secret=QLQrATrNSwGRFRLE-cbHJw" - - def __init__(self): - """Initializes the Events object with default values for events, rate_limit, and metadata.""" - self.events = [] # events list - self.rate_limit = 60.0 # rate limit (seconds) - self.t = 0.0 # rate limit timer (seconds) - self.metadata = { - "cli": Path(sys.argv[0]).name == "yolo", - "install": "git" if is_git_dir() else "pip" if is_pip_package() else "other", - "python": ".".join(platform.python_version_tuple()[:2]), # i.e. 3.10 - "version": __version__, - "env": ENVIRONMENT, - "session_id": round(random.random() * 1e15), - "engagement_time_msec": 1000, - } - self.enabled = ( - SETTINGS["sync"] - and RANK in (-1, 0) - and not TESTS_RUNNING - and ONLINE - and (is_pip_package() or get_git_origin_url() == "https://github.com/ultralytics/ultralytics.git") - ) - - def __call__(self, cfg): - """ - Attempts to add a new event to the events list and send events if the rate limit is reached. - - Args: - cfg (IterableSimpleNamespace): The configuration object containing mode and task information. - """ - if not self.enabled: - # Events disabled, do nothing - return - - # Attempt to add to events - if len(self.events) < 25: # Events list limited to 25 events (drop any events past this) - params = { - **self.metadata, - "task": cfg.task, - "model": cfg.model if cfg.model in GITHUB_ASSETS_NAMES else "custom", - } - if cfg.mode == "export": - params["format"] = cfg.format - self.events.append({"name": cfg.mode, "params": params}) - - # Check rate limit - t = time.time() - if (t - self.t) < self.rate_limit: - # Time is under rate limiter, wait to send - return - - # Time is over rate limiter, send now - data = {"client_id": SETTINGS["uuid"], "events": self.events} # SHA-256 anonymized UUID hash and events list - - # POST equivalent to requests.post(self.url, json=data) - smart_request("post", self.url, json=data, retry=0, verbose=False) - - # Reset events and rate limit timer - self.events = [] - self.t = t - - -# Run below code on hub/utils init ------------------------------------------------------------------------------------- -events = Events() diff --git a/ultralytics-main/ultralytics/models/__init__.py b/ultralytics-main/ultralytics/models/__init__.py deleted file mode 100644 index b9b6eb3..0000000 --- a/ultralytics-main/ultralytics/models/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .rtdetr import RTDETR -from .sam import SAM -from .yolo import YOLO, YOLOWorld - -__all__ = "YOLO", "RTDETR", "SAM", "YOLOWorld" # allow simpler import diff --git a/ultralytics-main/ultralytics/models/fastsam/__init__.py b/ultralytics-main/ultralytics/models/fastsam/__init__.py deleted file mode 100644 index eabf5b9..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/__init__.py +++ /dev/null @@ -1,8 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .model import FastSAM -from .predict import FastSAMPredictor -from .prompt import FastSAMPrompt -from .val import FastSAMValidator - -__all__ = "FastSAMPredictor", "FastSAM", "FastSAMPrompt", "FastSAMValidator" diff --git a/ultralytics-main/ultralytics/models/fastsam/model.py b/ultralytics-main/ultralytics/models/fastsam/model.py deleted file mode 100644 index c01e66b..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/model.py +++ /dev/null @@ -1,33 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from pathlib import Path - -from ultralytics.engine.model import Model -from .predict import FastSAMPredictor -from .val import FastSAMValidator - - -class FastSAM(Model): - """ - FastSAM model interface. - - Example: - ```python - from ultralytics import FastSAM - - model = FastSAM('last.pt') - results = model.predict('ultralytics/assets/bus.jpg') - ``` - """ - - def __init__(self, model="FastSAM-x.pt"): - """Call the __init__ method of the parent class (YOLO) with the updated default model.""" - if str(model) == "FastSAM.pt": - model = "FastSAM-x.pt" - assert Path(model).suffix not in (".yaml", ".yml"), "FastSAM models only support pre-trained models." - super().__init__(model=model, task="segment") - - @property - def task_map(self): - """Returns a dictionary mapping segment task to corresponding predictor and validator classes.""" - return {"segment": {"predictor": FastSAMPredictor, "validator": FastSAMValidator}} diff --git a/ultralytics-main/ultralytics/models/fastsam/predict.py b/ultralytics-main/ultralytics/models/fastsam/predict.py deleted file mode 100644 index 0ef1803..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/predict.py +++ /dev/null @@ -1,86 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.engine.results import Results -from ultralytics.models.fastsam.utils import bbox_iou -from ultralytics.models.yolo.detect.predict import DetectionPredictor -from ultralytics.utils import DEFAULT_CFG, ops - - -class FastSAMPredictor(DetectionPredictor): - """ - FastSAMPredictor is specialized for fast SAM (Segment Anything Model) segmentation prediction tasks in Ultralytics - YOLO framework. - - This class extends the DetectionPredictor, customizing the prediction pipeline specifically for fast SAM. - It adjusts post-processing steps to incorporate mask prediction and non-max suppression while optimizing - for single-class segmentation. - - Attributes: - cfg (dict): Configuration parameters for prediction. - overrides (dict, optional): Optional parameter overrides for custom behavior. - _callbacks (dict, optional): Optional list of callback functions to be invoked during prediction. - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """ - Initializes the FastSAMPredictor class, inheriting from DetectionPredictor and setting the task to 'segment'. - - Args: - cfg (dict): Configuration parameters for prediction. - overrides (dict, optional): Optional parameter overrides for custom behavior. - _callbacks (dict, optional): Optional list of callback functions to be invoked during prediction. - """ - super().__init__(cfg, overrides, _callbacks) - self.args.task = "segment" - - def postprocess(self, preds, img, orig_imgs): - """ - Perform post-processing steps on predictions, including non-max suppression and scaling boxes to original image - size, and returns the final results. - - Args: - preds (list): The raw output predictions from the model. - img (torch.Tensor): The processed image tensor. - orig_imgs (list | torch.Tensor): The original image or list of images. - - Returns: - (list): A list of Results objects, each containing processed boxes, masks, and other metadata. - """ - p = ops.non_max_suppression( - preds[0], - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - nc=1, # set to 1 class since SAM has no class predictions - classes=self.args.classes, - ) - full_box = torch.zeros(p[0].shape[1], device=p[0].device) - full_box[2], full_box[3], full_box[4], full_box[6:] = img.shape[3], img.shape[2], 1.0, 1.0 - full_box = full_box.view(1, -1) - critical_iou_index = bbox_iou(full_box[0][:4], p[0][:, :4], iou_thres=0.9, image_shape=img.shape[2:]) - if critical_iou_index.numel() != 0: - full_box[0][4] = p[0][critical_iou_index][:, 4] - full_box[0][6:] = p[0][critical_iou_index][:, 6:] - p[0][critical_iou_index] = full_box - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - proto = preds[1][-1] if len(preds[1]) == 3 else preds[1] # second output is len 3 if pt, but only 1 if exported - for i, pred in enumerate(p): - orig_img = orig_imgs[i] - img_path = self.batch[0][i] - if not len(pred): # save empty boxes - masks = None - elif self.args.retina_masks: - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2]) # HWC - else: - masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True) # HWC - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks)) - return results diff --git a/ultralytics-main/ultralytics/models/fastsam/prompt.py b/ultralytics-main/ultralytics/models/fastsam/prompt.py deleted file mode 100644 index f7bf5ad..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/prompt.py +++ /dev/null @@ -1,357 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import os -from pathlib import Path - -import cv2 -import matplotlib.pyplot as plt -import numpy as np -import torch -from PIL import Image - -from ultralytics.utils import TQDM - - -class FastSAMPrompt: - """ - Fast Segment Anything Model class for image annotation and visualization. - - Attributes: - device (str): Computing device ('cuda' or 'cpu'). - results: Object detection or segmentation results. - source: Source image or image path. - clip: CLIP model for linear assignment. - """ - - def __init__(self, source, results, device="cuda") -> None: - """Initializes FastSAMPrompt with given source, results and device, and assigns clip for linear assignment.""" - self.device = device - self.results = results - self.source = source - - # Import and assign clip - try: - import clip - except ImportError: - from ultralytics.utils.checks import check_requirements - - check_requirements("git+https://github.com/openai/CLIP.git") - import clip - self.clip = clip - - @staticmethod - def _segment_image(image, bbox): - """Segments the given image according to the provided bounding box coordinates.""" - image_array = np.array(image) - segmented_image_array = np.zeros_like(image_array) - x1, y1, x2, y2 = bbox - segmented_image_array[y1:y2, x1:x2] = image_array[y1:y2, x1:x2] - segmented_image = Image.fromarray(segmented_image_array) - black_image = Image.new("RGB", image.size, (255, 255, 255)) - # transparency_mask = np.zeros_like((), dtype=np.uint8) - transparency_mask = np.zeros((image_array.shape[0], image_array.shape[1]), dtype=np.uint8) - transparency_mask[y1:y2, x1:x2] = 255 - transparency_mask_image = Image.fromarray(transparency_mask, mode="L") - black_image.paste(segmented_image, mask=transparency_mask_image) - return black_image - - @staticmethod - def _format_results(result, filter=0): - """Formats detection results into list of annotations each containing ID, segmentation, bounding box, score and - area. - """ - annotations = [] - n = len(result.masks.data) if result.masks is not None else 0 - for i in range(n): - mask = result.masks.data[i] == 1.0 - if torch.sum(mask) >= filter: - annotation = { - "id": i, - "segmentation": mask.cpu().numpy(), - "bbox": result.boxes.data[i], - "score": result.boxes.conf[i], - } - annotation["area"] = annotation["segmentation"].sum() - annotations.append(annotation) - return annotations - - @staticmethod - def _get_bbox_from_mask(mask): - """Applies morphological transformations to the mask, displays it, and if with_contours is True, draws - contours. - """ - mask = mask.astype(np.uint8) - contours, hierarchy = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) - x1, y1, w, h = cv2.boundingRect(contours[0]) - x2, y2 = x1 + w, y1 + h - if len(contours) > 1: - for b in contours: - x_t, y_t, w_t, h_t = cv2.boundingRect(b) - x1 = min(x1, x_t) - y1 = min(y1, y_t) - x2 = max(x2, x_t + w_t) - y2 = max(y2, y_t + h_t) - return [x1, y1, x2, y2] - - def plot( - self, - annotations, - output, - bbox=None, - points=None, - point_label=None, - mask_random_color=True, - better_quality=True, - retina=False, - with_contours=True, - ): - """ - Plots annotations, bounding boxes, and points on images and saves the output. - - Args: - annotations (list): Annotations to be plotted. - output (str or Path): Output directory for saving the plots. - bbox (list, optional): Bounding box coordinates [x1, y1, x2, y2]. Defaults to None. - points (list, optional): Points to be plotted. Defaults to None. - point_label (list, optional): Labels for the points. Defaults to None. - mask_random_color (bool, optional): Whether to use random color for masks. Defaults to True. - better_quality (bool, optional): Whether to apply morphological transformations for better mask quality. Defaults to True. - retina (bool, optional): Whether to use retina mask. Defaults to False. - with_contours (bool, optional): Whether to plot contours. Defaults to True. - """ - pbar = TQDM(annotations, total=len(annotations)) - for ann in pbar: - result_name = os.path.basename(ann.path) - image = ann.orig_img[..., ::-1] # BGR to RGB - original_h, original_w = ann.orig_shape - # For macOS only - # plt.switch_backend('TkAgg') - plt.figure(figsize=(original_w / 100, original_h / 100)) - # Add subplot with no margin. - plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0) - plt.margins(0, 0) - plt.gca().xaxis.set_major_locator(plt.NullLocator()) - plt.gca().yaxis.set_major_locator(plt.NullLocator()) - plt.imshow(image) - - if ann.masks is not None: - masks = ann.masks.data - if better_quality: - if isinstance(masks[0], torch.Tensor): - masks = np.array(masks.cpu()) - for i, mask in enumerate(masks): - mask = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8)) - masks[i] = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8)) - - self.fast_show_mask( - masks, - plt.gca(), - random_color=mask_random_color, - bbox=bbox, - points=points, - pointlabel=point_label, - retinamask=retina, - target_height=original_h, - target_width=original_w, - ) - - if with_contours: - contour_all = [] - temp = np.zeros((original_h, original_w, 1)) - for i, mask in enumerate(masks): - mask = mask.astype(np.uint8) - if not retina: - mask = cv2.resize(mask, (original_w, original_h), interpolation=cv2.INTER_NEAREST) - contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) - contour_all.extend(iter(contours)) - cv2.drawContours(temp, contour_all, -1, (255, 255, 255), 2) - color = np.array([0 / 255, 0 / 255, 1.0, 0.8]) - contour_mask = temp / 255 * color.reshape(1, 1, -1) - plt.imshow(contour_mask) - - # Save the figure - save_path = Path(output) / result_name - save_path.parent.mkdir(exist_ok=True, parents=True) - plt.axis("off") - plt.savefig(save_path, bbox_inches="tight", pad_inches=0, transparent=True) - plt.close() - pbar.set_description(f"Saving {result_name} to {save_path}") - - @staticmethod - def fast_show_mask( - annotation, - ax, - random_color=False, - bbox=None, - points=None, - pointlabel=None, - retinamask=True, - target_height=960, - target_width=960, - ): - """ - Quickly shows the mask annotations on the given matplotlib axis. - - Args: - annotation (array-like): Mask annotation. - ax (matplotlib.axes.Axes): Matplotlib axis. - random_color (bool, optional): Whether to use random color for masks. Defaults to False. - bbox (list, optional): Bounding box coordinates [x1, y1, x2, y2]. Defaults to None. - points (list, optional): Points to be plotted. Defaults to None. - pointlabel (list, optional): Labels for the points. Defaults to None. - retinamask (bool, optional): Whether to use retina mask. Defaults to True. - target_height (int, optional): Target height for resizing. Defaults to 960. - target_width (int, optional): Target width for resizing. Defaults to 960. - """ - n, h, w = annotation.shape # batch, height, width - - areas = np.sum(annotation, axis=(1, 2)) - annotation = annotation[np.argsort(areas)] - - index = (annotation != 0).argmax(axis=0) - if random_color: - color = np.random.random((n, 1, 1, 3)) - else: - color = np.ones((n, 1, 1, 3)) * np.array([30 / 255, 144 / 255, 1.0]) - transparency = np.ones((n, 1, 1, 1)) * 0.6 - visual = np.concatenate([color, transparency], axis=-1) - mask_image = np.expand_dims(annotation, -1) * visual - - show = np.zeros((h, w, 4)) - h_indices, w_indices = np.meshgrid(np.arange(h), np.arange(w), indexing="ij") - indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None)) - - show[h_indices, w_indices, :] = mask_image[indices] - if bbox is not None: - x1, y1, x2, y2 = bbox - ax.add_patch(plt.Rectangle((x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1)) - # Draw point - if points is not None: - plt.scatter( - [point[0] for i, point in enumerate(points) if pointlabel[i] == 1], - [point[1] for i, point in enumerate(points) if pointlabel[i] == 1], - s=20, - c="y", - ) - plt.scatter( - [point[0] for i, point in enumerate(points) if pointlabel[i] == 0], - [point[1] for i, point in enumerate(points) if pointlabel[i] == 0], - s=20, - c="m", - ) - - if not retinamask: - show = cv2.resize(show, (target_width, target_height), interpolation=cv2.INTER_NEAREST) - ax.imshow(show) - - @torch.no_grad() - def retrieve(self, model, preprocess, elements, search_text: str, device) -> int: - """Processes images and text with a model, calculates similarity, and returns softmax score.""" - preprocessed_images = [preprocess(image).to(device) for image in elements] - tokenized_text = self.clip.tokenize([search_text]).to(device) - stacked_images = torch.stack(preprocessed_images) - image_features = model.encode_image(stacked_images) - text_features = model.encode_text(tokenized_text) - image_features /= image_features.norm(dim=-1, keepdim=True) - text_features /= text_features.norm(dim=-1, keepdim=True) - probs = 100.0 * image_features @ text_features.T - return probs[:, 0].softmax(dim=0) - - def _crop_image(self, format_results): - """Crops an image based on provided annotation format and returns cropped images and related data.""" - if os.path.isdir(self.source): - raise ValueError(f"'{self.source}' is a directory, not a valid source for this function.") - image = Image.fromarray(cv2.cvtColor(self.results[0].orig_img, cv2.COLOR_BGR2RGB)) - ori_w, ori_h = image.size - annotations = format_results - mask_h, mask_w = annotations[0]["segmentation"].shape - if ori_w != mask_w or ori_h != mask_h: - image = image.resize((mask_w, mask_h)) - cropped_boxes = [] - cropped_images = [] - not_crop = [] - filter_id = [] - for _, mask in enumerate(annotations): - if np.sum(mask["segmentation"]) <= 100: - filter_id.append(_) - continue - bbox = self._get_bbox_from_mask(mask["segmentation"]) # bbox from mask - cropped_boxes.append(self._segment_image(image, bbox)) # save cropped image - cropped_images.append(bbox) # save cropped image bbox - - return cropped_boxes, cropped_images, not_crop, filter_id, annotations - - def box_prompt(self, bbox): - """Modifies the bounding box properties and calculates IoU between masks and bounding box.""" - if self.results[0].masks is not None: - assert bbox[2] != 0 and bbox[3] != 0 - if os.path.isdir(self.source): - raise ValueError(f"'{self.source}' is a directory, not a valid source for this function.") - masks = self.results[0].masks.data - target_height, target_width = self.results[0].orig_shape - h = masks.shape[1] - w = masks.shape[2] - if h != target_height or w != target_width: - bbox = [ - int(bbox[0] * w / target_width), - int(bbox[1] * h / target_height), - int(bbox[2] * w / target_width), - int(bbox[3] * h / target_height), - ] - bbox[0] = max(round(bbox[0]), 0) - bbox[1] = max(round(bbox[1]), 0) - bbox[2] = min(round(bbox[2]), w) - bbox[3] = min(round(bbox[3]), h) - - # IoUs = torch.zeros(len(masks), dtype=torch.float32) - bbox_area = (bbox[3] - bbox[1]) * (bbox[2] - bbox[0]) - - masks_area = torch.sum(masks[:, bbox[1] : bbox[3], bbox[0] : bbox[2]], dim=(1, 2)) - orig_masks_area = torch.sum(masks, dim=(1, 2)) - - union = bbox_area + orig_masks_area - masks_area - iou = masks_area / union - max_iou_index = torch.argmax(iou) - - self.results[0].masks.data = torch.tensor(np.array([masks[max_iou_index].cpu().numpy()])) - return self.results - - def point_prompt(self, points, pointlabel): # numpy - """Adjusts points on detected masks based on user input and returns the modified results.""" - if self.results[0].masks is not None: - if os.path.isdir(self.source): - raise ValueError(f"'{self.source}' is a directory, not a valid source for this function.") - masks = self._format_results(self.results[0], 0) - target_height, target_width = self.results[0].orig_shape - h = masks[0]["segmentation"].shape[0] - w = masks[0]["segmentation"].shape[1] - if h != target_height or w != target_width: - points = [[int(point[0] * w / target_width), int(point[1] * h / target_height)] for point in points] - onemask = np.zeros((h, w)) - for annotation in masks: - mask = annotation["segmentation"] if isinstance(annotation, dict) else annotation - for i, point in enumerate(points): - if mask[point[1], point[0]] == 1 and pointlabel[i] == 1: - onemask += mask - if mask[point[1], point[0]] == 1 and pointlabel[i] == 0: - onemask -= mask - onemask = onemask >= 1 - self.results[0].masks.data = torch.tensor(np.array([onemask])) - return self.results - - def text_prompt(self, text): - """Processes a text prompt, applies it to existing results and returns the updated results.""" - if self.results[0].masks is not None: - format_results = self._format_results(self.results[0], 0) - cropped_boxes, cropped_images, not_crop, filter_id, annotations = self._crop_image(format_results) - clip_model, preprocess = self.clip.load("ViT-B/32", device=self.device) - scores = self.retrieve(clip_model, preprocess, cropped_boxes, text, device=self.device) - max_idx = scores.argsort() - max_idx = max_idx[-1] - max_idx += sum(np.array(filter_id) <= int(max_idx)) - self.results[0].masks.data = torch.tensor(np.array([annotations[max_idx]["segmentation"]])) - return self.results - - def everything_prompt(self): - """Returns the processed results from the previous methods in the class.""" - return self.results diff --git a/ultralytics-main/ultralytics/models/fastsam/utils.py b/ultralytics-main/ultralytics/models/fastsam/utils.py deleted file mode 100644 index 480e903..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/utils.py +++ /dev/null @@ -1,67 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - - -def adjust_bboxes_to_image_border(boxes, image_shape, threshold=20): - """ - Adjust bounding boxes to stick to image border if they are within a certain threshold. - - Args: - boxes (torch.Tensor): (n, 4) - image_shape (tuple): (height, width) - threshold (int): pixel threshold - - Returns: - adjusted_boxes (torch.Tensor): adjusted bounding boxes - """ - - # Image dimensions - h, w = image_shape - - # Adjust boxes - boxes[boxes[:, 0] < threshold, 0] = 0 # x1 - boxes[boxes[:, 1] < threshold, 1] = 0 # y1 - boxes[boxes[:, 2] > w - threshold, 2] = w # x2 - boxes[boxes[:, 3] > h - threshold, 3] = h # y2 - return boxes - - -def bbox_iou(box1, boxes, iou_thres=0.9, image_shape=(640, 640), raw_output=False): - """ - Compute the Intersection-Over-Union of a bounding box with respect to an array of other bounding boxes. - - Args: - box1 (torch.Tensor): (4, ) - boxes (torch.Tensor): (n, 4) - iou_thres (float): IoU threshold - image_shape (tuple): (height, width) - raw_output (bool): If True, return the raw IoU values instead of the indices - - Returns: - high_iou_indices (torch.Tensor): Indices of boxes with IoU > thres - """ - boxes = adjust_bboxes_to_image_border(boxes, image_shape) - # Obtain coordinates for intersections - x1 = torch.max(box1[0], boxes[:, 0]) - y1 = torch.max(box1[1], boxes[:, 1]) - x2 = torch.min(box1[2], boxes[:, 2]) - y2 = torch.min(box1[3], boxes[:, 3]) - - # Compute the area of intersection - intersection = (x2 - x1).clamp(0) * (y2 - y1).clamp(0) - - # Compute the area of both individual boxes - box1_area = (box1[2] - box1[0]) * (box1[3] - box1[1]) - box2_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) - - # Compute the area of union - union = box1_area + box2_area - intersection - - # Compute the IoU - iou = intersection / union # Should be shape (n, ) - if raw_output: - return 0 if iou.numel() == 0 else iou - - # return indices of boxes with IoU > thres - return torch.nonzero(iou > iou_thres).flatten() diff --git a/ultralytics-main/ultralytics/models/fastsam/val.py b/ultralytics-main/ultralytics/models/fastsam/val.py deleted file mode 100644 index 9014b27..0000000 --- a/ultralytics-main/ultralytics/models/fastsam/val.py +++ /dev/null @@ -1,40 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.models.yolo.segment import SegmentationValidator -from ultralytics.utils.metrics import SegmentMetrics - - -class FastSAMValidator(SegmentationValidator): - """ - Custom validation class for fast SAM (Segment Anything Model) segmentation in Ultralytics YOLO framework. - - Extends the SegmentationValidator class, customizing the validation process specifically for fast SAM. This class - sets the task to 'segment' and uses the SegmentMetrics for evaluation. Additionally, plotting features are disabled - to avoid errors during validation. - - Attributes: - dataloader: The data loader object used for validation. - save_dir (str): The directory where validation results will be saved. - pbar: A progress bar object. - args: Additional arguments for customization. - _callbacks: List of callback functions to be invoked during validation. - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """ - Initialize the FastSAMValidator class, setting the task to 'segment' and metrics to SegmentMetrics. - - Args: - dataloader (torch.utils.data.DataLoader): Dataloader to be used for validation. - save_dir (Path, optional): Directory to save results. - pbar (tqdm.tqdm): Progress bar for displaying progress. - args (SimpleNamespace): Configuration for the validator. - _callbacks (dict): Dictionary to store various callback functions. - - Notes: - Plots for ConfusionMatrix and other related metrics are disabled in this class to avoid errors. - """ - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.args.task = "segment" - self.args.plots = False # disable ConfusionMatrix and other plots to avoid errors - self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot) diff --git a/ultralytics-main/ultralytics/models/nas/__init__.py b/ultralytics-main/ultralytics/models/nas/__init__.py deleted file mode 100644 index b095a05..0000000 --- a/ultralytics-main/ultralytics/models/nas/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .model import NAS -from .predict import NASPredictor -from .val import NASValidator - -__all__ = "NASPredictor", "NASValidator", "NAS" diff --git a/ultralytics-main/ultralytics/models/nas/model.py b/ultralytics-main/ultralytics/models/nas/model.py deleted file mode 100644 index 7997e96..0000000 --- a/ultralytics-main/ultralytics/models/nas/model.py +++ /dev/null @@ -1,83 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -YOLO-NAS model interface. - -Example: - ```python - from ultralytics import NAS - - model = NAS('yolo_nas_s') - results = model.predict('ultralytics/assets/bus.jpg') - ``` -""" - -from pathlib import Path - -import torch - -from ultralytics.engine.model import Model -from ultralytics.utils.torch_utils import model_info, smart_inference_mode -from .predict import NASPredictor -from .val import NASValidator - - -class NAS(Model): - """ - YOLO NAS model for object detection. - - This class provides an interface for the YOLO-NAS models and extends the `Model` class from Ultralytics engine. - It is designed to facilitate the task of object detection using pre-trained or custom-trained YOLO-NAS models. - - Example: - ```python - from ultralytics import NAS - - model = NAS('yolo_nas_s') - results = model.predict('ultralytics/assets/bus.jpg') - ``` - - Attributes: - model (str): Path to the pre-trained model or model name. Defaults to 'yolo_nas_s.pt'. - - Note: - YOLO-NAS models only support pre-trained models. Do not provide YAML configuration files. - """ - - def __init__(self, model="yolo_nas_s.pt") -> None: - """Initializes the NAS model with the provided or default 'yolo_nas_s.pt' model.""" - assert Path(model).suffix not in (".yaml", ".yml"), "YOLO-NAS models only support pre-trained models." - super().__init__(model, task="detect") - - @smart_inference_mode() - def _load(self, weights: str, task: str): - """Loads an existing NAS model weights or creates a new NAS model with pretrained weights if not provided.""" - import super_gradients - - suffix = Path(weights).suffix - if suffix == ".pt": - self.model = torch.load(weights) - elif suffix == "": - self.model = super_gradients.training.models.get(weights, pretrained_weights="coco") - # Standardize model - self.model.fuse = lambda verbose=True: self.model - self.model.stride = torch.tensor([32]) - self.model.names = dict(enumerate(self.model._class_names)) - self.model.is_fused = lambda: False # for info() - self.model.yaml = {} # for info() - self.model.pt_path = weights # for export() - self.model.task = "detect" # for export() - - def info(self, detailed=False, verbose=True): - """ - Logs model info. - - Args: - detailed (bool): Show detailed information about model. - verbose (bool): Controls verbosity. - """ - return model_info(self.model, detailed=detailed, verbose=verbose, imgsz=640) - - @property - def task_map(self): - """Returns a dictionary mapping tasks to respective predictor and validator classes.""" - return {"detect": {"predictor": NASPredictor, "validator": NASValidator}} diff --git a/ultralytics-main/ultralytics/models/nas/predict.py b/ultralytics-main/ultralytics/models/nas/predict.py deleted file mode 100644 index 2e48546..0000000 --- a/ultralytics-main/ultralytics/models/nas/predict.py +++ /dev/null @@ -1,60 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.engine.predictor import BasePredictor -from ultralytics.engine.results import Results -from ultralytics.utils import ops - - -class NASPredictor(BasePredictor): - """ - Ultralytics YOLO NAS Predictor for object detection. - - This class extends the `BasePredictor` from Ultralytics engine and is responsible for post-processing the - raw predictions generated by the YOLO NAS models. It applies operations like non-maximum suppression and - scaling the bounding boxes to fit the original image dimensions. - - Attributes: - args (Namespace): Namespace containing various configurations for post-processing. - - Example: - ```python - from ultralytics import NAS - - model = NAS('yolo_nas_s') - predictor = model.predictor - # Assumes that raw_preds, img, orig_imgs are available - results = predictor.postprocess(raw_preds, img, orig_imgs) - ``` - - Note: - Typically, this class is not instantiated directly. It is used internally within the `NAS` class. - """ - - def postprocess(self, preds_in, img, orig_imgs): - """Postprocess predictions and returns a list of Results objects.""" - - # Cat boxes and class scores - boxes = ops.xyxy2xywh(preds_in[0][0]) - preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1) - - preds = ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - classes=self.args.classes, - ) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, pred in enumerate(preds): - orig_img = orig_imgs[i] - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - img_path = self.batch[0][i] - results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred)) - return results diff --git a/ultralytics-main/ultralytics/models/nas/val.py b/ultralytics-main/ultralytics/models/nas/val.py deleted file mode 100644 index a4a4f99..0000000 --- a/ultralytics-main/ultralytics/models/nas/val.py +++ /dev/null @@ -1,50 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.models.yolo.detect import DetectionValidator -from ultralytics.utils import ops - -__all__ = ["NASValidator"] - - -class NASValidator(DetectionValidator): - """ - Ultralytics YOLO NAS Validator for object detection. - - Extends `DetectionValidator` from the Ultralytics models package and is designed to post-process the raw predictions - generated by YOLO NAS models. It performs non-maximum suppression to remove overlapping and low-confidence boxes, - ultimately producing the final detections. - - Attributes: - args (Namespace): Namespace containing various configurations for post-processing, such as confidence and IoU thresholds. - lb (torch.Tensor): Optional tensor for multilabel NMS. - - Example: - ```python - from ultralytics import NAS - - model = NAS('yolo_nas_s') - validator = model.validator - # Assumes that raw_preds are available - final_preds = validator.postprocess(raw_preds) - ``` - - Note: - This class is generally not instantiated directly but is used internally within the `NAS` class. - """ - - def postprocess(self, preds_in): - """Apply Non-maximum suppression to prediction outputs.""" - boxes = ops.xyxy2xywh(preds_in[0][0]) - preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1) - return ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - labels=self.lb, - multi_label=False, - agnostic=self.args.single_cls, - max_det=self.args.max_det, - max_time_img=0.5, - ) diff --git a/ultralytics-main/ultralytics/models/rtdetr/__init__.py b/ultralytics-main/ultralytics/models/rtdetr/__init__.py deleted file mode 100644 index 172c74b..0000000 --- a/ultralytics-main/ultralytics/models/rtdetr/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .model import RTDETR -from .predict import RTDETRPredictor -from .val import RTDETRValidator - -__all__ = "RTDETRPredictor", "RTDETRValidator", "RTDETR" diff --git a/ultralytics-main/ultralytics/models/rtdetr/model.py b/ultralytics-main/ultralytics/models/rtdetr/model.py deleted file mode 100644 index 440df17..0000000 --- a/ultralytics-main/ultralytics/models/rtdetr/model.py +++ /dev/null @@ -1,54 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Interface for Baidu's RT-DETR, a Vision Transformer-based real-time object detector. RT-DETR offers real-time -performance and high accuracy, excelling in accelerated backends like CUDA with TensorRT. It features an efficient -hybrid encoder and IoU-aware query selection for enhanced detection accuracy. - -For more information on RT-DETR, visit: https://arxiv.org/pdf/2304.08069.pdf -""" - -from ultralytics.engine.model import Model -from ultralytics.nn.tasks import RTDETRDetectionModel - -from .predict import RTDETRPredictor -from .train import RTDETRTrainer -from .val import RTDETRValidator - - -class RTDETR(Model): - """ - Interface for Baidu's RT-DETR model. This Vision Transformer-based object detector provides real-time performance - with high accuracy. It supports efficient hybrid encoding, IoU-aware query selection, and adaptable inference speed. - - Attributes: - model (str): Path to the pre-trained model. Defaults to 'rtdetr-l.pt'. - """ - - def __init__(self, model="rtdetr-l.pt") -> None: - """ - Initializes the RT-DETR model with the given pre-trained model file. Supports .pt and .yaml formats. - - Args: - model (str): Path to the pre-trained model. Defaults to 'rtdetr-l.pt'. - - Raises: - NotImplementedError: If the model file extension is not 'pt', 'yaml', or 'yml'. - """ - super().__init__(model=model, task="detect") - - @property - def task_map(self) -> dict: - """ - Returns a task map for RT-DETR, associating tasks with corresponding Ultralytics classes. - - Returns: - dict: A dictionary mapping task names to Ultralytics task classes for the RT-DETR model. - """ - return { - "detect": { - "predictor": RTDETRPredictor, - "validator": RTDETRValidator, - "trainer": RTDETRTrainer, - "model": RTDETRDetectionModel, - } - } diff --git a/ultralytics-main/ultralytics/models/rtdetr/predict.py b/ultralytics-main/ultralytics/models/rtdetr/predict.py deleted file mode 100644 index 7fc918b..0000000 --- a/ultralytics-main/ultralytics/models/rtdetr/predict.py +++ /dev/null @@ -1,86 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.data.augment import LetterBox -from ultralytics.engine.predictor import BasePredictor -from ultralytics.engine.results import Results -from ultralytics.utils import ops - - -class RTDETRPredictor(BasePredictor): - """ - RT-DETR (Real-Time Detection Transformer) Predictor extending the BasePredictor class for making predictions using - Baidu's RT-DETR model. - - This class leverages the power of Vision Transformers to provide real-time object detection while maintaining - high accuracy. It supports key features like efficient hybrid encoding and IoU-aware query selection. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.rtdetr import RTDETRPredictor - - args = dict(model='rtdetr-l.pt', source=ASSETS) - predictor = RTDETRPredictor(overrides=args) - predictor.predict_cli() - ``` - - Attributes: - imgsz (int): Image size for inference (must be square and scale-filled). - args (dict): Argument overrides for the predictor. - """ - - def postprocess(self, preds, img, orig_imgs): - """ - Postprocess the raw predictions from the model to generate bounding boxes and confidence scores. - - The method filters detections based on confidence and class if specified in `self.args`. - - Args: - preds (list): List of [predictions, extra] from the model. - img (torch.Tensor): Processed input images. - orig_imgs (list or torch.Tensor): Original, unprocessed images. - - Returns: - (list[Results]): A list of Results objects containing the post-processed bounding boxes, confidence scores, - and class labels. - """ - if not isinstance(preds, (list, tuple)): # list for PyTorch inference but list[0] Tensor for export inference - preds = [preds, None] - - nd = preds[0].shape[-1] - bboxes, scores = preds[0].split((4, nd - 4), dim=-1) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, bbox in enumerate(bboxes): # (300, 4) - bbox = ops.xywh2xyxy(bbox) - score, cls = scores[i].max(-1, keepdim=True) # (300, 1) - idx = score.squeeze(-1) > self.args.conf # (300, ) - if self.args.classes is not None: - idx = (cls == torch.tensor(self.args.classes, device=cls.device)).any(1) & idx - pred = torch.cat([bbox, score, cls], dim=-1)[idx] # filter - orig_img = orig_imgs[i] - oh, ow = orig_img.shape[:2] - pred[..., [0, 2]] *= ow - pred[..., [1, 3]] *= oh - img_path = self.batch[0][i] - results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred)) - return results - - def pre_transform(self, im): - """ - Pre-transforms the input images before feeding them into the model for inference. The input images are - letterboxed to ensure a square aspect ratio and scale-filled. The size must be square(640) and scaleFilled. - - Args: - im (list[np.ndarray] |torch.Tensor): Input images of shape (N,3,h,w) for tensor, [(h,w,3) x N] for list. - - Returns: - (list): List of pre-transformed images ready for model inference. - """ - letterbox = LetterBox(self.imgsz, auto=False, scaleFill=True) - return [letterbox(image=x) for x in im] diff --git a/ultralytics-main/ultralytics/models/rtdetr/train.py b/ultralytics-main/ultralytics/models/rtdetr/train.py deleted file mode 100644 index 10a8f9b..0000000 --- a/ultralytics-main/ultralytics/models/rtdetr/train.py +++ /dev/null @@ -1,101 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from copy import copy - -import torch - -from ultralytics.models.yolo.detect import DetectionTrainer -from ultralytics.nn.tasks import RTDETRDetectionModel -from ultralytics.utils import RANK, colorstr -from .val import RTDETRDataset, RTDETRValidator - - -class RTDETRTrainer(DetectionTrainer): - """ - Trainer class for the RT-DETR model developed by Baidu for real-time object detection. Extends the DetectionTrainer - class for YOLO to adapt to the specific features and architecture of RT-DETR. This model leverages Vision - Transformers and has capabilities like IoU-aware query selection and adaptable inference speed. - - Notes: - - F.grid_sample used in RT-DETR does not support the `deterministic=True` argument. - - AMP training can lead to NaN outputs and may produce errors during bipartite graph matching. - - Example: - ```python - from ultralytics.models.rtdetr.train import RTDETRTrainer - - args = dict(model='rtdetr-l.yaml', data='coco8.yaml', imgsz=640, epochs=3) - trainer = RTDETRTrainer(overrides=args) - trainer.train() - ``` - """ - - def get_model(self, cfg=None, weights=None, verbose=True): - """ - Initialize and return an RT-DETR model for object detection tasks. - - Args: - cfg (dict, optional): Model configuration. Defaults to None. - weights (str, optional): Path to pre-trained model weights. Defaults to None. - verbose (bool): Verbose logging if True. Defaults to True. - - Returns: - (RTDETRDetectionModel): Initialized model. - """ - model = RTDETRDetectionModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1) - if weights: - model.load(weights) - return model - - def build_dataset(self, img_path, mode="val", batch=None): - """ - Build and return an RT-DETR dataset for training or validation. - - Args: - img_path (str): Path to the folder containing images. - mode (str): Dataset mode, either 'train' or 'val'. - batch (int, optional): Batch size for rectangle training. Defaults to None. - - Returns: - (RTDETRDataset): Dataset object for the specific mode. - """ - return RTDETRDataset( - img_path=img_path, - imgsz=self.args.imgsz, - batch_size=batch, - augment=mode == "train", - hyp=self.args, - rect=False, - cache=self.args.cache or None, - prefix=colorstr(f"{mode}: "), - data=self.data, - ) - - def get_validator(self): - """ - Returns a DetectionValidator suitable for RT-DETR model validation. - - Returns: - (RTDETRValidator): Validator object for model validation. - """ - self.loss_names = "giou_loss", "cls_loss", "l1_loss" - return RTDETRValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args)) - - def preprocess_batch(self, batch): - """ - Preprocess a batch of images. Scales and converts the images to float format. - - Args: - batch (dict): Dictionary containing a batch of images, bboxes, and labels. - - Returns: - (dict): Preprocessed batch. - """ - batch = super().preprocess_batch(batch) - bs = len(batch["img"]) - batch_idx = batch["batch_idx"] - gt_bbox, gt_class = [], [] - for i in range(bs): - gt_bbox.append(batch["bboxes"][batch_idx == i].to(batch_idx.device)) - gt_class.append(batch["cls"][batch_idx == i].to(device=batch_idx.device, dtype=torch.long)) - return batch diff --git a/ultralytics-main/ultralytics/models/rtdetr/val.py b/ultralytics-main/ultralytics/models/rtdetr/val.py deleted file mode 100644 index 88bb0ae..0000000 --- a/ultralytics-main/ultralytics/models/rtdetr/val.py +++ /dev/null @@ -1,135 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.data import YOLODataset -from ultralytics.data.augment import Compose, Format, v8_transforms -from ultralytics.models.yolo.detect import DetectionValidator -from ultralytics.utils import colorstr, ops - -__all__ = ("RTDETRValidator",) # tuple or list - - -class RTDETRDataset(YOLODataset): - """ - Real-Time DEtection and TRacking (RT-DETR) dataset class extending the base YOLODataset class. - - This specialized dataset class is designed for use with the RT-DETR object detection model and is optimized for - real-time detection and tracking tasks. - """ - - def __init__(self, *args, data=None, **kwargs): - """Initialize the RTDETRDataset class by inheriting from the YOLODataset class.""" - super().__init__(*args, data=data, **kwargs) - - # NOTE: add stretch version load_image for RTDETR mosaic - def load_image(self, i, rect_mode=False): - """Loads 1 image from dataset index 'i', returns (im, resized hw).""" - return super().load_image(i=i, rect_mode=rect_mode) - - def build_transforms(self, hyp=None): - """Temporary, only for evaluation.""" - if self.augment: - hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0 - hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0 - transforms = v8_transforms(self, self.imgsz, hyp, stretch=True) - else: - # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scaleFill=True)]) - transforms = Compose([]) - transforms.append( - Format( - bbox_format="xywh", - normalize=True, - return_mask=self.use_segments, - return_keypoint=self.use_keypoints, - batch_idx=True, - mask_ratio=hyp.mask_ratio, - mask_overlap=hyp.overlap_mask, - ) - ) - return transforms - - -class RTDETRValidator(DetectionValidator): - """ - RTDETRValidator extends the DetectionValidator class to provide validation capabilities specifically tailored for - the RT-DETR (Real-Time DETR) object detection model. - - The class allows building of an RTDETR-specific dataset for validation, applies Non-maximum suppression for - post-processing, and updates evaluation metrics accordingly. - - Example: - ```python - from ultralytics.models.rtdetr import RTDETRValidator - - args = dict(model='rtdetr-l.pt', data='coco8.yaml') - validator = RTDETRValidator(args=args) - validator() - ``` - - Note: - For further details on the attributes and methods, refer to the parent DetectionValidator class. - """ - - def build_dataset(self, img_path, mode="val", batch=None): - """ - Build an RTDETR Dataset. - - Args: - img_path (str): Path to the folder containing images. - mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode. - batch (int, optional): Size of batches, this is for `rect`. Defaults to None. - """ - return RTDETRDataset( - img_path=img_path, - imgsz=self.args.imgsz, - batch_size=batch, - augment=False, # no augmentation - hyp=self.args, - rect=False, # no rect - cache=self.args.cache or None, - prefix=colorstr(f"{mode}: "), - data=self.data, - ) - - def postprocess(self, preds): - """Apply Non-maximum suppression to prediction outputs.""" - if not isinstance(preds, (list, tuple)): # list for PyTorch inference but list[0] Tensor for export inference - preds = [preds, None] - - bs, _, nd = preds[0].shape - bboxes, scores = preds[0].split((4, nd - 4), dim=-1) - bboxes *= self.args.imgsz - outputs = [torch.zeros((0, 6), device=bboxes.device)] * bs - for i, bbox in enumerate(bboxes): # (300, 4) - bbox = ops.xywh2xyxy(bbox) - score, cls = scores[i].max(-1) # (300, ) - # Do not need threshold for evaluation as only got 300 boxes here - # idx = score > self.args.conf - pred = torch.cat([bbox, score[..., None], cls[..., None]], dim=-1) # filter - # Sort by confidence to correctly get internal metrics - pred = pred[score.argsort(descending=True)] - outputs[i] = pred # [idx] - - return outputs - - def _prepare_batch(self, si, batch): - """Prepares a batch for training or inference by applying transformations.""" - idx = batch["batch_idx"] == si - cls = batch["cls"][idx].squeeze(-1) - bbox = batch["bboxes"][idx] - ori_shape = batch["ori_shape"][si] - imgsz = batch["img"].shape[2:] - ratio_pad = batch["ratio_pad"][si] - if len(cls): - bbox = ops.xywh2xyxy(bbox) # target boxes - bbox[..., [0, 2]] *= ori_shape[1] # native-space pred - bbox[..., [1, 3]] *= ori_shape[0] # native-space pred - return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad) - - def _prepare_pred(self, pred, pbatch): - """Prepares and returns a batch with transformed bounding boxes and class labels.""" - predn = pred.clone() - predn[..., [0, 2]] *= pbatch["ori_shape"][1] / self.args.imgsz # native-space pred - predn[..., [1, 3]] *= pbatch["ori_shape"][0] / self.args.imgsz # native-space pred - return predn.float() diff --git a/ultralytics-main/ultralytics/models/sam/__init__.py b/ultralytics-main/ultralytics/models/sam/__init__.py deleted file mode 100644 index 8701fcc..0000000 --- a/ultralytics-main/ultralytics/models/sam/__init__.py +++ /dev/null @@ -1,6 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .model import SAM -from .predict import Predictor - -__all__ = "SAM", "Predictor" # tuple or list diff --git a/ultralytics-main/ultralytics/models/sam/amg.py b/ultralytics-main/ultralytics/models/sam/amg.py deleted file mode 100644 index 128108f..0000000 --- a/ultralytics-main/ultralytics/models/sam/amg.py +++ /dev/null @@ -1,187 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math -from itertools import product -from typing import Any, Generator, List, Tuple - -import numpy as np -import torch - - -def is_box_near_crop_edge( - boxes: torch.Tensor, crop_box: List[int], orig_box: List[int], atol: float = 20.0 -) -> torch.Tensor: - """Return a boolean tensor indicating if boxes are near the crop edge.""" - crop_box_torch = torch.as_tensor(crop_box, dtype=torch.float, device=boxes.device) - orig_box_torch = torch.as_tensor(orig_box, dtype=torch.float, device=boxes.device) - boxes = uncrop_boxes_xyxy(boxes, crop_box).float() - near_crop_edge = torch.isclose(boxes, crop_box_torch[None, :], atol=atol, rtol=0) - near_image_edge = torch.isclose(boxes, orig_box_torch[None, :], atol=atol, rtol=0) - near_crop_edge = torch.logical_and(near_crop_edge, ~near_image_edge) - return torch.any(near_crop_edge, dim=1) - - -def batch_iterator(batch_size: int, *args) -> Generator[List[Any], None, None]: - """Yield batches of data from the input arguments.""" - assert args and all(len(a) == len(args[0]) for a in args), "Batched iteration must have same-size inputs." - n_batches = len(args[0]) // batch_size + int(len(args[0]) % batch_size != 0) - for b in range(n_batches): - yield [arg[b * batch_size : (b + 1) * batch_size] for arg in args] - - -def calculate_stability_score(masks: torch.Tensor, mask_threshold: float, threshold_offset: float) -> torch.Tensor: - """ - Computes the stability score for a batch of masks. - - The stability score is the IoU between the binary masks obtained by thresholding the predicted mask logits at high - and low values. - - Notes: - - One mask is always contained inside the other. - - Save memory by preventing unnecessary cast to torch.int64 - """ - intersections = (masks > (mask_threshold + threshold_offset)).sum(-1, dtype=torch.int16).sum(-1, dtype=torch.int32) - unions = (masks > (mask_threshold - threshold_offset)).sum(-1, dtype=torch.int16).sum(-1, dtype=torch.int32) - return intersections / unions - - -def build_point_grid(n_per_side: int) -> np.ndarray: - """Generate a 2D grid of evenly spaced points in the range [0,1]x[0,1].""" - offset = 1 / (2 * n_per_side) - points_one_side = np.linspace(offset, 1 - offset, n_per_side) - points_x = np.tile(points_one_side[None, :], (n_per_side, 1)) - points_y = np.tile(points_one_side[:, None], (1, n_per_side)) - return np.stack([points_x, points_y], axis=-1).reshape(-1, 2) - - -def build_all_layer_point_grids(n_per_side: int, n_layers: int, scale_per_layer: int) -> List[np.ndarray]: - """Generate point grids for all crop layers.""" - return [build_point_grid(int(n_per_side / (scale_per_layer**i))) for i in range(n_layers + 1)] - - -def generate_crop_boxes( - im_size: Tuple[int, ...], n_layers: int, overlap_ratio: float -) -> Tuple[List[List[int]], List[int]]: - """ - Generates a list of crop boxes of different sizes. - - Each layer has (2**i)**2 boxes for the ith layer. - """ - crop_boxes, layer_idxs = [], [] - im_h, im_w = im_size - short_side = min(im_h, im_w) - - # Original image - crop_boxes.append([0, 0, im_w, im_h]) - layer_idxs.append(0) - - def crop_len(orig_len, n_crops, overlap): - """Crops bounding boxes to the size of the input image.""" - return int(math.ceil((overlap * (n_crops - 1) + orig_len) / n_crops)) - - for i_layer in range(n_layers): - n_crops_per_side = 2 ** (i_layer + 1) - overlap = int(overlap_ratio * short_side * (2 / n_crops_per_side)) - - crop_w = crop_len(im_w, n_crops_per_side, overlap) - crop_h = crop_len(im_h, n_crops_per_side, overlap) - - crop_box_x0 = [int((crop_w - overlap) * i) for i in range(n_crops_per_side)] - crop_box_y0 = [int((crop_h - overlap) * i) for i in range(n_crops_per_side)] - - # Crops in XYWH format - for x0, y0 in product(crop_box_x0, crop_box_y0): - box = [x0, y0, min(x0 + crop_w, im_w), min(y0 + crop_h, im_h)] - crop_boxes.append(box) - layer_idxs.append(i_layer + 1) - - return crop_boxes, layer_idxs - - -def uncrop_boxes_xyxy(boxes: torch.Tensor, crop_box: List[int]) -> torch.Tensor: - """Uncrop bounding boxes by adding the crop box offset.""" - x0, y0, _, _ = crop_box - offset = torch.tensor([[x0, y0, x0, y0]], device=boxes.device) - # Check if boxes has a channel dimension - if len(boxes.shape) == 3: - offset = offset.unsqueeze(1) - return boxes + offset - - -def uncrop_points(points: torch.Tensor, crop_box: List[int]) -> torch.Tensor: - """Uncrop points by adding the crop box offset.""" - x0, y0, _, _ = crop_box - offset = torch.tensor([[x0, y0]], device=points.device) - # Check if points has a channel dimension - if len(points.shape) == 3: - offset = offset.unsqueeze(1) - return points + offset - - -def uncrop_masks(masks: torch.Tensor, crop_box: List[int], orig_h: int, orig_w: int) -> torch.Tensor: - """Uncrop masks by padding them to the original image size.""" - x0, y0, x1, y1 = crop_box - if x0 == 0 and y0 == 0 and x1 == orig_w and y1 == orig_h: - return masks - # Coordinate transform masks - pad_x, pad_y = orig_w - (x1 - x0), orig_h - (y1 - y0) - pad = (x0, pad_x - x0, y0, pad_y - y0) - return torch.nn.functional.pad(masks, pad, value=0) - - -def remove_small_regions(mask: np.ndarray, area_thresh: float, mode: str) -> Tuple[np.ndarray, bool]: - """Remove small disconnected regions or holes in a mask, returning the mask and a modification indicator.""" - import cv2 # type: ignore - - assert mode in {"holes", "islands"} - correct_holes = mode == "holes" - working_mask = (correct_holes ^ mask).astype(np.uint8) - n_labels, regions, stats, _ = cv2.connectedComponentsWithStats(working_mask, 8) - sizes = stats[:, -1][1:] # Row 0 is background label - small_regions = [i + 1 for i, s in enumerate(sizes) if s < area_thresh] - if not small_regions: - return mask, False - fill_labels = [0] + small_regions - if not correct_holes: - # If every region is below threshold, keep largest - fill_labels = [i for i in range(n_labels) if i not in fill_labels] or [int(np.argmax(sizes)) + 1] - mask = np.isin(regions, fill_labels) - return mask, True - - -def batched_mask_to_box(masks: torch.Tensor) -> torch.Tensor: - """ - Calculates boxes in XYXY format around masks. - - Return [0,0,0,0] for an empty mask. For input shape C1xC2x...xHxW, the output shape is C1xC2x...x4. - """ - # torch.max below raises an error on empty inputs, just skip in this case - if torch.numel(masks) == 0: - return torch.zeros(*masks.shape[:-2], 4, device=masks.device) - - # Normalize shape to CxHxW - shape = masks.shape - h, w = shape[-2:] - masks = masks.flatten(0, -3) if len(shape) > 2 else masks.unsqueeze(0) - # Get top and bottom edges - in_height, _ = torch.max(masks, dim=-1) - in_height_coords = in_height * torch.arange(h, device=in_height.device)[None, :] - bottom_edges, _ = torch.max(in_height_coords, dim=-1) - in_height_coords = in_height_coords + h * (~in_height) - top_edges, _ = torch.min(in_height_coords, dim=-1) - - # Get left and right edges - in_width, _ = torch.max(masks, dim=-2) - in_width_coords = in_width * torch.arange(w, device=in_width.device)[None, :] - right_edges, _ = torch.max(in_width_coords, dim=-1) - in_width_coords = in_width_coords + w * (~in_width) - left_edges, _ = torch.min(in_width_coords, dim=-1) - - # If the mask is empty the right edge will be to the left of the left edge. - # Replace these boxes with [0, 0, 0, 0] - empty_filter = (right_edges < left_edges) | (bottom_edges < top_edges) - out = torch.stack([left_edges, top_edges, right_edges, bottom_edges], dim=-1) - out = out * (~empty_filter).unsqueeze(-1) - - # Return to original shape - return out.reshape(*shape[:-2], 4) if len(shape) > 2 else out[0] diff --git a/ultralytics-main/ultralytics/models/sam/build.py b/ultralytics-main/ultralytics/models/sam/build.py deleted file mode 100644 index 266587e..0000000 --- a/ultralytics-main/ultralytics/models/sam/build.py +++ /dev/null @@ -1,160 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. - -# This source code is licensed under the license found in the -# LICENSE file in the root directory of this source tree. - -from functools import partial - -import torch - -from ultralytics.utils.downloads import attempt_download_asset -from .modules.decoders import MaskDecoder -from .modules.encoders import ImageEncoderViT, PromptEncoder -from .modules.sam import Sam -from .modules.tiny_encoder import TinyViT -from .modules.transformer import TwoWayTransformer - - -def build_sam_vit_h(checkpoint=None): - """Build and return a Segment Anything Model (SAM) h-size model.""" - return _build_sam( - encoder_embed_dim=1280, - encoder_depth=32, - encoder_num_heads=16, - encoder_global_attn_indexes=[7, 15, 23, 31], - checkpoint=checkpoint, - ) - - -def build_sam_vit_l(checkpoint=None): - """Build and return a Segment Anything Model (SAM) l-size model.""" - return _build_sam( - encoder_embed_dim=1024, - encoder_depth=24, - encoder_num_heads=16, - encoder_global_attn_indexes=[5, 11, 17, 23], - checkpoint=checkpoint, - ) - - -def build_sam_vit_b(checkpoint=None): - """Build and return a Segment Anything Model (SAM) b-size model.""" - return _build_sam( - encoder_embed_dim=768, - encoder_depth=12, - encoder_num_heads=12, - encoder_global_attn_indexes=[2, 5, 8, 11], - checkpoint=checkpoint, - ) - - -def build_mobile_sam(checkpoint=None): - """Build and return Mobile Segment Anything Model (Mobile-SAM).""" - return _build_sam( - encoder_embed_dim=[64, 128, 160, 320], - encoder_depth=[2, 2, 6, 2], - encoder_num_heads=[2, 4, 5, 10], - encoder_global_attn_indexes=None, - mobile_sam=True, - checkpoint=checkpoint, - ) - - -def _build_sam( - encoder_embed_dim, encoder_depth, encoder_num_heads, encoder_global_attn_indexes, checkpoint=None, mobile_sam=False -): - """Builds the selected SAM model architecture.""" - prompt_embed_dim = 256 - image_size = 1024 - vit_patch_size = 16 - image_embedding_size = image_size // vit_patch_size - image_encoder = ( - TinyViT( - img_size=1024, - in_chans=3, - num_classes=1000, - embed_dims=encoder_embed_dim, - depths=encoder_depth, - num_heads=encoder_num_heads, - window_sizes=[7, 7, 14, 7], - mlp_ratio=4.0, - drop_rate=0.0, - drop_path_rate=0.0, - use_checkpoint=False, - mbconv_expand_ratio=4.0, - local_conv_size=3, - layer_lr_decay=0.8, - ) - if mobile_sam - else ImageEncoderViT( - depth=encoder_depth, - embed_dim=encoder_embed_dim, - img_size=image_size, - mlp_ratio=4, - norm_layer=partial(torch.nn.LayerNorm, eps=1e-6), - num_heads=encoder_num_heads, - patch_size=vit_patch_size, - qkv_bias=True, - use_rel_pos=True, - global_attn_indexes=encoder_global_attn_indexes, - window_size=14, - out_chans=prompt_embed_dim, - ) - ) - sam = Sam( - image_encoder=image_encoder, - prompt_encoder=PromptEncoder( - embed_dim=prompt_embed_dim, - image_embedding_size=(image_embedding_size, image_embedding_size), - input_image_size=(image_size, image_size), - mask_in_chans=16, - ), - mask_decoder=MaskDecoder( - num_multimask_outputs=3, - transformer=TwoWayTransformer( - depth=2, - embedding_dim=prompt_embed_dim, - mlp_dim=2048, - num_heads=8, - ), - transformer_dim=prompt_embed_dim, - iou_head_depth=3, - iou_head_hidden_dim=256, - ), - pixel_mean=[123.675, 116.28, 103.53], - pixel_std=[58.395, 57.12, 57.375], - ) - if checkpoint is not None: - checkpoint = attempt_download_asset(checkpoint) - with open(checkpoint, "rb") as f: - state_dict = torch.load(f) - sam.load_state_dict(state_dict) - sam.eval() - # sam.load_state_dict(torch.load(checkpoint), strict=True) - # sam.eval() - return sam - - -sam_model_map = { - "sam_h.pt": build_sam_vit_h, - "sam_l.pt": build_sam_vit_l, - "sam_b.pt": build_sam_vit_b, - "mobile_sam.pt": build_mobile_sam, -} - - -def build_sam(ckpt="sam_b.pt"): - """Build a SAM model specified by ckpt.""" - model_builder = None - ckpt = str(ckpt) # to allow Path ckpt types - for k in sam_model_map.keys(): - if ckpt.endswith(k): - model_builder = sam_model_map.get(k) - - if not model_builder: - raise FileNotFoundError(f"{ckpt} is not a supported SAM model. Available models are: \n {sam_model_map.keys()}") - - return model_builder(ckpt) diff --git a/ultralytics-main/ultralytics/models/sam/model.py b/ultralytics-main/ultralytics/models/sam/model.py deleted file mode 100644 index cb12bc7..0000000 --- a/ultralytics-main/ultralytics/models/sam/model.py +++ /dev/null @@ -1,114 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -SAM model interface. - -This module provides an interface to the Segment Anything Model (SAM) from Ultralytics, designed for real-time image -segmentation tasks. The SAM model allows for promptable segmentation with unparalleled versatility in image analysis, -and has been trained on the SA-1B dataset. It features zero-shot performance capabilities, enabling it to adapt to new -image distributions and tasks without prior knowledge. - -Key Features: - - Promptable segmentation - - Real-time performance - - Zero-shot transfer capabilities - - Trained on SA-1B dataset -""" - -from pathlib import Path - -from ultralytics.engine.model import Model -from ultralytics.utils.torch_utils import model_info -from .build import build_sam -from .predict import Predictor - - -class SAM(Model): - """ - SAM (Segment Anything Model) interface class. - - SAM is designed for promptable real-time image segmentation. It can be used with a variety of prompts such as - bounding boxes, points, or labels. The model has capabilities for zero-shot performance and is trained on the SA-1B - dataset. - """ - - def __init__(self, model="sam_b.pt") -> None: - """ - Initializes the SAM model with a pre-trained model file. - - Args: - model (str): Path to the pre-trained SAM model file. File should have a .pt or .pth extension. - - Raises: - NotImplementedError: If the model file extension is not .pt or .pth. - """ - if model and Path(model).suffix not in (".pt", ".pth"): - raise NotImplementedError("SAM prediction requires pre-trained *.pt or *.pth model.") - super().__init__(model=model, task="segment") - - def _load(self, weights: str, task=None): - """ - Loads the specified weights into the SAM model. - - Args: - weights (str): Path to the weights file. - task (str, optional): Task name. Defaults to None. - """ - self.model = build_sam(weights) - - def predict(self, source, stream=False, bboxes=None, points=None, labels=None, **kwargs): - """ - Performs segmentation prediction on the given image or video source. - - Args: - source (str): Path to the image or video file, or a PIL.Image object, or a numpy.ndarray object. - stream (bool, optional): If True, enables real-time streaming. Defaults to False. - bboxes (list, optional): List of bounding box coordinates for prompted segmentation. Defaults to None. - points (list, optional): List of points for prompted segmentation. Defaults to None. - labels (list, optional): List of labels for prompted segmentation. Defaults to None. - - Returns: - (list): The model predictions. - """ - overrides = dict(conf=0.25, task="segment", mode="predict", imgsz=1024) - kwargs.update(overrides) - prompts = dict(bboxes=bboxes, points=points, labels=labels) - return super().predict(source, stream, prompts=prompts, **kwargs) - - def __call__(self, source=None, stream=False, bboxes=None, points=None, labels=None, **kwargs): - """ - Alias for the 'predict' method. - - Args: - source (str): Path to the image or video file, or a PIL.Image object, or a numpy.ndarray object. - stream (bool, optional): If True, enables real-time streaming. Defaults to False. - bboxes (list, optional): List of bounding box coordinates for prompted segmentation. Defaults to None. - points (list, optional): List of points for prompted segmentation. Defaults to None. - labels (list, optional): List of labels for prompted segmentation. Defaults to None. - - Returns: - (list): The model predictions. - """ - return self.predict(source, stream, bboxes, points, labels, **kwargs) - - def info(self, detailed=False, verbose=True): - """ - Logs information about the SAM model. - - Args: - detailed (bool, optional): If True, displays detailed information about the model. Defaults to False. - verbose (bool, optional): If True, displays information on the console. Defaults to True. - - Returns: - (tuple): A tuple containing the model's information. - """ - return model_info(self.model, detailed=detailed, verbose=verbose) - - @property - def task_map(self): - """ - Provides a mapping from the 'segment' task to its corresponding 'Predictor'. - - Returns: - (dict): A dictionary mapping the 'segment' task to its corresponding 'Predictor'. - """ - return {"segment": {"predictor": Predictor}} diff --git a/ultralytics-main/ultralytics/models/sam/modules/__init__.py b/ultralytics-main/ultralytics/models/sam/modules/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/models/sam/modules/decoders.py b/ultralytics-main/ultralytics/models/sam/modules/decoders.py deleted file mode 100644 index 073b1ad..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/decoders.py +++ /dev/null @@ -1,190 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from typing import List, Tuple, Type - -import torch -from torch import nn -from torch.nn import functional as F - -from ultralytics.nn.modules import LayerNorm2d - - -class MaskDecoder(nn.Module): - """ - Decoder module for generating masks and their associated quality scores, using a transformer architecture to predict - masks given image and prompt embeddings. - - Attributes: - transformer_dim (int): Channel dimension for the transformer module. - transformer (nn.Module): The transformer module used for mask prediction. - num_multimask_outputs (int): Number of masks to predict for disambiguating masks. - iou_token (nn.Embedding): Embedding for the IoU token. - num_mask_tokens (int): Number of mask tokens. - mask_tokens (nn.Embedding): Embedding for the mask tokens. - output_upscaling (nn.Sequential): Neural network sequence for upscaling the output. - output_hypernetworks_mlps (nn.ModuleList): Hypernetwork MLPs for generating masks. - iou_prediction_head (nn.Module): MLP for predicting mask quality. - """ - - def __init__( - self, - *, - transformer_dim: int, - transformer: nn.Module, - num_multimask_outputs: int = 3, - activation: Type[nn.Module] = nn.GELU, - iou_head_depth: int = 3, - iou_head_hidden_dim: int = 256, - ) -> None: - """ - Predicts masks given an image and prompt embeddings, using a transformer architecture. - - Args: - transformer_dim (int): the channel dimension of the transformer module - transformer (nn.Module): the transformer used to predict masks - num_multimask_outputs (int): the number of masks to predict when disambiguating masks - activation (nn.Module): the type of activation to use when upscaling masks - iou_head_depth (int): the depth of the MLP used to predict mask quality - iou_head_hidden_dim (int): the hidden dimension of the MLP used to predict mask quality - """ - super().__init__() - self.transformer_dim = transformer_dim - self.transformer = transformer - - self.num_multimask_outputs = num_multimask_outputs - - self.iou_token = nn.Embedding(1, transformer_dim) - self.num_mask_tokens = num_multimask_outputs + 1 - self.mask_tokens = nn.Embedding(self.num_mask_tokens, transformer_dim) - - self.output_upscaling = nn.Sequential( - nn.ConvTranspose2d(transformer_dim, transformer_dim // 4, kernel_size=2, stride=2), - LayerNorm2d(transformer_dim // 4), - activation(), - nn.ConvTranspose2d(transformer_dim // 4, transformer_dim // 8, kernel_size=2, stride=2), - activation(), - ) - self.output_hypernetworks_mlps = nn.ModuleList( - [MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3) for _ in range(self.num_mask_tokens)] - ) - - self.iou_prediction_head = MLP(transformer_dim, iou_head_hidden_dim, self.num_mask_tokens, iou_head_depth) - - def forward( - self, - image_embeddings: torch.Tensor, - image_pe: torch.Tensor, - sparse_prompt_embeddings: torch.Tensor, - dense_prompt_embeddings: torch.Tensor, - multimask_output: bool, - ) -> Tuple[torch.Tensor, torch.Tensor]: - """ - Predict masks given image and prompt embeddings. - - Args: - image_embeddings (torch.Tensor): the embeddings from the image encoder - image_pe (torch.Tensor): positional encoding with the shape of image_embeddings - sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes - dense_prompt_embeddings (torch.Tensor): the embeddings of the mask inputs - multimask_output (bool): Whether to return multiple masks or a single mask. - - Returns: - torch.Tensor: batched predicted masks - torch.Tensor: batched predictions of mask quality - """ - masks, iou_pred = self.predict_masks( - image_embeddings=image_embeddings, - image_pe=image_pe, - sparse_prompt_embeddings=sparse_prompt_embeddings, - dense_prompt_embeddings=dense_prompt_embeddings, - ) - - # Select the correct mask or masks for output - mask_slice = slice(1, None) if multimask_output else slice(0, 1) - masks = masks[:, mask_slice, :, :] - iou_pred = iou_pred[:, mask_slice] - - # Prepare output - return masks, iou_pred - - def predict_masks( - self, - image_embeddings: torch.Tensor, - image_pe: torch.Tensor, - sparse_prompt_embeddings: torch.Tensor, - dense_prompt_embeddings: torch.Tensor, - ) -> Tuple[torch.Tensor, torch.Tensor]: - """ - Predicts masks. - - See 'forward' for more details. - """ - # Concatenate output tokens - output_tokens = torch.cat([self.iou_token.weight, self.mask_tokens.weight], dim=0) - output_tokens = output_tokens.unsqueeze(0).expand(sparse_prompt_embeddings.shape[0], -1, -1) - tokens = torch.cat((output_tokens, sparse_prompt_embeddings), dim=1) - - # Expand per-image data in batch direction to be per-mask - src = torch.repeat_interleave(image_embeddings, tokens.shape[0], dim=0) - src = src + dense_prompt_embeddings - pos_src = torch.repeat_interleave(image_pe, tokens.shape[0], dim=0) - b, c, h, w = src.shape - - # Run the transformer - hs, src = self.transformer(src, pos_src, tokens) - iou_token_out = hs[:, 0, :] - mask_tokens_out = hs[:, 1 : (1 + self.num_mask_tokens), :] - - # Upscale mask embeddings and predict masks using the mask tokens - src = src.transpose(1, 2).view(b, c, h, w) - upscaled_embedding = self.output_upscaling(src) - hyper_in_list: List[torch.Tensor] = [ - self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]) for i in range(self.num_mask_tokens) - ] - hyper_in = torch.stack(hyper_in_list, dim=1) - b, c, h, w = upscaled_embedding.shape - masks = (hyper_in @ upscaled_embedding.view(b, c, h * w)).view(b, -1, h, w) - - # Generate mask quality predictions - iou_pred = self.iou_prediction_head(iou_token_out) - - return masks, iou_pred - - -class MLP(nn.Module): - """ - MLP (Multi-Layer Perceptron) model lightly adapted from - https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transformer/transformer_predictor.py - """ - - def __init__( - self, - input_dim: int, - hidden_dim: int, - output_dim: int, - num_layers: int, - sigmoid_output: bool = False, - ) -> None: - """ - Initializes the MLP (Multi-Layer Perceptron) model. - - Args: - input_dim (int): The dimensionality of the input features. - hidden_dim (int): The dimensionality of the hidden layers. - output_dim (int): The dimensionality of the output layer. - num_layers (int): The number of hidden layers. - sigmoid_output (bool, optional): Apply a sigmoid activation to the output layer. Defaults to False. - """ - super().__init__() - self.num_layers = num_layers - h = [hidden_dim] * (num_layers - 1) - self.layers = nn.ModuleList(nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])) - self.sigmoid_output = sigmoid_output - - def forward(self, x): - """Executes feedforward within the neural network module and applies activation.""" - for i, layer in enumerate(self.layers): - x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x) - if self.sigmoid_output: - x = torch.sigmoid(x) - return x diff --git a/ultralytics-main/ultralytics/models/sam/modules/encoders.py b/ultralytics-main/ultralytics/models/sam/modules/encoders.py deleted file mode 100644 index a51c347..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/encoders.py +++ /dev/null @@ -1,603 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from typing import Any, Optional, Tuple, Type - -import numpy as np -import torch -import torch.nn as nn -import torch.nn.functional as F - -from ultralytics.nn.modules import LayerNorm2d, MLPBlock - - -class ImageEncoderViT(nn.Module): - """ - An image encoder using Vision Transformer (ViT) architecture for encoding an image into a compact latent space. The - encoder takes an image, splits it into patches, and processes these patches through a series of transformer blocks. - The encoded patches are then processed through a neck to generate the final encoded representation. - - This class and its supporting functions below lightly adapted from the ViTDet backbone available at - https://github.com/facebookresearch/detectron2/blob/main/detectron2/modeling/backbone/vit.py. - - Attributes: - img_size (int): Dimension of input images, assumed to be square. - patch_embed (PatchEmbed): Module for patch embedding. - pos_embed (nn.Parameter, optional): Absolute positional embedding for patches. - blocks (nn.ModuleList): List of transformer blocks for processing patch embeddings. - neck (nn.Sequential): Neck module to further process the output. - """ - - def __init__( - self, - img_size: int = 1024, - patch_size: int = 16, - in_chans: int = 3, - embed_dim: int = 768, - depth: int = 12, - num_heads: int = 12, - mlp_ratio: float = 4.0, - out_chans: int = 256, - qkv_bias: bool = True, - norm_layer: Type[nn.Module] = nn.LayerNorm, - act_layer: Type[nn.Module] = nn.GELU, - use_abs_pos: bool = True, - use_rel_pos: bool = False, - rel_pos_zero_init: bool = True, - window_size: int = 0, - global_attn_indexes: Tuple[int, ...] = (), - ) -> None: - """ - Args: - img_size (int): Input image size. - patch_size (int): Patch size. - in_chans (int): Number of input image channels. - embed_dim (int): Patch embedding dimension. - depth (int): Depth of ViT. - num_heads (int): Number of attention heads in each ViT block. - mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. - qkv_bias (bool): If True, add a learnable bias to query, key, value. - norm_layer (nn.Module): Normalization layer. - act_layer (nn.Module): Activation layer. - use_abs_pos (bool): If True, use absolute positional embeddings. - use_rel_pos (bool): If True, add relative positional embeddings to the attention map. - rel_pos_zero_init (bool): If True, zero initialize relative positional parameters. - window_size (int): Window size for window attention blocks. - global_attn_indexes (list): Indexes for blocks using global attention. - """ - super().__init__() - self.img_size = img_size - - self.patch_embed = PatchEmbed( - kernel_size=(patch_size, patch_size), - stride=(patch_size, patch_size), - in_chans=in_chans, - embed_dim=embed_dim, - ) - - self.pos_embed: Optional[nn.Parameter] = None - if use_abs_pos: - # Initialize absolute positional embedding with pretrain image size. - self.pos_embed = nn.Parameter(torch.zeros(1, img_size // patch_size, img_size // patch_size, embed_dim)) - - self.blocks = nn.ModuleList() - for i in range(depth): - block = Block( - dim=embed_dim, - num_heads=num_heads, - mlp_ratio=mlp_ratio, - qkv_bias=qkv_bias, - norm_layer=norm_layer, - act_layer=act_layer, - use_rel_pos=use_rel_pos, - rel_pos_zero_init=rel_pos_zero_init, - window_size=window_size if i not in global_attn_indexes else 0, - input_size=(img_size // patch_size, img_size // patch_size), - ) - self.blocks.append(block) - - self.neck = nn.Sequential( - nn.Conv2d( - embed_dim, - out_chans, - kernel_size=1, - bias=False, - ), - LayerNorm2d(out_chans), - nn.Conv2d( - out_chans, - out_chans, - kernel_size=3, - padding=1, - bias=False, - ), - LayerNorm2d(out_chans), - ) - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Processes input through patch embedding, applies positional embedding if present, and passes through blocks - and neck. - """ - x = self.patch_embed(x) - if self.pos_embed is not None: - x = x + self.pos_embed - for blk in self.blocks: - x = blk(x) - return self.neck(x.permute(0, 3, 1, 2)) - - -class PromptEncoder(nn.Module): - """ - Encodes different types of prompts, including points, boxes, and masks, for input to SAM's mask decoder. The encoder - produces both sparse and dense embeddings for the input prompts. - - Attributes: - embed_dim (int): Dimension of the embeddings. - input_image_size (Tuple[int, int]): Size of the input image as (H, W). - image_embedding_size (Tuple[int, int]): Spatial size of the image embedding as (H, W). - pe_layer (PositionEmbeddingRandom): Module for random position embedding. - num_point_embeddings (int): Number of point embeddings for different types of points. - point_embeddings (nn.ModuleList): List of point embeddings. - not_a_point_embed (nn.Embedding): Embedding for points that are not a part of any label. - mask_input_size (Tuple[int, int]): Size of the input mask. - mask_downscaling (nn.Sequential): Neural network for downscaling the mask. - no_mask_embed (nn.Embedding): Embedding for cases where no mask is provided. - """ - - def __init__( - self, - embed_dim: int, - image_embedding_size: Tuple[int, int], - input_image_size: Tuple[int, int], - mask_in_chans: int, - activation: Type[nn.Module] = nn.GELU, - ) -> None: - """ - Encodes prompts for input to SAM's mask decoder. - - Args: - embed_dim (int): The prompts' embedding dimension - image_embedding_size (tuple(int, int)): The spatial size of the - image embedding, as (H, W). - input_image_size (int): The padded size of the image as input - to the image encoder, as (H, W). - mask_in_chans (int): The number of hidden channels used for - encoding input masks. - activation (nn.Module): The activation to use when encoding - input masks. - """ - super().__init__() - self.embed_dim = embed_dim - self.input_image_size = input_image_size - self.image_embedding_size = image_embedding_size - self.pe_layer = PositionEmbeddingRandom(embed_dim // 2) - - self.num_point_embeddings: int = 4 # pos/neg point + 2 box corners - point_embeddings = [nn.Embedding(1, embed_dim) for _ in range(self.num_point_embeddings)] - self.point_embeddings = nn.ModuleList(point_embeddings) - self.not_a_point_embed = nn.Embedding(1, embed_dim) - - self.mask_input_size = (4 * image_embedding_size[0], 4 * image_embedding_size[1]) - self.mask_downscaling = nn.Sequential( - nn.Conv2d(1, mask_in_chans // 4, kernel_size=2, stride=2), - LayerNorm2d(mask_in_chans // 4), - activation(), - nn.Conv2d(mask_in_chans // 4, mask_in_chans, kernel_size=2, stride=2), - LayerNorm2d(mask_in_chans), - activation(), - nn.Conv2d(mask_in_chans, embed_dim, kernel_size=1), - ) - self.no_mask_embed = nn.Embedding(1, embed_dim) - - def get_dense_pe(self) -> torch.Tensor: - """ - Returns the positional encoding used to encode point prompts, applied to a dense set of points the shape of the - image encoding. - - Returns: - torch.Tensor: Positional encoding with shape 1x(embed_dim)x(embedding_h)x(embedding_w) - """ - return self.pe_layer(self.image_embedding_size).unsqueeze(0) - - def _embed_points(self, points: torch.Tensor, labels: torch.Tensor, pad: bool) -> torch.Tensor: - """Embeds point prompts.""" - points = points + 0.5 # Shift to center of pixel - if pad: - padding_point = torch.zeros((points.shape[0], 1, 2), device=points.device) - padding_label = -torch.ones((labels.shape[0], 1), device=labels.device) - points = torch.cat([points, padding_point], dim=1) - labels = torch.cat([labels, padding_label], dim=1) - point_embedding = self.pe_layer.forward_with_coords(points, self.input_image_size) - point_embedding[labels == -1] = 0.0 - point_embedding[labels == -1] += self.not_a_point_embed.weight - point_embedding[labels == 0] += self.point_embeddings[0].weight - point_embedding[labels == 1] += self.point_embeddings[1].weight - return point_embedding - - def _embed_boxes(self, boxes: torch.Tensor) -> torch.Tensor: - """Embeds box prompts.""" - boxes = boxes + 0.5 # Shift to center of pixel - coords = boxes.reshape(-1, 2, 2) - corner_embedding = self.pe_layer.forward_with_coords(coords, self.input_image_size) - corner_embedding[:, 0, :] += self.point_embeddings[2].weight - corner_embedding[:, 1, :] += self.point_embeddings[3].weight - return corner_embedding - - def _embed_masks(self, masks: torch.Tensor) -> torch.Tensor: - """Embeds mask inputs.""" - return self.mask_downscaling(masks) - - def _get_batch_size( - self, - points: Optional[Tuple[torch.Tensor, torch.Tensor]], - boxes: Optional[torch.Tensor], - masks: Optional[torch.Tensor], - ) -> int: - """Gets the batch size of the output given the batch size of the input prompts.""" - if points is not None: - return points[0].shape[0] - elif boxes is not None: - return boxes.shape[0] - elif masks is not None: - return masks.shape[0] - else: - return 1 - - def _get_device(self) -> torch.device: - """Returns the device of the first point embedding's weight tensor.""" - return self.point_embeddings[0].weight.device - - def forward( - self, - points: Optional[Tuple[torch.Tensor, torch.Tensor]], - boxes: Optional[torch.Tensor], - masks: Optional[torch.Tensor], - ) -> Tuple[torch.Tensor, torch.Tensor]: - """ - Embeds different types of prompts, returning both sparse and dense embeddings. - - Args: - points (tuple(torch.Tensor, torch.Tensor), None): point coordinates and labels to embed. - boxes (torch.Tensor, None): boxes to embed - masks (torch.Tensor, None): masks to embed - - Returns: - torch.Tensor: sparse embeddings for the points and boxes, with shape BxNx(embed_dim), where N is determined - by the number of input points and boxes. - torch.Tensor: dense embeddings for the masks, in the shape Bx(embed_dim)x(embed_H)x(embed_W) - """ - bs = self._get_batch_size(points, boxes, masks) - sparse_embeddings = torch.empty((bs, 0, self.embed_dim), device=self._get_device()) - if points is not None: - coords, labels = points - point_embeddings = self._embed_points(coords, labels, pad=(boxes is None)) - sparse_embeddings = torch.cat([sparse_embeddings, point_embeddings], dim=1) - if boxes is not None: - box_embeddings = self._embed_boxes(boxes) - sparse_embeddings = torch.cat([sparse_embeddings, box_embeddings], dim=1) - - if masks is not None: - dense_embeddings = self._embed_masks(masks) - else: - dense_embeddings = self.no_mask_embed.weight.reshape(1, -1, 1, 1).expand( - bs, -1, self.image_embedding_size[0], self.image_embedding_size[1] - ) - - return sparse_embeddings, dense_embeddings - - -class PositionEmbeddingRandom(nn.Module): - """Positional encoding using random spatial frequencies.""" - - def __init__(self, num_pos_feats: int = 64, scale: Optional[float] = None) -> None: - """Initializes a position embedding using random spatial frequencies.""" - super().__init__() - if scale is None or scale <= 0.0: - scale = 1.0 - self.register_buffer("positional_encoding_gaussian_matrix", scale * torch.randn((2, num_pos_feats))) - - # Set non-deterministic for forward() error 'cumsum_cuda_kernel does not have a deterministic implementation' - torch.use_deterministic_algorithms(False) - torch.backends.cudnn.deterministic = False - - def _pe_encoding(self, coords: torch.Tensor) -> torch.Tensor: - """Positionally encode points that are normalized to [0,1].""" - # Assuming coords are in [0, 1]^2 square and have d_1 x ... x d_n x 2 shape - coords = 2 * coords - 1 - coords = coords @ self.positional_encoding_gaussian_matrix - coords = 2 * np.pi * coords - # Outputs d_1 x ... x d_n x C shape - return torch.cat([torch.sin(coords), torch.cos(coords)], dim=-1) - - def forward(self, size: Tuple[int, int]) -> torch.Tensor: - """Generate positional encoding for a grid of the specified size.""" - h, w = size - device: Any = self.positional_encoding_gaussian_matrix.device - grid = torch.ones((h, w), device=device, dtype=torch.float32) - y_embed = grid.cumsum(dim=0) - 0.5 - x_embed = grid.cumsum(dim=1) - 0.5 - y_embed = y_embed / h - x_embed = x_embed / w - - pe = self._pe_encoding(torch.stack([x_embed, y_embed], dim=-1)) - return pe.permute(2, 0, 1) # C x H x W - - def forward_with_coords(self, coords_input: torch.Tensor, image_size: Tuple[int, int]) -> torch.Tensor: - """Positionally encode points that are not normalized to [0,1].""" - coords = coords_input.clone() - coords[:, :, 0] = coords[:, :, 0] / image_size[1] - coords[:, :, 1] = coords[:, :, 1] / image_size[0] - return self._pe_encoding(coords.to(torch.float)) # B x N x C - - -class Block(nn.Module): - """Transformer blocks with support of window attention and residual propagation blocks.""" - - def __init__( - self, - dim: int, - num_heads: int, - mlp_ratio: float = 4.0, - qkv_bias: bool = True, - norm_layer: Type[nn.Module] = nn.LayerNorm, - act_layer: Type[nn.Module] = nn.GELU, - use_rel_pos: bool = False, - rel_pos_zero_init: bool = True, - window_size: int = 0, - input_size: Optional[Tuple[int, int]] = None, - ) -> None: - """ - Args: - dim (int): Number of input channels. - num_heads (int): Number of attention heads in each ViT block. - mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. - qkv_bias (bool): If True, add a learnable bias to query, key, value. - norm_layer (nn.Module): Normalization layer. - act_layer (nn.Module): Activation layer. - use_rel_pos (bool): If True, add relative positional embeddings to the attention map. - rel_pos_zero_init (bool): If True, zero initialize relative positional parameters. - window_size (int): Window size for window attention blocks. If it equals 0, then - use global attention. - input_size (tuple(int, int), None): Input resolution for calculating the relative - positional parameter size. - """ - super().__init__() - self.norm1 = norm_layer(dim) - self.attn = Attention( - dim, - num_heads=num_heads, - qkv_bias=qkv_bias, - use_rel_pos=use_rel_pos, - rel_pos_zero_init=rel_pos_zero_init, - input_size=input_size if window_size == 0 else (window_size, window_size), - ) - - self.norm2 = norm_layer(dim) - self.mlp = MLPBlock(embedding_dim=dim, mlp_dim=int(dim * mlp_ratio), act=act_layer) - - self.window_size = window_size - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Executes a forward pass through the transformer block with window attention and non-overlapping windows.""" - shortcut = x - x = self.norm1(x) - # Window partition - if self.window_size > 0: - H, W = x.shape[1], x.shape[2] - x, pad_hw = window_partition(x, self.window_size) - - x = self.attn(x) - # Reverse window partition - if self.window_size > 0: - x = window_unpartition(x, self.window_size, pad_hw, (H, W)) - - x = shortcut + x - return x + self.mlp(self.norm2(x)) - - -class Attention(nn.Module): - """Multi-head Attention block with relative position embeddings.""" - - def __init__( - self, - dim: int, - num_heads: int = 8, - qkv_bias: bool = True, - use_rel_pos: bool = False, - rel_pos_zero_init: bool = True, - input_size: Optional[Tuple[int, int]] = None, - ) -> None: - """ - Initialize Attention module. - - Args: - dim (int): Number of input channels. - num_heads (int): Number of attention heads. - qkv_bias (bool): If True, add a learnable bias to query, key, value. - rel_pos_zero_init (bool): If True, zero initialize relative positional parameters. - input_size (tuple(int, int), None): Input resolution for calculating the relative - positional parameter size. - """ - super().__init__() - self.num_heads = num_heads - head_dim = dim // num_heads - self.scale = head_dim**-0.5 - - self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias) - self.proj = nn.Linear(dim, dim) - - self.use_rel_pos = use_rel_pos - if self.use_rel_pos: - assert input_size is not None, "Input size must be provided if using relative positional encoding." - # Initialize relative positional embeddings - self.rel_pos_h = nn.Parameter(torch.zeros(2 * input_size[0] - 1, head_dim)) - self.rel_pos_w = nn.Parameter(torch.zeros(2 * input_size[1] - 1, head_dim)) - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Applies the forward operation including attention, normalization, MLP, and indexing within window limits.""" - B, H, W, _ = x.shape - # qkv with shape (3, B, nHead, H * W, C) - qkv = self.qkv(x).reshape(B, H * W, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) - # q, k, v with shape (B * nHead, H * W, C) - q, k, v = qkv.reshape(3, B * self.num_heads, H * W, -1).unbind(0) - - attn = (q * self.scale) @ k.transpose(-2, -1) - - if self.use_rel_pos: - attn = add_decomposed_rel_pos(attn, q, self.rel_pos_h, self.rel_pos_w, (H, W), (H, W)) - - attn = attn.softmax(dim=-1) - x = (attn @ v).view(B, self.num_heads, H, W, -1).permute(0, 2, 3, 1, 4).reshape(B, H, W, -1) - return self.proj(x) - - -def window_partition(x: torch.Tensor, window_size: int) -> Tuple[torch.Tensor, Tuple[int, int]]: - """ - Partition into non-overlapping windows with padding if needed. - Args: - x (tensor): input tokens with [B, H, W, C]. - window_size (int): window size. - - Returns: - windows: windows after partition with [B * num_windows, window_size, window_size, C]. - (Hp, Wp): padded height and width before partition - """ - B, H, W, C = x.shape - - pad_h = (window_size - H % window_size) % window_size - pad_w = (window_size - W % window_size) % window_size - if pad_h > 0 or pad_w > 0: - x = F.pad(x, (0, 0, 0, pad_w, 0, pad_h)) - Hp, Wp = H + pad_h, W + pad_w - - x = x.view(B, Hp // window_size, window_size, Wp // window_size, window_size, C) - windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C) - return windows, (Hp, Wp) - - -def window_unpartition( - windows: torch.Tensor, window_size: int, pad_hw: Tuple[int, int], hw: Tuple[int, int] -) -> torch.Tensor: - """ - Window unpartition into original sequences and removing padding. - - Args: - windows (tensor): input tokens with [B * num_windows, window_size, window_size, C]. - window_size (int): window size. - pad_hw (Tuple): padded height and width (Hp, Wp). - hw (Tuple): original height and width (H, W) before padding. - - Returns: - x: unpartitioned sequences with [B, H, W, C]. - """ - Hp, Wp = pad_hw - H, W = hw - B = windows.shape[0] // (Hp * Wp // window_size // window_size) - x = windows.view(B, Hp // window_size, Wp // window_size, window_size, window_size, -1) - x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, Hp, Wp, -1) - - if Hp > H or Wp > W: - x = x[:, :H, :W, :].contiguous() - return x - - -def get_rel_pos(q_size: int, k_size: int, rel_pos: torch.Tensor) -> torch.Tensor: - """ - Get relative positional embeddings according to the relative positions of query and key sizes. - - Args: - q_size (int): size of query q. - k_size (int): size of key k. - rel_pos (Tensor): relative position embeddings (L, C). - - Returns: - Extracted positional embeddings according to relative positions. - """ - max_rel_dist = int(2 * max(q_size, k_size) - 1) - # Interpolate rel pos if needed. - if rel_pos.shape[0] != max_rel_dist: - # Interpolate rel pos. - rel_pos_resized = F.interpolate( - rel_pos.reshape(1, rel_pos.shape[0], -1).permute(0, 2, 1), - size=max_rel_dist, - mode="linear", - ) - rel_pos_resized = rel_pos_resized.reshape(-1, max_rel_dist).permute(1, 0) - else: - rel_pos_resized = rel_pos - - # Scale the coords with short length if shapes for q and k are different. - q_coords = torch.arange(q_size)[:, None] * max(k_size / q_size, 1.0) - k_coords = torch.arange(k_size)[None, :] * max(q_size / k_size, 1.0) - relative_coords = (q_coords - k_coords) + (k_size - 1) * max(q_size / k_size, 1.0) - - return rel_pos_resized[relative_coords.long()] - - -def add_decomposed_rel_pos( - attn: torch.Tensor, - q: torch.Tensor, - rel_pos_h: torch.Tensor, - rel_pos_w: torch.Tensor, - q_size: Tuple[int, int], - k_size: Tuple[int, int], -) -> torch.Tensor: - """ - Calculate decomposed Relative Positional Embeddings from mvitv2 paper at - https://github.com/facebookresearch/mvit/blob/main/mvit/models/attention.py. - - Args: - attn (Tensor): attention map. - q (Tensor): query q in the attention layer with shape (B, q_h * q_w, C). - rel_pos_h (Tensor): relative position embeddings (Lh, C) for height axis. - rel_pos_w (Tensor): relative position embeddings (Lw, C) for width axis. - q_size (Tuple): spatial sequence size of query q with (q_h, q_w). - k_size (Tuple): spatial sequence size of key k with (k_h, k_w). - - Returns: - attn (Tensor): attention map with added relative positional embeddings. - """ - q_h, q_w = q_size - k_h, k_w = k_size - Rh = get_rel_pos(q_h, k_h, rel_pos_h) - Rw = get_rel_pos(q_w, k_w, rel_pos_w) - - B, _, dim = q.shape - r_q = q.reshape(B, q_h, q_w, dim) - rel_h = torch.einsum("bhwc,hkc->bhwk", r_q, Rh) - rel_w = torch.einsum("bhwc,wkc->bhwk", r_q, Rw) - - attn = (attn.view(B, q_h, q_w, k_h, k_w) + rel_h[:, :, :, :, None] + rel_w[:, :, :, None, :]).view( - B, q_h * q_w, k_h * k_w - ) - - return attn - - -class PatchEmbed(nn.Module): - """Image to Patch Embedding.""" - - def __init__( - self, - kernel_size: Tuple[int, int] = (16, 16), - stride: Tuple[int, int] = (16, 16), - padding: Tuple[int, int] = (0, 0), - in_chans: int = 3, - embed_dim: int = 768, - ) -> None: - """ - Initialize PatchEmbed module. - - Args: - kernel_size (Tuple): kernel size of the projection layer. - stride (Tuple): stride of the projection layer. - padding (Tuple): padding size of the projection layer. - in_chans (int): Number of input image channels. - embed_dim (int): Patch embedding dimension. - """ - super().__init__() - - self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=kernel_size, stride=stride, padding=padding) - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Computes patch embedding by applying convolution and transposing resulting tensor.""" - return self.proj(x).permute(0, 2, 3, 1) # B C H W -> B H W C diff --git a/ultralytics-main/ultralytics/models/sam/modules/sam.py b/ultralytics-main/ultralytics/models/sam/modules/sam.py deleted file mode 100644 index 95d9bbe..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/sam.py +++ /dev/null @@ -1,65 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. - -# This source code is licensed under the license found in the -# LICENSE file in the root directory of this source tree. - -from typing import List - -import torch -from torch import nn - -from .decoders import MaskDecoder -from .encoders import ImageEncoderViT, PromptEncoder - - -class Sam(nn.Module): - """ - Sam (Segment Anything Model) is designed for object segmentation tasks. It uses image encoders to generate image - embeddings, and prompt encoders to encode various types of input prompts. These embeddings are then used by the mask - decoder to predict object masks. - - Attributes: - mask_threshold (float): Threshold value for mask prediction. - image_format (str): Format of the input image, default is 'RGB'. - image_encoder (ImageEncoderViT): The backbone used to encode the image into embeddings. - prompt_encoder (PromptEncoder): Encodes various types of input prompts. - mask_decoder (MaskDecoder): Predicts object masks from the image and prompt embeddings. - pixel_mean (List[float]): Mean pixel values for image normalization. - pixel_std (List[float]): Standard deviation values for image normalization. - """ - - mask_threshold: float = 0.0 - image_format: str = "RGB" - - def __init__( - self, - image_encoder: ImageEncoderViT, - prompt_encoder: PromptEncoder, - mask_decoder: MaskDecoder, - pixel_mean: List[float] = (123.675, 116.28, 103.53), - pixel_std: List[float] = (58.395, 57.12, 57.375), - ) -> None: - """ - Initialize the Sam class to predict object masks from an image and input prompts. - - Note: - All forward() operations moved to SAMPredictor. - - Args: - image_encoder (ImageEncoderViT): The backbone used to encode the image into image embeddings. - prompt_encoder (PromptEncoder): Encodes various types of input prompts. - mask_decoder (MaskDecoder): Predicts masks from the image embeddings and encoded prompts. - pixel_mean (List[float], optional): Mean values for normalizing pixels in the input image. Defaults to - (123.675, 116.28, 103.53). - pixel_std (List[float], optional): Std values for normalizing pixels in the input image. Defaults to - (58.395, 57.12, 57.375). - """ - super().__init__() - self.image_encoder = image_encoder - self.prompt_encoder = prompt_encoder - self.mask_decoder = mask_decoder - self.register_buffer("pixel_mean", torch.Tensor(pixel_mean).view(-1, 1, 1), False) - self.register_buffer("pixel_std", torch.Tensor(pixel_std).view(-1, 1, 1), False) diff --git a/ultralytics-main/ultralytics/models/sam/modules/tiny_encoder.py b/ultralytics-main/ultralytics/models/sam/modules/tiny_encoder.py deleted file mode 100644 index 98f5ac0..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/tiny_encoder.py +++ /dev/null @@ -1,742 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -# -------------------------------------------------------- -# TinyViT Model Architecture -# Copyright (c) 2022 Microsoft -# Adapted from LeViT and Swin Transformer -# LeViT: (https://github.com/facebookresearch/levit) -# Swin: (https://github.com/microsoft/swin-transformer) -# Build the TinyViT Model -# -------------------------------------------------------- - -import itertools -from typing import Tuple - -import torch -import torch.nn as nn -import torch.nn.functional as F -import torch.utils.checkpoint as checkpoint - -from ultralytics.utils.instance import to_2tuple - - -class Conv2d_BN(torch.nn.Sequential): - """A sequential container that performs 2D convolution followed by batch normalization.""" - - def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1, groups=1, bn_weight_init=1): - """Initializes the MBConv model with given input channels, output channels, expansion ratio, activation, and - drop path. - """ - super().__init__() - self.add_module("c", torch.nn.Conv2d(a, b, ks, stride, pad, dilation, groups, bias=False)) - bn = torch.nn.BatchNorm2d(b) - torch.nn.init.constant_(bn.weight, bn_weight_init) - torch.nn.init.constant_(bn.bias, 0) - self.add_module("bn", bn) - - -class PatchEmbed(nn.Module): - """Embeds images into patches and projects them into a specified embedding dimension.""" - - def __init__(self, in_chans, embed_dim, resolution, activation): - """Initialize the PatchMerging class with specified input, output dimensions, resolution and activation - function. - """ - super().__init__() - img_size: Tuple[int, int] = to_2tuple(resolution) - self.patches_resolution = (img_size[0] // 4, img_size[1] // 4) - self.num_patches = self.patches_resolution[0] * self.patches_resolution[1] - self.in_chans = in_chans - self.embed_dim = embed_dim - n = embed_dim - self.seq = nn.Sequential( - Conv2d_BN(in_chans, n // 2, 3, 2, 1), - activation(), - Conv2d_BN(n // 2, n, 3, 2, 1), - ) - - def forward(self, x): - """Runs input tensor 'x' through the PatchMerging model's sequence of operations.""" - return self.seq(x) - - -class MBConv(nn.Module): - """Mobile Inverted Bottleneck Conv (MBConv) layer, part of the EfficientNet architecture.""" - - def __init__(self, in_chans, out_chans, expand_ratio, activation, drop_path): - """Initializes a convolutional layer with specified dimensions, input resolution, depth, and activation - function. - """ - super().__init__() - self.in_chans = in_chans - self.hidden_chans = int(in_chans * expand_ratio) - self.out_chans = out_chans - - self.conv1 = Conv2d_BN(in_chans, self.hidden_chans, ks=1) - self.act1 = activation() - - self.conv2 = Conv2d_BN(self.hidden_chans, self.hidden_chans, ks=3, stride=1, pad=1, groups=self.hidden_chans) - self.act2 = activation() - - self.conv3 = Conv2d_BN(self.hidden_chans, out_chans, ks=1, bn_weight_init=0.0) - self.act3 = activation() - - # NOTE: `DropPath` is needed only for training. - # self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity() - self.drop_path = nn.Identity() - - def forward(self, x): - """Implements the forward pass for the model architecture.""" - shortcut = x - x = self.conv1(x) - x = self.act1(x) - x = self.conv2(x) - x = self.act2(x) - x = self.conv3(x) - x = self.drop_path(x) - x += shortcut - return self.act3(x) - - -class PatchMerging(nn.Module): - """Merges neighboring patches in the feature map and projects to a new dimension.""" - - def __init__(self, input_resolution, dim, out_dim, activation): - """Initializes the ConvLayer with specific dimension, input resolution, depth, activation, drop path, and other - optional parameters. - """ - super().__init__() - - self.input_resolution = input_resolution - self.dim = dim - self.out_dim = out_dim - self.act = activation() - self.conv1 = Conv2d_BN(dim, out_dim, 1, 1, 0) - stride_c = 1 if out_dim in [320, 448, 576] else 2 - self.conv2 = Conv2d_BN(out_dim, out_dim, 3, stride_c, 1, groups=out_dim) - self.conv3 = Conv2d_BN(out_dim, out_dim, 1, 1, 0) - - def forward(self, x): - """Applies forward pass on the input utilizing convolution and activation layers, and returns the result.""" - if x.ndim == 3: - H, W = self.input_resolution - B = len(x) - # (B, C, H, W) - x = x.view(B, H, W, -1).permute(0, 3, 1, 2) - - x = self.conv1(x) - x = self.act(x) - - x = self.conv2(x) - x = self.act(x) - x = self.conv3(x) - return x.flatten(2).transpose(1, 2) - - -class ConvLayer(nn.Module): - """ - Convolutional Layer featuring multiple MobileNetV3-style inverted bottleneck convolutions (MBConv). - - Optionally applies downsample operations to the output, and provides support for gradient checkpointing. - """ - - def __init__( - self, - dim, - input_resolution, - depth, - activation, - drop_path=0.0, - downsample=None, - use_checkpoint=False, - out_dim=None, - conv_expand_ratio=4.0, - ): - """ - Initializes the ConvLayer with the given dimensions and settings. - - Args: - dim (int): The dimensionality of the input and output. - input_resolution (Tuple[int, int]): The resolution of the input image. - depth (int): The number of MBConv layers in the block. - activation (Callable): Activation function applied after each convolution. - drop_path (Union[float, List[float]]): Drop path rate. Single float or a list of floats for each MBConv. - downsample (Optional[Callable]): Function for downsampling the output. None to skip downsampling. - use_checkpoint (bool): Whether to use gradient checkpointing to save memory. - out_dim (Optional[int]): The dimensionality of the output. None means it will be the same as `dim`. - conv_expand_ratio (float): Expansion ratio for the MBConv layers. - """ - super().__init__() - self.dim = dim - self.input_resolution = input_resolution - self.depth = depth - self.use_checkpoint = use_checkpoint - - # Build blocks - self.blocks = nn.ModuleList( - [ - MBConv( - dim, - dim, - conv_expand_ratio, - activation, - drop_path[i] if isinstance(drop_path, list) else drop_path, - ) - for i in range(depth) - ] - ) - - # Patch merging layer - self.downsample = ( - None - if downsample is None - else downsample(input_resolution, dim=dim, out_dim=out_dim, activation=activation) - ) - - def forward(self, x): - """Processes the input through a series of convolutional layers and returns the activated output.""" - for blk in self.blocks: - x = checkpoint.checkpoint(blk, x) if self.use_checkpoint else blk(x) - return x if self.downsample is None else self.downsample(x) - - -class Mlp(nn.Module): - """ - Multi-layer Perceptron (MLP) for transformer architectures. - - This layer takes an input with in_features, applies layer normalization and two fully-connected layers. - """ - - def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.0): - """Initializes Attention module with the given parameters including dimension, key_dim, number of heads, etc.""" - super().__init__() - out_features = out_features or in_features - hidden_features = hidden_features or in_features - self.norm = nn.LayerNorm(in_features) - self.fc1 = nn.Linear(in_features, hidden_features) - self.fc2 = nn.Linear(hidden_features, out_features) - self.act = act_layer() - self.drop = nn.Dropout(drop) - - def forward(self, x): - """Applies operations on input x and returns modified x, runs downsample if not None.""" - x = self.norm(x) - x = self.fc1(x) - x = self.act(x) - x = self.drop(x) - x = self.fc2(x) - return self.drop(x) - - -class Attention(torch.nn.Module): - """ - Multi-head attention module with support for spatial awareness, applying attention biases based on spatial - resolution. Implements trainable attention biases for each unique offset between spatial positions in the resolution - grid. - - Attributes: - ab (Tensor, optional): Cached attention biases for inference, deleted during training. - """ - - def __init__( - self, - dim, - key_dim, - num_heads=8, - attn_ratio=4, - resolution=(14, 14), - ): - """ - Initializes the Attention module. - - Args: - dim (int): The dimensionality of the input and output. - key_dim (int): The dimensionality of the keys and queries. - num_heads (int, optional): Number of attention heads. Default is 8. - attn_ratio (float, optional): Attention ratio, affecting the dimensions of the value vectors. Default is 4. - resolution (Tuple[int, int], optional): Spatial resolution of the input feature map. Default is (14, 14). - - Raises: - AssertionError: If `resolution` is not a tuple of length 2. - """ - super().__init__() - - assert isinstance(resolution, tuple) and len(resolution) == 2 - self.num_heads = num_heads - self.scale = key_dim**-0.5 - self.key_dim = key_dim - self.nh_kd = nh_kd = key_dim * num_heads - self.d = int(attn_ratio * key_dim) - self.dh = int(attn_ratio * key_dim) * num_heads - self.attn_ratio = attn_ratio - h = self.dh + nh_kd * 2 - - self.norm = nn.LayerNorm(dim) - self.qkv = nn.Linear(dim, h) - self.proj = nn.Linear(self.dh, dim) - - points = list(itertools.product(range(resolution[0]), range(resolution[1]))) - N = len(points) - attention_offsets = {} - idxs = [] - for p1 in points: - for p2 in points: - offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1])) - if offset not in attention_offsets: - attention_offsets[offset] = len(attention_offsets) - idxs.append(attention_offsets[offset]) - self.attention_biases = torch.nn.Parameter(torch.zeros(num_heads, len(attention_offsets))) - self.register_buffer("attention_bias_idxs", torch.LongTensor(idxs).view(N, N), persistent=False) - - @torch.no_grad() - def train(self, mode=True): - """Sets the module in training mode and handles attribute 'ab' based on the mode.""" - super().train(mode) - if mode and hasattr(self, "ab"): - del self.ab - else: - self.ab = self.attention_biases[:, self.attention_bias_idxs] - - def forward(self, x): # x - """Performs forward pass over the input tensor 'x' by applying normalization and querying keys/values.""" - B, N, _ = x.shape # B, N, C - - # Normalization - x = self.norm(x) - - qkv = self.qkv(x) - # (B, N, num_heads, d) - q, k, v = qkv.view(B, N, self.num_heads, -1).split([self.key_dim, self.key_dim, self.d], dim=3) - # (B, num_heads, N, d) - q = q.permute(0, 2, 1, 3) - k = k.permute(0, 2, 1, 3) - v = v.permute(0, 2, 1, 3) - self.ab = self.ab.to(self.attention_biases.device) - - attn = (q @ k.transpose(-2, -1)) * self.scale + ( - self.attention_biases[:, self.attention_bias_idxs] if self.training else self.ab - ) - attn = attn.softmax(dim=-1) - x = (attn @ v).transpose(1, 2).reshape(B, N, self.dh) - return self.proj(x) - - -class TinyViTBlock(nn.Module): - """TinyViT Block that applies self-attention and a local convolution to the input.""" - - def __init__( - self, - dim, - input_resolution, - num_heads, - window_size=7, - mlp_ratio=4.0, - drop=0.0, - drop_path=0.0, - local_conv_size=3, - activation=nn.GELU, - ): - """ - Initializes the TinyViTBlock. - - Args: - dim (int): The dimensionality of the input and output. - input_resolution (Tuple[int, int]): Spatial resolution of the input feature map. - num_heads (int): Number of attention heads. - window_size (int, optional): Window size for attention. Default is 7. - mlp_ratio (float, optional): Ratio of mlp hidden dim to embedding dim. Default is 4. - drop (float, optional): Dropout rate. Default is 0. - drop_path (float, optional): Stochastic depth rate. Default is 0. - local_conv_size (int, optional): The kernel size of the local convolution. Default is 3. - activation (torch.nn, optional): Activation function for MLP. Default is nn.GELU. - - Raises: - AssertionError: If `window_size` is not greater than 0. - AssertionError: If `dim` is not divisible by `num_heads`. - """ - super().__init__() - self.dim = dim - self.input_resolution = input_resolution - self.num_heads = num_heads - assert window_size > 0, "window_size must be greater than 0" - self.window_size = window_size - self.mlp_ratio = mlp_ratio - - # NOTE: `DropPath` is needed only for training. - # self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity() - self.drop_path = nn.Identity() - - assert dim % num_heads == 0, "dim must be divisible by num_heads" - head_dim = dim // num_heads - - window_resolution = (window_size, window_size) - self.attn = Attention(dim, head_dim, num_heads, attn_ratio=1, resolution=window_resolution) - - mlp_hidden_dim = int(dim * mlp_ratio) - mlp_activation = activation - self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=mlp_activation, drop=drop) - - pad = local_conv_size // 2 - self.local_conv = Conv2d_BN(dim, dim, ks=local_conv_size, stride=1, pad=pad, groups=dim) - - def forward(self, x): - """Applies attention-based transformation or padding to input 'x' before passing it through a local - convolution. - """ - H, W = self.input_resolution - B, L, C = x.shape - assert L == H * W, "input feature has wrong size" - res_x = x - if H == self.window_size and W == self.window_size: - x = self.attn(x) - else: - x = x.view(B, H, W, C) - pad_b = (self.window_size - H % self.window_size) % self.window_size - pad_r = (self.window_size - W % self.window_size) % self.window_size - padding = pad_b > 0 or pad_r > 0 - - if padding: - x = F.pad(x, (0, 0, 0, pad_r, 0, pad_b)) - - pH, pW = H + pad_b, W + pad_r - nH = pH // self.window_size - nW = pW // self.window_size - # Window partition - x = ( - x.view(B, nH, self.window_size, nW, self.window_size, C) - .transpose(2, 3) - .reshape(B * nH * nW, self.window_size * self.window_size, C) - ) - x = self.attn(x) - # Window reverse - x = x.view(B, nH, nW, self.window_size, self.window_size, C).transpose(2, 3).reshape(B, pH, pW, C) - - if padding: - x = x[:, :H, :W].contiguous() - - x = x.view(B, L, C) - - x = res_x + self.drop_path(x) - - x = x.transpose(1, 2).reshape(B, C, H, W) - x = self.local_conv(x) - x = x.view(B, C, L).transpose(1, 2) - - return x + self.drop_path(self.mlp(x)) - - def extra_repr(self) -> str: - """Returns a formatted string representing the TinyViTBlock's parameters: dimension, input resolution, number of - attentions heads, window size, and MLP ratio. - """ - return ( - f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " - f"window_size={self.window_size}, mlp_ratio={self.mlp_ratio}" - ) - - -class BasicLayer(nn.Module): - """A basic TinyViT layer for one stage in a TinyViT architecture.""" - - def __init__( - self, - dim, - input_resolution, - depth, - num_heads, - window_size, - mlp_ratio=4.0, - drop=0.0, - drop_path=0.0, - downsample=None, - use_checkpoint=False, - local_conv_size=3, - activation=nn.GELU, - out_dim=None, - ): - """ - Initializes the BasicLayer. - - Args: - dim (int): The dimensionality of the input and output. - input_resolution (Tuple[int, int]): Spatial resolution of the input feature map. - depth (int): Number of TinyViT blocks. - num_heads (int): Number of attention heads. - window_size (int): Local window size. - mlp_ratio (float, optional): Ratio of mlp hidden dim to embedding dim. Default is 4. - drop (float, optional): Dropout rate. Default is 0. - drop_path (float | tuple[float], optional): Stochastic depth rate. Default is 0. - downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default is None. - use_checkpoint (bool, optional): Whether to use checkpointing to save memory. Default is False. - local_conv_size (int, optional): Kernel size of the local convolution. Default is 3. - activation (torch.nn, optional): Activation function for MLP. Default is nn.GELU. - out_dim (int | None, optional): The output dimension of the layer. Default is None. - - Raises: - ValueError: If `drop_path` is a list of float but its length doesn't match `depth`. - """ - super().__init__() - self.dim = dim - self.input_resolution = input_resolution - self.depth = depth - self.use_checkpoint = use_checkpoint - - # Build blocks - self.blocks = nn.ModuleList( - [ - TinyViTBlock( - dim=dim, - input_resolution=input_resolution, - num_heads=num_heads, - window_size=window_size, - mlp_ratio=mlp_ratio, - drop=drop, - drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path, - local_conv_size=local_conv_size, - activation=activation, - ) - for i in range(depth) - ] - ) - - # Patch merging layer - self.downsample = ( - None - if downsample is None - else downsample(input_resolution, dim=dim, out_dim=out_dim, activation=activation) - ) - - def forward(self, x): - """Performs forward propagation on the input tensor and returns a normalized tensor.""" - for blk in self.blocks: - x = checkpoint.checkpoint(blk, x) if self.use_checkpoint else blk(x) - return x if self.downsample is None else self.downsample(x) - - def extra_repr(self) -> str: - """Returns a string representation of the extra_repr function with the layer's parameters.""" - return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}" - - -class LayerNorm2d(nn.Module): - """A PyTorch implementation of Layer Normalization in 2D.""" - - def __init__(self, num_channels: int, eps: float = 1e-6) -> None: - """Initialize LayerNorm2d with the number of channels and an optional epsilon.""" - super().__init__() - self.weight = nn.Parameter(torch.ones(num_channels)) - self.bias = nn.Parameter(torch.zeros(num_channels)) - self.eps = eps - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Perform a forward pass, normalizing the input tensor.""" - u = x.mean(1, keepdim=True) - s = (x - u).pow(2).mean(1, keepdim=True) - x = (x - u) / torch.sqrt(s + self.eps) - return self.weight[:, None, None] * x + self.bias[:, None, None] - - -class TinyViT(nn.Module): - """ - The TinyViT architecture for vision tasks. - - Attributes: - img_size (int): Input image size. - in_chans (int): Number of input channels. - num_classes (int): Number of classification classes. - embed_dims (List[int]): List of embedding dimensions for each layer. - depths (List[int]): List of depths for each layer. - num_heads (List[int]): List of number of attention heads for each layer. - window_sizes (List[int]): List of window sizes for each layer. - mlp_ratio (float): Ratio of MLP hidden dimension to embedding dimension. - drop_rate (float): Dropout rate for drop layers. - drop_path_rate (float): Drop path rate for stochastic depth. - use_checkpoint (bool): Use checkpointing for efficient memory usage. - mbconv_expand_ratio (float): Expansion ratio for MBConv layer. - local_conv_size (int): Local convolution kernel size. - layer_lr_decay (float): Layer-wise learning rate decay. - - Note: - This implementation is generalized to accept a list of depths, attention heads, - embedding dimensions and window sizes, which allows you to create a - "stack" of TinyViT models of varying configurations. - """ - - def __init__( - self, - img_size=224, - in_chans=3, - num_classes=1000, - embed_dims=[96, 192, 384, 768], - depths=[2, 2, 6, 2], - num_heads=[3, 6, 12, 24], - window_sizes=[7, 7, 14, 7], - mlp_ratio=4.0, - drop_rate=0.0, - drop_path_rate=0.1, - use_checkpoint=False, - mbconv_expand_ratio=4.0, - local_conv_size=3, - layer_lr_decay=1.0, - ): - """ - Initializes the TinyViT model. - - Args: - img_size (int, optional): The input image size. Defaults to 224. - in_chans (int, optional): Number of input channels. Defaults to 3. - num_classes (int, optional): Number of classification classes. Defaults to 1000. - embed_dims (List[int], optional): List of embedding dimensions for each layer. Defaults to [96, 192, 384, 768]. - depths (List[int], optional): List of depths for each layer. Defaults to [2, 2, 6, 2]. - num_heads (List[int], optional): List of number of attention heads for each layer. Defaults to [3, 6, 12, 24]. - window_sizes (List[int], optional): List of window sizes for each layer. Defaults to [7, 7, 14, 7]. - mlp_ratio (float, optional): Ratio of MLP hidden dimension to embedding dimension. Defaults to 4. - drop_rate (float, optional): Dropout rate. Defaults to 0. - drop_path_rate (float, optional): Drop path rate for stochastic depth. Defaults to 0.1. - use_checkpoint (bool, optional): Whether to use checkpointing for efficient memory usage. Defaults to False. - mbconv_expand_ratio (float, optional): Expansion ratio for MBConv layer. Defaults to 4.0. - local_conv_size (int, optional): Local convolution kernel size. Defaults to 3. - layer_lr_decay (float, optional): Layer-wise learning rate decay. Defaults to 1.0. - """ - super().__init__() - self.img_size = img_size - self.num_classes = num_classes - self.depths = depths - self.num_layers = len(depths) - self.mlp_ratio = mlp_ratio - - activation = nn.GELU - - self.patch_embed = PatchEmbed( - in_chans=in_chans, embed_dim=embed_dims[0], resolution=img_size, activation=activation - ) - - patches_resolution = self.patch_embed.patches_resolution - self.patches_resolution = patches_resolution - - # Stochastic depth - dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule - - # Build layers - self.layers = nn.ModuleList() - for i_layer in range(self.num_layers): - kwargs = dict( - dim=embed_dims[i_layer], - input_resolution=( - patches_resolution[0] // (2 ** (i_layer - 1 if i_layer == 3 else i_layer)), - patches_resolution[1] // (2 ** (i_layer - 1 if i_layer == 3 else i_layer)), - ), - # input_resolution=(patches_resolution[0] // (2 ** i_layer), - # patches_resolution[1] // (2 ** i_layer)), - depth=depths[i_layer], - drop_path=dpr[sum(depths[:i_layer]) : sum(depths[: i_layer + 1])], - downsample=PatchMerging if (i_layer < self.num_layers - 1) else None, - use_checkpoint=use_checkpoint, - out_dim=embed_dims[min(i_layer + 1, len(embed_dims) - 1)], - activation=activation, - ) - if i_layer == 0: - layer = ConvLayer(conv_expand_ratio=mbconv_expand_ratio, **kwargs) - else: - layer = BasicLayer( - num_heads=num_heads[i_layer], - window_size=window_sizes[i_layer], - mlp_ratio=self.mlp_ratio, - drop=drop_rate, - local_conv_size=local_conv_size, - **kwargs, - ) - self.layers.append(layer) - - # Classifier head - self.norm_head = nn.LayerNorm(embed_dims[-1]) - self.head = nn.Linear(embed_dims[-1], num_classes) if num_classes > 0 else torch.nn.Identity() - - # Init weights - self.apply(self._init_weights) - self.set_layer_lr_decay(layer_lr_decay) - self.neck = nn.Sequential( - nn.Conv2d( - embed_dims[-1], - 256, - kernel_size=1, - bias=False, - ), - LayerNorm2d(256), - nn.Conv2d( - 256, - 256, - kernel_size=3, - padding=1, - bias=False, - ), - LayerNorm2d(256), - ) - - def set_layer_lr_decay(self, layer_lr_decay): - """Sets the learning rate decay for each layer in the TinyViT model.""" - decay_rate = layer_lr_decay - - # Layers -> blocks (depth) - depth = sum(self.depths) - lr_scales = [decay_rate ** (depth - i - 1) for i in range(depth)] - - def _set_lr_scale(m, scale): - """Sets the learning rate scale for each layer in the model based on the layer's depth.""" - for p in m.parameters(): - p.lr_scale = scale - - self.patch_embed.apply(lambda x: _set_lr_scale(x, lr_scales[0])) - i = 0 - for layer in self.layers: - for block in layer.blocks: - block.apply(lambda x: _set_lr_scale(x, lr_scales[i])) - i += 1 - if layer.downsample is not None: - layer.downsample.apply(lambda x: _set_lr_scale(x, lr_scales[i - 1])) - assert i == depth - for m in [self.norm_head, self.head]: - m.apply(lambda x: _set_lr_scale(x, lr_scales[-1])) - - for k, p in self.named_parameters(): - p.param_name = k - - def _check_lr_scale(m): - """Checks if the learning rate scale attribute is present in module's parameters.""" - for p in m.parameters(): - assert hasattr(p, "lr_scale"), p.param_name - - self.apply(_check_lr_scale) - - def _init_weights(self, m): - """Initializes weights for linear layers and layer normalization in the given module.""" - if isinstance(m, nn.Linear): - # NOTE: This initialization is needed only for training. - # trunc_normal_(m.weight, std=.02) - if m.bias is not None: - nn.init.constant_(m.bias, 0) - elif isinstance(m, nn.LayerNorm): - nn.init.constant_(m.bias, 0) - nn.init.constant_(m.weight, 1.0) - - @torch.jit.ignore - def no_weight_decay_keywords(self): - """Returns a dictionary of parameter names where weight decay should not be applied.""" - return {"attention_biases"} - - def forward_features(self, x): - """Runs the input through the model layers and returns the transformed output.""" - x = self.patch_embed(x) # x input is (N, C, H, W) - - x = self.layers[0](x) - start_i = 1 - - for i in range(start_i, len(self.layers)): - layer = self.layers[i] - x = layer(x) - B, _, C = x.shape - x = x.view(B, 64, 64, C) - x = x.permute(0, 3, 1, 2) - return self.neck(x) - - def forward(self, x): - """Executes a forward pass on the input tensor through the constructed model layers.""" - return self.forward_features(x) diff --git a/ultralytics-main/ultralytics/models/sam/modules/transformer.py b/ultralytics-main/ultralytics/models/sam/modules/transformer.py deleted file mode 100644 index 1ad0741..0000000 --- a/ultralytics-main/ultralytics/models/sam/modules/transformer.py +++ /dev/null @@ -1,274 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math -from typing import Tuple, Type - -import torch -from torch import Tensor, nn - -from ultralytics.nn.modules import MLPBlock - - -class TwoWayTransformer(nn.Module): - """ - A Two-Way Transformer module that enables the simultaneous attention to both image and query points. This class - serves as a specialized transformer decoder that attends to an input image using queries whose positional embedding - is supplied. This is particularly useful for tasks like object detection, image segmentation, and point cloud - processing. - - Attributes: - depth (int): The number of layers in the transformer. - embedding_dim (int): The channel dimension for the input embeddings. - num_heads (int): The number of heads for multihead attention. - mlp_dim (int): The internal channel dimension for the MLP block. - layers (nn.ModuleList): The list of TwoWayAttentionBlock layers that make up the transformer. - final_attn_token_to_image (Attention): The final attention layer applied from the queries to the image. - norm_final_attn (nn.LayerNorm): The layer normalization applied to the final queries. - """ - - def __init__( - self, - depth: int, - embedding_dim: int, - num_heads: int, - mlp_dim: int, - activation: Type[nn.Module] = nn.ReLU, - attention_downsample_rate: int = 2, - ) -> None: - """ - A transformer decoder that attends to an input image using queries whose positional embedding is supplied. - - Args: - depth (int): number of layers in the transformer - embedding_dim (int): the channel dimension for the input embeddings - num_heads (int): the number of heads for multihead attention. Must - divide embedding_dim - mlp_dim (int): the channel dimension internal to the MLP block - activation (nn.Module): the activation to use in the MLP block - """ - super().__init__() - self.depth = depth - self.embedding_dim = embedding_dim - self.num_heads = num_heads - self.mlp_dim = mlp_dim - self.layers = nn.ModuleList() - - for i in range(depth): - self.layers.append( - TwoWayAttentionBlock( - embedding_dim=embedding_dim, - num_heads=num_heads, - mlp_dim=mlp_dim, - activation=activation, - attention_downsample_rate=attention_downsample_rate, - skip_first_layer_pe=(i == 0), - ) - ) - - self.final_attn_token_to_image = Attention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate) - self.norm_final_attn = nn.LayerNorm(embedding_dim) - - def forward( - self, - image_embedding: Tensor, - image_pe: Tensor, - point_embedding: Tensor, - ) -> Tuple[Tensor, Tensor]: - """ - Args: - image_embedding (torch.Tensor): image to attend to. Should be shape B x embedding_dim x h x w for any h and w. - image_pe (torch.Tensor): the positional encoding to add to the image. Must have same shape as image_embedding. - point_embedding (torch.Tensor): the embedding to add to the query points. - Must have shape B x N_points x embedding_dim for any N_points. - - Returns: - (torch.Tensor): the processed point_embedding - (torch.Tensor): the processed image_embedding - """ - # BxCxHxW -> BxHWxC == B x N_image_tokens x C - bs, c, h, w = image_embedding.shape - image_embedding = image_embedding.flatten(2).permute(0, 2, 1) - image_pe = image_pe.flatten(2).permute(0, 2, 1) - - # Prepare queries - queries = point_embedding - keys = image_embedding - - # Apply transformer blocks and final layernorm - for layer in self.layers: - queries, keys = layer( - queries=queries, - keys=keys, - query_pe=point_embedding, - key_pe=image_pe, - ) - - # Apply the final attention layer from the points to the image - q = queries + point_embedding - k = keys + image_pe - attn_out = self.final_attn_token_to_image(q=q, k=k, v=keys) - queries = queries + attn_out - queries = self.norm_final_attn(queries) - - return queries, keys - - -class TwoWayAttentionBlock(nn.Module): - """ - An attention block that performs both self-attention and cross-attention in two directions: queries to keys and - keys to queries. This block consists of four main layers: (1) self-attention on sparse inputs, (2) cross-attention - of sparse inputs to dense inputs, (3) an MLP block on sparse inputs, and (4) cross-attention of dense inputs to - sparse inputs. - - Attributes: - self_attn (Attention): The self-attention layer for the queries. - norm1 (nn.LayerNorm): Layer normalization following the first attention block. - cross_attn_token_to_image (Attention): Cross-attention layer from queries to keys. - norm2 (nn.LayerNorm): Layer normalization following the second attention block. - mlp (MLPBlock): MLP block that transforms the query embeddings. - norm3 (nn.LayerNorm): Layer normalization following the MLP block. - norm4 (nn.LayerNorm): Layer normalization following the third attention block. - cross_attn_image_to_token (Attention): Cross-attention layer from keys to queries. - skip_first_layer_pe (bool): Whether to skip the positional encoding in the first layer. - """ - - def __init__( - self, - embedding_dim: int, - num_heads: int, - mlp_dim: int = 2048, - activation: Type[nn.Module] = nn.ReLU, - attention_downsample_rate: int = 2, - skip_first_layer_pe: bool = False, - ) -> None: - """ - A transformer block with four layers: (1) self-attention of sparse inputs, (2) cross attention of sparse - inputs to dense inputs, (3) mlp block on sparse inputs, and (4) cross attention of dense inputs to sparse - inputs. - - Args: - embedding_dim (int): the channel dimension of the embeddings - num_heads (int): the number of heads in the attention layers - mlp_dim (int): the hidden dimension of the mlp block - activation (nn.Module): the activation of the mlp block - skip_first_layer_pe (bool): skip the PE on the first layer - """ - super().__init__() - self.self_attn = Attention(embedding_dim, num_heads) - self.norm1 = nn.LayerNorm(embedding_dim) - - self.cross_attn_token_to_image = Attention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate) - self.norm2 = nn.LayerNorm(embedding_dim) - - self.mlp = MLPBlock(embedding_dim, mlp_dim, activation) - self.norm3 = nn.LayerNorm(embedding_dim) - - self.norm4 = nn.LayerNorm(embedding_dim) - self.cross_attn_image_to_token = Attention(embedding_dim, num_heads, downsample_rate=attention_downsample_rate) - - self.skip_first_layer_pe = skip_first_layer_pe - - def forward(self, queries: Tensor, keys: Tensor, query_pe: Tensor, key_pe: Tensor) -> Tuple[Tensor, Tensor]: - """Apply self-attention and cross-attention to queries and keys and return the processed embeddings.""" - - # Self attention block - if self.skip_first_layer_pe: - queries = self.self_attn(q=queries, k=queries, v=queries) - else: - q = queries + query_pe - attn_out = self.self_attn(q=q, k=q, v=queries) - queries = queries + attn_out - queries = self.norm1(queries) - - # Cross attention block, tokens attending to image embedding - q = queries + query_pe - k = keys + key_pe - attn_out = self.cross_attn_token_to_image(q=q, k=k, v=keys) - queries = queries + attn_out - queries = self.norm2(queries) - - # MLP block - mlp_out = self.mlp(queries) - queries = queries + mlp_out - queries = self.norm3(queries) - - # Cross attention block, image embedding attending to tokens - q = queries + query_pe - k = keys + key_pe - attn_out = self.cross_attn_image_to_token(q=k, k=q, v=queries) - keys = keys + attn_out - keys = self.norm4(keys) - - return queries, keys - - -class Attention(nn.Module): - """An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and - values. - """ - - def __init__( - self, - embedding_dim: int, - num_heads: int, - downsample_rate: int = 1, - ) -> None: - """ - Initializes the Attention model with the given dimensions and settings. - - Args: - embedding_dim (int): The dimensionality of the input embeddings. - num_heads (int): The number of attention heads. - downsample_rate (int, optional): The factor by which the internal dimensions are downsampled. Defaults to 1. - - Raises: - AssertionError: If 'num_heads' does not evenly divide the internal dimension (embedding_dim / downsample_rate). - """ - super().__init__() - self.embedding_dim = embedding_dim - self.internal_dim = embedding_dim // downsample_rate - self.num_heads = num_heads - assert self.internal_dim % num_heads == 0, "num_heads must divide embedding_dim." - - self.q_proj = nn.Linear(embedding_dim, self.internal_dim) - self.k_proj = nn.Linear(embedding_dim, self.internal_dim) - self.v_proj = nn.Linear(embedding_dim, self.internal_dim) - self.out_proj = nn.Linear(self.internal_dim, embedding_dim) - - @staticmethod - def _separate_heads(x: Tensor, num_heads: int) -> Tensor: - """Separate the input tensor into the specified number of attention heads.""" - b, n, c = x.shape - x = x.reshape(b, n, num_heads, c // num_heads) - return x.transpose(1, 2) # B x N_heads x N_tokens x C_per_head - - @staticmethod - def _recombine_heads(x: Tensor) -> Tensor: - """Recombine the separated attention heads into a single tensor.""" - b, n_heads, n_tokens, c_per_head = x.shape - x = x.transpose(1, 2) - return x.reshape(b, n_tokens, n_heads * c_per_head) # B x N_tokens x C - - def forward(self, q: Tensor, k: Tensor, v: Tensor) -> Tensor: - """Compute the attention output given the input query, key, and value tensors.""" - - # Input projections - q = self.q_proj(q) - k = self.k_proj(k) - v = self.v_proj(v) - - # Separate into heads - q = self._separate_heads(q, self.num_heads) - k = self._separate_heads(k, self.num_heads) - v = self._separate_heads(v, self.num_heads) - - # Attention - _, _, _, c_per_head = q.shape - attn = q @ k.permute(0, 1, 3, 2) # B x N_heads x N_tokens x N_tokens - attn = attn / math.sqrt(c_per_head) - attn = torch.softmax(attn, dim=-1) - - # Get output - out = attn @ v - out = self._recombine_heads(out) - return self.out_proj(out) diff --git a/ultralytics-main/ultralytics/models/sam/predict.py b/ultralytics-main/ultralytics/models/sam/predict.py deleted file mode 100644 index 63ca632..0000000 --- a/ultralytics-main/ultralytics/models/sam/predict.py +++ /dev/null @@ -1,474 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Generate predictions using the Segment Anything Model (SAM). - -SAM is an advanced image segmentation model offering features like promptable segmentation and zero-shot performance. -This module contains the implementation of the prediction logic and auxiliary utilities required to perform segmentation -using SAM. It forms an integral part of the Ultralytics framework and is designed for high-performance, real-time image -segmentation tasks. -""" - -import numpy as np -import torch -import torch.nn.functional as F -import torchvision - -from ultralytics.data.augment import LetterBox -from ultralytics.engine.predictor import BasePredictor -from ultralytics.engine.results import Results -from ultralytics.utils import DEFAULT_CFG, ops -from ultralytics.utils.torch_utils import select_device -from .amg import ( - batch_iterator, - batched_mask_to_box, - build_all_layer_point_grids, - calculate_stability_score, - generate_crop_boxes, - is_box_near_crop_edge, - remove_small_regions, - uncrop_boxes_xyxy, - uncrop_masks, -) -from .build import build_sam - - -class Predictor(BasePredictor): - """ - Predictor class for the Segment Anything Model (SAM), extending BasePredictor. - - The class provides an interface for model inference tailored to image segmentation tasks. - With advanced architecture and promptable segmentation capabilities, it facilitates flexible and real-time - mask generation. The class is capable of working with various types of prompts such as bounding boxes, - points, and low-resolution masks. - - Attributes: - cfg (dict): Configuration dictionary specifying model and task-related parameters. - overrides (dict): Dictionary containing values that override the default configuration. - _callbacks (dict): Dictionary of user-defined callback functions to augment behavior. - args (namespace): Namespace to hold command-line arguments or other operational variables. - im (torch.Tensor): Preprocessed input image tensor. - features (torch.Tensor): Extracted image features used for inference. - prompts (dict): Collection of various prompt types, such as bounding boxes and points. - segment_all (bool): Flag to control whether to segment all objects in the image or only specified ones. - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """ - Initialize the Predictor with configuration, overrides, and callbacks. - - The method sets up the Predictor object and applies any configuration overrides or callbacks provided. It - initializes task-specific settings for SAM, such as retina_masks being set to True for optimal results. - - Args: - cfg (dict): Configuration dictionary. - overrides (dict, optional): Dictionary of values to override default configuration. - _callbacks (dict, optional): Dictionary of callback functions to customize behavior. - """ - if overrides is None: - overrides = {} - overrides.update(dict(task="segment", mode="predict", imgsz=1024)) - super().__init__(cfg, overrides, _callbacks) - self.args.retina_masks = True - self.im = None - self.features = None - self.prompts = {} - self.segment_all = False - - def preprocess(self, im): - """ - Preprocess the input image for model inference. - - The method prepares the input image by applying transformations and normalization. - It supports both torch.Tensor and list of np.ndarray as input formats. - - Args: - im (torch.Tensor | List[np.ndarray]): BCHW tensor format or list of HWC numpy arrays. - - Returns: - (torch.Tensor): The preprocessed image tensor. - """ - if self.im is not None: - return self.im - not_tensor = not isinstance(im, torch.Tensor) - if not_tensor: - im = np.stack(self.pre_transform(im)) - im = im[..., ::-1].transpose((0, 3, 1, 2)) - im = np.ascontiguousarray(im) - im = torch.from_numpy(im) - - im = im.to(self.device) - im = im.half() if self.model.fp16 else im.float() - if not_tensor: - im = (im - self.mean) / self.std - return im - - def pre_transform(self, im): - """ - Perform initial transformations on the input image for preprocessing. - - The method applies transformations such as resizing to prepare the image for further preprocessing. - Currently, batched inference is not supported; hence the list length should be 1. - - Args: - im (List[np.ndarray]): List containing images in HWC numpy array format. - - Returns: - (List[np.ndarray]): List of transformed images. - """ - assert len(im) == 1, "SAM model does not currently support batched inference" - letterbox = LetterBox(self.args.imgsz, auto=False, center=False) - return [letterbox(image=x) for x in im] - - def inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False, *args, **kwargs): - """ - Perform image segmentation inference based on the given input cues, using the currently loaded image. This - method leverages SAM's (Segment Anything Model) architecture consisting of image encoder, prompt encoder, and - mask decoder for real-time and promptable segmentation tasks. - - Args: - im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W). - bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format. - points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates. - labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background. - masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256. - multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False. - - Returns: - (tuple): Contains the following three elements. - - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks. - - np.ndarray: An array of length C containing quality scores predicted by the model for each mask. - - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256. - """ - # Override prompts if any stored in self.prompts - bboxes = self.prompts.pop("bboxes", bboxes) - points = self.prompts.pop("points", points) - masks = self.prompts.pop("masks", masks) - - if all(i is None for i in [bboxes, points, masks]): - return self.generate(im, *args, **kwargs) - - return self.prompt_inference(im, bboxes, points, labels, masks, multimask_output) - - def prompt_inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False): - """ - Internal function for image segmentation inference based on cues like bounding boxes, points, and masks. - Leverages SAM's specialized architecture for prompt-based, real-time segmentation. - - Args: - im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W). - bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format. - points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates. - labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background. - masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256. - multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False. - - Returns: - (tuple): Contains the following three elements. - - np.ndarray: The output masks in shape CxHxW, where C is the number of generated masks. - - np.ndarray: An array of length C containing quality scores predicted by the model for each mask. - - np.ndarray: Low-resolution logits of shape CxHxW for subsequent inference, where H=W=256. - """ - features = self.model.image_encoder(im) if self.features is None else self.features - - src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:] - r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1]) - # Transform input prompts - if points is not None: - points = torch.as_tensor(points, dtype=torch.float32, device=self.device) - points = points[None] if points.ndim == 1 else points - # Assuming labels are all positive if users don't pass labels. - if labels is None: - labels = np.ones(points.shape[0]) - labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device) - points *= r - # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1) - points, labels = points[:, None, :], labels[:, None] - if bboxes is not None: - bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device) - bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes - bboxes *= r - if masks is not None: - masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1) - - points = (points, labels) if points is not None else None - # Embed prompts - sparse_embeddings, dense_embeddings = self.model.prompt_encoder(points=points, boxes=bboxes, masks=masks) - - # Predict masks - pred_masks, pred_scores = self.model.mask_decoder( - image_embeddings=features, - image_pe=self.model.prompt_encoder.get_dense_pe(), - sparse_prompt_embeddings=sparse_embeddings, - dense_prompt_embeddings=dense_embeddings, - multimask_output=multimask_output, - ) - - # (N, d, H, W) --> (N*d, H, W), (N, d) --> (N*d, ) - # `d` could be 1 or 3 depends on `multimask_output`. - return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1) - - def generate( - self, - im, - crop_n_layers=0, - crop_overlap_ratio=512 / 1500, - crop_downscale_factor=1, - point_grids=None, - points_stride=32, - points_batch_size=64, - conf_thres=0.88, - stability_score_thresh=0.95, - stability_score_offset=0.95, - crop_nms_thresh=0.7, - ): - """ - Perform image segmentation using the Segment Anything Model (SAM). - - This function segments an entire image into constituent parts by leveraging SAM's advanced architecture - and real-time performance capabilities. It can optionally work on image crops for finer segmentation. - - Args: - im (torch.Tensor): Input tensor representing the preprocessed image with dimensions (N, C, H, W). - crop_n_layers (int): Specifies the number of layers for additional mask predictions on image crops. - Each layer produces 2**i_layer number of image crops. - crop_overlap_ratio (float): Determines the extent of overlap between crops. Scaled down in subsequent layers. - crop_downscale_factor (int): Scaling factor for the number of sampled points-per-side in each layer. - point_grids (list[np.ndarray], optional): Custom grids for point sampling normalized to [0,1]. - Used in the nth crop layer. - points_stride (int, optional): Number of points to sample along each side of the image. - Exclusive with 'point_grids'. - points_batch_size (int): Batch size for the number of points processed simultaneously. - conf_thres (float): Confidence threshold [0,1] for filtering based on the model's mask quality prediction. - stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on mask stability. - stability_score_offset (float): Offset value for calculating stability score. - crop_nms_thresh (float): IoU cutoff for Non-Maximum Suppression (NMS) to remove duplicate masks between crops. - - Returns: - (tuple): A tuple containing segmented masks, confidence scores, and bounding boxes. - """ - self.segment_all = True - ih, iw = im.shape[2:] - crop_regions, layer_idxs = generate_crop_boxes((ih, iw), crop_n_layers, crop_overlap_ratio) - if point_grids is None: - point_grids = build_all_layer_point_grids(points_stride, crop_n_layers, crop_downscale_factor) - pred_masks, pred_scores, pred_bboxes, region_areas = [], [], [], [] - for crop_region, layer_idx in zip(crop_regions, layer_idxs): - x1, y1, x2, y2 = crop_region - w, h = x2 - x1, y2 - y1 - area = torch.tensor(w * h, device=im.device) - points_scale = np.array([[w, h]]) # w, h - # Crop image and interpolate to input size - crop_im = F.interpolate(im[..., y1:y2, x1:x2], (ih, iw), mode="bilinear", align_corners=False) - # (num_points, 2) - points_for_image = point_grids[layer_idx] * points_scale - crop_masks, crop_scores, crop_bboxes = [], [], [] - for (points,) in batch_iterator(points_batch_size, points_for_image): - pred_mask, pred_score = self.prompt_inference(crop_im, points=points, multimask_output=True) - # Interpolate predicted masks to input size - pred_mask = F.interpolate(pred_mask[None], (h, w), mode="bilinear", align_corners=False)[0] - idx = pred_score > conf_thres - pred_mask, pred_score = pred_mask[idx], pred_score[idx] - - stability_score = calculate_stability_score( - pred_mask, self.model.mask_threshold, stability_score_offset - ) - idx = stability_score > stability_score_thresh - pred_mask, pred_score = pred_mask[idx], pred_score[idx] - # Bool type is much more memory-efficient. - pred_mask = pred_mask > self.model.mask_threshold - # (N, 4) - pred_bbox = batched_mask_to_box(pred_mask).float() - keep_mask = ~is_box_near_crop_edge(pred_bbox, crop_region, [0, 0, iw, ih]) - if not torch.all(keep_mask): - pred_bbox, pred_mask, pred_score = pred_bbox[keep_mask], pred_mask[keep_mask], pred_score[keep_mask] - - crop_masks.append(pred_mask) - crop_bboxes.append(pred_bbox) - crop_scores.append(pred_score) - - # Do nms within this crop - crop_masks = torch.cat(crop_masks) - crop_bboxes = torch.cat(crop_bboxes) - crop_scores = torch.cat(crop_scores) - keep = torchvision.ops.nms(crop_bboxes, crop_scores, self.args.iou) # NMS - crop_bboxes = uncrop_boxes_xyxy(crop_bboxes[keep], crop_region) - crop_masks = uncrop_masks(crop_masks[keep], crop_region, ih, iw) - crop_scores = crop_scores[keep] - - pred_masks.append(crop_masks) - pred_bboxes.append(crop_bboxes) - pred_scores.append(crop_scores) - region_areas.append(area.expand(len(crop_masks))) - - pred_masks = torch.cat(pred_masks) - pred_bboxes = torch.cat(pred_bboxes) - pred_scores = torch.cat(pred_scores) - region_areas = torch.cat(region_areas) - - # Remove duplicate masks between crops - if len(crop_regions) > 1: - scores = 1 / region_areas - keep = torchvision.ops.nms(pred_bboxes, scores, crop_nms_thresh) - pred_masks, pred_bboxes, pred_scores = pred_masks[keep], pred_bboxes[keep], pred_scores[keep] - - return pred_masks, pred_scores, pred_bboxes - - def setup_model(self, model, verbose=True): - """ - Initializes the Segment Anything Model (SAM) for inference. - - This method sets up the SAM model by allocating it to the appropriate device and initializing the necessary - parameters for image normalization and other Ultralytics compatibility settings. - - Args: - model (torch.nn.Module): A pre-trained SAM model. If None, a model will be built based on configuration. - verbose (bool): If True, prints selected device information. - - Attributes: - model (torch.nn.Module): The SAM model allocated to the chosen device for inference. - device (torch.device): The device to which the model and tensors are allocated. - mean (torch.Tensor): The mean values for image normalization. - std (torch.Tensor): The standard deviation values for image normalization. - """ - device = select_device(self.args.device, verbose=verbose) - if model is None: - model = build_sam(self.args.model) - model.eval() - self.model = model.to(device) - self.device = device - self.mean = torch.tensor([123.675, 116.28, 103.53]).view(-1, 1, 1).to(device) - self.std = torch.tensor([58.395, 57.12, 57.375]).view(-1, 1, 1).to(device) - - # Ultralytics compatibility settings - self.model.pt = False - self.model.triton = False - self.model.stride = 32 - self.model.fp16 = False - self.done_warmup = True - - def postprocess(self, preds, img, orig_imgs): - """ - Post-processes SAM's inference outputs to generate object detection masks and bounding boxes. - - The method scales masks and boxes to the original image size and applies a threshold to the mask predictions. The - SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance. - - Args: - preds (tuple): The output from SAM model inference, containing masks, scores, and optional bounding boxes. - img (torch.Tensor): The processed input image tensor. - orig_imgs (list | torch.Tensor): The original, unprocessed images. - - Returns: - (list): List of Results objects containing detection masks, bounding boxes, and other metadata. - """ - # (N, 1, H, W), (N, 1) - pred_masks, pred_scores = preds[:2] - pred_bboxes = preds[2] if self.segment_all else None - names = dict(enumerate(str(i) for i in range(len(pred_masks)))) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, masks in enumerate([pred_masks]): - orig_img = orig_imgs[i] - if pred_bboxes is not None: - pred_bboxes = ops.scale_boxes(img.shape[2:], pred_bboxes.float(), orig_img.shape, padding=False) - cls = torch.arange(len(pred_masks), dtype=torch.int32, device=pred_masks.device) - pred_bboxes = torch.cat([pred_bboxes, pred_scores[:, None], cls[:, None]], dim=-1) - - masks = ops.scale_masks(masks[None].float(), orig_img.shape[:2], padding=False)[0] - masks = masks > self.model.mask_threshold # to bool - img_path = self.batch[0][i] - results.append(Results(orig_img, path=img_path, names=names, masks=masks, boxes=pred_bboxes)) - # Reset segment-all mode. - self.segment_all = False - return results - - def setup_source(self, source): - """ - Sets up the data source for inference. - - This method configures the data source from which images will be fetched for inference. The source could be a - directory, a video file, or other types of image data sources. - - Args: - source (str | Path): The path to the image data source for inference. - """ - if source is not None: - super().setup_source(source) - - def set_image(self, image): - """ - Preprocesses and sets a single image for inference. - - This function sets up the model if not already initialized, configures the data source to the specified image, - and preprocesses the image for feature extraction. Only one image can be set at a time. - - Args: - image (str | np.ndarray): Image file path as a string, or a np.ndarray image read by cv2. - - Raises: - AssertionError: If more than one image is set. - """ - if self.model is None: - model = build_sam(self.args.model) - self.setup_model(model) - self.setup_source(image) - assert len(self.dataset) == 1, "`set_image` only supports setting one image!" - for batch in self.dataset: - im = self.preprocess(batch[1]) - self.features = self.model.image_encoder(im) - self.im = im - break - - def set_prompts(self, prompts): - """Set prompts in advance.""" - self.prompts = prompts - - def reset_image(self): - """Resets the image and its features to None.""" - self.im = None - self.features = None - - @staticmethod - def remove_small_regions(masks, min_area=0, nms_thresh=0.7): - """ - Perform post-processing on segmentation masks generated by the Segment Anything Model (SAM). Specifically, this - function removes small disconnected regions and holes from the input masks, and then performs Non-Maximum - Suppression (NMS) to eliminate any newly created duplicate boxes. - - Args: - masks (torch.Tensor): A tensor containing the masks to be processed. Shape should be (N, H, W), where N is - the number of masks, H is height, and W is width. - min_area (int): The minimum area below which disconnected regions and holes will be removed. Defaults to 0. - nms_thresh (float): The IoU threshold for the NMS algorithm. Defaults to 0.7. - - Returns: - (tuple([torch.Tensor, List[int]])): - - new_masks (torch.Tensor): The processed masks with small regions removed. Shape is (N, H, W). - - keep (List[int]): The indices of the remaining masks post-NMS, which can be used to filter the boxes. - """ - if len(masks) == 0: - return masks - - # Filter small disconnected regions and holes - new_masks = [] - scores = [] - for mask in masks: - mask = mask.cpu().numpy().astype(np.uint8) - mask, changed = remove_small_regions(mask, min_area, mode="holes") - unchanged = not changed - mask, changed = remove_small_regions(mask, min_area, mode="islands") - unchanged = unchanged and not changed - - new_masks.append(torch.as_tensor(mask).unsqueeze(0)) - # Give score=0 to changed masks and 1 to unchanged masks so NMS prefers masks not needing postprocessing - scores.append(float(unchanged)) - - # Recalculate boxes and remove any new duplicates - new_masks = torch.cat(new_masks, dim=0) - boxes = batched_mask_to_box(new_masks) - keep = torchvision.ops.nms(boxes.float(), torch.as_tensor(scores), nms_thresh) - - return new_masks[keep].to(device=masks.device, dtype=masks.dtype), keep diff --git a/ultralytics-main/ultralytics/models/utils/__init__.py b/ultralytics-main/ultralytics/models/utils/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/models/utils/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/models/utils/loss.py b/ultralytics-main/ultralytics/models/utils/loss.py deleted file mode 100644 index ac48775..0000000 --- a/ultralytics-main/ultralytics/models/utils/loss.py +++ /dev/null @@ -1,345 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch -import torch.nn as nn -import torch.nn.functional as F - -from ultralytics.utils.loss import FocalLoss, VarifocalLoss -from ultralytics.utils.metrics import bbox_iou -from .ops import HungarianMatcher - - -class DETRLoss(nn.Module): - """ - DETR (DEtection TRansformer) Loss class. This class calculates and returns the different loss components for the - DETR object detection model. It computes classification loss, bounding box loss, GIoU loss, and optionally auxiliary - losses. - - Attributes: - nc (int): The number of classes. - loss_gain (dict): Coefficients for different loss components. - aux_loss (bool): Whether to compute auxiliary losses. - use_fl (bool): Use FocalLoss or not. - use_vfl (bool): Use VarifocalLoss or not. - use_uni_match (bool): Whether to use a fixed layer to assign labels for the auxiliary branch. - uni_match_ind (int): The fixed indices of a layer to use if `use_uni_match` is True. - matcher (HungarianMatcher): Object to compute matching cost and indices. - fl (FocalLoss or None): Focal Loss object if `use_fl` is True, otherwise None. - vfl (VarifocalLoss or None): Varifocal Loss object if `use_vfl` is True, otherwise None. - device (torch.device): Device on which tensors are stored. - """ - - def __init__( - self, nc=80, loss_gain=None, aux_loss=True, use_fl=True, use_vfl=False, use_uni_match=False, uni_match_ind=0 - ): - """ - DETR loss function. - - Args: - nc (int): The number of classes. - loss_gain (dict): The coefficient of loss. - aux_loss (bool): If 'aux_loss = True', loss at each decoder layer are to be used. - use_vfl (bool): Use VarifocalLoss or not. - use_uni_match (bool): Whether to use a fixed layer to assign labels for auxiliary branch. - uni_match_ind (int): The fixed indices of a layer. - """ - super().__init__() - - if loss_gain is None: - loss_gain = {"class": 1, "bbox": 5, "giou": 2, "no_object": 0.1, "mask": 1, "dice": 1} - self.nc = nc - self.matcher = HungarianMatcher(cost_gain={"class": 2, "bbox": 5, "giou": 2}) - self.loss_gain = loss_gain - self.aux_loss = aux_loss - self.fl = FocalLoss() if use_fl else None - self.vfl = VarifocalLoss() if use_vfl else None - - self.use_uni_match = use_uni_match - self.uni_match_ind = uni_match_ind - self.device = None - - def _get_loss_class(self, pred_scores, targets, gt_scores, num_gts, postfix=""): - """Computes the classification loss based on predictions, target values, and ground truth scores.""" - # Logits: [b, query, num_classes], gt_class: list[[n, 1]] - name_class = f"loss_class{postfix}" - bs, nq = pred_scores.shape[:2] - # one_hot = F.one_hot(targets, self.nc + 1)[..., :-1] # (bs, num_queries, num_classes) - one_hot = torch.zeros((bs, nq, self.nc + 1), dtype=torch.int64, device=targets.device) - one_hot.scatter_(2, targets.unsqueeze(-1), 1) - one_hot = one_hot[..., :-1] - gt_scores = gt_scores.view(bs, nq, 1) * one_hot - - if self.fl: - if num_gts and self.vfl: - loss_cls = self.vfl(pred_scores, gt_scores, one_hot) - else: - loss_cls = self.fl(pred_scores, one_hot.float()) - loss_cls /= max(num_gts, 1) / nq - else: - loss_cls = nn.BCEWithLogitsLoss(reduction="none")(pred_scores, gt_scores).mean(1).sum() # YOLO CLS loss - - return {name_class: loss_cls.squeeze() * self.loss_gain["class"]} - - def _get_loss_bbox(self, pred_bboxes, gt_bboxes, postfix=""): - """Calculates and returns the bounding box loss and GIoU loss for the predicted and ground truth bounding - boxes. - """ - # Boxes: [b, query, 4], gt_bbox: list[[n, 4]] - name_bbox = f"loss_bbox{postfix}" - name_giou = f"loss_giou{postfix}" - - loss = {} - if len(gt_bboxes) == 0: - loss[name_bbox] = torch.tensor(0.0, device=self.device) - loss[name_giou] = torch.tensor(0.0, device=self.device) - return loss - - loss[name_bbox] = self.loss_gain["bbox"] * F.l1_loss(pred_bboxes, gt_bboxes, reduction="sum") / len(gt_bboxes) - loss[name_giou] = 1.0 - bbox_iou(pred_bboxes, gt_bboxes, xywh=True, GIoU=True) - loss[name_giou] = loss[name_giou].sum() / len(gt_bboxes) - loss[name_giou] = self.loss_gain["giou"] * loss[name_giou] - return {k: v.squeeze() for k, v in loss.items()} - - # This function is for future RT-DETR Segment models - # def _get_loss_mask(self, masks, gt_mask, match_indices, postfix=''): - # # masks: [b, query, h, w], gt_mask: list[[n, H, W]] - # name_mask = f'loss_mask{postfix}' - # name_dice = f'loss_dice{postfix}' - # - # loss = {} - # if sum(len(a) for a in gt_mask) == 0: - # loss[name_mask] = torch.tensor(0., device=self.device) - # loss[name_dice] = torch.tensor(0., device=self.device) - # return loss - # - # num_gts = len(gt_mask) - # src_masks, target_masks = self._get_assigned_bboxes(masks, gt_mask, match_indices) - # src_masks = F.interpolate(src_masks.unsqueeze(0), size=target_masks.shape[-2:], mode='bilinear')[0] - # # TODO: torch does not have `sigmoid_focal_loss`, but it's not urgent since we don't use mask branch for now. - # loss[name_mask] = self.loss_gain['mask'] * F.sigmoid_focal_loss(src_masks, target_masks, - # torch.tensor([num_gts], dtype=torch.float32)) - # loss[name_dice] = self.loss_gain['dice'] * self._dice_loss(src_masks, target_masks, num_gts) - # return loss - - # This function is for future RT-DETR Segment models - # @staticmethod - # def _dice_loss(inputs, targets, num_gts): - # inputs = F.sigmoid(inputs).flatten(1) - # targets = targets.flatten(1) - # numerator = 2 * (inputs * targets).sum(1) - # denominator = inputs.sum(-1) + targets.sum(-1) - # loss = 1 - (numerator + 1) / (denominator + 1) - # return loss.sum() / num_gts - - def _get_loss_aux( - self, - pred_bboxes, - pred_scores, - gt_bboxes, - gt_cls, - gt_groups, - match_indices=None, - postfix="", - masks=None, - gt_mask=None, - ): - """Get auxiliary losses.""" - # NOTE: loss class, bbox, giou, mask, dice - loss = torch.zeros(5 if masks is not None else 3, device=pred_bboxes.device) - if match_indices is None and self.use_uni_match: - match_indices = self.matcher( - pred_bboxes[self.uni_match_ind], - pred_scores[self.uni_match_ind], - gt_bboxes, - gt_cls, - gt_groups, - masks=masks[self.uni_match_ind] if masks is not None else None, - gt_mask=gt_mask, - ) - for i, (aux_bboxes, aux_scores) in enumerate(zip(pred_bboxes, pred_scores)): - aux_masks = masks[i] if masks is not None else None - loss_ = self._get_loss( - aux_bboxes, - aux_scores, - gt_bboxes, - gt_cls, - gt_groups, - masks=aux_masks, - gt_mask=gt_mask, - postfix=postfix, - match_indices=match_indices, - ) - loss[0] += loss_[f"loss_class{postfix}"] - loss[1] += loss_[f"loss_bbox{postfix}"] - loss[2] += loss_[f"loss_giou{postfix}"] - # if masks is not None and gt_mask is not None: - # loss_ = self._get_loss_mask(aux_masks, gt_mask, match_indices, postfix) - # loss[3] += loss_[f'loss_mask{postfix}'] - # loss[4] += loss_[f'loss_dice{postfix}'] - - loss = { - f"loss_class_aux{postfix}": loss[0], - f"loss_bbox_aux{postfix}": loss[1], - f"loss_giou_aux{postfix}": loss[2], - } - # if masks is not None and gt_mask is not None: - # loss[f'loss_mask_aux{postfix}'] = loss[3] - # loss[f'loss_dice_aux{postfix}'] = loss[4] - return loss - - @staticmethod - def _get_index(match_indices): - """Returns batch indices, source indices, and destination indices from provided match indices.""" - batch_idx = torch.cat([torch.full_like(src, i) for i, (src, _) in enumerate(match_indices)]) - src_idx = torch.cat([src for (src, _) in match_indices]) - dst_idx = torch.cat([dst for (_, dst) in match_indices]) - return (batch_idx, src_idx), dst_idx - - def _get_assigned_bboxes(self, pred_bboxes, gt_bboxes, match_indices): - """Assigns predicted bounding boxes to ground truth bounding boxes based on the match indices.""" - pred_assigned = torch.cat( - [ - t[i] if len(i) > 0 else torch.zeros(0, t.shape[-1], device=self.device) - for t, (i, _) in zip(pred_bboxes, match_indices) - ] - ) - gt_assigned = torch.cat( - [ - t[j] if len(j) > 0 else torch.zeros(0, t.shape[-1], device=self.device) - for t, (_, j) in zip(gt_bboxes, match_indices) - ] - ) - return pred_assigned, gt_assigned - - def _get_loss( - self, - pred_bboxes, - pred_scores, - gt_bboxes, - gt_cls, - gt_groups, - masks=None, - gt_mask=None, - postfix="", - match_indices=None, - ): - """Get losses.""" - if match_indices is None: - match_indices = self.matcher( - pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=masks, gt_mask=gt_mask - ) - - idx, gt_idx = self._get_index(match_indices) - pred_bboxes, gt_bboxes = pred_bboxes[idx], gt_bboxes[gt_idx] - - bs, nq = pred_scores.shape[:2] - targets = torch.full((bs, nq), self.nc, device=pred_scores.device, dtype=gt_cls.dtype) - targets[idx] = gt_cls[gt_idx] - - gt_scores = torch.zeros([bs, nq], device=pred_scores.device) - if len(gt_bboxes): - gt_scores[idx] = bbox_iou(pred_bboxes.detach(), gt_bboxes, xywh=True).squeeze(-1) - - loss = {} - loss.update(self._get_loss_class(pred_scores, targets, gt_scores, len(gt_bboxes), postfix)) - loss.update(self._get_loss_bbox(pred_bboxes, gt_bboxes, postfix)) - # if masks is not None and gt_mask is not None: - # loss.update(self._get_loss_mask(masks, gt_mask, match_indices, postfix)) - return loss - - def forward(self, pred_bboxes, pred_scores, batch, postfix="", **kwargs): - """ - Args: - pred_bboxes (torch.Tensor): [l, b, query, 4] - pred_scores (torch.Tensor): [l, b, query, num_classes] - batch (dict): A dict includes: - gt_cls (torch.Tensor) with shape [num_gts, ], - gt_bboxes (torch.Tensor): [num_gts, 4], - gt_groups (List(int)): a list of batch size length includes the number of gts of each image. - postfix (str): postfix of loss name. - """ - self.device = pred_bboxes.device - match_indices = kwargs.get("match_indices", None) - gt_cls, gt_bboxes, gt_groups = batch["cls"], batch["bboxes"], batch["gt_groups"] - - total_loss = self._get_loss( - pred_bboxes[-1], pred_scores[-1], gt_bboxes, gt_cls, gt_groups, postfix=postfix, match_indices=match_indices - ) - - if self.aux_loss: - total_loss.update( - self._get_loss_aux( - pred_bboxes[:-1], pred_scores[:-1], gt_bboxes, gt_cls, gt_groups, match_indices, postfix - ) - ) - - return total_loss - - -class RTDETRDetectionLoss(DETRLoss): - """ - Real-Time DeepTracker (RT-DETR) Detection Loss class that extends the DETRLoss. - - This class computes the detection loss for the RT-DETR model, which includes the standard detection loss as well as - an additional denoising training loss when provided with denoising metadata. - """ - - def forward(self, preds, batch, dn_bboxes=None, dn_scores=None, dn_meta=None): - """ - Forward pass to compute the detection loss. - - Args: - preds (tuple): Predicted bounding boxes and scores. - batch (dict): Batch data containing ground truth information. - dn_bboxes (torch.Tensor, optional): Denoising bounding boxes. Default is None. - dn_scores (torch.Tensor, optional): Denoising scores. Default is None. - dn_meta (dict, optional): Metadata for denoising. Default is None. - - Returns: - (dict): Dictionary containing the total loss and, if applicable, the denoising loss. - """ - pred_bboxes, pred_scores = preds - total_loss = super().forward(pred_bboxes, pred_scores, batch) - - # Check for denoising metadata to compute denoising training loss - if dn_meta is not None: - dn_pos_idx, dn_num_group = dn_meta["dn_pos_idx"], dn_meta["dn_num_group"] - assert len(batch["gt_groups"]) == len(dn_pos_idx) - - # Get the match indices for denoising - match_indices = self.get_dn_match_indices(dn_pos_idx, dn_num_group, batch["gt_groups"]) - - # Compute the denoising training loss - dn_loss = super().forward(dn_bboxes, dn_scores, batch, postfix="_dn", match_indices=match_indices) - total_loss.update(dn_loss) - else: - # If no denoising metadata is provided, set denoising loss to zero - total_loss.update({f"{k}_dn": torch.tensor(0.0, device=self.device) for k in total_loss.keys()}) - - return total_loss - - @staticmethod - def get_dn_match_indices(dn_pos_idx, dn_num_group, gt_groups): - """ - Get the match indices for denoising. - - Args: - dn_pos_idx (List[torch.Tensor]): List of tensors containing positive indices for denoising. - dn_num_group (int): Number of denoising groups. - gt_groups (List[int]): List of integers representing the number of ground truths for each image. - - Returns: - (List[tuple]): List of tuples containing matched indices for denoising. - """ - dn_match_indices = [] - idx_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0) - for i, num_gt in enumerate(gt_groups): - if num_gt > 0: - gt_idx = torch.arange(end=num_gt, dtype=torch.long) + idx_groups[i] - gt_idx = gt_idx.repeat(dn_num_group) - assert len(dn_pos_idx[i]) == len(gt_idx), "Expected the same length, " - f"but got {len(dn_pos_idx[i])} and {len(gt_idx)} respectively." - dn_match_indices.append((dn_pos_idx[i], gt_idx)) - else: - dn_match_indices.append((torch.zeros([0], dtype=torch.long), torch.zeros([0], dtype=torch.long))) - return dn_match_indices diff --git a/ultralytics-main/ultralytics/models/utils/ops.py b/ultralytics-main/ultralytics/models/utils/ops.py deleted file mode 100644 index 4f66fee..0000000 --- a/ultralytics-main/ultralytics/models/utils/ops.py +++ /dev/null @@ -1,263 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch -import torch.nn as nn -import torch.nn.functional as F -from scipy.optimize import linear_sum_assignment - -from ultralytics.utils.metrics import bbox_iou -from ultralytics.utils.ops import xywh2xyxy, xyxy2xywh - - -class HungarianMatcher(nn.Module): - """ - A module implementing the HungarianMatcher, which is a differentiable module to solve the assignment problem in an - end-to-end fashion. - - HungarianMatcher performs optimal assignment over the predicted and ground truth bounding boxes using a cost - function that considers classification scores, bounding box coordinates, and optionally, mask predictions. - - Attributes: - cost_gain (dict): Dictionary of cost coefficients: 'class', 'bbox', 'giou', 'mask', and 'dice'. - use_fl (bool): Indicates whether to use Focal Loss for the classification cost calculation. - with_mask (bool): Indicates whether the model makes mask predictions. - num_sample_points (int): The number of sample points used in mask cost calculation. - alpha (float): The alpha factor in Focal Loss calculation. - gamma (float): The gamma factor in Focal Loss calculation. - - Methods: - forward(pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None): Computes the - assignment between predictions and ground truths for a batch. - _cost_mask(bs, num_gts, masks=None, gt_mask=None): Computes the mask cost and dice cost if masks are predicted. - """ - - def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0): - """Initializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha - gamma factors. - """ - super().__init__() - if cost_gain is None: - cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1} - self.cost_gain = cost_gain - self.use_fl = use_fl - self.with_mask = with_mask - self.num_sample_points = num_sample_points - self.alpha = alpha - self.gamma = gamma - - def forward(self, pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None): - """ - Forward pass for HungarianMatcher. This function computes costs based on prediction and ground truth - (classification cost, L1 cost between boxes and GIoU cost between boxes) and finds the optimal matching between - predictions and ground truth based on these costs. - - Args: - pred_bboxes (Tensor): Predicted bounding boxes with shape [batch_size, num_queries, 4]. - pred_scores (Tensor): Predicted scores with shape [batch_size, num_queries, num_classes]. - gt_cls (torch.Tensor): Ground truth classes with shape [num_gts, ]. - gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape [num_gts, 4]. - gt_groups (List[int]): List of length equal to batch size, containing the number of ground truths for - each image. - masks (Tensor, optional): Predicted masks with shape [batch_size, num_queries, height, width]. - Defaults to None. - gt_mask (List[Tensor], optional): List of ground truth masks, each with shape [num_masks, Height, Width]. - Defaults to None. - - Returns: - (List[Tuple[Tensor, Tensor]]): A list of size batch_size, each element is a tuple (index_i, index_j), where: - - index_i is the tensor of indices of the selected predictions (in order) - - index_j is the tensor of indices of the corresponding selected ground truth targets (in order) - For each batch element, it holds: - len(index_i) = len(index_j) = min(num_queries, num_target_boxes) - """ - - bs, nq, nc = pred_scores.shape - - if sum(gt_groups) == 0: - return [(torch.tensor([], dtype=torch.long), torch.tensor([], dtype=torch.long)) for _ in range(bs)] - - # We flatten to compute the cost matrices in a batch - # [batch_size * num_queries, num_classes] - pred_scores = pred_scores.detach().view(-1, nc) - pred_scores = F.sigmoid(pred_scores) if self.use_fl else F.softmax(pred_scores, dim=-1) - # [batch_size * num_queries, 4] - pred_bboxes = pred_bboxes.detach().view(-1, 4) - - # Compute the classification cost - pred_scores = pred_scores[:, gt_cls] - if self.use_fl: - neg_cost_class = (1 - self.alpha) * (pred_scores**self.gamma) * (-(1 - pred_scores + 1e-8).log()) - pos_cost_class = self.alpha * ((1 - pred_scores) ** self.gamma) * (-(pred_scores + 1e-8).log()) - cost_class = pos_cost_class - neg_cost_class - else: - cost_class = -pred_scores - - # Compute the L1 cost between boxes - cost_bbox = (pred_bboxes.unsqueeze(1) - gt_bboxes.unsqueeze(0)).abs().sum(-1) # (bs*num_queries, num_gt) - - # Compute the GIoU cost between boxes, (bs*num_queries, num_gt) - cost_giou = 1.0 - bbox_iou(pred_bboxes.unsqueeze(1), gt_bboxes.unsqueeze(0), xywh=True, GIoU=True).squeeze(-1) - - # Final cost matrix - C = ( - self.cost_gain["class"] * cost_class - + self.cost_gain["bbox"] * cost_bbox - + self.cost_gain["giou"] * cost_giou - ) - # Compute the mask cost and dice cost - if self.with_mask: - C += self._cost_mask(bs, gt_groups, masks, gt_mask) - - # Set invalid values (NaNs and infinities) to 0 (fixes ValueError: matrix contains invalid numeric entries) - C[C.isnan() | C.isinf()] = 0.0 - - C = C.view(bs, nq, -1).cpu() - indices = [linear_sum_assignment(c[i]) for i, c in enumerate(C.split(gt_groups, -1))] - gt_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0) # (idx for queries, idx for gt) - return [ - (torch.tensor(i, dtype=torch.long), torch.tensor(j, dtype=torch.long) + gt_groups[k]) - for k, (i, j) in enumerate(indices) - ] - - # This function is for future RT-DETR Segment models - # def _cost_mask(self, bs, num_gts, masks=None, gt_mask=None): - # assert masks is not None and gt_mask is not None, 'Make sure the input has `mask` and `gt_mask`' - # # all masks share the same set of points for efficient matching - # sample_points = torch.rand([bs, 1, self.num_sample_points, 2]) - # sample_points = 2.0 * sample_points - 1.0 - # - # out_mask = F.grid_sample(masks.detach(), sample_points, align_corners=False).squeeze(-2) - # out_mask = out_mask.flatten(0, 1) - # - # tgt_mask = torch.cat(gt_mask).unsqueeze(1) - # sample_points = torch.cat([a.repeat(b, 1, 1, 1) for a, b in zip(sample_points, num_gts) if b > 0]) - # tgt_mask = F.grid_sample(tgt_mask, sample_points, align_corners=False).squeeze([1, 2]) - # - # with torch.cuda.amp.autocast(False): - # # binary cross entropy cost - # pos_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.ones_like(out_mask), reduction='none') - # neg_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.zeros_like(out_mask), reduction='none') - # cost_mask = torch.matmul(pos_cost_mask, tgt_mask.T) + torch.matmul(neg_cost_mask, 1 - tgt_mask.T) - # cost_mask /= self.num_sample_points - # - # # dice cost - # out_mask = F.sigmoid(out_mask) - # numerator = 2 * torch.matmul(out_mask, tgt_mask.T) - # denominator = out_mask.sum(-1, keepdim=True) + tgt_mask.sum(-1).unsqueeze(0) - # cost_dice = 1 - (numerator + 1) / (denominator + 1) - # - # C = self.cost_gain['mask'] * cost_mask + self.cost_gain['dice'] * cost_dice - # return C - - -def get_cdn_group( - batch, num_classes, num_queries, class_embed, num_dn=100, cls_noise_ratio=0.5, box_noise_scale=1.0, training=False -): - """ - Get contrastive denoising training group. This function creates a contrastive denoising training group with positive - and negative samples from the ground truths (gt). It applies noise to the class labels and bounding box coordinates, - and returns the modified labels, bounding boxes, attention mask and meta information. - - Args: - batch (dict): A dict that includes 'gt_cls' (torch.Tensor with shape [num_gts, ]), 'gt_bboxes' - (torch.Tensor with shape [num_gts, 4]), 'gt_groups' (List(int)) which is a list of batch size length - indicating the number of gts of each image. - num_classes (int): Number of classes. - num_queries (int): Number of queries. - class_embed (torch.Tensor): Embedding weights to map class labels to embedding space. - num_dn (int, optional): Number of denoising. Defaults to 100. - cls_noise_ratio (float, optional): Noise ratio for class labels. Defaults to 0.5. - box_noise_scale (float, optional): Noise scale for bounding box coordinates. Defaults to 1.0. - training (bool, optional): If it's in training mode. Defaults to False. - - Returns: - (Tuple[Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Dict]]): The modified class embeddings, - bounding boxes, attention mask and meta information for denoising. If not in training mode or 'num_dn' - is less than or equal to 0, the function returns None for all elements in the tuple. - """ - - if (not training) or num_dn <= 0: - return None, None, None, None - gt_groups = batch["gt_groups"] - total_num = sum(gt_groups) - max_nums = max(gt_groups) - if max_nums == 0: - return None, None, None, None - - num_group = num_dn // max_nums - num_group = 1 if num_group == 0 else num_group - # Pad gt to max_num of a batch - bs = len(gt_groups) - gt_cls = batch["cls"] # (bs*num, ) - gt_bbox = batch["bboxes"] # bs*num, 4 - b_idx = batch["batch_idx"] - - # Each group has positive and negative queries. - dn_cls = gt_cls.repeat(2 * num_group) # (2*num_group*bs*num, ) - dn_bbox = gt_bbox.repeat(2 * num_group, 1) # 2*num_group*bs*num, 4 - dn_b_idx = b_idx.repeat(2 * num_group).view(-1) # (2*num_group*bs*num, ) - - # Positive and negative mask - # (bs*num*num_group, ), the second total_num*num_group part as negative samples - neg_idx = torch.arange(total_num * num_group, dtype=torch.long, device=gt_bbox.device) + num_group * total_num - - if cls_noise_ratio > 0: - # Half of bbox prob - mask = torch.rand(dn_cls.shape) < (cls_noise_ratio * 0.5) - idx = torch.nonzero(mask).squeeze(-1) - # Randomly put a new one here - new_label = torch.randint_like(idx, 0, num_classes, dtype=dn_cls.dtype, device=dn_cls.device) - dn_cls[idx] = new_label - - if box_noise_scale > 0: - known_bbox = xywh2xyxy(dn_bbox) - - diff = (dn_bbox[..., 2:] * 0.5).repeat(1, 2) * box_noise_scale # 2*num_group*bs*num, 4 - - rand_sign = torch.randint_like(dn_bbox, 0, 2) * 2.0 - 1.0 - rand_part = torch.rand_like(dn_bbox) - rand_part[neg_idx] += 1.0 - rand_part *= rand_sign - known_bbox += rand_part * diff - known_bbox.clip_(min=0.0, max=1.0) - dn_bbox = xyxy2xywh(known_bbox) - dn_bbox = torch.logit(dn_bbox, eps=1e-6) # inverse sigmoid - - num_dn = int(max_nums * 2 * num_group) # total denoising queries - # class_embed = torch.cat([class_embed, torch.zeros([1, class_embed.shape[-1]], device=class_embed.device)]) - dn_cls_embed = class_embed[dn_cls] # bs*num * 2 * num_group, 256 - padding_cls = torch.zeros(bs, num_dn, dn_cls_embed.shape[-1], device=gt_cls.device) - padding_bbox = torch.zeros(bs, num_dn, 4, device=gt_bbox.device) - - map_indices = torch.cat([torch.tensor(range(num), dtype=torch.long) for num in gt_groups]) - pos_idx = torch.stack([map_indices + max_nums * i for i in range(num_group)], dim=0) - - map_indices = torch.cat([map_indices + max_nums * i for i in range(2 * num_group)]) - padding_cls[(dn_b_idx, map_indices)] = dn_cls_embed - padding_bbox[(dn_b_idx, map_indices)] = dn_bbox - - tgt_size = num_dn + num_queries - attn_mask = torch.zeros([tgt_size, tgt_size], dtype=torch.bool) - # Match query cannot see the reconstruct - attn_mask[num_dn:, :num_dn] = True - # Reconstruct cannot see each other - for i in range(num_group): - if i == 0: - attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True - if i == num_group - 1: - attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * i * 2] = True - else: - attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True - attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * 2 * i] = True - dn_meta = { - "dn_pos_idx": [p.reshape(-1) for p in pos_idx.cpu().split(list(gt_groups), dim=1)], - "dn_num_group": num_group, - "dn_num_split": [num_dn, num_queries], - } - - return ( - padding_cls.to(class_embed.device), - padding_bbox.to(class_embed.device), - attn_mask.to(class_embed.device), - dn_meta, - ) diff --git a/ultralytics-main/ultralytics/models/yolo/__init__.py b/ultralytics-main/ultralytics/models/yolo/__init__.py deleted file mode 100644 index 7b1a597..0000000 --- a/ultralytics-main/ultralytics/models/yolo/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.models.yolo import classify, detect, obb, pose, segment - -from .model import YOLO, YOLOWorld - -__all__ = "classify", "segment", "detect", "pose", "obb", "YOLO", "YOLOWorld" diff --git a/ultralytics-main/ultralytics/models/yolo/classify/__init__.py b/ultralytics-main/ultralytics/models/yolo/classify/__init__.py deleted file mode 100644 index ca92f89..0000000 --- a/ultralytics-main/ultralytics/models/yolo/classify/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.models.yolo.classify.predict import ClassificationPredictor -from ultralytics.models.yolo.classify.train import ClassificationTrainer -from ultralytics.models.yolo.classify.val import ClassificationValidator - -__all__ = "ClassificationPredictor", "ClassificationTrainer", "ClassificationValidator" diff --git a/ultralytics-main/ultralytics/models/yolo/classify/predict.py b/ultralytics-main/ultralytics/models/yolo/classify/predict.py deleted file mode 100644 index 853ef04..0000000 --- a/ultralytics-main/ultralytics/models/yolo/classify/predict.py +++ /dev/null @@ -1,61 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import cv2 -import torch -from PIL import Image - -from ultralytics.engine.predictor import BasePredictor -from ultralytics.engine.results import Results -from ultralytics.utils import DEFAULT_CFG, ops - - -class ClassificationPredictor(BasePredictor): - """ - A class extending the BasePredictor class for prediction based on a classification model. - - Notes: - - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.yolo.classify import ClassificationPredictor - - args = dict(model='yolov8n-cls.pt', source=ASSETS) - predictor = ClassificationPredictor(overrides=args) - predictor.predict_cli() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initializes ClassificationPredictor setting the task to 'classify'.""" - super().__init__(cfg, overrides, _callbacks) - self.args.task = "classify" - self._legacy_transform_name = "ultralytics.yolo.data.augment.ToTensor" - - def preprocess(self, img): - """Converts input image to model-compatible data type.""" - if not isinstance(img, torch.Tensor): - is_legacy_transform = any( - self._legacy_transform_name in str(transform) for transform in self.transforms.transforms - ) - if is_legacy_transform: # to handle legacy transforms - img = torch.stack([self.transforms(im) for im in img], dim=0) - else: - img = torch.stack( - [self.transforms(Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))) for im in img], dim=0 - ) - img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device) - return img.half() if self.model.fp16 else img.float() # uint8 to fp16/32 - - def postprocess(self, preds, img, orig_imgs): - """Post-processes predictions to return Results objects.""" - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, pred in enumerate(preds): - orig_img = orig_imgs[i] - img_path = self.batch[0][i] - results.append(Results(orig_img, path=img_path, names=self.model.names, probs=pred)) - return results diff --git a/ultralytics-main/ultralytics/models/yolo/classify/train.py b/ultralytics-main/ultralytics/models/yolo/classify/train.py deleted file mode 100644 index a7bbe77..0000000 --- a/ultralytics-main/ultralytics/models/yolo/classify/train.py +++ /dev/null @@ -1,158 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch -import torchvision - -from ultralytics.data import ClassificationDataset, build_dataloader -from ultralytics.engine.trainer import BaseTrainer -from ultralytics.models import yolo -from ultralytics.nn.tasks import ClassificationModel, attempt_load_one_weight -from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK, colorstr -from ultralytics.utils.plotting import plot_images, plot_results -from ultralytics.utils.torch_utils import is_parallel, strip_optimizer, torch_distributed_zero_first - - -class ClassificationTrainer(BaseTrainer): - """ - A class extending the BaseTrainer class for training based on a classification model. - - Notes: - - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'. - - Example: - ```python - from ultralytics.models.yolo.classify import ClassificationTrainer - - args = dict(model='yolov8n-cls.pt', data='imagenet10', epochs=3) - trainer = ClassificationTrainer(overrides=args) - trainer.train() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initialize a ClassificationTrainer object with optional configuration overrides and callbacks.""" - if overrides is None: - overrides = {} - overrides["task"] = "classify" - if overrides.get("imgsz") is None: - overrides["imgsz"] = 224 - super().__init__(cfg, overrides, _callbacks) - - def set_model_attributes(self): - """Set the YOLO model's class names from the loaded dataset.""" - self.model.names = self.data["names"] - - def get_model(self, cfg=None, weights=None, verbose=True): - """Returns a modified PyTorch model configured for training YOLO.""" - model = ClassificationModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1) - if weights: - model.load(weights) - - for m in model.modules(): - if not self.args.pretrained and hasattr(m, "reset_parameters"): - m.reset_parameters() - if isinstance(m, torch.nn.Dropout) and self.args.dropout: - m.p = self.args.dropout # set dropout - for p in model.parameters(): - p.requires_grad = True # for training - return model - - def setup_model(self): - """Load, create or download model for any task.""" - if isinstance(self.model, torch.nn.Module): # if model is loaded beforehand. No setup needed - return - - model, ckpt = str(self.model), None - # Load a YOLO model locally, from torchvision, or from Ultralytics assets - if model.endswith(".pt"): - self.model, ckpt = attempt_load_one_weight(model, device="cpu") - for p in self.model.parameters(): - p.requires_grad = True # for training - elif model.split(".")[-1] in ("yaml", "yml"): - self.model = self.get_model(cfg=model) - elif model in torchvision.models.__dict__: - self.model = torchvision.models.__dict__[model](weights="IMAGENET1K_V1" if self.args.pretrained else None) - else: - FileNotFoundError(f"ERROR: model={model} not found locally or online. Please check model name.") - ClassificationModel.reshape_outputs(self.model, self.data["nc"]) - - return ckpt - - def build_dataset(self, img_path, mode="train", batch=None): - """Creates a ClassificationDataset instance given an image path, and mode (train/test etc.).""" - return ClassificationDataset(root=img_path, args=self.args, augment=mode == "train", prefix=mode) - - def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"): - """Returns PyTorch DataLoader with transforms to preprocess images for inference.""" - with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP - dataset = self.build_dataset(dataset_path, mode) - - loader = build_dataloader(dataset, batch_size, self.args.workers, rank=rank) - # Attach inference transforms - if mode != "train": - if is_parallel(self.model): - self.model.module.transforms = loader.dataset.torch_transforms - else: - self.model.transforms = loader.dataset.torch_transforms - return loader - - def preprocess_batch(self, batch): - """Preprocesses a batch of images and classes.""" - batch["img"] = batch["img"].to(self.device) - batch["cls"] = batch["cls"].to(self.device) - return batch - - def progress_string(self): - """Returns a formatted string showing training progress.""" - return ("\n" + "%11s" * (4 + len(self.loss_names))) % ( - "Epoch", - "GPU_mem", - *self.loss_names, - "Instances", - "Size", - ) - - def get_validator(self): - """Returns an instance of ClassificationValidator for validation.""" - self.loss_names = ["loss"] - return yolo.classify.ClassificationValidator(self.test_loader, self.save_dir, _callbacks=self.callbacks) - - def label_loss_items(self, loss_items=None, prefix="train"): - """ - Returns a loss dict with labelled training loss items tensor. - - Not needed for classification but necessary for segmentation & detection - """ - keys = [f"{prefix}/{x}" for x in self.loss_names] - if loss_items is None: - return keys - loss_items = [round(float(loss_items), 5)] - return dict(zip(keys, loss_items)) - - def plot_metrics(self): - """Plots metrics from a CSV file.""" - plot_results(file=self.csv, classify=True, on_plot=self.on_plot) # save results.png - - def final_eval(self): - """Evaluate trained model and save validation results.""" - for f in self.last, self.best: - if f.exists(): - strip_optimizer(f) # strip optimizers - if f is self.best: - LOGGER.info(f"\nValidating {f}...") - self.validator.args.data = self.args.data - self.validator.args.plots = self.args.plots - self.metrics = self.validator(model=f) - self.metrics.pop("fitness", None) - self.run_callbacks("on_fit_epoch_end") - LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}") - - def plot_training_samples(self, batch, ni): - """Plots training samples with their annotations.""" - plot_images( - images=batch["img"], - batch_idx=torch.arange(len(batch["img"])), - cls=batch["cls"].view(-1), # warning: use .view(), not .squeeze() for Classify models - fname=self.save_dir / f"train_batch{ni}.jpg", - on_plot=self.on_plot, - ) diff --git a/ultralytics-main/ultralytics/models/yolo/classify/val.py b/ultralytics-main/ultralytics/models/yolo/classify/val.py deleted file mode 100644 index de3cff2..0000000 --- a/ultralytics-main/ultralytics/models/yolo/classify/val.py +++ /dev/null @@ -1,113 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.data import ClassificationDataset, build_dataloader -from ultralytics.engine.validator import BaseValidator -from ultralytics.utils import LOGGER -from ultralytics.utils.metrics import ClassifyMetrics, ConfusionMatrix -from ultralytics.utils.plotting import plot_images - - -class ClassificationValidator(BaseValidator): - """ - A class extending the BaseValidator class for validation based on a classification model. - - Notes: - - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'. - - Example: - ```python - from ultralytics.models.yolo.classify import ClassificationValidator - - args = dict(model='yolov8n-cls.pt', data='imagenet10') - validator = ClassificationValidator(args=args) - validator() - ``` - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """Initializes ClassificationValidator instance with args, dataloader, save_dir, and progress bar.""" - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.targets = None - self.pred = None - self.args.task = "classify" - self.metrics = ClassifyMetrics() - - def get_desc(self): - """Returns a formatted string summarizing classification metrics.""" - return ("%22s" + "%11s" * 2) % ("classes", "top1_acc", "top5_acc") - - def init_metrics(self, model): - """Initialize confusion matrix, class names, and top-1 and top-5 accuracy.""" - self.names = model.names - self.nc = len(model.names) - self.confusion_matrix = ConfusionMatrix(nc=self.nc, conf=self.args.conf, task="classify") - self.pred = [] - self.targets = [] - - def preprocess(self, batch): - """Preprocesses input batch and returns it.""" - batch["img"] = batch["img"].to(self.device, non_blocking=True) - batch["img"] = batch["img"].half() if self.args.half else batch["img"].float() - batch["cls"] = batch["cls"].to(self.device) - return batch - - def update_metrics(self, preds, batch): - """Updates running metrics with model predictions and batch targets.""" - n5 = min(len(self.names), 5) - self.pred.append(preds.argsort(1, descending=True)[:, :n5]) - self.targets.append(batch["cls"]) - - def finalize_metrics(self, *args, **kwargs): - """Finalizes metrics of the model such as confusion_matrix and speed.""" - self.confusion_matrix.process_cls_preds(self.pred, self.targets) - if self.args.plots: - for normalize in True, False: - self.confusion_matrix.plot( - save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot - ) - self.metrics.speed = self.speed - self.metrics.confusion_matrix = self.confusion_matrix - self.metrics.save_dir = self.save_dir - - def get_stats(self): - """Returns a dictionary of metrics obtained by processing targets and predictions.""" - self.metrics.process(self.targets, self.pred) - return self.metrics.results_dict - - def build_dataset(self, img_path): - """Creates and returns a ClassificationDataset instance using given image path and preprocessing parameters.""" - return ClassificationDataset(root=img_path, args=self.args, augment=False, prefix=self.args.split) - - def get_dataloader(self, dataset_path, batch_size): - """Builds and returns a data loader for classification tasks with given parameters.""" - dataset = self.build_dataset(dataset_path) - return build_dataloader(dataset, batch_size, self.args.workers, rank=-1) - - def print_results(self): - """Prints evaluation metrics for YOLO object detection model.""" - pf = "%22s" + "%11.3g" * len(self.metrics.keys) # print format - LOGGER.info(pf % ("all", self.metrics.top1, self.metrics.top5)) - - def plot_val_samples(self, batch, ni): - """Plot validation image samples.""" - plot_images( - images=batch["img"], - batch_idx=torch.arange(len(batch["img"])), - cls=batch["cls"].view(-1), # warning: use .view(), not .squeeze() for Classify models - fname=self.save_dir / f"val_batch{ni}_labels.jpg", - names=self.names, - on_plot=self.on_plot, - ) - - def plot_predictions(self, batch, preds, ni): - """Plots predicted bounding boxes on input images and saves the result.""" - plot_images( - batch["img"], - batch_idx=torch.arange(len(batch["img"])), - cls=torch.argmax(preds, dim=1), - fname=self.save_dir / f"val_batch{ni}_pred.jpg", - names=self.names, - on_plot=self.on_plot, - ) # pred diff --git a/ultralytics-main/ultralytics/models/yolo/detect/__init__.py b/ultralytics-main/ultralytics/models/yolo/detect/__init__.py deleted file mode 100644 index 5f3e62c..0000000 --- a/ultralytics-main/ultralytics/models/yolo/detect/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .predict import DetectionPredictor -from .train import DetectionTrainer -from .val import DetectionValidator - -__all__ = "DetectionPredictor", "DetectionTrainer", "DetectionValidator" diff --git a/ultralytics-main/ultralytics/models/yolo/detect/predict.py b/ultralytics-main/ultralytics/models/yolo/detect/predict.py deleted file mode 100644 index 3a0c628..0000000 --- a/ultralytics-main/ultralytics/models/yolo/detect/predict.py +++ /dev/null @@ -1,43 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.engine.predictor import BasePredictor -from ultralytics.engine.results import Results -from ultralytics.utils import ops - - -class DetectionPredictor(BasePredictor): - """ - A class extending the BasePredictor class for prediction based on a detection model. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.yolo.detect import DetectionPredictor - - args = dict(model='yolov8n.pt', source=ASSETS) - predictor = DetectionPredictor(overrides=args) - predictor.predict_cli() - ``` - """ - - def postprocess(self, preds, img, orig_imgs): - """Post-processes predictions and returns a list of Results objects.""" - preds = ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - classes=self.args.classes, - ) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, pred in enumerate(preds): - orig_img = orig_imgs[i] - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - img_path = self.batch[0][i] - results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred)) - return results diff --git a/ultralytics-main/ultralytics/models/yolo/detect/train.py b/ultralytics-main/ultralytics/models/yolo/detect/train.py deleted file mode 100644 index 3326512..0000000 --- a/ultralytics-main/ultralytics/models/yolo/detect/train.py +++ /dev/null @@ -1,143 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math -import random -from copy import copy - -import numpy as np -import torch.nn as nn - -from ultralytics.data import build_dataloader, build_yolo_dataset -from ultralytics.engine.trainer import BaseTrainer -from ultralytics.models import yolo -from ultralytics.nn.tasks import DetectionModel -from ultralytics.utils import LOGGER, RANK -from ultralytics.utils.plotting import plot_images, plot_labels, plot_results -from ultralytics.utils.torch_utils import de_parallel, torch_distributed_zero_first - - -class DetectionTrainer(BaseTrainer): - """ - A class extending the BaseTrainer class for training based on a detection model. - - Example: - ```python - from ultralytics.models.yolo.detect import DetectionTrainer - - args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3) - trainer = DetectionTrainer(overrides=args) - trainer.train() - ``` - """ - - def build_dataset(self, img_path, mode="train", batch=None): - """ - Build YOLO Dataset. - - Args: - img_path (str): Path to the folder containing images. - mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode. - batch (int, optional): Size of batches, this is for `rect`. Defaults to None. - """ - gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32) - return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs) - - def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"): - """Construct and return dataloader.""" - assert mode in ["train", "val"] - with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP - dataset = self.build_dataset(dataset_path, mode, batch_size) - shuffle = mode == "train" - if getattr(dataset, "rect", False) and shuffle: - LOGGER.warning("WARNING ⚠️ 'rect=True' is incompatible with DataLoader shuffle, setting shuffle=False") - shuffle = False - workers = self.args.workers if mode == "train" else self.args.workers * 2 - return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader - - def preprocess_batch(self, batch): - """Preprocesses a batch of images by scaling and converting to float.""" - batch["img"] = batch["img"].to(self.device, non_blocking=True).float() / 255 - if self.args.multi_scale: - imgs = batch["img"] - sz = ( - random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride) - // self.stride - * self.stride - ) # size - sf = sz / max(imgs.shape[2:]) # scale factor - if sf != 1: - ns = [ - math.ceil(x * sf / self.stride) * self.stride for x in imgs.shape[2:] - ] # new shape (stretched to gs-multiple) - imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False) - batch["img"] = imgs - return batch - - def set_model_attributes(self): - """Nl = de_parallel(self.model).model[-1].nl # number of detection layers (to scale hyps).""" - # self.args.box *= 3 / nl # scale to layers - # self.args.cls *= self.data["nc"] / 80 * 3 / nl # scale to classes and layers - # self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl # scale to image size and layers - self.model.nc = self.data["nc"] # attach number of classes to model - self.model.names = self.data["names"] # attach class names to model - self.model.args = self.args # attach hyperparameters to model - # TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc - - def get_model(self, cfg=None, weights=None, verbose=True): - """Return a YOLO detection model.""" - model = DetectionModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1) - if weights: - model.load(weights) - return model - - def get_validator(self): - """Returns a DetectionValidator for YOLO model validation.""" - self.loss_names = "box_loss", "cls_loss", "dfl_loss" - return yolo.detect.DetectionValidator( - self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks - ) - - def label_loss_items(self, loss_items=None, prefix="train"): - """ - Returns a loss dict with labelled training loss items tensor. - - Not needed for classification but necessary for segmentation & detection - """ - keys = [f"{prefix}/{x}" for x in self.loss_names] - if loss_items is not None: - loss_items = [round(float(x), 5) for x in loss_items] # convert tensors to 5 decimal place floats - return dict(zip(keys, loss_items)) - else: - return keys - - def progress_string(self): - """Returns a formatted string of training progress with epoch, GPU memory, loss, instances and size.""" - return ("\n" + "%11s" * (4 + len(self.loss_names))) % ( - "Epoch", - "GPU_mem", - *self.loss_names, - "Instances", - "Size", - ) - - def plot_training_samples(self, batch, ni): - """Plots training samples with their annotations.""" - plot_images( - images=batch["img"], - batch_idx=batch["batch_idx"], - cls=batch["cls"].squeeze(-1), - bboxes=batch["bboxes"], - paths=batch["im_file"], - fname=self.save_dir / f"train_batch{ni}.jpg", - on_plot=self.on_plot, - ) - - def plot_metrics(self): - """Plots metrics from a CSV file.""" - plot_results(file=self.csv, on_plot=self.on_plot) # save results.png - - def plot_training_labels(self): - """Create a labeled training plot of the YOLO model.""" - boxes = np.concatenate([lb["bboxes"] for lb in self.train_loader.dataset.labels], 0) - cls = np.concatenate([lb["cls"] for lb in self.train_loader.dataset.labels], 0) - plot_labels(boxes, cls.squeeze(), names=self.data["names"], save_dir=self.save_dir, on_plot=self.on_plot) diff --git a/ultralytics-main/ultralytics/models/yolo/detect/val.py b/ultralytics-main/ultralytics/models/yolo/detect/val.py deleted file mode 100644 index 8226cd6..0000000 --- a/ultralytics-main/ultralytics/models/yolo/detect/val.py +++ /dev/null @@ -1,299 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import os -from pathlib import Path - -import numpy as np -import torch - -from ultralytics.data import build_dataloader, build_yolo_dataset, converter -from ultralytics.engine.validator import BaseValidator -from ultralytics.utils import LOGGER, ops -from ultralytics.utils.checks import check_requirements -from ultralytics.utils.metrics import ConfusionMatrix, DetMetrics, box_iou -from ultralytics.utils.plotting import output_to_target, plot_images - - -class DetectionValidator(BaseValidator): - """ - A class extending the BaseValidator class for validation based on a detection model. - - Example: - ```python - from ultralytics.models.yolo.detect import DetectionValidator - - args = dict(model='yolov8n.pt', data='coco8.yaml') - validator = DetectionValidator(args=args) - validator() - ``` - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """Initialize detection model with necessary variables and settings.""" - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.nt_per_class = None - self.is_coco = False - self.class_map = None - self.args.task = "detect" - self.metrics = DetMetrics(save_dir=self.save_dir, on_plot=self.on_plot) - self.iouv = torch.linspace(0.5, 0.95, 10) # IoU vector for mAP@0.5:0.95 - self.niou = self.iouv.numel() - self.lb = [] # for autolabelling - - def preprocess(self, batch): - """Preprocesses batch of images for YOLO training.""" - batch["img"] = batch["img"].to(self.device, non_blocking=True) - batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255 - for k in ["batch_idx", "cls", "bboxes"]: - batch[k] = batch[k].to(self.device) - - if self.args.save_hybrid: - height, width = batch["img"].shape[2:] - nb = len(batch["img"]) - bboxes = batch["bboxes"] * torch.tensor((width, height, width, height), device=self.device) - self.lb = ( - [ - torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1) - for i in range(nb) - ] - if self.args.save_hybrid - else [] - ) # for autolabelling - - return batch - - def init_metrics(self, model): - """Initialize evaluation metrics for YOLO.""" - val = self.data.get(self.args.split, "") # validation path - self.is_coco = isinstance(val, str) and "coco" in val and val.endswith(f"{os.sep}val2017.txt") # is COCO - self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1000)) - self.args.save_json |= self.is_coco and not self.training # run on final val if training COCO - self.names = model.names - self.nc = len(model.names) - self.metrics.names = self.names - self.metrics.plot = self.args.plots - self.confusion_matrix = ConfusionMatrix(nc=self.nc, conf=self.args.conf) - self.seen = 0 - self.jdict = [] - self.stats = dict(tp=[], conf=[], pred_cls=[], target_cls=[]) - - def get_desc(self): - """Return a formatted string summarizing class metrics of YOLO model.""" - return ("%22s" + "%11s" * 6) % ("Class", "Images", "Instances", "Box(P", "R", "mAP50", "mAP50-95)") - - def postprocess(self, preds): - """Apply Non-maximum suppression to prediction outputs.""" - return ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - labels=self.lb, - multi_label=True, - agnostic=self.args.single_cls, - max_det=self.args.max_det, - ) - - def _prepare_batch(self, si, batch): - """Prepares a batch of images and annotations for validation.""" - idx = batch["batch_idx"] == si - cls = batch["cls"][idx].squeeze(-1) - bbox = batch["bboxes"][idx] - ori_shape = batch["ori_shape"][si] - imgsz = batch["img"].shape[2:] - ratio_pad = batch["ratio_pad"][si] - if len(cls): - bbox = ops.xywh2xyxy(bbox) * torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]] # target boxes - ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad) # native-space labels - return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad) - - def _prepare_pred(self, pred, pbatch): - """Prepares a batch of images and annotations for validation.""" - predn = pred.clone() - ops.scale_boxes( - pbatch["imgsz"], predn[:, :4], pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"] - ) # native-space pred - return predn - - def update_metrics(self, preds, batch): - """Metrics.""" - for si, pred in enumerate(preds): - self.seen += 1 - npr = len(pred) - stat = dict( - conf=torch.zeros(0, device=self.device), - pred_cls=torch.zeros(0, device=self.device), - tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device), - ) - pbatch = self._prepare_batch(si, batch) - cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox") - nl = len(cls) - stat["target_cls"] = cls - if npr == 0: - if nl: - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - if self.args.plots: - self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls) - continue - - # Predictions - if self.args.single_cls: - pred[:, 5] = 0 - predn = self._prepare_pred(pred, pbatch) - stat["conf"] = predn[:, 4] - stat["pred_cls"] = predn[:, 5] - - # Evaluate - if nl: - stat["tp"] = self._process_batch(predn, bbox, cls) - if self.args.plots: - self.confusion_matrix.process_batch(predn, bbox, cls) - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - - # Save - if self.args.save_json: - self.pred_to_json(predn, batch["im_file"][si]) - if self.args.save_txt: - file = self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt' - self.save_one_txt(predn, self.args.save_conf, pbatch["ori_shape"], file) - - def finalize_metrics(self, *args, **kwargs): - """Set final values for metrics speed and confusion matrix.""" - self.metrics.speed = self.speed - self.metrics.confusion_matrix = self.confusion_matrix - - def get_stats(self): - """Returns metrics statistics and results dictionary.""" - stats = {k: torch.cat(v, 0).cpu().numpy() for k, v in self.stats.items()} # to numpy - if len(stats) and stats["tp"].any(): - self.metrics.process(**stats) - self.nt_per_class = np.bincount( - stats["target_cls"].astype(int), minlength=self.nc - ) # number of targets per class - return self.metrics.results_dict - - def print_results(self): - """Prints training/validation set metrics per class.""" - pf = "%22s" + "%11i" * 2 + "%11.3g" * len(self.metrics.keys) # print format - LOGGER.info(pf % ("all", self.seen, self.nt_per_class.sum(), *self.metrics.mean_results())) - if self.nt_per_class.sum() == 0: - LOGGER.warning(f"WARNING ⚠️ no labels found in {self.args.task} set, can not compute metrics without labels") - - # Print results per class - if self.args.verbose and not self.training and self.nc > 1 and len(self.stats): - for i, c in enumerate(self.metrics.ap_class_index): - LOGGER.info(pf % (self.names[c], self.seen, self.nt_per_class[c], *self.metrics.class_result(i))) - - if self.args.plots: - for normalize in True, False: - self.confusion_matrix.plot( - save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot - ) - - def _process_batch(self, detections, gt_bboxes, gt_cls): - """ - Return correct prediction matrix. - - Args: - detections (torch.Tensor): Tensor of shape [N, 6] representing detections. - Each detection is of the format: x1, y1, x2, y2, conf, class. - labels (torch.Tensor): Tensor of shape [M, 5] representing labels. - Each label is of the format: class, x1, y1, x2, y2. - - Returns: - (torch.Tensor): Correct prediction matrix of shape [N, 10] for 10 IoU levels. - """ - iou = box_iou(gt_bboxes, detections[:, :4]) - return self.match_predictions(detections[:, 5], gt_cls, iou) - - def build_dataset(self, img_path, mode="val", batch=None): - """ - Build YOLO Dataset. - - Args: - img_path (str): Path to the folder containing images. - mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode. - batch (int, optional): Size of batches, this is for `rect`. Defaults to None. - """ - return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, stride=self.stride) - - def get_dataloader(self, dataset_path, batch_size): - """Construct and return dataloader.""" - dataset = self.build_dataset(dataset_path, batch=batch_size, mode="val") - return build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1) # return dataloader - - def plot_val_samples(self, batch, ni): - """Plot validation image samples.""" - plot_images( - batch["img"], - batch["batch_idx"], - batch["cls"].squeeze(-1), - batch["bboxes"], - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_labels.jpg", - names=self.names, - on_plot=self.on_plot, - ) - - def plot_predictions(self, batch, preds, ni): - """Plots predicted bounding boxes on input images and saves the result.""" - plot_images( - batch["img"], - *output_to_target(preds, max_det=self.args.max_det), - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_pred.jpg", - names=self.names, - on_plot=self.on_plot, - ) # pred - - def save_one_txt(self, predn, save_conf, shape, file): - """Save YOLO detections to a txt file in normalized coordinates in a specific format.""" - gn = torch.tensor(shape)[[1, 0, 1, 0]] # normalization gain whwh - for *xyxy, conf, cls in predn.tolist(): - xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh - line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format - with open(file, "a") as f: - f.write(("%g " * len(line)).rstrip() % line + "\n") - - def pred_to_json(self, predn, filename): - """Serialize YOLO predictions to COCO json format.""" - stem = Path(filename).stem - image_id = int(stem) if stem.isnumeric() else stem - box = ops.xyxy2xywh(predn[:, :4]) # xywh - box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner - for p, b in zip(predn.tolist(), box.tolist()): - self.jdict.append( - { - "image_id": image_id, - "category_id": self.class_map[int(p[5])], - "bbox": [round(x, 3) for x in b], - "score": round(p[4], 5), - } - ) - - def eval_json(self, stats): - """Evaluates YOLO output in JSON format and returns performance statistics.""" - if self.args.save_json and self.is_coco and len(self.jdict): - anno_json = self.data["path"] / "annotations/instances_val2017.json" # annotations - pred_json = self.save_dir / "predictions.json" # predictions - LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...") - try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb - check_requirements("pycocotools>=2.0.6") - from pycocotools.coco import COCO # noqa - from pycocotools.cocoeval import COCOeval # noqa - - for x in anno_json, pred_json: - assert x.is_file(), f"{x} file not found" - anno = COCO(str(anno_json)) # init annotations api - pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path) - eval = COCOeval(anno, pred, "bbox") - if self.is_coco: - eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval - eval.evaluate() - eval.accumulate() - eval.summarize() - stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2] # update mAP50-95 and mAP50 - except Exception as e: - LOGGER.warning(f"pycocotools unable to run: {e}") - return stats diff --git a/ultralytics-main/ultralytics/models/yolo/model.py b/ultralytics-main/ultralytics/models/yolo/model.py deleted file mode 100644 index 1bd38d3..0000000 --- a/ultralytics-main/ultralytics/models/yolo/model.py +++ /dev/null @@ -1,106 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from pathlib import Path - -from ultralytics.engine.model import Model -from ultralytics.models import yolo -from ultralytics.nn.tasks import ClassificationModel, DetectionModel, OBBModel, PoseModel, SegmentationModel, WorldModel -from ultralytics.utils import yaml_load, ROOT - - -class YOLO(Model): - """YOLO (You Only Look Once) object detection model.""" - - def __init__(self, model="yolov8n.pt", task=None, verbose=False): - """Initialize YOLO model, switching to YOLOWorld if model filename contains '-world'.""" - path = Path(model) - if "-world" in path.stem and path.suffix in {".pt", ".yaml", ".yml"}: # if YOLOWorld PyTorch model - new_instance = YOLOWorld(path) - self.__class__ = type(new_instance) - self.__dict__ = new_instance.__dict__ - else: - # Continue with default YOLO initialization - super().__init__(model=model, task=task, verbose=verbose) - - @property - def task_map(self): - """Map head to model, trainer, validator, and predictor classes.""" - return { - "classify": { - "model": ClassificationModel, - "trainer": yolo.classify.ClassificationTrainer, - "validator": yolo.classify.ClassificationValidator, - "predictor": yolo.classify.ClassificationPredictor, - }, - "detect": { - "model": DetectionModel, - "trainer": yolo.detect.DetectionTrainer, - "validator": yolo.detect.DetectionValidator, - "predictor": yolo.detect.DetectionPredictor, - }, - "segment": { - "model": SegmentationModel, - "trainer": yolo.segment.SegmentationTrainer, - "validator": yolo.segment.SegmentationValidator, - "predictor": yolo.segment.SegmentationPredictor, - }, - "pose": { - "model": PoseModel, - "trainer": yolo.pose.PoseTrainer, - "validator": yolo.pose.PoseValidator, - "predictor": yolo.pose.PosePredictor, - }, - "obb": { - "model": OBBModel, - "trainer": yolo.obb.OBBTrainer, - "validator": yolo.obb.OBBValidator, - "predictor": yolo.obb.OBBPredictor, - }, - } - - -class YOLOWorld(Model): - """YOLO-World object detection model.""" - - def __init__(self, model="yolov8s-world.pt") -> None: - """ - Initializes the YOLOv8-World model with the given pre-trained model file. Supports *.pt and *.yaml formats. - - Args: - model (str | Path): Path to the pre-trained model. Defaults to 'yolov8s-world.pt'. - """ - super().__init__(model=model, task="detect") - - # Assign default COCO class names when there are no custom names - if not hasattr(self.model, "names"): - self.model.names = yaml_load(ROOT / "cfg/datasets/coco8.yaml").get("names") - - @property - def task_map(self): - """Map head to model, validator, and predictor classes.""" - return { - "detect": { - "model": WorldModel, - "validator": yolo.detect.DetectionValidator, - "predictor": yolo.detect.DetectionPredictor, - } - } - - def set_classes(self, classes): - """ - Set classes. - - Args: - classes (List(str)): A list of categories i.e ["person"]. - """ - self.model.set_classes(classes) - # Remove background if it's given - background = " " - if background in classes: - classes.remove(background) - self.model.names = classes - - # Reset method class names - # self.predictor = None # reset predictor otherwise old names remain - if self.predictor: - self.predictor.model.names = classes diff --git a/ultralytics-main/ultralytics/models/yolo/obb/__init__.py b/ultralytics-main/ultralytics/models/yolo/obb/__init__.py deleted file mode 100644 index f60349a..0000000 --- a/ultralytics-main/ultralytics/models/yolo/obb/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .predict import OBBPredictor -from .train import OBBTrainer -from .val import OBBValidator - -__all__ = "OBBPredictor", "OBBTrainer", "OBBValidator" diff --git a/ultralytics-main/ultralytics/models/yolo/obb/predict.py b/ultralytics-main/ultralytics/models/yolo/obb/predict.py deleted file mode 100644 index bb8d4d3..0000000 --- a/ultralytics-main/ultralytics/models/yolo/obb/predict.py +++ /dev/null @@ -1,53 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch - -from ultralytics.engine.results import Results -from ultralytics.models.yolo.detect.predict import DetectionPredictor -from ultralytics.utils import DEFAULT_CFG, ops - - -class OBBPredictor(DetectionPredictor): - """ - A class extending the DetectionPredictor class for prediction based on an Oriented Bounding Box (OBB) model. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.yolo.obb import OBBPredictor - - args = dict(model='yolov8n-obb.pt', source=ASSETS) - predictor = OBBPredictor(overrides=args) - predictor.predict_cli() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initializes OBBPredictor with optional model and data configuration overrides.""" - super().__init__(cfg, overrides, _callbacks) - self.args.task = "obb" - - def postprocess(self, preds, img, orig_imgs): - """Post-processes predictions and returns a list of Results objects.""" - preds = ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - nc=len(self.model.names), - classes=self.args.classes, - rotated=True, - ) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0]): - rboxes = ops.regularize_rboxes(torch.cat([pred[:, :4], pred[:, -1:]], dim=-1)) - rboxes[:, :4] = ops.scale_boxes(img.shape[2:], rboxes[:, :4], orig_img.shape, xywh=True) - # xywh, r, conf, cls - obb = torch.cat([rboxes, pred[:, 4:6]], dim=-1) - results.append(Results(orig_img, path=img_path, names=self.model.names, obb=obb)) - return results diff --git a/ultralytics-main/ultralytics/models/yolo/obb/train.py b/ultralytics-main/ultralytics/models/yolo/obb/train.py deleted file mode 100644 index 40a35a9..0000000 --- a/ultralytics-main/ultralytics/models/yolo/obb/train.py +++ /dev/null @@ -1,42 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from copy import copy - -from ultralytics.models import yolo -from ultralytics.nn.tasks import OBBModel -from ultralytics.utils import DEFAULT_CFG, RANK - - -class OBBTrainer(yolo.detect.DetectionTrainer): - """ - A class extending the DetectionTrainer class for training based on an Oriented Bounding Box (OBB) model. - - Example: - ```python - from ultralytics.models.yolo.obb import OBBTrainer - - args = dict(model='yolov8n-obb.pt', data='dota8.yaml', epochs=3) - trainer = OBBTrainer(overrides=args) - trainer.train() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initialize a OBBTrainer object with given arguments.""" - if overrides is None: - overrides = {} - overrides["task"] = "obb" - super().__init__(cfg, overrides, _callbacks) - - def get_model(self, cfg=None, weights=None, verbose=True): - """Return OBBModel initialized with specified config and weights.""" - model = OBBModel(cfg, ch=3, nc=self.data["nc"], verbose=verbose and RANK == -1) - if weights: - model.load(weights) - - return model - - def get_validator(self): - """Return an instance of OBBValidator for validation of YOLO model.""" - self.loss_names = "box_loss", "cls_loss", "dfl_loss" - return yolo.obb.OBBValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args)) diff --git a/ultralytics-main/ultralytics/models/yolo/obb/val.py b/ultralytics-main/ultralytics/models/yolo/obb/val.py deleted file mode 100644 index c440fe2..0000000 --- a/ultralytics-main/ultralytics/models/yolo/obb/val.py +++ /dev/null @@ -1,185 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from pathlib import Path - -import torch - -from ultralytics.models.yolo.detect import DetectionValidator -from ultralytics.utils import LOGGER, ops -from ultralytics.utils.metrics import OBBMetrics, batch_probiou -from ultralytics.utils.plotting import output_to_rotated_target, plot_images - - -class OBBValidator(DetectionValidator): - """ - A class extending the DetectionValidator class for validation based on an Oriented Bounding Box (OBB) model. - - Example: - ```python - from ultralytics.models.yolo.obb import OBBValidator - - args = dict(model='yolov8n-obb.pt', data='dota8.yaml') - validator = OBBValidator(args=args) - validator(model=args['model']) - ``` - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """Initialize OBBValidator and set task to 'obb', metrics to OBBMetrics.""" - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.args.task = "obb" - self.metrics = OBBMetrics(save_dir=self.save_dir, plot=True, on_plot=self.on_plot) - - def init_metrics(self, model): - """Initialize evaluation metrics for YOLO.""" - super().init_metrics(model) - val = self.data.get(self.args.split, "") # validation path - self.is_dota = isinstance(val, str) and "DOTA" in val # is COCO - - def postprocess(self, preds): - """Apply Non-maximum suppression to prediction outputs.""" - return ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - labels=self.lb, - nc=self.nc, - multi_label=True, - agnostic=self.args.single_cls, - max_det=self.args.max_det, - rotated=True, - ) - - def _process_batch(self, detections, gt_bboxes, gt_cls): - """ - Return correct prediction matrix. - - Args: - detections (torch.Tensor): Tensor of shape [N, 7] representing detections. - Each detection is of the format: x1, y1, x2, y2, conf, class, angle. - gt_bboxes (torch.Tensor): Tensor of shape [M, 5] representing rotated boxes. - Each box is of the format: x1, y1, x2, y2, angle. - labels (torch.Tensor): Tensor of shape [M] representing labels. - - Returns: - (torch.Tensor): Correct prediction matrix of shape [N, 10] for 10 IoU levels. - """ - iou = batch_probiou(gt_bboxes, torch.cat([detections[:, :4], detections[:, -1:]], dim=-1)) - return self.match_predictions(detections[:, 5], gt_cls, iou) - - def _prepare_batch(self, si, batch): - """Prepares and returns a batch for OBB validation.""" - idx = batch["batch_idx"] == si - cls = batch["cls"][idx].squeeze(-1) - bbox = batch["bboxes"][idx] - ori_shape = batch["ori_shape"][si] - imgsz = batch["img"].shape[2:] - ratio_pad = batch["ratio_pad"][si] - if len(cls): - bbox[..., :4].mul_(torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]]) # target boxes - ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad, xywh=True) # native-space labels - return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad) - - def _prepare_pred(self, pred, pbatch): - """Prepares and returns a batch for OBB validation with scaled and padded bounding boxes.""" - predn = pred.clone() - ops.scale_boxes( - pbatch["imgsz"], predn[:, :4], pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"], xywh=True - ) # native-space pred - return predn - - def plot_predictions(self, batch, preds, ni): - """Plots predicted bounding boxes on input images and saves the result.""" - plot_images( - batch["img"], - *output_to_rotated_target(preds, max_det=self.args.max_det), - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_pred.jpg", - names=self.names, - on_plot=self.on_plot, - ) # pred - - def pred_to_json(self, predn, filename): - """Serialize YOLO predictions to COCO json format.""" - stem = Path(filename).stem - image_id = int(stem) if stem.isnumeric() else stem - rbox = torch.cat([predn[:, :4], predn[:, -1:]], dim=-1) - poly = ops.xywhr2xyxyxyxy(rbox).view(-1, 8) - for i, (r, b) in enumerate(zip(rbox.tolist(), poly.tolist())): - self.jdict.append( - { - "image_id": image_id, - "category_id": self.class_map[int(predn[i, 5].item())], - "score": round(predn[i, 4].item(), 5), - "rbox": [round(x, 3) for x in r], - "poly": [round(x, 3) for x in b], - } - ) - - def save_one_txt(self, predn, save_conf, shape, file): - """Save YOLO detections to a txt file in normalized coordinates in a specific format.""" - gn = torch.tensor(shape)[[1, 0]] # normalization gain whwh - for *xywh, conf, cls, angle in predn.tolist(): - xywha = torch.tensor([*xywh, angle]).view(1, 5) - xyxyxyxy = (ops.xywhr2xyxyxyxy(xywha) / gn).view(-1).tolist() # normalized xywh - line = (cls, *xyxyxyxy, conf) if save_conf else (cls, *xyxyxyxy) # label format - with open(file, "a") as f: - f.write(("%g " * len(line)).rstrip() % line + "\n") - - def eval_json(self, stats): - """Evaluates YOLO output in JSON format and returns performance statistics.""" - if self.args.save_json and self.is_dota and len(self.jdict): - import json - import re - from collections import defaultdict - - pred_json = self.save_dir / "predictions.json" # predictions - pred_txt = self.save_dir / "predictions_txt" # predictions - pred_txt.mkdir(parents=True, exist_ok=True) - data = json.load(open(pred_json)) - # Save split results - LOGGER.info(f"Saving predictions with DOTA format to {pred_txt}...") - for d in data: - image_id = d["image_id"] - score = d["score"] - classname = self.names[d["category_id"]].replace(" ", "-") - p = d["poly"] - - with open(f'{pred_txt / f"Task1_{classname}"}.txt', "a") as f: - f.writelines(f"{image_id} {score} {p[0]} {p[1]} {p[2]} {p[3]} {p[4]} {p[5]} {p[6]} {p[7]}\n") - # Save merged results, this could result slightly lower map than using official merging script, - # because of the probiou calculation. - pred_merged_txt = self.save_dir / "predictions_merged_txt" # predictions - pred_merged_txt.mkdir(parents=True, exist_ok=True) - merged_results = defaultdict(list) - LOGGER.info(f"Saving merged predictions with DOTA format to {pred_merged_txt}...") - for d in data: - image_id = d["image_id"].split("__")[0] - pattern = re.compile(r"\d+___\d+") - x, y = (int(c) for c in re.findall(pattern, d["image_id"])[0].split("___")) - bbox, score, cls = d["rbox"], d["score"], d["category_id"] - bbox[0] += x - bbox[1] += y - bbox.extend([score, cls]) - merged_results[image_id].append(bbox) - for image_id, bbox in merged_results.items(): - bbox = torch.tensor(bbox) - max_wh = torch.max(bbox[:, :2]).item() * 2 - c = bbox[:, 6:7] * max_wh # classes - scores = bbox[:, 5] # scores - b = bbox[:, :5].clone() - b[:, :2] += c - # 0.3 could get results close to the ones from official merging script, even slightly better. - i = ops.nms_rotated(b, scores, 0.3) - bbox = bbox[i] - - b = ops.xywhr2xyxyxyxy(bbox[:, :5]).view(-1, 8) - for x in torch.cat([b, bbox[:, 5:7]], dim=-1).tolist(): - classname = self.names[int(x[-1])].replace(" ", "-") - p = [round(i, 3) for i in x[:-2]] # poly - score = round(x[-2], 3) - - with open(f'{pred_merged_txt / f"Task1_{classname}"}.txt', "a") as f: - f.writelines(f"{image_id} {score} {p[0]} {p[1]} {p[2]} {p[3]} {p[4]} {p[5]} {p[6]} {p[7]}\n") - - return stats diff --git a/ultralytics-main/ultralytics/models/yolo/pose/__init__.py b/ultralytics-main/ultralytics/models/yolo/pose/__init__.py deleted file mode 100644 index d566943..0000000 --- a/ultralytics-main/ultralytics/models/yolo/pose/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .predict import PosePredictor -from .train import PoseTrainer -from .val import PoseValidator - -__all__ = "PoseTrainer", "PoseValidator", "PosePredictor" diff --git a/ultralytics-main/ultralytics/models/yolo/pose/predict.py b/ultralytics-main/ultralytics/models/yolo/pose/predict.py deleted file mode 100644 index 7c55709..0000000 --- a/ultralytics-main/ultralytics/models/yolo/pose/predict.py +++ /dev/null @@ -1,58 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.engine.results import Results -from ultralytics.models.yolo.detect.predict import DetectionPredictor -from ultralytics.utils import DEFAULT_CFG, LOGGER, ops - - -class PosePredictor(DetectionPredictor): - """ - A class extending the DetectionPredictor class for prediction based on a pose model. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.yolo.pose import PosePredictor - - args = dict(model='yolov8n-pose.pt', source=ASSETS) - predictor = PosePredictor(overrides=args) - predictor.predict_cli() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initializes PosePredictor, sets task to 'pose' and logs a warning for using 'mps' as device.""" - super().__init__(cfg, overrides, _callbacks) - self.args.task = "pose" - if isinstance(self.args.device, str) and self.args.device.lower() == "mps": - LOGGER.warning( - "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. " - "See https://github.com/ultralytics/ultralytics/issues/4031." - ) - - def postprocess(self, preds, img, orig_imgs): - """Return detection results for a given input image or list of images.""" - preds = ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - classes=self.args.classes, - nc=len(self.model.names), - ) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - for i, pred in enumerate(preds): - orig_img = orig_imgs[i] - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape).round() - pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:] - pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, orig_img.shape) - img_path = self.batch[0][i] - results.append( - Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], keypoints=pred_kpts) - ) - return results diff --git a/ultralytics-main/ultralytics/models/yolo/pose/train.py b/ultralytics-main/ultralytics/models/yolo/pose/train.py deleted file mode 100644 index f5229e5..0000000 --- a/ultralytics-main/ultralytics/models/yolo/pose/train.py +++ /dev/null @@ -1,79 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from copy import copy - -from ultralytics.models import yolo -from ultralytics.nn.tasks import PoseModel -from ultralytics.utils import DEFAULT_CFG, LOGGER -from ultralytics.utils.plotting import plot_images, plot_results - - -class PoseTrainer(yolo.detect.DetectionTrainer): - """ - A class extending the DetectionTrainer class for training based on a pose model. - - Example: - ```python - from ultralytics.models.yolo.pose import PoseTrainer - - args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml', epochs=3) - trainer = PoseTrainer(overrides=args) - trainer.train() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initialize a PoseTrainer object with specified configurations and overrides.""" - if overrides is None: - overrides = {} - overrides["task"] = "pose" - super().__init__(cfg, overrides, _callbacks) - - if isinstance(self.args.device, str) and self.args.device.lower() == "mps": - LOGGER.warning( - "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. " - "See https://github.com/ultralytics/ultralytics/issues/4031." - ) - - def get_model(self, cfg=None, weights=None, verbose=True): - """Get pose estimation model with specified configuration and weights.""" - model = PoseModel(cfg, ch=3, nc=self.data["nc"], data_kpt_shape=self.data["kpt_shape"], verbose=verbose) - if weights: - model.load(weights) - - return model - - def set_model_attributes(self): - """Sets keypoints shape attribute of PoseModel.""" - super().set_model_attributes() - self.model.kpt_shape = self.data["kpt_shape"] - - def get_validator(self): - """Returns an instance of the PoseValidator class for validation.""" - self.loss_names = "box_loss", "pose_loss", "kobj_loss", "cls_loss", "dfl_loss" - return yolo.pose.PoseValidator( - self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks - ) - - def plot_training_samples(self, batch, ni): - """Plot a batch of training samples with annotated class labels, bounding boxes, and keypoints.""" - images = batch["img"] - kpts = batch["keypoints"] - cls = batch["cls"].squeeze(-1) - bboxes = batch["bboxes"] - paths = batch["im_file"] - batch_idx = batch["batch_idx"] - plot_images( - images, - batch_idx, - cls, - bboxes, - kpts=kpts, - paths=paths, - fname=self.save_dir / f"train_batch{ni}.jpg", - on_plot=self.on_plot, - ) - - def plot_metrics(self): - """Plots training/val metrics.""" - plot_results(file=self.csv, pose=True, on_plot=self.on_plot) # save results.png diff --git a/ultralytics-main/ultralytics/models/yolo/pose/val.py b/ultralytics-main/ultralytics/models/yolo/pose/val.py deleted file mode 100644 index 8405686..0000000 --- a/ultralytics-main/ultralytics/models/yolo/pose/val.py +++ /dev/null @@ -1,248 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from pathlib import Path - -import numpy as np -import torch - -from ultralytics.models.yolo.detect import DetectionValidator -from ultralytics.utils import LOGGER, ops -from ultralytics.utils.checks import check_requirements -from ultralytics.utils.metrics import OKS_SIGMA, PoseMetrics, box_iou, kpt_iou -from ultralytics.utils.plotting import output_to_target, plot_images - - -class PoseValidator(DetectionValidator): - """ - A class extending the DetectionValidator class for validation based on a pose model. - - Example: - ```python - from ultralytics.models.yolo.pose import PoseValidator - - args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml') - validator = PoseValidator(args=args) - validator() - ``` - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """Initialize a 'PoseValidator' object with custom parameters and assigned attributes.""" - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.sigma = None - self.kpt_shape = None - self.args.task = "pose" - self.metrics = PoseMetrics(save_dir=self.save_dir, on_plot=self.on_plot) - if isinstance(self.args.device, str) and self.args.device.lower() == "mps": - LOGGER.warning( - "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. " - "See https://github.com/ultralytics/ultralytics/issues/4031." - ) - - def preprocess(self, batch): - """Preprocesses the batch by converting the 'keypoints' data into a float and moving it to the device.""" - batch = super().preprocess(batch) - batch["keypoints"] = batch["keypoints"].to(self.device).float() - return batch - - def get_desc(self): - """Returns description of evaluation metrics in string format.""" - return ("%22s" + "%11s" * 10) % ( - "Class", - "Images", - "Instances", - "Box(P", - "R", - "mAP50", - "mAP50-95)", - "Pose(P", - "R", - "mAP50", - "mAP50-95)", - ) - - def postprocess(self, preds): - """Apply non-maximum suppression and return detections with high confidence scores.""" - return ops.non_max_suppression( - preds, - self.args.conf, - self.args.iou, - labels=self.lb, - multi_label=True, - agnostic=self.args.single_cls, - max_det=self.args.max_det, - nc=self.nc, - ) - - def init_metrics(self, model): - """Initiate pose estimation metrics for YOLO model.""" - super().init_metrics(model) - self.kpt_shape = self.data["kpt_shape"] - is_pose = self.kpt_shape == [17, 3] - nkpt = self.kpt_shape[0] - self.sigma = OKS_SIGMA if is_pose else np.ones(nkpt) / nkpt - self.stats = dict(tp_p=[], tp=[], conf=[], pred_cls=[], target_cls=[]) - - def _prepare_batch(self, si, batch): - """Prepares a batch for processing by converting keypoints to float and moving to device.""" - pbatch = super()._prepare_batch(si, batch) - kpts = batch["keypoints"][batch["batch_idx"] == si] - h, w = pbatch["imgsz"] - kpts = kpts.clone() - kpts[..., 0] *= w - kpts[..., 1] *= h - kpts = ops.scale_coords(pbatch["imgsz"], kpts, pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"]) - pbatch["kpts"] = kpts - return pbatch - - def _prepare_pred(self, pred, pbatch): - """Prepares and scales keypoints in a batch for pose processing.""" - predn = super()._prepare_pred(pred, pbatch) - nk = pbatch["kpts"].shape[1] - pred_kpts = predn[:, 6:].view(len(predn), nk, -1) - ops.scale_coords(pbatch["imgsz"], pred_kpts, pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"]) - return predn, pred_kpts - - def update_metrics(self, preds, batch): - """Metrics.""" - for si, pred in enumerate(preds): - self.seen += 1 - npr = len(pred) - stat = dict( - conf=torch.zeros(0, device=self.device), - pred_cls=torch.zeros(0, device=self.device), - tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device), - tp_p=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device), - ) - pbatch = self._prepare_batch(si, batch) - cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox") - nl = len(cls) - stat["target_cls"] = cls - if npr == 0: - if nl: - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - if self.args.plots: - self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls) - continue - - # Predictions - if self.args.single_cls: - pred[:, 5] = 0 - predn, pred_kpts = self._prepare_pred(pred, pbatch) - stat["conf"] = predn[:, 4] - stat["pred_cls"] = predn[:, 5] - - # Evaluate - if nl: - stat["tp"] = self._process_batch(predn, bbox, cls) - stat["tp_p"] = self._process_batch(predn, bbox, cls, pred_kpts, pbatch["kpts"]) - if self.args.plots: - self.confusion_matrix.process_batch(predn, bbox, cls) - - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - - # Save - if self.args.save_json: - self.pred_to_json(predn, batch["im_file"][si]) - # if self.args.save_txt: - # save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt') - - def _process_batch(self, detections, gt_bboxes, gt_cls, pred_kpts=None, gt_kpts=None): - """ - Return correct prediction matrix. - - Args: - detections (torch.Tensor): Tensor of shape [N, 6] representing detections. - Each detection is of the format: x1, y1, x2, y2, conf, class. - labels (torch.Tensor): Tensor of shape [M, 5] representing labels. - Each label is of the format: class, x1, y1, x2, y2. - pred_kpts (torch.Tensor, optional): Tensor of shape [N, 51] representing predicted keypoints. - 51 corresponds to 17 keypoints each with 3 values. - gt_kpts (torch.Tensor, optional): Tensor of shape [N, 51] representing ground truth keypoints. - - Returns: - torch.Tensor: Correct prediction matrix of shape [N, 10] for 10 IoU levels. - """ - if pred_kpts is not None and gt_kpts is not None: - # `0.53` is from https://github.com/jin-s13/xtcocoapi/blob/master/xtcocotools/cocoeval.py#L384 - area = ops.xyxy2xywh(gt_bboxes)[:, 2:].prod(1) * 0.53 - iou = kpt_iou(gt_kpts, pred_kpts, sigma=self.sigma, area=area) - else: # boxes - iou = box_iou(gt_bboxes, detections[:, :4]) - - return self.match_predictions(detections[:, 5], gt_cls, iou) - - def plot_val_samples(self, batch, ni): - """Plots and saves validation set samples with predicted bounding boxes and keypoints.""" - plot_images( - batch["img"], - batch["batch_idx"], - batch["cls"].squeeze(-1), - batch["bboxes"], - kpts=batch["keypoints"], - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_labels.jpg", - names=self.names, - on_plot=self.on_plot, - ) - - def plot_predictions(self, batch, preds, ni): - """Plots predictions for YOLO model.""" - pred_kpts = torch.cat([p[:, 6:].view(-1, *self.kpt_shape) for p in preds], 0) - plot_images( - batch["img"], - *output_to_target(preds, max_det=self.args.max_det), - kpts=pred_kpts, - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_pred.jpg", - names=self.names, - on_plot=self.on_plot, - ) # pred - - def pred_to_json(self, predn, filename): - """Converts YOLO predictions to COCO JSON format.""" - stem = Path(filename).stem - image_id = int(stem) if stem.isnumeric() else stem - box = ops.xyxy2xywh(predn[:, :4]) # xywh - box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner - for p, b in zip(predn.tolist(), box.tolist()): - self.jdict.append( - { - "image_id": image_id, - "category_id": self.class_map[int(p[5])], - "bbox": [round(x, 3) for x in b], - "keypoints": p[6:], - "score": round(p[4], 5), - } - ) - - def eval_json(self, stats): - """Evaluates object detection model using COCO JSON format.""" - if self.args.save_json and self.is_coco and len(self.jdict): - anno_json = self.data["path"] / "annotations/person_keypoints_val2017.json" # annotations - pred_json = self.save_dir / "predictions.json" # predictions - LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...") - try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb - check_requirements("pycocotools>=2.0.6") - from pycocotools.coco import COCO # noqa - from pycocotools.cocoeval import COCOeval # noqa - - for x in anno_json, pred_json: - assert x.is_file(), f"{x} file not found" - anno = COCO(str(anno_json)) # init annotations api - pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path) - for i, eval in enumerate([COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "keypoints")]): - if self.is_coco: - eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # im to eval - eval.evaluate() - eval.accumulate() - eval.summarize() - idx = i * 4 + 2 - stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[ - :2 - ] # update mAP50-95 and mAP50 - except Exception as e: - LOGGER.warning(f"pycocotools unable to run: {e}") - return stats diff --git a/ultralytics-main/ultralytics/models/yolo/segment/__init__.py b/ultralytics-main/ultralytics/models/yolo/segment/__init__.py deleted file mode 100644 index ec1ac79..0000000 --- a/ultralytics-main/ultralytics/models/yolo/segment/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .predict import SegmentationPredictor -from .train import SegmentationTrainer -from .val import SegmentationValidator - -__all__ = "SegmentationPredictor", "SegmentationTrainer", "SegmentationValidator" diff --git a/ultralytics-main/ultralytics/models/yolo/segment/predict.py b/ultralytics-main/ultralytics/models/yolo/segment/predict.py deleted file mode 100644 index 9d7015f..0000000 --- a/ultralytics-main/ultralytics/models/yolo/segment/predict.py +++ /dev/null @@ -1,57 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.engine.results import Results -from ultralytics.models.yolo.detect.predict import DetectionPredictor -from ultralytics.utils import DEFAULT_CFG, ops - - -class SegmentationPredictor(DetectionPredictor): - """ - A class extending the DetectionPredictor class for prediction based on a segmentation model. - - Example: - ```python - from ultralytics.utils import ASSETS - from ultralytics.models.yolo.segment import SegmentationPredictor - - args = dict(model='yolov8n-seg.pt', source=ASSETS) - predictor = SegmentationPredictor(overrides=args) - predictor.predict_cli() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initializes the SegmentationPredictor with the provided configuration, overrides, and callbacks.""" - super().__init__(cfg, overrides, _callbacks) - self.args.task = "segment" - - def postprocess(self, preds, img, orig_imgs): - """Applies non-max suppression and processes detections for each image in an input batch.""" - p = ops.non_max_suppression( - preds[0], - self.args.conf, - self.args.iou, - agnostic=self.args.agnostic_nms, - max_det=self.args.max_det, - nc=len(self.model.names), - classes=self.args.classes, - ) - - if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list - orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) - - results = [] - proto = preds[1][-1] if isinstance(preds[1], tuple) else preds[1] # tuple if PyTorch model or array if exported - for i, pred in enumerate(p): - orig_img = orig_imgs[i] - img_path = self.batch[0][i] - if not len(pred): # save empty boxes - masks = None - elif self.args.retina_masks: - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2]) # HWC - else: - masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True) # HWC - pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape) - results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks)) - return results diff --git a/ultralytics-main/ultralytics/models/yolo/segment/train.py b/ultralytics-main/ultralytics/models/yolo/segment/train.py deleted file mode 100644 index 126baf2..0000000 --- a/ultralytics-main/ultralytics/models/yolo/segment/train.py +++ /dev/null @@ -1,62 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from copy import copy - -from ultralytics.models import yolo -from ultralytics.nn.tasks import SegmentationModel -from ultralytics.utils import DEFAULT_CFG, RANK -from ultralytics.utils.plotting import plot_images, plot_results - - -class SegmentationTrainer(yolo.detect.DetectionTrainer): - """ - A class extending the DetectionTrainer class for training based on a segmentation model. - - Example: - ```python - from ultralytics.models.yolo.segment import SegmentationTrainer - - args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml', epochs=3) - trainer = SegmentationTrainer(overrides=args) - trainer.train() - ``` - """ - - def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None): - """Initialize a SegmentationTrainer object with given arguments.""" - if overrides is None: - overrides = {} - overrides["task"] = "segment" - super().__init__(cfg, overrides, _callbacks) - - def get_model(self, cfg=None, weights=None, verbose=True): - """Return SegmentationModel initialized with specified config and weights.""" - model = SegmentationModel(cfg, ch=3, nc=self.data["nc"], verbose=verbose and RANK == -1) - if weights: - model.load(weights) - - return model - - def get_validator(self): - """Return an instance of SegmentationValidator for validation of YOLO model.""" - self.loss_names = "box_loss", "seg_loss", "cls_loss", "dfl_loss" - return yolo.segment.SegmentationValidator( - self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks - ) - - def plot_training_samples(self, batch, ni): - """Creates a plot of training sample images with labels and box coordinates.""" - plot_images( - batch["img"], - batch["batch_idx"], - batch["cls"].squeeze(-1), - batch["bboxes"], - masks=batch["masks"], - paths=batch["im_file"], - fname=self.save_dir / f"train_batch{ni}.jpg", - on_plot=self.on_plot, - ) - - def plot_metrics(self): - """Plots training/val metrics.""" - plot_results(file=self.csv, segment=True, on_plot=self.on_plot) # save results.png diff --git a/ultralytics-main/ultralytics/models/yolo/segment/val.py b/ultralytics-main/ultralytics/models/yolo/segment/val.py deleted file mode 100644 index 94757c4..0000000 --- a/ultralytics-main/ultralytics/models/yolo/segment/val.py +++ /dev/null @@ -1,277 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from multiprocessing.pool import ThreadPool -from pathlib import Path - -import numpy as np -import torch -import torch.nn.functional as F - -from ultralytics.models.yolo.detect import DetectionValidator -from ultralytics.utils import LOGGER, NUM_THREADS, ops -from ultralytics.utils.checks import check_requirements -from ultralytics.utils.metrics import SegmentMetrics, box_iou, mask_iou -from ultralytics.utils.plotting import output_to_target, plot_images - - -class SegmentationValidator(DetectionValidator): - """ - A class extending the DetectionValidator class for validation based on a segmentation model. - - Example: - ```python - from ultralytics.models.yolo.segment import SegmentationValidator - - args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml') - validator = SegmentationValidator(args=args) - validator() - ``` - """ - - def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None): - """Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics.""" - super().__init__(dataloader, save_dir, pbar, args, _callbacks) - self.plot_masks = None - self.process = None - self.args.task = "segment" - self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot) - - def preprocess(self, batch): - """Preprocesses batch by converting masks to float and sending to device.""" - batch = super().preprocess(batch) - batch["masks"] = batch["masks"].to(self.device).float() - return batch - - def init_metrics(self, model): - """Initialize metrics and select mask processing function based on save_json flag.""" - super().init_metrics(model) - self.plot_masks = [] - if self.args.save_json: - check_requirements("pycocotools>=2.0.6") - self.process = ops.process_mask_upsample # more accurate - else: - self.process = ops.process_mask # faster - self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[]) - - def get_desc(self): - """Return a formatted description of evaluation metrics.""" - return ("%22s" + "%11s" * 10) % ( - "Class", - "Images", - "Instances", - "Box(P", - "R", - "mAP50", - "mAP50-95)", - "Mask(P", - "R", - "mAP50", - "mAP50-95)", - ) - - def postprocess(self, preds): - """Post-processes YOLO predictions and returns output detections with proto.""" - p = ops.non_max_suppression( - preds[0], - self.args.conf, - self.args.iou, - labels=self.lb, - multi_label=True, - agnostic=self.args.single_cls, - max_det=self.args.max_det, - nc=self.nc, - ) - proto = preds[1][-1] if len(preds[1]) == 3 else preds[1] # second output is len 3 if pt, but only 1 if exported - return p, proto - - def _prepare_batch(self, si, batch): - """Prepares a batch for training or inference by processing images and targets.""" - prepared_batch = super()._prepare_batch(si, batch) - midx = [si] if self.args.overlap_mask else batch["batch_idx"] == si - prepared_batch["masks"] = batch["masks"][midx] - return prepared_batch - - def _prepare_pred(self, pred, pbatch, proto): - """Prepares a batch for training or inference by processing images and targets.""" - predn = super()._prepare_pred(pred, pbatch) - pred_masks = self.process(proto, pred[:, 6:], pred[:, :4], shape=pbatch["imgsz"]) - return predn, pred_masks - - def update_metrics(self, preds, batch): - """Metrics.""" - for si, (pred, proto) in enumerate(zip(preds[0], preds[1])): - self.seen += 1 - npr = len(pred) - stat = dict( - conf=torch.zeros(0, device=self.device), - pred_cls=torch.zeros(0, device=self.device), - tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device), - tp_m=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device), - ) - pbatch = self._prepare_batch(si, batch) - cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox") - nl = len(cls) - stat["target_cls"] = cls - if npr == 0: - if nl: - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - if self.args.plots: - self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls) - continue - - # Masks - gt_masks = pbatch.pop("masks") - # Predictions - if self.args.single_cls: - pred[:, 5] = 0 - predn, pred_masks = self._prepare_pred(pred, pbatch, proto) - stat["conf"] = predn[:, 4] - stat["pred_cls"] = predn[:, 5] - - # Evaluate - if nl: - stat["tp"] = self._process_batch(predn, bbox, cls) - stat["tp_m"] = self._process_batch( - predn, bbox, cls, pred_masks, gt_masks, self.args.overlap_mask, masks=True - ) - if self.args.plots: - self.confusion_matrix.process_batch(predn, bbox, cls) - - for k in self.stats.keys(): - self.stats[k].append(stat[k]) - - pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8) - if self.args.plots and self.batch_i < 3: - self.plot_masks.append(pred_masks[:15].cpu()) # filter top 15 to plot - - # Save - if self.args.save_json: - pred_masks = ops.scale_image( - pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(), - pbatch["ori_shape"], - ratio_pad=batch["ratio_pad"][si], - ) - self.pred_to_json(predn, batch["im_file"][si], pred_masks) - # if self.args.save_txt: - # save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt') - - def finalize_metrics(self, *args, **kwargs): - """Sets speed and confusion matrix for evaluation metrics.""" - self.metrics.speed = self.speed - self.metrics.confusion_matrix = self.confusion_matrix - - def _process_batch(self, detections, gt_bboxes, gt_cls, pred_masks=None, gt_masks=None, overlap=False, masks=False): - """ - Return correct prediction matrix. - - Args: - detections (array[N, 6]), x1, y1, x2, y2, conf, class - labels (array[M, 5]), class, x1, y1, x2, y2 - - Returns: - correct (array[N, 10]), for 10 IoU levels - """ - if masks: - if overlap: - nl = len(gt_cls) - index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1 - gt_masks = gt_masks.repeat(nl, 1, 1) # shape(1,640,640) -> (n,640,640) - gt_masks = torch.where(gt_masks == index, 1.0, 0.0) - if gt_masks.shape[1:] != pred_masks.shape[1:]: - gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode="bilinear", align_corners=False)[0] - gt_masks = gt_masks.gt_(0.5) - iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1)) - else: # boxes - iou = box_iou(gt_bboxes, detections[:, :4]) - - return self.match_predictions(detections[:, 5], gt_cls, iou) - - def plot_val_samples(self, batch, ni): - """Plots validation samples with bounding box labels.""" - plot_images( - batch["img"], - batch["batch_idx"], - batch["cls"].squeeze(-1), - batch["bboxes"], - masks=batch["masks"], - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_labels.jpg", - names=self.names, - on_plot=self.on_plot, - ) - - def plot_predictions(self, batch, preds, ni): - """Plots batch predictions with masks and bounding boxes.""" - plot_images( - batch["img"], - *output_to_target(preds[0], max_det=15), # not set to self.args.max_det due to slow plotting speed - torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks, - paths=batch["im_file"], - fname=self.save_dir / f"val_batch{ni}_pred.jpg", - names=self.names, - on_plot=self.on_plot, - ) # pred - self.plot_masks.clear() - - def pred_to_json(self, predn, filename, pred_masks): - """ - Save one JSON result. - - Examples: - >>> result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236} - """ - from pycocotools.mask import encode # noqa - - def single_encode(x): - """Encode predicted masks as RLE and append results to jdict.""" - rle = encode(np.asarray(x[:, :, None], order="F", dtype="uint8"))[0] - rle["counts"] = rle["counts"].decode("utf-8") - return rle - - stem = Path(filename).stem - image_id = int(stem) if stem.isnumeric() else stem - box = ops.xyxy2xywh(predn[:, :4]) # xywh - box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner - pred_masks = np.transpose(pred_masks, (2, 0, 1)) - with ThreadPool(NUM_THREADS) as pool: - rles = pool.map(single_encode, pred_masks) - for i, (p, b) in enumerate(zip(predn.tolist(), box.tolist())): - self.jdict.append( - { - "image_id": image_id, - "category_id": self.class_map[int(p[5])], - "bbox": [round(x, 3) for x in b], - "score": round(p[4], 5), - "segmentation": rles[i], - } - ) - - def eval_json(self, stats): - """Return COCO-style object detection evaluation metrics.""" - if self.args.save_json and self.is_coco and len(self.jdict): - anno_json = self.data["path"] / "annotations/instances_val2017.json" # annotations - pred_json = self.save_dir / "predictions.json" # predictions - LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...") - try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb - check_requirements("pycocotools>=2.0.6") - from pycocotools.coco import COCO # noqa - from pycocotools.cocoeval import COCOeval # noqa - - for x in anno_json, pred_json: - assert x.is_file(), f"{x} file not found" - anno = COCO(str(anno_json)) # init annotations api - pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path) - for i, eval in enumerate([COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "segm")]): - if self.is_coco: - eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # im to eval - eval.evaluate() - eval.accumulate() - eval.summarize() - idx = i * 4 + 2 - stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[ - :2 - ] # update mAP50-95 and mAP50 - except Exception as e: - LOGGER.warning(f"pycocotools unable to run: {e}") - return stats diff --git a/ultralytics-main/ultralytics/nn/__init__.py b/ultralytics-main/ultralytics/nn/__init__.py deleted file mode 100644 index 6905d34..0000000 --- a/ultralytics-main/ultralytics/nn/__init__.py +++ /dev/null @@ -1,29 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .tasks import ( - BaseModel, - ClassificationModel, - DetectionModel, - SegmentationModel, - attempt_load_one_weight, - attempt_load_weights, - guess_model_scale, - guess_model_task, - parse_model, - torch_safe_load, - yaml_model_load, -) - -__all__ = ( - "attempt_load_one_weight", - "attempt_load_weights", - "parse_model", - "yaml_model_load", - "guess_model_task", - "guess_model_scale", - "torch_safe_load", - "DetectionModel", - "SegmentationModel", - "ClassificationModel", - "BaseModel", -) diff --git a/ultralytics-main/ultralytics/nn/autobackend.py b/ultralytics-main/ultralytics/nn/autobackend.py deleted file mode 100644 index bebfdbe..0000000 --- a/ultralytics-main/ultralytics/nn/autobackend.py +++ /dev/null @@ -1,628 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import ast -import contextlib -import json -import platform -import zipfile -from collections import OrderedDict, namedtuple -from pathlib import Path - -import cv2 -import numpy as np -import torch -import torch.nn as nn -from PIL import Image - -from ultralytics.utils import ARM64, LINUX, LOGGER, ROOT, yaml_load -from ultralytics.utils.checks import check_requirements, check_suffix, check_version, check_yaml -from ultralytics.utils.downloads import attempt_download_asset, is_url - - -def check_class_names(names): - """ - Check class names. - - Map imagenet class codes to human-readable names if required. Convert lists to dicts. - """ - if isinstance(names, list): # names is a list - names = dict(enumerate(names)) # convert to dict - if isinstance(names, dict): - # Convert 1) string keys to int, i.e. '0' to 0, and non-string values to strings, i.e. True to 'True' - names = {int(k): str(v) for k, v in names.items()} - n = len(names) - if max(names.keys()) >= n: - raise KeyError( - f"{n}-class dataset requires class indices 0-{n - 1}, but you have invalid class indices " - f"{min(names.keys())}-{max(names.keys())} defined in your dataset YAML." - ) - if isinstance(names[0], str) and names[0].startswith("n0"): # imagenet class codes, i.e. 'n01440764' - names_map = yaml_load(ROOT / "cfg/datasets/ImageNet.yaml")["map"] # human-readable names - names = {k: names_map[v] for k, v in names.items()} - return names - - -def default_class_names(data=None): - """Applies default class names to an input YAML file or returns numerical class names.""" - if data: - with contextlib.suppress(Exception): - return yaml_load(check_yaml(data))["names"] - return {i: f"class{i}" for i in range(999)} # return default if above errors - - -class AutoBackend(nn.Module): - """ - Handles dynamic backend selection for running inference using Ultralytics YOLO models. - - The AutoBackend class is designed to provide an abstraction layer for various inference engines. It supports a wide - range of formats, each with specific naming conventions as outlined below: - - Supported Formats and Naming Conventions: - | Format | File Suffix | - |-----------------------|------------------| - | PyTorch | *.pt | - | TorchScript | *.torchscript | - | ONNX Runtime | *.onnx | - | ONNX OpenCV DNN | *.onnx (dnn=True)| - | OpenVINO | *openvino_model/ | - | CoreML | *.mlpackage | - | TensorRT | *.engine | - | TensorFlow SavedModel | *_saved_model | - | TensorFlow GraphDef | *.pb | - | TensorFlow Lite | *.tflite | - | TensorFlow Edge TPU | *_edgetpu.tflite | - | PaddlePaddle | *_paddle_model | - | NCNN | *_ncnn_model | - - This class offers dynamic backend switching capabilities based on the input model format, making it easier to deploy - models across various platforms. - """ - - @torch.no_grad() - def __init__( - self, - weights="yolov8n.pt", - device=torch.device("cpu"), - dnn=False, - data=None, - fp16=False, - batch=1, - fuse=True, - verbose=True, - ): - """ - Initialize the AutoBackend for inference. - - Args: - weights (str): Path to the model weights file. Defaults to 'yolov8n.pt'. - device (torch.device): Device to run the model on. Defaults to CPU. - dnn (bool): Use OpenCV DNN module for ONNX inference. Defaults to False. - data (str | Path | optional): Path to the additional data.yaml file containing class names. Optional. - fp16 (bool): Enable half-precision inference. Supported only on specific backends. Defaults to False. - batch (int): Batch-size to assume for inference. - fuse (bool): Fuse Conv2D + BatchNorm layers for optimization. Defaults to True. - verbose (bool): Enable verbose logging. Defaults to True. - """ - super().__init__() - w = str(weights[0] if isinstance(weights, list) else weights) - nn_module = isinstance(weights, torch.nn.Module) - ( - pt, - jit, - onnx, - xml, - engine, - coreml, - saved_model, - pb, - tflite, - edgetpu, - tfjs, - paddle, - ncnn, - triton, - ) = self._model_type(w) - fp16 &= pt or jit or onnx or xml or engine or nn_module or triton # FP16 - nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH) - stride = 32 # default stride - model, metadata = None, None - - # Set device - cuda = torch.cuda.is_available() and device.type != "cpu" # use CUDA - if cuda and not any([nn_module, pt, jit, engine, onnx]): # GPU dataloader formats - device = torch.device("cpu") - cuda = False - - # Download if not local - if not (pt or triton or nn_module): - w = attempt_download_asset(w) - - # In-memory PyTorch model - if nn_module: - model = weights.to(device) - model = model.fuse(verbose=verbose) if fuse else model - if hasattr(model, "kpt_shape"): - kpt_shape = model.kpt_shape # pose-only - stride = max(int(model.stride.max()), 32) # model stride - names = model.module.names if hasattr(model, "module") else model.names # get class names - model.half() if fp16 else model.float() - self.model = model # explicitly assign for to(), cpu(), cuda(), half() - pt = True - - # PyTorch - elif pt: - from ultralytics.nn.tasks import attempt_load_weights - - model = attempt_load_weights( - weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse - ) - if hasattr(model, "kpt_shape"): - kpt_shape = model.kpt_shape # pose-only - stride = max(int(model.stride.max()), 32) # model stride - names = model.module.names if hasattr(model, "module") else model.names # get class names - model.half() if fp16 else model.float() - self.model = model # explicitly assign for to(), cpu(), cuda(), half() - - # TorchScript - elif jit: - LOGGER.info(f"Loading {w} for TorchScript inference...") - extra_files = {"config.txt": ""} # model metadata - model = torch.jit.load(w, _extra_files=extra_files, map_location=device) - model.half() if fp16 else model.float() - if extra_files["config.txt"]: # load metadata dict - metadata = json.loads(extra_files["config.txt"], object_hook=lambda x: dict(x.items())) - - # ONNX OpenCV DNN - elif dnn: - LOGGER.info(f"Loading {w} for ONNX OpenCV DNN inference...") - check_requirements("opencv-python>=4.5.4") - net = cv2.dnn.readNetFromONNX(w) - - # ONNX Runtime - elif onnx: - LOGGER.info(f"Loading {w} for ONNX Runtime inference...") - check_requirements(("onnx", "onnxruntime-gpu" if cuda else "onnxruntime")) - import onnxruntime - - providers = ["CUDAExecutionProvider", "CPUExecutionProvider"] if cuda else ["CPUExecutionProvider"] - session = onnxruntime.InferenceSession(w, providers=providers) - output_names = [x.name for x in session.get_outputs()] - metadata = session.get_modelmeta().custom_metadata_map - - # OpenVINO - elif xml: - LOGGER.info(f"Loading {w} for OpenVINO inference...") - check_requirements("openvino>=2024.0.0") - import openvino as ov - - core = ov.Core() - w = Path(w) - if not w.is_file(): # if not *.xml - w = next(w.glob("*.xml")) # get *.xml file from *_openvino_model dir - ov_model = core.read_model(model=str(w), weights=w.with_suffix(".bin")) - if ov_model.get_parameters()[0].get_layout().empty: - ov_model.get_parameters()[0].set_layout(ov.Layout("NCHW")) - batch_dim = ov.get_batch(ov_model) - if batch_dim.is_static: - batch_size = batch_dim.get_length() - - # OpenVINO inference modes are 'LATENCY', 'THROUGHPUT' (not recommended), or 'CUMULATIVE_THROUGHPUT' - inference_mode = "CUMULATIVE_THROUGHPUT" if batch > 1 else "LATENCY" - LOGGER.info(f"Using OpenVINO {inference_mode} mode for batch-size={batch_size} inference...") - ov_compiled_model = core.compile_model( - ov_model, - device_name="AUTO", # AUTO selects best available device, do not modify - config={"PERFORMANCE_HINT": inference_mode}, - ) - input_name = ov_compiled_model.input().get_any_name() - metadata = w.parent / "metadata.yaml" - - # TensorRT - elif engine: - LOGGER.info(f"Loading {w} for TensorRT inference...") - try: - import tensorrt as trt # noqa https://developer.nvidia.com/nvidia-tensorrt-download - except ImportError: - if LINUX: - check_requirements("nvidia-tensorrt", cmds="-U --index-url https://pypi.ngc.nvidia.com") - import tensorrt as trt # noqa - check_version(trt.__version__, "7.0.0", hard=True) # require tensorrt>=7.0.0 - if device.type == "cpu": - device = torch.device("cuda:0") - Binding = namedtuple("Binding", ("name", "dtype", "shape", "data", "ptr")) - logger = trt.Logger(trt.Logger.INFO) - # Read file - with open(w, "rb") as f, trt.Runtime(logger) as runtime: - meta_len = int.from_bytes(f.read(4), byteorder="little") # read metadata length - metadata = json.loads(f.read(meta_len).decode("utf-8")) # read metadata - model = runtime.deserialize_cuda_engine(f.read()) # read engine - context = model.create_execution_context() - bindings = OrderedDict() - output_names = [] - fp16 = False # default updated below - dynamic = False - for i in range(model.num_bindings): - name = model.get_binding_name(i) - dtype = trt.nptype(model.get_binding_dtype(i)) - if model.binding_is_input(i): - if -1 in tuple(model.get_binding_shape(i)): # dynamic - dynamic = True - context.set_binding_shape(i, tuple(model.get_profile_shape(0, i)[2])) - if dtype == np.float16: - fp16 = True - else: # output - output_names.append(name) - shape = tuple(context.get_binding_shape(i)) - im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device) - bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr())) - binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items()) - batch_size = bindings["images"].shape[0] # if dynamic, this is instead max batch size - - # CoreML - elif coreml: - LOGGER.info(f"Loading {w} for CoreML inference...") - import coremltools as ct - - model = ct.models.MLModel(w) - metadata = dict(model.user_defined_metadata) - - # TF SavedModel - elif saved_model: - LOGGER.info(f"Loading {w} for TensorFlow SavedModel inference...") - import tensorflow as tf - - keras = False # assume TF1 saved_model - model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w) - metadata = Path(w) / "metadata.yaml" - - # TF GraphDef - elif pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt - LOGGER.info(f"Loading {w} for TensorFlow GraphDef inference...") - import tensorflow as tf - - from ultralytics.engine.exporter import gd_outputs - - def wrap_frozen_graph(gd, inputs, outputs): - """Wrap frozen graphs for deployment.""" - x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped - ge = x.graph.as_graph_element - return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs)) - - gd = tf.Graph().as_graph_def() # TF GraphDef - with open(w, "rb") as f: - gd.ParseFromString(f.read()) - frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs=gd_outputs(gd)) - - # TFLite or TFLite Edge TPU - elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python - try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu - from tflite_runtime.interpreter import Interpreter, load_delegate - except ImportError: - import tensorflow as tf - - Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate - if edgetpu: # TF Edge TPU https://coral.ai/software/#edgetpu-runtime - LOGGER.info(f"Loading {w} for TensorFlow Lite Edge TPU inference...") - delegate = {"Linux": "libedgetpu.so.1", "Darwin": "libedgetpu.1.dylib", "Windows": "edgetpu.dll"}[ - platform.system() - ] - interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)]) - else: # TFLite - LOGGER.info(f"Loading {w} for TensorFlow Lite inference...") - interpreter = Interpreter(model_path=w) # load TFLite model - interpreter.allocate_tensors() # allocate - input_details = interpreter.get_input_details() # inputs - output_details = interpreter.get_output_details() # outputs - # Load metadata - with contextlib.suppress(zipfile.BadZipFile): - with zipfile.ZipFile(w, "r") as model: - meta_file = model.namelist()[0] - metadata = ast.literal_eval(model.read(meta_file).decode("utf-8")) - - # TF.js - elif tfjs: - raise NotImplementedError("YOLOv8 TF.js inference is not currently supported.") - - # PaddlePaddle - elif paddle: - LOGGER.info(f"Loading {w} for PaddlePaddle inference...") - check_requirements("paddlepaddle-gpu" if cuda else "paddlepaddle") - import paddle.inference as pdi # noqa - - w = Path(w) - if not w.is_file(): # if not *.pdmodel - w = next(w.rglob("*.pdmodel")) # get *.pdmodel file from *_paddle_model dir - config = pdi.Config(str(w), str(w.with_suffix(".pdiparams"))) - if cuda: - config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0) - predictor = pdi.create_predictor(config) - input_handle = predictor.get_input_handle(predictor.get_input_names()[0]) - output_names = predictor.get_output_names() - metadata = w.parents[1] / "metadata.yaml" - - # NCNN - elif ncnn: - LOGGER.info(f"Loading {w} for NCNN inference...") - check_requirements("git+https://github.com/Tencent/ncnn.git" if ARM64 else "ncnn") # requires NCNN - import ncnn as pyncnn - - net = pyncnn.Net() - net.opt.use_vulkan_compute = cuda - w = Path(w) - if not w.is_file(): # if not *.param - w = next(w.glob("*.param")) # get *.param file from *_ncnn_model dir - net.load_param(str(w)) - net.load_model(str(w.with_suffix(".bin"))) - metadata = w.parent / "metadata.yaml" - - # NVIDIA Triton Inference Server - elif triton: - check_requirements("tritonclient[all]") - from ultralytics.utils.triton import TritonRemoteModel - - model = TritonRemoteModel(w) - - # Any other format (unsupported) - else: - from ultralytics.engine.exporter import export_formats - - raise TypeError( - f"model='{w}' is not a supported model format. " - f"See https://docs.ultralytics.com/modes/predict for help.\n\n{export_formats()}" - ) - - # Load external metadata YAML - if isinstance(metadata, (str, Path)) and Path(metadata).exists(): - metadata = yaml_load(metadata) - if metadata: - for k, v in metadata.items(): - if k in ("stride", "batch"): - metadata[k] = int(v) - elif k in ("imgsz", "names", "kpt_shape") and isinstance(v, str): - metadata[k] = eval(v) - stride = metadata["stride"] - task = metadata["task"] - batch = metadata["batch"] - imgsz = metadata["imgsz"] - names = metadata["names"] - kpt_shape = metadata.get("kpt_shape") - elif not (pt or triton or nn_module): - LOGGER.warning(f"WARNING ⚠️ Metadata not found for 'model={weights}'") - - # Check names - if "names" not in locals(): # names missing - names = default_class_names(data) - names = check_class_names(names) - - # Disable gradients - if pt: - for p in model.parameters(): - p.requires_grad = False - - self.__dict__.update(locals()) # assign all variables to self - - def forward(self, im, augment=False, visualize=False, embed=None): - """ - Runs inference on the YOLOv8 MultiBackend model. - - Args: - im (torch.Tensor): The image tensor to perform inference on. - augment (bool): whether to perform data augmentation during inference, defaults to False - visualize (bool): whether to visualize the output predictions, defaults to False - embed (list, optional): A list of feature vectors/embeddings to return. - - Returns: - (tuple): Tuple containing the raw output tensor, and processed output for visualization (if visualize=True) - """ - b, ch, h, w = im.shape # batch, channel, height, width - if self.fp16 and im.dtype != torch.float16: - im = im.half() # to FP16 - if self.nhwc: - im = im.permute(0, 2, 3, 1) # torch BCHW to numpy BHWC shape(1,320,192,3) - - # PyTorch - if self.pt or self.nn_module: - y = self.model(im, augment=augment, visualize=visualize, embed=embed) - - # TorchScript - elif self.jit: - y = self.model(im) - - # ONNX OpenCV DNN - elif self.dnn: - im = im.cpu().numpy() # torch to numpy - self.net.setInput(im) - y = self.net.forward() - - # ONNX Runtime - elif self.onnx: - im = im.cpu().numpy() # torch to numpy - y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im}) - - # OpenVINO - elif self.xml: - im = im.cpu().numpy() # FP32 - - if self.inference_mode in {"THROUGHPUT", "CUMULATIVE_THROUGHPUT"}: # optimized for larger batch-sizes - n = im.shape[0] # number of images in batch - results = [None] * n # preallocate list with None to match the number of images - - def callback(request, userdata): - """Places result in preallocated list using userdata index.""" - results[userdata] = request.results - - # Create AsyncInferQueue, set the callback and start asynchronous inference for each input image - async_queue = self.ov.runtime.AsyncInferQueue(self.ov_compiled_model) - async_queue.set_callback(callback) - for i in range(n): - # Start async inference with userdata=i to specify the position in results list - async_queue.start_async(inputs={self.input_name: im[i : i + 1]}, userdata=i) # keep image as BCHW - async_queue.wait_all() # wait for all inference requests to complete - y = np.concatenate([list(r.values())[0] for r in results]) - - else: # inference_mode = "LATENCY", optimized for fastest first result at batch-size 1 - y = list(self.ov_compiled_model(im).values()) - - # TensorRT - elif self.engine: - if self.dynamic and im.shape != self.bindings["images"].shape: - i = self.model.get_binding_index("images") - self.context.set_binding_shape(i, im.shape) # reshape if dynamic - self.bindings["images"] = self.bindings["images"]._replace(shape=im.shape) - for name in self.output_names: - i = self.model.get_binding_index(name) - self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i))) - s = self.bindings["images"].shape - assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}" - self.binding_addrs["images"] = int(im.data_ptr()) - self.context.execute_v2(list(self.binding_addrs.values())) - y = [self.bindings[x].data for x in sorted(self.output_names)] - - # CoreML - elif self.coreml: - im = im[0].cpu().numpy() - im_pil = Image.fromarray((im * 255).astype("uint8")) - # im = im.resize((192, 320), Image.BILINEAR) - y = self.model.predict({"image": im_pil}) # coordinates are xywh normalized - if "confidence" in y: - raise TypeError( - "Ultralytics only supports inference of non-pipelined CoreML models exported with " - f"'nms=False', but 'model={w}' has an NMS pipeline created by an 'nms=True' export." - ) - # TODO: CoreML NMS inference handling - # from ultralytics.utils.ops import xywh2xyxy - # box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels - # conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float32) - # y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) - elif len(y) == 1: # classification model - y = list(y.values()) - elif len(y) == 2: # segmentation model - y = list(reversed(y.values())) # reversed for segmentation models (pred, proto) - - # PaddlePaddle - elif self.paddle: - im = im.cpu().numpy().astype(np.float32) - self.input_handle.copy_from_cpu(im) - self.predictor.run() - y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names] - - # NCNN - elif self.ncnn: - mat_in = self.pyncnn.Mat(im[0].cpu().numpy()) - ex = self.net.create_extractor() - input_names, output_names = self.net.input_names(), self.net.output_names() - ex.input(input_names[0], mat_in) - y = [] - for output_name in output_names: - mat_out = self.pyncnn.Mat() - ex.extract(output_name, mat_out) - y.append(np.array(mat_out)[None]) - - # NVIDIA Triton Inference Server - elif self.triton: - im = im.cpu().numpy() # torch to numpy - y = self.model(im) - - # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) - else: - im = im.cpu().numpy() - if self.saved_model: # SavedModel - y = self.model(im, training=False) if self.keras else self.model(im) - if not isinstance(y, list): - y = [y] - elif self.pb: # GraphDef - y = self.frozen_func(x=self.tf.constant(im)) - if len(y) == 2 and len(self.names) == 999: # segments and names not defined - ip, ib = (0, 1) if len(y[0].shape) == 4 else (1, 0) # index of protos, boxes - nc = y[ib].shape[1] - y[ip].shape[3] - 4 # y = (1, 160, 160, 32), (1, 116, 8400) - self.names = {i: f"class{i}" for i in range(nc)} - else: # Lite or Edge TPU - details = self.input_details[0] - integer = details["dtype"] in (np.int8, np.int16) # is TFLite quantized int8 or int16 model - if integer: - scale, zero_point = details["quantization"] - im = (im / scale + zero_point).astype(details["dtype"]) # de-scale - self.interpreter.set_tensor(details["index"], im) - self.interpreter.invoke() - y = [] - for output in self.output_details: - x = self.interpreter.get_tensor(output["index"]) - if integer: - scale, zero_point = output["quantization"] - x = (x.astype(np.float32) - zero_point) * scale # re-scale - if x.ndim > 2: # if task is not classification - # Denormalize xywh by image size. See https://github.com/ultralytics/ultralytics/pull/1695 - # xywh are normalized in TFLite/EdgeTPU to mitigate quantization error of integer models - x[:, [0, 2]] *= w - x[:, [1, 3]] *= h - y.append(x) - # TF segment fixes: export is reversed vs ONNX export and protos are transposed - if len(y) == 2: # segment with (det, proto) output order reversed - if len(y[1].shape) != 4: - y = list(reversed(y)) # should be y = (1, 116, 8400), (1, 160, 160, 32) - y[1] = np.transpose(y[1], (0, 3, 1, 2)) # should be y = (1, 116, 8400), (1, 32, 160, 160) - y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y] - - # for x in y: - # print(type(x), len(x)) if isinstance(x, (list, tuple)) else print(type(x), x.shape) # debug shapes - if isinstance(y, (list, tuple)): - return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y] - else: - return self.from_numpy(y) - - def from_numpy(self, x): - """ - Convert a numpy array to a tensor. - - Args: - x (np.ndarray): The array to be converted. - - Returns: - (torch.Tensor): The converted tensor - """ - return torch.tensor(x).to(self.device) if isinstance(x, np.ndarray) else x - - def warmup(self, imgsz=(1, 3, 640, 640)): - """ - Warm up the model by running one forward pass with a dummy input. - - Args: - imgsz (tuple): The shape of the dummy input tensor in the format (batch_size, channels, height, width) - """ - warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton, self.nn_module - if any(warmup_types) and (self.device.type != "cpu" or self.triton): - im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input - for _ in range(2 if self.jit else 1): - self.forward(im) # warmup - - @staticmethod - def _model_type(p="path/to/model.pt"): - """ - This function takes a path to a model file and returns the model type. Possibles types are pt, jit, onnx, xml, - engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, ncnn or paddle. - - Args: - p: path to the model file. Defaults to path/to/model.pt - - Examples: - >>> model = AutoBackend(weights="path/to/model.onnx") - >>> model_type = model._model_type() # returns "onnx" - """ - from ultralytics.engine.exporter import export_formats - - sf = list(export_formats().Suffix) # export suffixes - if not is_url(p, check=False) and not isinstance(p, str): - check_suffix(p, sf) # checks - name = Path(p).name - types = [s in name for s in sf] - types[5] |= name.endswith(".mlmodel") # retain support for older Apple CoreML *.mlmodel formats - types[8] &= not types[9] # tflite &= not edgetpu - if any(types): - triton = False - else: - from urllib.parse import urlsplit - - url = urlsplit(p) - triton = bool(url.netloc) and bool(url.path) and url.scheme in {"http", "grpc"} - - return types + [triton] diff --git a/ultralytics-main/ultralytics/nn/modules/__init__.py b/ultralytics-main/ultralytics/nn/modules/__init__.py deleted file mode 100644 index d785c00..0000000 --- a/ultralytics-main/ultralytics/nn/modules/__init__.py +++ /dev/null @@ -1,138 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Ultralytics modules. - -Example: - Visualize a module with Netron. - ```python - from ultralytics.nn.modules import * - import torch - import os - - x = torch.ones(1, 128, 40, 40) - m = Conv(128, 128) - f = f'{m._get_name()}.onnx' - torch.onnx.export(m, x, f) - os.system(f'onnxsim {f} {f} && open {f}') - ``` -""" - -from .block import ( - C1, - C2, - C3, - C3TR, - DFL, - SPP, - SPPF, - Bottleneck, - BottleneckCSP, - C2f, - C2fAttn, - ImagePoolingAttn, - C3Ghost, - C3x, - GhostBottleneck, - HGBlock, - HGStem, - Proto, - RepC3, - ResNetLayer, - ContrastiveHead, - BNContrastiveHead, - RepNCSPELAN4, - ADown, - SPPELAN, - CBFuse, - CBLinear, - Silence, -) -from .conv import ( - CBAM, - ChannelAttention, - Concat, - Conv, - Conv2, - ConvTranspose, - DWConv, - DWConvTranspose2d, - Focus, - GhostConv, - LightConv, - RepConv, - SpatialAttention, -) -from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect -from .transformer import ( - AIFI, - MLP, - DeformableTransformerDecoder, - DeformableTransformerDecoderLayer, - LayerNorm2d, - MLPBlock, - MSDeformAttn, - TransformerBlock, - TransformerEncoderLayer, - TransformerLayer, -) - -__all__ = ( - "Conv", - "Conv2", - "LightConv", - "RepConv", - "DWConv", - "DWConvTranspose2d", - "ConvTranspose", - "Focus", - "GhostConv", - "ChannelAttention", - "SpatialAttention", - "CBAM", - "Concat", - "TransformerLayer", - "TransformerBlock", - "MLPBlock", - "LayerNorm2d", - "DFL", - "HGBlock", - "HGStem", - "SPP", - "SPPF", - "C1", - "C2", - "C3", - "C2f", - "C2fAttn", - "C3x", - "C3TR", - "C3Ghost", - "GhostBottleneck", - "Bottleneck", - "BottleneckCSP", - "Proto", - "Detect", - "Segment", - "Pose", - "Classify", - "TransformerEncoderLayer", - "RepC3", - "RTDETRDecoder", - "AIFI", - "DeformableTransformerDecoder", - "DeformableTransformerDecoderLayer", - "MSDeformAttn", - "MLP", - "ResNetLayer", - "OBB", - "WorldDetect", - "ImagePoolingAttn", - "ContrastiveHead", - "BNContrastiveHead", - "RepNCSPELAN4", - "ADown", - "SPPELAN", - "CBFuse", - "CBLinear", - "Silence", -) diff --git a/ultralytics-main/ultralytics/nn/modules/block.py b/ultralytics-main/ultralytics/nn/modules/block.py deleted file mode 100644 index a263b60..0000000 --- a/ultralytics-main/ultralytics/nn/modules/block.py +++ /dev/null @@ -1,698 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Block modules.""" - -import torch -import torch.nn as nn -import torch.nn.functional as F - -from .conv import Conv, DWConv, GhostConv, LightConv, RepConv, autopad -from .transformer import TransformerBlock - -__all__ = ( - "DFL", - "HGBlock", - "HGStem", - "SPP", - "SPPF", - "C1", - "C2", - "C3", - "C2f", - "C2fAttn", - "ImagePoolingAttn", - "ContrastiveHead", - "BNContrastiveHead", - "C3x", - "C3TR", - "C3Ghost", - "GhostBottleneck", - "Bottleneck", - "BottleneckCSP", - "Proto", - "RepC3", - "ResNetLayer", - "RepNCSPELAN4", - "ADown", - "SPPELAN", - "CBFuse", - "CBLinear", - "Silence", -) - - -class DFL(nn.Module): - """ - Integral module of Distribution Focal Loss (DFL). - - Proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391 - """ - - def __init__(self, c1=16): - """Initialize a convolutional layer with a given number of input channels.""" - super().__init__() - self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False) - x = torch.arange(c1, dtype=torch.float) - self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1)) - self.c1 = c1 - - def forward(self, x): - """Applies a transformer layer on input tensor 'x' and returns a tensor.""" - b, _, a = x.shape # batch, channels, anchors - return self.conv(x.view(b, 4, self.c1, a).transpose(2, 1).softmax(1)).view(b, 4, a) - # return self.conv(x.view(b, self.c1, 4, a).softmax(1)).view(b, 4, a) - - -class Proto(nn.Module): - """YOLOv8 mask Proto module for segmentation models.""" - - def __init__(self, c1, c_=256, c2=32): - """ - Initializes the YOLOv8 mask Proto module with specified number of protos and masks. - - Input arguments are ch_in, number of protos, number of masks. - """ - super().__init__() - self.cv1 = Conv(c1, c_, k=3) - self.upsample = nn.ConvTranspose2d(c_, c_, 2, 2, 0, bias=True) # nn.Upsample(scale_factor=2, mode='nearest') - self.cv2 = Conv(c_, c_, k=3) - self.cv3 = Conv(c_, c2) - - def forward(self, x): - """Performs a forward pass through layers using an upsampled input image.""" - return self.cv3(self.cv2(self.upsample(self.cv1(x)))) - - -class HGStem(nn.Module): - """ - StemBlock of PPHGNetV2 with 5 convolutions and one maxpool2d. - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py - """ - - def __init__(self, c1, cm, c2): - """Initialize the SPP layer with input/output channels and specified kernel sizes for max pooling.""" - super().__init__() - self.stem1 = Conv(c1, cm, 3, 2, act=nn.ReLU()) - self.stem2a = Conv(cm, cm // 2, 2, 1, 0, act=nn.ReLU()) - self.stem2b = Conv(cm // 2, cm, 2, 1, 0, act=nn.ReLU()) - self.stem3 = Conv(cm * 2, cm, 3, 2, act=nn.ReLU()) - self.stem4 = Conv(cm, c2, 1, 1, act=nn.ReLU()) - self.pool = nn.MaxPool2d(kernel_size=2, stride=1, padding=0, ceil_mode=True) - - def forward(self, x): - """Forward pass of a PPHGNetV2 backbone layer.""" - x = self.stem1(x) - x = F.pad(x, [0, 1, 0, 1]) - x2 = self.stem2a(x) - x2 = F.pad(x2, [0, 1, 0, 1]) - x2 = self.stem2b(x2) - x1 = self.pool(x) - x = torch.cat([x1, x2], dim=1) - x = self.stem3(x) - x = self.stem4(x) - return x - - -class HGBlock(nn.Module): - """ - HG_Block of PPHGNetV2 with 2 convolutions and LightConv. - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py - """ - - def __init__(self, c1, cm, c2, k=3, n=6, lightconv=False, shortcut=False, act=nn.ReLU()): - """Initializes a CSP Bottleneck with 1 convolution using specified input and output channels.""" - super().__init__() - block = LightConv if lightconv else Conv - self.m = nn.ModuleList(block(c1 if i == 0 else cm, cm, k=k, act=act) for i in range(n)) - self.sc = Conv(c1 + n * cm, c2 // 2, 1, 1, act=act) # squeeze conv - self.ec = Conv(c2 // 2, c2, 1, 1, act=act) # excitation conv - self.add = shortcut and c1 == c2 - - def forward(self, x): - """Forward pass of a PPHGNetV2 backbone layer.""" - y = [x] - y.extend(m(y[-1]) for m in self.m) - y = self.ec(self.sc(torch.cat(y, 1))) - return y + x if self.add else y - - -class SPP(nn.Module): - """Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729.""" - - def __init__(self, c1, c2, k=(5, 9, 13)): - """Initialize the SPP layer with input/output channels and pooling kernel sizes.""" - super().__init__() - c_ = c1 // 2 # hidden channels - self.cv1 = Conv(c1, c_, 1, 1) - self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) - self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) - - def forward(self, x): - """Forward pass of the SPP layer, performing spatial pyramid pooling.""" - x = self.cv1(x) - return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) - - -class SPPF(nn.Module): - """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher.""" - - def __init__(self, c1, c2, k=5): - """ - Initializes the SPPF layer with given input/output channels and kernel size. - - This module is equivalent to SPP(k=(5, 9, 13)). - """ - super().__init__() - c_ = c1 // 2 # hidden channels - self.cv1 = Conv(c1, c_, 1, 1) - self.cv2 = Conv(c_ * 4, c2, 1, 1) - self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) - - def forward(self, x): - """Forward pass through Ghost Convolution block.""" - x = self.cv1(x) - y1 = self.m(x) - y2 = self.m(y1) - return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1)) - - -class C1(nn.Module): - """CSP Bottleneck with 1 convolution.""" - - def __init__(self, c1, c2, n=1): - """Initializes the CSP Bottleneck with configurations for 1 convolution with arguments ch_in, ch_out, number.""" - super().__init__() - self.cv1 = Conv(c1, c2, 1, 1) - self.m = nn.Sequential(*(Conv(c2, c2, 3) for _ in range(n))) - - def forward(self, x): - """Applies cross-convolutions to input in the C3 module.""" - y = self.cv1(x) - return self.m(y) + y - - -class C2(nn.Module): - """CSP Bottleneck with 2 convolutions.""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initializes the CSP Bottleneck with 2 convolutions module with arguments ch_in, ch_out, number, shortcut, - groups, expansion. - """ - super().__init__() - self.c = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, 2 * self.c, 1, 1) - self.cv2 = Conv(2 * self.c, c2, 1) # optional act=FReLU(c2) - # self.attention = ChannelAttention(2 * self.c) # or SpatialAttention() - self.m = nn.Sequential(*(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))) - - def forward(self, x): - """Forward pass through the CSP bottleneck with 2 convolutions.""" - a, b = self.cv1(x).chunk(2, 1) - return self.cv2(torch.cat((self.m(a), b), 1)) - - -class C2f(nn.Module): - """Faster Implementation of CSP Bottleneck with 2 convolutions.""" - - def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): - """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups, - expansion. - """ - super().__init__() - self.c = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, 2 * self.c, 1, 1) - self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2) - self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)) - - def forward(self, x): - """Forward pass through C2f layer.""" - y = list(self.cv1(x).chunk(2, 1)) - y.extend(m(y[-1]) for m in self.m) - return self.cv2(torch.cat(y, 1)) - - def forward_split(self, x): - """Forward pass using split() instead of chunk().""" - y = list(self.cv1(x).split((self.c, self.c), 1)) - y.extend(m(y[-1]) for m in self.m) - return self.cv2(torch.cat(y, 1)) - - -class C3(nn.Module): - """CSP Bottleneck with 3 convolutions.""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values.""" - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, c_, 1, 1) - self.cv2 = Conv(c1, c_, 1, 1) - self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) - self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n))) - - def forward(self, x): - """Forward pass through the CSP bottleneck with 2 convolutions.""" - return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)) - - -class C3x(C3): - """C3 module with cross-convolutions.""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initialize C3TR instance and set default parameters.""" - super().__init__(c1, c2, n, shortcut, g, e) - self.c_ = int(c2 * e) - self.m = nn.Sequential(*(Bottleneck(self.c_, self.c_, shortcut, g, k=((1, 3), (3, 1)), e=1) for _ in range(n))) - - -class RepC3(nn.Module): - """Rep C3.""" - - def __init__(self, c1, c2, n=3, e=1.0): - """Initialize CSP Bottleneck with a single convolution using input channels, output channels, and number.""" - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, c2, 1, 1) - self.cv2 = Conv(c1, c2, 1, 1) - self.m = nn.Sequential(*[RepConv(c_, c_) for _ in range(n)]) - self.cv3 = Conv(c_, c2, 1, 1) if c_ != c2 else nn.Identity() - - def forward(self, x): - """Forward pass of RT-DETR neck layer.""" - return self.cv3(self.m(self.cv1(x)) + self.cv2(x)) - - -class C3TR(C3): - """C3 module with TransformerBlock().""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initialize C3Ghost module with GhostBottleneck().""" - super().__init__(c1, c2, n, shortcut, g, e) - c_ = int(c2 * e) - self.m = TransformerBlock(c_, c_, 4, n) - - -class C3Ghost(C3): - """C3 module with GhostBottleneck().""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initialize 'SPP' module with various pooling sizes for spatial pyramid pooling.""" - super().__init__(c1, c2, n, shortcut, g, e) - c_ = int(c2 * e) # hidden channels - self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n))) - - -class GhostBottleneck(nn.Module): - """Ghost Bottleneck https://github.com/huawei-noah/ghostnet.""" - - def __init__(self, c1, c2, k=3, s=1): - """Initializes GhostBottleneck module with arguments ch_in, ch_out, kernel, stride.""" - super().__init__() - c_ = c2 // 2 - self.conv = nn.Sequential( - GhostConv(c1, c_, 1, 1), # pw - DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw - GhostConv(c_, c2, 1, 1, act=False), # pw-linear - ) - self.shortcut = ( - nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity() - ) - - def forward(self, x): - """Applies skip connection and concatenation to input tensor.""" - return self.conv(x) + self.shortcut(x) - - -class Bottleneck(nn.Module): - """Standard bottleneck.""" - - def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5): - """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and - expansion. - """ - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, c_, k[0], 1) - self.cv2 = Conv(c_, c2, k[1], 1, g=g) - self.add = shortcut and c1 == c2 - - def forward(self, x): - """'forward()' applies the YOLO FPN to input data.""" - return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) - - -class BottleneckCSP(nn.Module): - """CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks.""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initializes the CSP Bottleneck given arguments for ch_in, ch_out, number, shortcut, groups, expansion.""" - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, c_, 1, 1) - self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False) - self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False) - self.cv4 = Conv(2 * c_, c2, 1, 1) - self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3) - self.act = nn.SiLU() - self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) - - def forward(self, x): - """Applies a CSP bottleneck with 3 convolutions.""" - y1 = self.cv3(self.m(self.cv1(x))) - y2 = self.cv2(x) - return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1)))) - - -class ResNetBlock(nn.Module): - """ResNet block with standard convolution layers.""" - - def __init__(self, c1, c2, s=1, e=4): - """Initialize convolution with given parameters.""" - super().__init__() - c3 = e * c2 - self.cv1 = Conv(c1, c2, k=1, s=1, act=True) - self.cv2 = Conv(c2, c2, k=3, s=s, p=1, act=True) - self.cv3 = Conv(c2, c3, k=1, act=False) - self.shortcut = nn.Sequential(Conv(c1, c3, k=1, s=s, act=False)) if s != 1 or c1 != c3 else nn.Identity() - - def forward(self, x): - """Forward pass through the ResNet block.""" - return F.relu(self.cv3(self.cv2(self.cv1(x))) + self.shortcut(x)) - - -class ResNetLayer(nn.Module): - """ResNet layer with multiple ResNet blocks.""" - - def __init__(self, c1, c2, s=1, is_first=False, n=1, e=4): - """Initializes the ResNetLayer given arguments.""" - super().__init__() - self.is_first = is_first - - if self.is_first: - self.layer = nn.Sequential( - Conv(c1, c2, k=7, s=2, p=3, act=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1) - ) - else: - blocks = [ResNetBlock(c1, c2, s, e=e)] - blocks.extend([ResNetBlock(e * c2, c2, 1, e=e) for _ in range(n - 1)]) - self.layer = nn.Sequential(*blocks) - - def forward(self, x): - """Forward pass through the ResNet layer.""" - return self.layer(x) - - -class MaxSigmoidAttnBlock(nn.Module): - """Max Sigmoid attention block.""" - - def __init__(self, c1, c2, nh=1, ec=128, gc=512, scale=False): - """Initializes MaxSigmoidAttnBlock with specified arguments.""" - super().__init__() - self.nh = nh - self.hc = c2 // nh - self.ec = Conv(c1, ec, k=1, act=False) if c1 != ec else None - self.gl = nn.Linear(gc, ec) - self.bias = nn.Parameter(torch.zeros(nh)) - self.proj_conv = Conv(c1, c2, k=3, s=1, act=False) - self.scale = nn.Parameter(torch.ones(1, nh, 1, 1)) if scale else 1.0 - - def forward(self, x, guide): - """Forward process.""" - bs, _, h, w = x.shape - - guide = self.gl(guide) - guide = guide.view(bs, -1, self.nh, self.hc) - embed = self.ec(x) if self.ec is not None else x - embed = embed.view(bs, self.nh, self.hc, h, w) - - aw = torch.einsum("bmchw,bnmc->bmhwn", embed, guide) - aw = aw.max(dim=-1)[0] - aw = aw / (self.hc**0.5) - aw = aw + self.bias[None, :, None, None] - aw = aw.sigmoid() * self.scale - - x = self.proj_conv(x) - x = x.view(bs, self.nh, -1, h, w) - x = x * aw.unsqueeze(2) - return x.view(bs, -1, h, w) - - -class C2fAttn(nn.Module): - """C2f module with an additional attn module.""" - - def __init__(self, c1, c2, n=1, ec=128, nh=1, gc=512, shortcut=False, g=1, e=0.5): - """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups, - expansion. - """ - super().__init__() - self.c = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, 2 * self.c, 1, 1) - self.cv2 = Conv((3 + n) * self.c, c2, 1) # optional act=FReLU(c2) - self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)) - self.attn = MaxSigmoidAttnBlock(self.c, self.c, gc=gc, ec=ec, nh=nh) - - def forward(self, x, guide): - """Forward pass through C2f layer.""" - y = list(self.cv1(x).chunk(2, 1)) - y.extend(m(y[-1]) for m in self.m) - y.append(self.attn(y[-1], guide)) - return self.cv2(torch.cat(y, 1)) - - def forward_split(self, x, guide): - """Forward pass using split() instead of chunk().""" - y = list(self.cv1(x).split((self.c, self.c), 1)) - y.extend(m(y[-1]) for m in self.m) - y.append(self.attn(y[-1], guide)) - return self.cv2(torch.cat(y, 1)) - - -class ImagePoolingAttn(nn.Module): - """ImagePoolingAttn: Enhance the text embeddings with image-aware information.""" - - def __init__(self, ec=256, ch=(), ct=512, nh=8, k=3, scale=False): - """Initializes ImagePoolingAttn with specified arguments.""" - super().__init__() - - nf = len(ch) - self.query = nn.Sequential(nn.LayerNorm(ct), nn.Linear(ct, ec)) - self.key = nn.Sequential(nn.LayerNorm(ec), nn.Linear(ec, ec)) - self.value = nn.Sequential(nn.LayerNorm(ec), nn.Linear(ec, ec)) - self.proj = nn.Linear(ec, ct) - self.scale = nn.Parameter(torch.tensor([0.0]), requires_grad=True) if scale else 1.0 - self.projections = nn.ModuleList([nn.Conv2d(in_channels, ec, kernel_size=1) for in_channels in ch]) - self.im_pools = nn.ModuleList([nn.AdaptiveMaxPool2d((k, k)) for _ in range(nf)]) - self.ec = ec - self.nh = nh - self.nf = nf - self.hc = ec // nh - self.k = k - - def forward(self, x, text): - """Executes attention mechanism on input tensor x and guide tensor.""" - bs = x[0].shape[0] - assert len(x) == self.nf - num_patches = self.k**2 - x = [pool(proj(x)).view(bs, -1, num_patches) for (x, proj, pool) in zip(x, self.projections, self.im_pools)] - x = torch.cat(x, dim=-1).transpose(1, 2) - q = self.query(text) - k = self.key(x) - v = self.value(x) - - # q = q.reshape(1, text.shape[1], self.nh, self.hc).repeat(bs, 1, 1, 1) - q = q.reshape(bs, -1, self.nh, self.hc) - k = k.reshape(bs, -1, self.nh, self.hc) - v = v.reshape(bs, -1, self.nh, self.hc) - - aw = torch.einsum("bnmc,bkmc->bmnk", q, k) - aw = aw / (self.hc**0.5) - aw = F.softmax(aw, dim=-1) - - x = torch.einsum("bmnk,bkmc->bnmc", aw, v) - x = self.proj(x.reshape(bs, -1, self.ec)) - return x * self.scale + text - - -class ContrastiveHead(nn.Module): - """Contrastive Head for YOLO-World compute the region-text scores according to the similarity between image and text - features. - """ - - def __init__(self): - """Initializes ContrastiveHead with specified region-text similarity parameters.""" - super().__init__() - self.bias = nn.Parameter(torch.zeros([])) - self.logit_scale = nn.Parameter(torch.ones([]) * torch.tensor(1 / 0.07).log()) - - def forward(self, x, w): - """Forward function of contrastive learning.""" - x = F.normalize(x, dim=1, p=2) - w = F.normalize(w, dim=-1, p=2) - x = torch.einsum("bchw,bkc->bkhw", x, w) - return x * self.logit_scale.exp() + self.bias - - -class BNContrastiveHead(nn.Module): - """ - Batch Norm Contrastive Head for YOLO-World using batch norm instead of l2-normalization. - - Args: - embed_dims (int): Embed dimensions of text and image features. - """ - - def __init__(self, embed_dims: int): - """Initialize ContrastiveHead with region-text similarity parameters.""" - super().__init__() - self.norm = nn.BatchNorm2d(embed_dims) - self.bias = nn.Parameter(torch.zeros([])) - # use -1.0 is more stable - self.logit_scale = nn.Parameter(-1.0 * torch.ones([])) - - def forward(self, x, w): - """Forward function of contrastive learning.""" - x = self.norm(x) - w = F.normalize(w, dim=-1, p=2) - x = torch.einsum("bchw,bkc->bkhw", x, w) - return x * self.logit_scale.exp() + self.bias - - -class RepBottleneck(nn.Module): - """Rep bottleneck.""" - - def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5): - """Initializes a RepBottleneck module with customizable in/out channels, shortcut option, groups and expansion - ratio. - """ - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = RepConv(c1, c_, k[0], 1) - self.cv2 = Conv(c_, c2, k[1], 1, g=g) - self.add = shortcut and c1 == c2 - - def forward(self, x): - """Forward pass through RepBottleneck layer.""" - return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) - - -class RepCSP(nn.Module): - """Rep CSP Bottleneck with 3 convolutions.""" - - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): - """Initializes RepCSP layer with given channels, repetitions, shortcut, groups and expansion ratio.""" - super().__init__() - c_ = int(c2 * e) # hidden channels - self.cv1 = Conv(c1, c_, 1, 1) - self.cv2 = Conv(c1, c_, 1, 1) - self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) - self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) - - def forward(self, x): - """Forward pass through RepCSP layer.""" - return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)) - - -class RepNCSPELAN4(nn.Module): - """CSP-ELAN.""" - - def __init__(self, c1, c2, c3, c4, n=1): - """Initializes CSP-ELAN layer with specified channel sizes, repetitions, and convolutions.""" - super().__init__() - self.c = c3 // 2 - self.cv1 = Conv(c1, c3, 1, 1) - self.cv2 = nn.Sequential(RepCSP(c3 // 2, c4, n), Conv(c4, c4, 3, 1)) - self.cv3 = nn.Sequential(RepCSP(c4, c4, n), Conv(c4, c4, 3, 1)) - self.cv4 = Conv(c3 + (2 * c4), c2, 1, 1) - - def forward(self, x): - """Forward pass through RepNCSPELAN4 layer.""" - y = list(self.cv1(x).chunk(2, 1)) - y.extend((m(y[-1])) for m in [self.cv2, self.cv3]) - return self.cv4(torch.cat(y, 1)) - - def forward_split(self, x): - """Forward pass using split() instead of chunk().""" - y = list(self.cv1(x).split((self.c, self.c), 1)) - y.extend(m(y[-1]) for m in [self.cv2, self.cv3]) - return self.cv4(torch.cat(y, 1)) - - -class ADown(nn.Module): - """ADown.""" - - def __init__(self, c1, c2): - """Initializes ADown module with convolution layers to downsample input from channels c1 to c2.""" - super().__init__() - self.c = c2 // 2 - self.cv1 = Conv(c1 // 2, self.c, 3, 2, 1) - self.cv2 = Conv(c1 // 2, self.c, 1, 1, 0) - - def forward(self, x): - """Forward pass through ADown layer.""" - x = torch.nn.functional.avg_pool2d(x, 2, 1, 0, False, True) - x1, x2 = x.chunk(2, 1) - x1 = self.cv1(x1) - x2 = torch.nn.functional.max_pool2d(x2, 3, 2, 1) - x2 = self.cv2(x2) - return torch.cat((x1, x2), 1) - - -class SPPELAN(nn.Module): - """SPP-ELAN.""" - - def __init__(self, c1, c2, c3, k=5): - """Initializes SPP-ELAN block with convolution and max pooling layers for spatial pyramid pooling.""" - super().__init__() - self.c = c3 - self.cv1 = Conv(c1, c3, 1, 1) - self.cv2 = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) - self.cv3 = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) - self.cv4 = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) - self.cv5 = Conv(4 * c3, c2, 1, 1) - - def forward(self, x): - """Forward pass through SPPELAN layer.""" - y = [self.cv1(x)] - y.extend(m(y[-1]) for m in [self.cv2, self.cv3, self.cv4]) - return self.cv5(torch.cat(y, 1)) - - -class Silence(nn.Module): - """Silence.""" - - def __init__(self): - """Initializes the Silence module.""" - super(Silence, self).__init__() - - def forward(self, x): - """Forward pass through Silence layer.""" - return x - - -class CBLinear(nn.Module): - """CBLinear.""" - - def __init__(self, c1, c2s, k=1, s=1, p=None, g=1): - """Initializes the CBLinear module, passing inputs unchanged.""" - super(CBLinear, self).__init__() - self.c2s = c2s - self.conv = nn.Conv2d(c1, sum(c2s), k, s, autopad(k, p), groups=g, bias=True) - - def forward(self, x): - """Forward pass through CBLinear layer.""" - outs = self.conv(x).split(self.c2s, dim=1) - return outs - - -class CBFuse(nn.Module): - """CBFuse.""" - - def __init__(self, idx): - """Initializes CBFuse module with layer index for selective feature fusion.""" - super(CBFuse, self).__init__() - self.idx = idx - - def forward(self, xs): - """Forward pass through CBFuse layer.""" - target_size = xs[-1].shape[2:] - res = [F.interpolate(x[self.idx[i]], size=target_size, mode="nearest") for i, x in enumerate(xs[:-1])] - out = torch.sum(torch.stack(res + xs[-1:]), dim=0) - return out diff --git a/ultralytics-main/ultralytics/nn/modules/conv.py b/ultralytics-main/ultralytics/nn/modules/conv.py deleted file mode 100644 index 399c422..0000000 --- a/ultralytics-main/ultralytics/nn/modules/conv.py +++ /dev/null @@ -1,333 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Convolution modules.""" - -import math - -import numpy as np -import torch -import torch.nn as nn - -__all__ = ( - "Conv", - "Conv2", - "LightConv", - "DWConv", - "DWConvTranspose2d", - "ConvTranspose", - "Focus", - "GhostConv", - "ChannelAttention", - "SpatialAttention", - "CBAM", - "Concat", - "RepConv", -) - - -def autopad(k, p=None, d=1): # kernel, padding, dilation - """Pad to 'same' shape outputs.""" - if d > 1: - k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size - if p is None: - p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad - return p - - -class Conv(nn.Module): - """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation).""" - - default_act = nn.SiLU() # default activation - - def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): - """Initialize Conv layer with given arguments including activation.""" - super().__init__() - self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) - self.bn = nn.BatchNorm2d(c2) - self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() - - def forward(self, x): - """Apply convolution, batch normalization and activation to input tensor.""" - return self.act(self.bn(self.conv(x))) - - def forward_fuse(self, x): - """Perform transposed convolution of 2D data.""" - return self.act(self.conv(x)) - - -class Conv2(Conv): - """Simplified RepConv module with Conv fusing.""" - - def __init__(self, c1, c2, k=3, s=1, p=None, g=1, d=1, act=True): - """Initialize Conv layer with given arguments including activation.""" - super().__init__(c1, c2, k, s, p, g=g, d=d, act=act) - self.cv2 = nn.Conv2d(c1, c2, 1, s, autopad(1, p, d), groups=g, dilation=d, bias=False) # add 1x1 conv - - def forward(self, x): - """Apply convolution, batch normalization and activation to input tensor.""" - return self.act(self.bn(self.conv(x) + self.cv2(x))) - - def forward_fuse(self, x): - """Apply fused convolution, batch normalization and activation to input tensor.""" - return self.act(self.bn(self.conv(x))) - - def fuse_convs(self): - """Fuse parallel convolutions.""" - w = torch.zeros_like(self.conv.weight.data) - i = [x // 2 for x in w.shape[2:]] - w[:, :, i[0] : i[0] + 1, i[1] : i[1] + 1] = self.cv2.weight.data.clone() - self.conv.weight.data += w - self.__delattr__("cv2") - self.forward = self.forward_fuse - - -class LightConv(nn.Module): - """ - Light convolution with args(ch_in, ch_out, kernel). - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py - """ - - def __init__(self, c1, c2, k=1, act=nn.ReLU()): - """Initialize Conv layer with given arguments including activation.""" - super().__init__() - self.conv1 = Conv(c1, c2, 1, act=False) - self.conv2 = DWConv(c2, c2, k, act=act) - - def forward(self, x): - """Apply 2 convolutions to input tensor.""" - return self.conv2(self.conv1(x)) - - -class DWConv(Conv): - """Depth-wise convolution.""" - - def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation - """Initialize Depth-wise convolution with given parameters.""" - super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act) - - -class DWConvTranspose2d(nn.ConvTranspose2d): - """Depth-wise transpose convolution.""" - - def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out - """Initialize DWConvTranspose2d class with given parameters.""" - super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2)) - - -class ConvTranspose(nn.Module): - """Convolution transpose 2d layer.""" - - default_act = nn.SiLU() # default activation - - def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True): - """Initialize ConvTranspose2d layer with batch normalization and activation function.""" - super().__init__() - self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn) - self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity() - self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() - - def forward(self, x): - """Applies transposed convolutions, batch normalization and activation to input.""" - return self.act(self.bn(self.conv_transpose(x))) - - def forward_fuse(self, x): - """Applies activation and convolution transpose operation to input.""" - return self.act(self.conv_transpose(x)) - - -class Focus(nn.Module): - """Focus wh information into c-space.""" - - def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): - """Initializes Focus object with user defined channel, convolution, padding, group and activation values.""" - super().__init__() - self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act) - # self.contract = Contract(gain=2) - - def forward(self, x): - """ - Applies convolution to concatenated tensor and returns the output. - - Input shape is (b,c,w,h) and output shape is (b,4c,w/2,h/2). - """ - return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1)) - # return self.conv(self.contract(x)) - - -class GhostConv(nn.Module): - """Ghost Convolution https://github.com/huawei-noah/ghostnet.""" - - def __init__(self, c1, c2, k=1, s=1, g=1, act=True): - """Initializes the GhostConv object with input channels, output channels, kernel size, stride, groups and - activation. - """ - super().__init__() - c_ = c2 // 2 # hidden channels - self.cv1 = Conv(c1, c_, k, s, None, g, act=act) - self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act) - - def forward(self, x): - """Forward propagation through a Ghost Bottleneck layer with skip connection.""" - y = self.cv1(x) - return torch.cat((y, self.cv2(y)), 1) - - -class RepConv(nn.Module): - """ - RepConv is a basic rep-style block, including training and deploy status. - - This module is used in RT-DETR. - Based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py - """ - - default_act = nn.SiLU() # default activation - - def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False): - """Initializes Light Convolution layer with inputs, outputs & optional activation function.""" - super().__init__() - assert k == 3 and p == 1 - self.g = g - self.c1 = c1 - self.c2 = c2 - self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() - - self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None - self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False) - self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False) - - def forward_fuse(self, x): - """Forward process.""" - return self.act(self.conv(x)) - - def forward(self, x): - """Forward process.""" - id_out = 0 if self.bn is None else self.bn(x) - return self.act(self.conv1(x) + self.conv2(x) + id_out) - - def get_equivalent_kernel_bias(self): - """Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases.""" - kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1) - kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2) - kernelid, biasid = self._fuse_bn_tensor(self.bn) - return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid - - def _pad_1x1_to_3x3_tensor(self, kernel1x1): - """Pads a 1x1 tensor to a 3x3 tensor.""" - if kernel1x1 is None: - return 0 - else: - return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1]) - - def _fuse_bn_tensor(self, branch): - """Generates appropriate kernels and biases for convolution by fusing branches of the neural network.""" - if branch is None: - return 0, 0 - if isinstance(branch, Conv): - kernel = branch.conv.weight - running_mean = branch.bn.running_mean - running_var = branch.bn.running_var - gamma = branch.bn.weight - beta = branch.bn.bias - eps = branch.bn.eps - elif isinstance(branch, nn.BatchNorm2d): - if not hasattr(self, "id_tensor"): - input_dim = self.c1 // self.g - kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32) - for i in range(self.c1): - kernel_value[i, i % input_dim, 1, 1] = 1 - self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device) - kernel = self.id_tensor - running_mean = branch.running_mean - running_var = branch.running_var - gamma = branch.weight - beta = branch.bias - eps = branch.eps - std = (running_var + eps).sqrt() - t = (gamma / std).reshape(-1, 1, 1, 1) - return kernel * t, beta - running_mean * gamma / std - - def fuse_convs(self): - """Combines two convolution layers into a single layer and removes unused attributes from the class.""" - if hasattr(self, "conv"): - return - kernel, bias = self.get_equivalent_kernel_bias() - self.conv = nn.Conv2d( - in_channels=self.conv1.conv.in_channels, - out_channels=self.conv1.conv.out_channels, - kernel_size=self.conv1.conv.kernel_size, - stride=self.conv1.conv.stride, - padding=self.conv1.conv.padding, - dilation=self.conv1.conv.dilation, - groups=self.conv1.conv.groups, - bias=True, - ).requires_grad_(False) - self.conv.weight.data = kernel - self.conv.bias.data = bias - for para in self.parameters(): - para.detach_() - self.__delattr__("conv1") - self.__delattr__("conv2") - if hasattr(self, "nm"): - self.__delattr__("nm") - if hasattr(self, "bn"): - self.__delattr__("bn") - if hasattr(self, "id_tensor"): - self.__delattr__("id_tensor") - - -class ChannelAttention(nn.Module): - """Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet.""" - - def __init__(self, channels: int) -> None: - """Initializes the class and sets the basic configurations and instance variables required.""" - super().__init__() - self.pool = nn.AdaptiveAvgPool2d(1) - self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True) - self.act = nn.Sigmoid() - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Applies forward pass using activation on convolutions of the input, optionally using batch normalization.""" - return x * self.act(self.fc(self.pool(x))) - - -class SpatialAttention(nn.Module): - """Spatial-attention module.""" - - def __init__(self, kernel_size=7): - """Initialize Spatial-attention module with kernel size argument.""" - super().__init__() - assert kernel_size in (3, 7), "kernel size must be 3 or 7" - padding = 3 if kernel_size == 7 else 1 - self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False) - self.act = nn.Sigmoid() - - def forward(self, x): - """Apply channel and spatial attention on input for feature recalibration.""" - return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1))) - - -class CBAM(nn.Module): - """Convolutional Block Attention Module.""" - - def __init__(self, c1, kernel_size=7): - """Initialize CBAM with given input channel (c1) and kernel size.""" - super().__init__() - self.channel_attention = ChannelAttention(c1) - self.spatial_attention = SpatialAttention(kernel_size) - - def forward(self, x): - """Applies the forward pass through C1 module.""" - return self.spatial_attention(self.channel_attention(x)) - - -class Concat(nn.Module): - """Concatenate a list of tensors along dimension.""" - - def __init__(self, dimension=1): - """Concatenates a list of tensors along a specified dimension.""" - super().__init__() - self.d = dimension - - def forward(self, x): - """Forward pass for the YOLOv8 mask Proto module.""" - return torch.cat(x, self.d) diff --git a/ultralytics-main/ultralytics/nn/modules/head.py b/ultralytics-main/ultralytics/nn/modules/head.py deleted file mode 100644 index 9cd794e..0000000 --- a/ultralytics-main/ultralytics/nn/modules/head.py +++ /dev/null @@ -1,482 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Model head modules.""" - -import math - -import torch -import torch.nn as nn -from torch.nn.init import constant_, xavier_uniform_ - -from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, make_anchors -from .block import DFL, Proto, ContrastiveHead, BNContrastiveHead -from .conv import Conv -from .transformer import MLP, DeformableTransformerDecoder, DeformableTransformerDecoderLayer -from .utils import bias_init_with_prob, linear_init - -__all__ = "Detect", "Segment", "Pose", "Classify", "OBB", "RTDETRDecoder" - - -class Detect(nn.Module): - """YOLOv8 Detect head for detection models.""" - - dynamic = False # force grid reconstruction - export = False # export mode - shape = None - anchors = torch.empty(0) # init - strides = torch.empty(0) # init - - def __init__(self, nc=80, ch=()): - """Initializes the YOLOv8 detection layer with specified number of classes and channels.""" - super().__init__() - self.nc = nc # number of classes - self.nl = len(ch) # number of detection layers - self.reg_max = 16 # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x) - self.no = nc + self.reg_max * 4 # number of outputs per anchor - self.stride = torch.zeros(self.nl) # strides computed during build - c2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], min(self.nc, 100)) # channels - self.cv2 = nn.ModuleList( - nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch - ) - self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch) - self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity() - - def forward(self, x): - """Concatenates and returns predicted bounding boxes and class probabilities.""" - for i in range(self.nl): - x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1) - if self.training: # Training path - return x - - # Inference path - shape = x[0].shape # BCHW - x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2) - if self.dynamic or self.shape != shape: - self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5)) - self.shape = shape - - if self.export and self.format in ("saved_model", "pb", "tflite", "edgetpu", "tfjs"): # avoid TF FlexSplitV ops - box = x_cat[:, : self.reg_max * 4] - cls = x_cat[:, self.reg_max * 4 :] - else: - box, cls = x_cat.split((self.reg_max * 4, self.nc), 1) - - if self.export and self.format in ("tflite", "edgetpu"): - # Precompute normalization factor to increase numerical stability - # See https://github.com/ultralytics/ultralytics/issues/7371 - grid_h = shape[2] - grid_w = shape[3] - grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1) - norm = self.strides / (self.stride[0] * grid_size) - dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2]) - else: - dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides - - y = torch.cat((dbox, cls.sigmoid()), 1) - return y if self.export else (y, x) - - def bias_init(self): - """Initialize Detect() biases, WARNING: requires stride availability.""" - m = self # self.model[-1] # Detect() module - # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1 - # ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # nominal class frequency - for a, b, s in zip(m.cv2, m.cv3, m.stride): # from - a[-1].bias.data[:] = 1.0 # box - b[-1].bias.data[: m.nc] = math.log(5 / m.nc / (640 / s) ** 2) # cls (.01 objects, 80 classes, 640 img) - - def decode_bboxes(self, bboxes, anchors): - """Decode bounding boxes.""" - return dist2bbox(bboxes, anchors, xywh=True, dim=1) - - -class Segment(Detect): - """YOLOv8 Segment head for segmentation models.""" - - def __init__(self, nc=80, nm=32, npr=256, ch=()): - """Initialize the YOLO model attributes such as the number of masks, prototypes, and the convolution layers.""" - super().__init__(nc, ch) - self.nm = nm # number of masks - self.npr = npr # number of protos - self.proto = Proto(ch[0], self.npr, self.nm) # protos - self.detect = Detect.forward - - c4 = max(ch[0] // 4, self.nm) - self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nm, 1)) for x in ch) - - def forward(self, x): - """Return model outputs and mask coefficients if training, otherwise return outputs and mask coefficients.""" - p = self.proto(x[0]) # mask protos - bs = p.shape[0] # batch size - - mc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)], 2) # mask coefficients - x = self.detect(self, x) - if self.training: - return x, mc, p - return (torch.cat([x, mc], 1), p) if self.export else (torch.cat([x[0], mc], 1), (x[1], mc, p)) - - -class OBB(Detect): - """YOLOv8 OBB detection head for detection with rotation models.""" - - def __init__(self, nc=80, ne=1, ch=()): - """Initialize OBB with number of classes `nc` and layer channels `ch`.""" - super().__init__(nc, ch) - self.ne = ne # number of extra parameters - self.detect = Detect.forward - - c4 = max(ch[0] // 4, self.ne) - self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.ne, 1)) for x in ch) - - def forward(self, x): - """Concatenates and returns predicted bounding boxes and class probabilities.""" - bs = x[0].shape[0] # batch size - angle = torch.cat([self.cv4[i](x[i]).view(bs, self.ne, -1) for i in range(self.nl)], 2) # OBB theta logits - # NOTE: set `angle` as an attribute so that `decode_bboxes` could use it. - angle = (angle.sigmoid() - 0.25) * math.pi # [-pi/4, 3pi/4] - # angle = angle.sigmoid() * math.pi / 2 # [0, pi/2] - if not self.training: - self.angle = angle - x = self.detect(self, x) - if self.training: - return x, angle - return torch.cat([x, angle], 1) if self.export else (torch.cat([x[0], angle], 1), (x[1], angle)) - - def decode_bboxes(self, bboxes, anchors): - """Decode rotated bounding boxes.""" - return dist2rbox(bboxes, self.angle, anchors, dim=1) - - -class Pose(Detect): - """YOLOv8 Pose head for keypoints models.""" - - def __init__(self, nc=80, kpt_shape=(17, 3), ch=()): - """Initialize YOLO network with default parameters and Convolutional Layers.""" - super().__init__(nc, ch) - self.kpt_shape = kpt_shape # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible) - self.nk = kpt_shape[0] * kpt_shape[1] # number of keypoints total - self.detect = Detect.forward - - c4 = max(ch[0] // 4, self.nk) - self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nk, 1)) for x in ch) - - def forward(self, x): - """Perform forward pass through YOLO model and return predictions.""" - bs = x[0].shape[0] # batch size - kpt = torch.cat([self.cv4[i](x[i]).view(bs, self.nk, -1) for i in range(self.nl)], -1) # (bs, 17*3, h*w) - x = self.detect(self, x) - if self.training: - return x, kpt - pred_kpt = self.kpts_decode(bs, kpt) - return torch.cat([x, pred_kpt], 1) if self.export else (torch.cat([x[0], pred_kpt], 1), (x[1], kpt)) - - def kpts_decode(self, bs, kpts): - """Decodes keypoints.""" - ndim = self.kpt_shape[1] - if self.export: # required for TFLite export to avoid 'PLACEHOLDER_FOR_GREATER_OP_CODES' bug - y = kpts.view(bs, *self.kpt_shape, -1) - a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * self.strides - if ndim == 3: - a = torch.cat((a, y[:, :, 2:3].sigmoid()), 2) - return a.view(bs, self.nk, -1) - else: - y = kpts.clone() - if ndim == 3: - y[:, 2::3] = y[:, 2::3].sigmoid() # sigmoid (WARNING: inplace .sigmoid_() Apple MPS bug) - y[:, 0::ndim] = (y[:, 0::ndim] * 2.0 + (self.anchors[0] - 0.5)) * self.strides - y[:, 1::ndim] = (y[:, 1::ndim] * 2.0 + (self.anchors[1] - 0.5)) * self.strides - return y - - -class Classify(nn.Module): - """YOLOv8 classification head, i.e. x(b,c1,20,20) to x(b,c2).""" - - def __init__(self, c1, c2, k=1, s=1, p=None, g=1): - """Initializes YOLOv8 classification head with specified input and output channels, kernel size, stride, - padding, and groups. - """ - super().__init__() - c_ = 1280 # efficientnet_b0 size - self.conv = Conv(c1, c_, k, s, p, g) - self.pool = nn.AdaptiveAvgPool2d(1) # to x(b,c_,1,1) - self.drop = nn.Dropout(p=0.0, inplace=True) - self.linear = nn.Linear(c_, c2) # to x(b,c2) - - def forward(self, x): - """Performs a forward pass of the YOLO model on input image data.""" - if isinstance(x, list): - x = torch.cat(x, 1) - x = self.linear(self.drop(self.pool(self.conv(x)).flatten(1))) - return x if self.training else x.softmax(1) - - -class WorldDetect(Detect): - def __init__(self, nc=80, embed=512, with_bn=False, ch=()): - """Initialize YOLOv8 detection layer with nc classes and layer channels ch.""" - super().__init__(nc, ch) - c3 = max(ch[0], min(self.nc, 100)) - self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, embed, 1)) for x in ch) - self.cv4 = nn.ModuleList(BNContrastiveHead(embed) if with_bn else ContrastiveHead() for _ in ch) - - def forward(self, x, text): - """Concatenates and returns predicted bounding boxes and class probabilities.""" - for i in range(self.nl): - x[i] = torch.cat((self.cv2[i](x[i]), self.cv4[i](self.cv3[i](x[i]), text)), 1) - if self.training: - return x - - # Inference path - shape = x[0].shape # BCHW - x_cat = torch.cat([xi.view(shape[0], self.nc + self.reg_max * 4, -1) for xi in x], 2) - if self.dynamic or self.shape != shape: - self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5)) - self.shape = shape - - if self.export and self.format in ("saved_model", "pb", "tflite", "edgetpu", "tfjs"): # avoid TF FlexSplitV ops - box = x_cat[:, : self.reg_max * 4] - cls = x_cat[:, self.reg_max * 4 :] - else: - box, cls = x_cat.split((self.reg_max * 4, self.nc), 1) - - if self.export and self.format in ("tflite", "edgetpu"): - # Precompute normalization factor to increase numerical stability - # See https://github.com/ultralytics/ultralytics/issues/7371 - grid_h = shape[2] - grid_w = shape[3] - grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1) - norm = self.strides / (self.stride[0] * grid_size) - dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2]) - else: - dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides - - y = torch.cat((dbox, cls.sigmoid()), 1) - return y if self.export else (y, x) - - -class RTDETRDecoder(nn.Module): - """ - Real-Time Deformable Transformer Decoder (RTDETRDecoder) module for object detection. - - This decoder module utilizes Transformer architecture along with deformable convolutions to predict bounding boxes - and class labels for objects in an image. It integrates features from multiple layers and runs through a series of - Transformer decoder layers to output the final predictions. - """ - - export = False # export mode - - def __init__( - self, - nc=80, - ch=(512, 1024, 2048), - hd=256, # hidden dim - nq=300, # num queries - ndp=4, # num decoder points - nh=8, # num head - ndl=6, # num decoder layers - d_ffn=1024, # dim of feedforward - dropout=0.0, - act=nn.ReLU(), - eval_idx=-1, - # Training args - nd=100, # num denoising - label_noise_ratio=0.5, - box_noise_scale=1.0, - learnt_init_query=False, - ): - """ - Initializes the RTDETRDecoder module with the given parameters. - - Args: - nc (int): Number of classes. Default is 80. - ch (tuple): Channels in the backbone feature maps. Default is (512, 1024, 2048). - hd (int): Dimension of hidden layers. Default is 256. - nq (int): Number of query points. Default is 300. - ndp (int): Number of decoder points. Default is 4. - nh (int): Number of heads in multi-head attention. Default is 8. - ndl (int): Number of decoder layers. Default is 6. - d_ffn (int): Dimension of the feed-forward networks. Default is 1024. - dropout (float): Dropout rate. Default is 0. - act (nn.Module): Activation function. Default is nn.ReLU. - eval_idx (int): Evaluation index. Default is -1. - nd (int): Number of denoising. Default is 100. - label_noise_ratio (float): Label noise ratio. Default is 0.5. - box_noise_scale (float): Box noise scale. Default is 1.0. - learnt_init_query (bool): Whether to learn initial query embeddings. Default is False. - """ - super().__init__() - self.hidden_dim = hd - self.nhead = nh - self.nl = len(ch) # num level - self.nc = nc - self.num_queries = nq - self.num_decoder_layers = ndl - - # Backbone feature projection - self.input_proj = nn.ModuleList(nn.Sequential(nn.Conv2d(x, hd, 1, bias=False), nn.BatchNorm2d(hd)) for x in ch) - # NOTE: simplified version but it's not consistent with .pt weights. - # self.input_proj = nn.ModuleList(Conv(x, hd, act=False) for x in ch) - - # Transformer module - decoder_layer = DeformableTransformerDecoderLayer(hd, nh, d_ffn, dropout, act, self.nl, ndp) - self.decoder = DeformableTransformerDecoder(hd, decoder_layer, ndl, eval_idx) - - # Denoising part - self.denoising_class_embed = nn.Embedding(nc, hd) - self.num_denoising = nd - self.label_noise_ratio = label_noise_ratio - self.box_noise_scale = box_noise_scale - - # Decoder embedding - self.learnt_init_query = learnt_init_query - if learnt_init_query: - self.tgt_embed = nn.Embedding(nq, hd) - self.query_pos_head = MLP(4, 2 * hd, hd, num_layers=2) - - # Encoder head - self.enc_output = nn.Sequential(nn.Linear(hd, hd), nn.LayerNorm(hd)) - self.enc_score_head = nn.Linear(hd, nc) - self.enc_bbox_head = MLP(hd, hd, 4, num_layers=3) - - # Decoder head - self.dec_score_head = nn.ModuleList([nn.Linear(hd, nc) for _ in range(ndl)]) - self.dec_bbox_head = nn.ModuleList([MLP(hd, hd, 4, num_layers=3) for _ in range(ndl)]) - - self._reset_parameters() - - def forward(self, x, batch=None): - """Runs the forward pass of the module, returning bounding box and classification scores for the input.""" - from ultralytics.models.utils.ops import get_cdn_group - - # Input projection and embedding - feats, shapes = self._get_encoder_input(x) - - # Prepare denoising training - dn_embed, dn_bbox, attn_mask, dn_meta = get_cdn_group( - batch, - self.nc, - self.num_queries, - self.denoising_class_embed.weight, - self.num_denoising, - self.label_noise_ratio, - self.box_noise_scale, - self.training, - ) - - embed, refer_bbox, enc_bboxes, enc_scores = self._get_decoder_input(feats, shapes, dn_embed, dn_bbox) - - # Decoder - dec_bboxes, dec_scores = self.decoder( - embed, - refer_bbox, - feats, - shapes, - self.dec_bbox_head, - self.dec_score_head, - self.query_pos_head, - attn_mask=attn_mask, - ) - x = dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta - if self.training: - return x - # (bs, 300, 4+nc) - y = torch.cat((dec_bboxes.squeeze(0), dec_scores.squeeze(0).sigmoid()), -1) - return y if self.export else (y, x) - - def _generate_anchors(self, shapes, grid_size=0.05, dtype=torch.float32, device="cpu", eps=1e-2): - """Generates anchor bounding boxes for given shapes with specific grid size and validates them.""" - anchors = [] - for i, (h, w) in enumerate(shapes): - sy = torch.arange(end=h, dtype=dtype, device=device) - sx = torch.arange(end=w, dtype=dtype, device=device) - grid_y, grid_x = torch.meshgrid(sy, sx, indexing="ij") if TORCH_1_10 else torch.meshgrid(sy, sx) - grid_xy = torch.stack([grid_x, grid_y], -1) # (h, w, 2) - - valid_WH = torch.tensor([w, h], dtype=dtype, device=device) - grid_xy = (grid_xy.unsqueeze(0) + 0.5) / valid_WH # (1, h, w, 2) - wh = torch.ones_like(grid_xy, dtype=dtype, device=device) * grid_size * (2.0**i) - anchors.append(torch.cat([grid_xy, wh], -1).view(-1, h * w, 4)) # (1, h*w, 4) - - anchors = torch.cat(anchors, 1) # (1, h*w*nl, 4) - valid_mask = ((anchors > eps) & (anchors < 1 - eps)).all(-1, keepdim=True) # 1, h*w*nl, 1 - anchors = torch.log(anchors / (1 - anchors)) - anchors = anchors.masked_fill(~valid_mask, float("inf")) - return anchors, valid_mask - - def _get_encoder_input(self, x): - """Processes and returns encoder inputs by getting projection features from input and concatenating them.""" - # Get projection features - x = [self.input_proj[i](feat) for i, feat in enumerate(x)] - # Get encoder inputs - feats = [] - shapes = [] - for feat in x: - h, w = feat.shape[2:] - # [b, c, h, w] -> [b, h*w, c] - feats.append(feat.flatten(2).permute(0, 2, 1)) - # [nl, 2] - shapes.append([h, w]) - - # [b, h*w, c] - feats = torch.cat(feats, 1) - return feats, shapes - - def _get_decoder_input(self, feats, shapes, dn_embed=None, dn_bbox=None): - """Generates and prepares the input required for the decoder from the provided features and shapes.""" - bs = feats.shape[0] - # Prepare input for decoder - anchors, valid_mask = self._generate_anchors(shapes, dtype=feats.dtype, device=feats.device) - features = self.enc_output(valid_mask * feats) # bs, h*w, 256 - - enc_outputs_scores = self.enc_score_head(features) # (bs, h*w, nc) - - # Query selection - # (bs, num_queries) - topk_ind = torch.topk(enc_outputs_scores.max(-1).values, self.num_queries, dim=1).indices.view(-1) - # (bs, num_queries) - batch_ind = torch.arange(end=bs, dtype=topk_ind.dtype).unsqueeze(-1).repeat(1, self.num_queries).view(-1) - - # (bs, num_queries, 256) - top_k_features = features[batch_ind, topk_ind].view(bs, self.num_queries, -1) - # (bs, num_queries, 4) - top_k_anchors = anchors[:, topk_ind].view(bs, self.num_queries, -1) - - # Dynamic anchors + static content - refer_bbox = self.enc_bbox_head(top_k_features) + top_k_anchors - - enc_bboxes = refer_bbox.sigmoid() - if dn_bbox is not None: - refer_bbox = torch.cat([dn_bbox, refer_bbox], 1) - enc_scores = enc_outputs_scores[batch_ind, topk_ind].view(bs, self.num_queries, -1) - - embeddings = self.tgt_embed.weight.unsqueeze(0).repeat(bs, 1, 1) if self.learnt_init_query else top_k_features - if self.training: - refer_bbox = refer_bbox.detach() - if not self.learnt_init_query: - embeddings = embeddings.detach() - if dn_embed is not None: - embeddings = torch.cat([dn_embed, embeddings], 1) - - return embeddings, refer_bbox, enc_bboxes, enc_scores - - # TODO - def _reset_parameters(self): - """Initializes or resets the parameters of the model's various components with predefined weights and biases.""" - # Class and bbox head init - bias_cls = bias_init_with_prob(0.01) / 80 * self.nc - # NOTE: the weight initialization in `linear_init` would cause NaN when training with custom datasets. - # linear_init(self.enc_score_head) - constant_(self.enc_score_head.bias, bias_cls) - constant_(self.enc_bbox_head.layers[-1].weight, 0.0) - constant_(self.enc_bbox_head.layers[-1].bias, 0.0) - for cls_, reg_ in zip(self.dec_score_head, self.dec_bbox_head): - # linear_init(cls_) - constant_(cls_.bias, bias_cls) - constant_(reg_.layers[-1].weight, 0.0) - constant_(reg_.layers[-1].bias, 0.0) - - linear_init(self.enc_output[0]) - xavier_uniform_(self.enc_output[0].weight) - if self.learnt_init_query: - xavier_uniform_(self.tgt_embed.weight) - xavier_uniform_(self.query_pos_head.layers[0].weight) - xavier_uniform_(self.query_pos_head.layers[1].weight) - for layer in self.input_proj: - xavier_uniform_(layer[0].weight) diff --git a/ultralytics-main/ultralytics/nn/modules/transformer.py b/ultralytics-main/ultralytics/nn/modules/transformer.py deleted file mode 100644 index 062c609..0000000 --- a/ultralytics-main/ultralytics/nn/modules/transformer.py +++ /dev/null @@ -1,426 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Transformer modules.""" - -import math - -import torch -import torch.nn as nn -import torch.nn.functional as F -from torch.nn.init import constant_, xavier_uniform_ - -from .conv import Conv -from .utils import _get_clones, inverse_sigmoid, multi_scale_deformable_attn_pytorch - -__all__ = ( - "TransformerEncoderLayer", - "TransformerLayer", - "TransformerBlock", - "MLPBlock", - "LayerNorm2d", - "AIFI", - "DeformableTransformerDecoder", - "DeformableTransformerDecoderLayer", - "MSDeformAttn", - "MLP", -) - - -class TransformerEncoderLayer(nn.Module): - """Defines a single layer of the transformer encoder.""" - - def __init__(self, c1, cm=2048, num_heads=8, dropout=0.0, act=nn.GELU(), normalize_before=False): - """Initialize the TransformerEncoderLayer with specified parameters.""" - super().__init__() - from ...utils.torch_utils import TORCH_1_9 - - if not TORCH_1_9: - raise ModuleNotFoundError( - "TransformerEncoderLayer() requires torch>=1.9 to use nn.MultiheadAttention(batch_first=True)." - ) - self.ma = nn.MultiheadAttention(c1, num_heads, dropout=dropout, batch_first=True) - # Implementation of Feedforward model - self.fc1 = nn.Linear(c1, cm) - self.fc2 = nn.Linear(cm, c1) - - self.norm1 = nn.LayerNorm(c1) - self.norm2 = nn.LayerNorm(c1) - self.dropout = nn.Dropout(dropout) - self.dropout1 = nn.Dropout(dropout) - self.dropout2 = nn.Dropout(dropout) - - self.act = act - self.normalize_before = normalize_before - - @staticmethod - def with_pos_embed(tensor, pos=None): - """Add position embeddings to the tensor if provided.""" - return tensor if pos is None else tensor + pos - - def forward_post(self, src, src_mask=None, src_key_padding_mask=None, pos=None): - """Performs forward pass with post-normalization.""" - q = k = self.with_pos_embed(src, pos) - src2 = self.ma(q, k, value=src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0] - src = src + self.dropout1(src2) - src = self.norm1(src) - src2 = self.fc2(self.dropout(self.act(self.fc1(src)))) - src = src + self.dropout2(src2) - return self.norm2(src) - - def forward_pre(self, src, src_mask=None, src_key_padding_mask=None, pos=None): - """Performs forward pass with pre-normalization.""" - src2 = self.norm1(src) - q = k = self.with_pos_embed(src2, pos) - src2 = self.ma(q, k, value=src2, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0] - src = src + self.dropout1(src2) - src2 = self.norm2(src) - src2 = self.fc2(self.dropout(self.act(self.fc1(src2)))) - return src + self.dropout2(src2) - - def forward(self, src, src_mask=None, src_key_padding_mask=None, pos=None): - """Forward propagates the input through the encoder module.""" - if self.normalize_before: - return self.forward_pre(src, src_mask, src_key_padding_mask, pos) - return self.forward_post(src, src_mask, src_key_padding_mask, pos) - - -class AIFI(TransformerEncoderLayer): - """Defines the AIFI transformer layer.""" - - def __init__(self, c1, cm=2048, num_heads=8, dropout=0, act=nn.GELU(), normalize_before=False): - """Initialize the AIFI instance with specified parameters.""" - super().__init__(c1, cm, num_heads, dropout, act, normalize_before) - - def forward(self, x): - """Forward pass for the AIFI transformer layer.""" - c, h, w = x.shape[1:] - pos_embed = self.build_2d_sincos_position_embedding(w, h, c) - # Flatten [B, C, H, W] to [B, HxW, C] - x = super().forward(x.flatten(2).permute(0, 2, 1), pos=pos_embed.to(device=x.device, dtype=x.dtype)) - return x.permute(0, 2, 1).view([-1, c, h, w]).contiguous() - - @staticmethod - def build_2d_sincos_position_embedding(w, h, embed_dim=256, temperature=10000.0): - """Builds 2D sine-cosine position embedding.""" - assert embed_dim % 4 == 0, "Embed dimension must be divisible by 4 for 2D sin-cos position embedding" - grid_w = torch.arange(w, dtype=torch.float32) - grid_h = torch.arange(h, dtype=torch.float32) - grid_w, grid_h = torch.meshgrid(grid_w, grid_h, indexing="ij") - pos_dim = embed_dim // 4 - omega = torch.arange(pos_dim, dtype=torch.float32) / pos_dim - omega = 1.0 / (temperature**omega) - - out_w = grid_w.flatten()[..., None] @ omega[None] - out_h = grid_h.flatten()[..., None] @ omega[None] - - return torch.cat([torch.sin(out_w), torch.cos(out_w), torch.sin(out_h), torch.cos(out_h)], 1)[None] - - -class TransformerLayer(nn.Module): - """Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance).""" - - def __init__(self, c, num_heads): - """Initializes a self-attention mechanism using linear transformations and multi-head attention.""" - super().__init__() - self.q = nn.Linear(c, c, bias=False) - self.k = nn.Linear(c, c, bias=False) - self.v = nn.Linear(c, c, bias=False) - self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads) - self.fc1 = nn.Linear(c, c, bias=False) - self.fc2 = nn.Linear(c, c, bias=False) - - def forward(self, x): - """Apply a transformer block to the input x and return the output.""" - x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x - return self.fc2(self.fc1(x)) + x - - -class TransformerBlock(nn.Module): - """Vision Transformer https://arxiv.org/abs/2010.11929.""" - - def __init__(self, c1, c2, num_heads, num_layers): - """Initialize a Transformer module with position embedding and specified number of heads and layers.""" - super().__init__() - self.conv = None - if c1 != c2: - self.conv = Conv(c1, c2) - self.linear = nn.Linear(c2, c2) # learnable position embedding - self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers))) - self.c2 = c2 - - def forward(self, x): - """Forward propagates the input through the bottleneck module.""" - if self.conv is not None: - x = self.conv(x) - b, _, w, h = x.shape - p = x.flatten(2).permute(2, 0, 1) - return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h) - - -class MLPBlock(nn.Module): - """Implements a single block of a multi-layer perceptron.""" - - def __init__(self, embedding_dim, mlp_dim, act=nn.GELU): - """Initialize the MLPBlock with specified embedding dimension, MLP dimension, and activation function.""" - super().__init__() - self.lin1 = nn.Linear(embedding_dim, mlp_dim) - self.lin2 = nn.Linear(mlp_dim, embedding_dim) - self.act = act() - - def forward(self, x: torch.Tensor) -> torch.Tensor: - """Forward pass for the MLPBlock.""" - return self.lin2(self.act(self.lin1(x))) - - -class MLP(nn.Module): - """Implements a simple multi-layer perceptron (also called FFN).""" - - def __init__(self, input_dim, hidden_dim, output_dim, num_layers): - """Initialize the MLP with specified input, hidden, output dimensions and number of layers.""" - super().__init__() - self.num_layers = num_layers - h = [hidden_dim] * (num_layers - 1) - self.layers = nn.ModuleList(nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])) - - def forward(self, x): - """Forward pass for the entire MLP.""" - for i, layer in enumerate(self.layers): - x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x) - return x - - -class LayerNorm2d(nn.Module): - """ - 2D Layer Normalization module inspired by Detectron2 and ConvNeXt implementations. - - Original implementations in - https://github.com/facebookresearch/detectron2/blob/main/detectron2/layers/batch_norm.py - and - https://github.com/facebookresearch/ConvNeXt/blob/main/models/convnext.py. - """ - - def __init__(self, num_channels, eps=1e-6): - """Initialize LayerNorm2d with the given parameters.""" - super().__init__() - self.weight = nn.Parameter(torch.ones(num_channels)) - self.bias = nn.Parameter(torch.zeros(num_channels)) - self.eps = eps - - def forward(self, x): - """Perform forward pass for 2D layer normalization.""" - u = x.mean(1, keepdim=True) - s = (x - u).pow(2).mean(1, keepdim=True) - x = (x - u) / torch.sqrt(s + self.eps) - return self.weight[:, None, None] * x + self.bias[:, None, None] - - -class MSDeformAttn(nn.Module): - """ - Multiscale Deformable Attention Module based on Deformable-DETR and PaddleDetection implementations. - - https://github.com/fundamentalvision/Deformable-DETR/blob/main/models/ops/modules/ms_deform_attn.py - """ - - def __init__(self, d_model=256, n_levels=4, n_heads=8, n_points=4): - """Initialize MSDeformAttn with the given parameters.""" - super().__init__() - if d_model % n_heads != 0: - raise ValueError(f"d_model must be divisible by n_heads, but got {d_model} and {n_heads}") - _d_per_head = d_model // n_heads - # Better to set _d_per_head to a power of 2 which is more efficient in a CUDA implementation - assert _d_per_head * n_heads == d_model, "`d_model` must be divisible by `n_heads`" - - self.im2col_step = 64 - - self.d_model = d_model - self.n_levels = n_levels - self.n_heads = n_heads - self.n_points = n_points - - self.sampling_offsets = nn.Linear(d_model, n_heads * n_levels * n_points * 2) - self.attention_weights = nn.Linear(d_model, n_heads * n_levels * n_points) - self.value_proj = nn.Linear(d_model, d_model) - self.output_proj = nn.Linear(d_model, d_model) - - self._reset_parameters() - - def _reset_parameters(self): - """Reset module parameters.""" - constant_(self.sampling_offsets.weight.data, 0.0) - thetas = torch.arange(self.n_heads, dtype=torch.float32) * (2.0 * math.pi / self.n_heads) - grid_init = torch.stack([thetas.cos(), thetas.sin()], -1) - grid_init = ( - (grid_init / grid_init.abs().max(-1, keepdim=True)[0]) - .view(self.n_heads, 1, 1, 2) - .repeat(1, self.n_levels, self.n_points, 1) - ) - for i in range(self.n_points): - grid_init[:, :, i, :] *= i + 1 - with torch.no_grad(): - self.sampling_offsets.bias = nn.Parameter(grid_init.view(-1)) - constant_(self.attention_weights.weight.data, 0.0) - constant_(self.attention_weights.bias.data, 0.0) - xavier_uniform_(self.value_proj.weight.data) - constant_(self.value_proj.bias.data, 0.0) - xavier_uniform_(self.output_proj.weight.data) - constant_(self.output_proj.bias.data, 0.0) - - def forward(self, query, refer_bbox, value, value_shapes, value_mask=None): - """ - Perform forward pass for multiscale deformable attention. - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/transformers/deformable_transformer.py - - Args: - query (torch.Tensor): [bs, query_length, C] - refer_bbox (torch.Tensor): [bs, query_length, n_levels, 2], range in [0, 1], top-left (0,0), - bottom-right (1, 1), including padding area - value (torch.Tensor): [bs, value_length, C] - value_shapes (List): [n_levels, 2], [(H_0, W_0), (H_1, W_1), ..., (H_{L-1}, W_{L-1})] - value_mask (Tensor): [bs, value_length], True for non-padding elements, False for padding elements - - Returns: - output (Tensor): [bs, Length_{query}, C] - """ - bs, len_q = query.shape[:2] - len_v = value.shape[1] - assert sum(s[0] * s[1] for s in value_shapes) == len_v - - value = self.value_proj(value) - if value_mask is not None: - value = value.masked_fill(value_mask[..., None], float(0)) - value = value.view(bs, len_v, self.n_heads, self.d_model // self.n_heads) - sampling_offsets = self.sampling_offsets(query).view(bs, len_q, self.n_heads, self.n_levels, self.n_points, 2) - attention_weights = self.attention_weights(query).view(bs, len_q, self.n_heads, self.n_levels * self.n_points) - attention_weights = F.softmax(attention_weights, -1).view(bs, len_q, self.n_heads, self.n_levels, self.n_points) - # N, Len_q, n_heads, n_levels, n_points, 2 - num_points = refer_bbox.shape[-1] - if num_points == 2: - offset_normalizer = torch.as_tensor(value_shapes, dtype=query.dtype, device=query.device).flip(-1) - add = sampling_offsets / offset_normalizer[None, None, None, :, None, :] - sampling_locations = refer_bbox[:, :, None, :, None, :] + add - elif num_points == 4: - add = sampling_offsets / self.n_points * refer_bbox[:, :, None, :, None, 2:] * 0.5 - sampling_locations = refer_bbox[:, :, None, :, None, :2] + add - else: - raise ValueError(f"Last dim of reference_points must be 2 or 4, but got {num_points}.") - output = multi_scale_deformable_attn_pytorch(value, value_shapes, sampling_locations, attention_weights) - return self.output_proj(output) - - -class DeformableTransformerDecoderLayer(nn.Module): - """ - Deformable Transformer Decoder Layer inspired by PaddleDetection and Deformable-DETR implementations. - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/transformers/deformable_transformer.py - https://github.com/fundamentalvision/Deformable-DETR/blob/main/models/deformable_transformer.py - """ - - def __init__(self, d_model=256, n_heads=8, d_ffn=1024, dropout=0.0, act=nn.ReLU(), n_levels=4, n_points=4): - """Initialize the DeformableTransformerDecoderLayer with the given parameters.""" - super().__init__() - - # Self attention - self.self_attn = nn.MultiheadAttention(d_model, n_heads, dropout=dropout) - self.dropout1 = nn.Dropout(dropout) - self.norm1 = nn.LayerNorm(d_model) - - # Cross attention - self.cross_attn = MSDeformAttn(d_model, n_levels, n_heads, n_points) - self.dropout2 = nn.Dropout(dropout) - self.norm2 = nn.LayerNorm(d_model) - - # FFN - self.linear1 = nn.Linear(d_model, d_ffn) - self.act = act - self.dropout3 = nn.Dropout(dropout) - self.linear2 = nn.Linear(d_ffn, d_model) - self.dropout4 = nn.Dropout(dropout) - self.norm3 = nn.LayerNorm(d_model) - - @staticmethod - def with_pos_embed(tensor, pos): - """Add positional embeddings to the input tensor, if provided.""" - return tensor if pos is None else tensor + pos - - def forward_ffn(self, tgt): - """Perform forward pass through the Feed-Forward Network part of the layer.""" - tgt2 = self.linear2(self.dropout3(self.act(self.linear1(tgt)))) - tgt = tgt + self.dropout4(tgt2) - return self.norm3(tgt) - - def forward(self, embed, refer_bbox, feats, shapes, padding_mask=None, attn_mask=None, query_pos=None): - """Perform the forward pass through the entire decoder layer.""" - - # Self attention - q = k = self.with_pos_embed(embed, query_pos) - tgt = self.self_attn(q.transpose(0, 1), k.transpose(0, 1), embed.transpose(0, 1), attn_mask=attn_mask)[ - 0 - ].transpose(0, 1) - embed = embed + self.dropout1(tgt) - embed = self.norm1(embed) - - # Cross attention - tgt = self.cross_attn( - self.with_pos_embed(embed, query_pos), refer_bbox.unsqueeze(2), feats, shapes, padding_mask - ) - embed = embed + self.dropout2(tgt) - embed = self.norm2(embed) - - # FFN - return self.forward_ffn(embed) - - -class DeformableTransformerDecoder(nn.Module): - """ - Implementation of Deformable Transformer Decoder based on PaddleDetection. - - https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/transformers/deformable_transformer.py - """ - - def __init__(self, hidden_dim, decoder_layer, num_layers, eval_idx=-1): - """Initialize the DeformableTransformerDecoder with the given parameters.""" - super().__init__() - self.layers = _get_clones(decoder_layer, num_layers) - self.num_layers = num_layers - self.hidden_dim = hidden_dim - self.eval_idx = eval_idx if eval_idx >= 0 else num_layers + eval_idx - - def forward( - self, - embed, # decoder embeddings - refer_bbox, # anchor - feats, # image features - shapes, # feature shapes - bbox_head, - score_head, - pos_mlp, - attn_mask=None, - padding_mask=None, - ): - """Perform the forward pass through the entire decoder.""" - output = embed - dec_bboxes = [] - dec_cls = [] - last_refined_bbox = None - refer_bbox = refer_bbox.sigmoid() - for i, layer in enumerate(self.layers): - output = layer(output, refer_bbox, feats, shapes, padding_mask, attn_mask, pos_mlp(refer_bbox)) - - bbox = bbox_head[i](output) - refined_bbox = torch.sigmoid(bbox + inverse_sigmoid(refer_bbox)) - - if self.training: - dec_cls.append(score_head[i](output)) - if i == 0: - dec_bboxes.append(refined_bbox) - else: - dec_bboxes.append(torch.sigmoid(bbox + inverse_sigmoid(last_refined_bbox))) - elif i == self.eval_idx: - dec_cls.append(score_head[i](output)) - dec_bboxes.append(refined_bbox) - break - - last_refined_bbox = refined_bbox - refer_bbox = refined_bbox.detach() if self.training else refined_bbox - - return torch.stack(dec_bboxes), torch.stack(dec_cls) diff --git a/ultralytics-main/ultralytics/nn/modules/utils.py b/ultralytics-main/ultralytics/nn/modules/utils.py deleted file mode 100644 index 1512967..0000000 --- a/ultralytics-main/ultralytics/nn/modules/utils.py +++ /dev/null @@ -1,85 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Module utils.""" - -import copy -import math - -import numpy as np -import torch -import torch.nn as nn -import torch.nn.functional as F -from torch.nn.init import uniform_ - -__all__ = "multi_scale_deformable_attn_pytorch", "inverse_sigmoid" - - -def _get_clones(module, n): - """Create a list of cloned modules from the given module.""" - return nn.ModuleList([copy.deepcopy(module) for _ in range(n)]) - - -def bias_init_with_prob(prior_prob=0.01): - """Initialize conv/fc bias value according to a given probability value.""" - return float(-np.log((1 - prior_prob) / prior_prob)) # return bias_init - - -def linear_init(module): - """Initialize the weights and biases of a linear module.""" - bound = 1 / math.sqrt(module.weight.shape[0]) - uniform_(module.weight, -bound, bound) - if hasattr(module, "bias") and module.bias is not None: - uniform_(module.bias, -bound, bound) - - -def inverse_sigmoid(x, eps=1e-5): - """Calculate the inverse sigmoid function for a tensor.""" - x = x.clamp(min=0, max=1) - x1 = x.clamp(min=eps) - x2 = (1 - x).clamp(min=eps) - return torch.log(x1 / x2) - - -def multi_scale_deformable_attn_pytorch( - value: torch.Tensor, - value_spatial_shapes: torch.Tensor, - sampling_locations: torch.Tensor, - attention_weights: torch.Tensor, -) -> torch.Tensor: - """ - Multiscale deformable attention. - - https://github.com/IDEA-Research/detrex/blob/main/detrex/layers/multi_scale_deform_attn.py - """ - - bs, _, num_heads, embed_dims = value.shape - _, num_queries, num_heads, num_levels, num_points, _ = sampling_locations.shape - value_list = value.split([H_ * W_ for H_, W_ in value_spatial_shapes], dim=1) - sampling_grids = 2 * sampling_locations - 1 - sampling_value_list = [] - for level, (H_, W_) in enumerate(value_spatial_shapes): - # bs, H_*W_, num_heads, embed_dims -> - # bs, H_*W_, num_heads*embed_dims -> - # bs, num_heads*embed_dims, H_*W_ -> - # bs*num_heads, embed_dims, H_, W_ - value_l_ = value_list[level].flatten(2).transpose(1, 2).reshape(bs * num_heads, embed_dims, H_, W_) - # bs, num_queries, num_heads, num_points, 2 -> - # bs, num_heads, num_queries, num_points, 2 -> - # bs*num_heads, num_queries, num_points, 2 - sampling_grid_l_ = sampling_grids[:, :, :, level].transpose(1, 2).flatten(0, 1) - # bs*num_heads, embed_dims, num_queries, num_points - sampling_value_l_ = F.grid_sample( - value_l_, sampling_grid_l_, mode="bilinear", padding_mode="zeros", align_corners=False - ) - sampling_value_list.append(sampling_value_l_) - # (bs, num_queries, num_heads, num_levels, num_points) -> - # (bs, num_heads, num_queries, num_levels, num_points) -> - # (bs, num_heads, 1, num_queries, num_levels*num_points) - attention_weights = attention_weights.transpose(1, 2).reshape( - bs * num_heads, 1, num_queries, num_levels * num_points - ) - output = ( - (torch.stack(sampling_value_list, dim=-2).flatten(-2) * attention_weights) - .sum(-1) - .view(bs, num_heads * embed_dims, num_queries) - ) - return output.transpose(1, 2).contiguous() diff --git a/ultralytics-main/ultralytics/nn/tasks.py b/ultralytics-main/ultralytics/nn/tasks.py deleted file mode 100644 index 64ee7f5..0000000 --- a/ultralytics-main/ultralytics/nn/tasks.py +++ /dev/null @@ -1,1037 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -from copy import deepcopy -from pathlib import Path - -import torch -import torch.nn as nn - -from ultralytics.nn.modules import ( - AIFI, - C1, - C2, - C3, - C3TR, - OBB, - SPP, - SPPF, - Bottleneck, - BottleneckCSP, - C2f, - C2fAttn, - ImagePoolingAttn, - C3Ghost, - C3x, - Classify, - Concat, - Conv, - Conv2, - ConvTranspose, - Detect, - DWConv, - DWConvTranspose2d, - Focus, - GhostBottleneck, - GhostConv, - HGBlock, - HGStem, - Pose, - RepC3, - RepConv, - ResNetLayer, - RTDETRDecoder, - Segment, - WorldDetect, - RepNCSPELAN4, - ADown, - SPPELAN, - CBFuse, - CBLinear, - Silence, -) -from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, emojis, yaml_load -from ultralytics.utils.checks import check_requirements, check_suffix, check_yaml -from ultralytics.utils.loss import v8ClassificationLoss, v8DetectionLoss, v8OBBLoss, v8PoseLoss, v8SegmentationLoss -from ultralytics.utils.plotting import feature_visualization -from ultralytics.utils.torch_utils import ( - fuse_conv_and_bn, - fuse_deconv_and_bn, - initialize_weights, - intersect_dicts, - make_divisible, - model_info, - scale_img, - time_sync, -) - -try: - import thop -except ImportError: - thop = None - - -class BaseModel(nn.Module): - """The BaseModel class serves as a base class for all the models in the Ultralytics YOLO family.""" - - def forward(self, x, *args, **kwargs): - """ - Forward pass of the model on a single scale. Wrapper for `_forward_once` method. - - Args: - x (torch.Tensor | dict): The input image tensor or a dict including image tensor and gt labels. - - Returns: - (torch.Tensor): The output of the network. - """ - if isinstance(x, dict): # for cases of training and validating while training. - return self.loss(x, *args, **kwargs) - return self.predict(x, *args, **kwargs) - - def predict(self, x, profile=False, visualize=False, augment=False, embed=None): - """ - Perform a forward pass through the network. - - Args: - x (torch.Tensor): The input tensor to the model. - profile (bool): Print the computation time of each layer if True, defaults to False. - visualize (bool): Save the feature maps of the model if True, defaults to False. - augment (bool): Augment image during prediction, defaults to False. - embed (list, optional): A list of feature vectors/embeddings to return. - - Returns: - (torch.Tensor): The last output of the model. - """ - if augment: - return self._predict_augment(x) - return self._predict_once(x, profile, visualize, embed) - - def _predict_once(self, x, profile=False, visualize=False, embed=None): - """ - Perform a forward pass through the network. - - Args: - x (torch.Tensor): The input tensor to the model. - profile (bool): Print the computation time of each layer if True, defaults to False. - visualize (bool): Save the feature maps of the model if True, defaults to False. - embed (list, optional): A list of feature vectors/embeddings to return. - - Returns: - (torch.Tensor): The last output of the model. - """ - y, dt, embeddings = [], [], [] # outputs - for m in self.model: - if m.f != -1: # if not from previous layer - x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers - if profile: - self._profile_one_layer(m, x, dt) - x = m(x) # run - y.append(x if m.i in self.save else None) # save output - if visualize: - feature_visualization(x, m.type, m.i, save_dir=visualize) - if embed and m.i in embed: - embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten - if m.i == max(embed): - return torch.unbind(torch.cat(embeddings, 1), dim=0) - return x - - def _predict_augment(self, x): - """Perform augmentations on input image x and return augmented inference.""" - LOGGER.warning( - f"WARNING ⚠️ {self.__class__.__name__} does not support augmented inference yet. " - f"Reverting to single-scale inference instead." - ) - return self._predict_once(x) - - def _profile_one_layer(self, m, x, dt): - """ - Profile the computation time and FLOPs of a single layer of the model on a given input. Appends the results to - the provided list. - - Args: - m (nn.Module): The layer to be profiled. - x (torch.Tensor): The input data to the layer. - dt (list): A list to store the computation time of the layer. - - Returns: - None - """ - c = m == self.model[-1] and isinstance(x, list) # is final layer list, copy input as inplace fix - flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1e9 * 2 if thop else 0 # FLOPs - t = time_sync() - for _ in range(10): - m(x.copy() if c else x) - dt.append((time_sync() - t) * 100) - if m == self.model[0]: - LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module") - LOGGER.info(f"{dt[-1]:10.2f} {flops:10.2f} {m.np:10.0f} {m.type}") - if c: - LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") - - def fuse(self, verbose=True): - """ - Fuse the `Conv2d()` and `BatchNorm2d()` layers of the model into a single layer, in order to improve the - computation efficiency. - - Returns: - (nn.Module): The fused model is returned. - """ - if not self.is_fused(): - for m in self.model.modules(): - if isinstance(m, (Conv, Conv2, DWConv)) and hasattr(m, "bn"): - if isinstance(m, Conv2): - m.fuse_convs() - m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv - delattr(m, "bn") # remove batchnorm - m.forward = m.forward_fuse # update forward - if isinstance(m, ConvTranspose) and hasattr(m, "bn"): - m.conv_transpose = fuse_deconv_and_bn(m.conv_transpose, m.bn) - delattr(m, "bn") # remove batchnorm - m.forward = m.forward_fuse # update forward - if isinstance(m, RepConv): - m.fuse_convs() - m.forward = m.forward_fuse # update forward - self.info(verbose=verbose) - - return self - - def is_fused(self, thresh=10): - """ - Check if the model has less than a certain threshold of BatchNorm layers. - - Args: - thresh (int, optional): The threshold number of BatchNorm layers. Default is 10. - - Returns: - (bool): True if the number of BatchNorm layers in the model is less than the threshold, False otherwise. - """ - bn = tuple(v for k, v in nn.__dict__.items() if "Norm" in k) # normalization layers, i.e. BatchNorm2d() - return sum(isinstance(v, bn) for v in self.modules()) < thresh # True if < 'thresh' BatchNorm layers in model - - def info(self, detailed=False, verbose=True, imgsz=640): - """ - Prints model information. - - Args: - detailed (bool): if True, prints out detailed information about the model. Defaults to False - verbose (bool): if True, prints out the model information. Defaults to False - imgsz (int): the size of the image that the model will be trained on. Defaults to 640 - """ - return model_info(self, detailed=detailed, verbose=verbose, imgsz=imgsz) - - def _apply(self, fn): - """ - Applies a function to all the tensors in the model that are not parameters or registered buffers. - - Args: - fn (function): the function to apply to the model - - Returns: - (BaseModel): An updated BaseModel object. - """ - self = super()._apply(fn) - m = self.model[-1] # Detect() - if isinstance(m, Detect): # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect - m.stride = fn(m.stride) - m.anchors = fn(m.anchors) - m.strides = fn(m.strides) - return self - - def load(self, weights, verbose=True): - """ - Load the weights into the model. - - Args: - weights (dict | torch.nn.Module): The pre-trained weights to be loaded. - verbose (bool, optional): Whether to log the transfer progress. Defaults to True. - """ - model = weights["model"] if isinstance(weights, dict) else weights # torchvision models are not dicts - csd = model.float().state_dict() # checkpoint state_dict as FP32 - csd = intersect_dicts(csd, self.state_dict()) # intersect - self.load_state_dict(csd, strict=False) # load - if verbose: - LOGGER.info(f"Transferred {len(csd)}/{len(self.model.state_dict())} items from pretrained weights") - - def loss(self, batch, preds=None): - """ - Compute loss. - - Args: - batch (dict): Batch to compute loss on - preds (torch.Tensor | List[torch.Tensor]): Predictions. - """ - if not hasattr(self, "criterion"): - self.criterion = self.init_criterion() - - preds = self.forward(batch["img"]) if preds is None else preds - return self.criterion(preds, batch) - - def init_criterion(self): - """Initialize the loss criterion for the BaseModel.""" - raise NotImplementedError("compute_loss() needs to be implemented by task heads") - - -class DetectionModel(BaseModel): - """YOLOv8 detection model.""" - - def __init__(self, cfg="yolov8n.yaml", ch=3, nc=None, verbose=True): # model, input channels, number of classes - """Initialize the YOLOv8 detection model with the given config and parameters.""" - super().__init__() - self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg) # cfg dict - - # Define model - ch = self.yaml["ch"] = self.yaml.get("ch", ch) # input channels - if nc and nc != self.yaml["nc"]: - LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") - self.yaml["nc"] = nc # override YAML value - self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose) # model, savelist - self.names = {i: f"{i}" for i in range(self.yaml["nc"])} # default names dict - self.inplace = self.yaml.get("inplace", True) - - # Build strides - m = self.model[-1] # Detect() - if isinstance(m, Detect): # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect - s = 256 # 2x min stride - m.inplace = self.inplace - forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x) - m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward - self.stride = m.stride - m.bias_init() # only run once - else: - self.stride = torch.Tensor([32]) # default stride for i.e. RTDETR - - # Init weights, biases - initialize_weights(self) - if verbose: - self.info() - LOGGER.info("") - - def _predict_augment(self, x): - """Perform augmentations on input image x and return augmented inference and train outputs.""" - img_size = x.shape[-2:] # height, width - s = [1, 0.83, 0.67] # scales - f = [None, 3, None] # flips (2-ud, 3-lr) - y = [] # outputs - for si, fi in zip(s, f): - xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max())) - yi = super().predict(xi)[0] # forward - yi = self._descale_pred(yi, fi, si, img_size) - y.append(yi) - y = self._clip_augmented(y) # clip augmented tails - return torch.cat(y, -1), None # augmented inference, train - - @staticmethod - def _descale_pred(p, flips, scale, img_size, dim=1): - """De-scale predictions following augmented inference (inverse operation).""" - p[:, :4] /= scale # de-scale - x, y, wh, cls = p.split((1, 1, 2, p.shape[dim] - 4), dim) - if flips == 2: - y = img_size[0] - y # de-flip ud - elif flips == 3: - x = img_size[1] - x # de-flip lr - return torch.cat((x, y, wh, cls), dim) - - def _clip_augmented(self, y): - """Clip YOLO augmented inference tails.""" - nl = self.model[-1].nl # number of detection layers (P3-P5) - g = sum(4**x for x in range(nl)) # grid points - e = 1 # exclude layer count - i = (y[0].shape[-1] // g) * sum(4**x for x in range(e)) # indices - y[0] = y[0][..., :-i] # large - i = (y[-1].shape[-1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices - y[-1] = y[-1][..., i:] # small - return y - - def init_criterion(self): - """Initialize the loss criterion for the DetectionModel.""" - return v8DetectionLoss(self) - - -class OBBModel(DetectionModel): - """YOLOv8 Oriented Bounding Box (OBB) model.""" - - def __init__(self, cfg="yolov8n-obb.yaml", ch=3, nc=None, verbose=True): - """Initialize YOLOv8 OBB model with given config and parameters.""" - super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose) - - def init_criterion(self): - """Initialize the loss criterion for the model.""" - return v8OBBLoss(self) - - -class SegmentationModel(DetectionModel): - """YOLOv8 segmentation model.""" - - def __init__(self, cfg="yolov8n-seg.yaml", ch=3, nc=None, verbose=True): - """Initialize YOLOv8 segmentation model with given config and parameters.""" - super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose) - - def init_criterion(self): - """Initialize the loss criterion for the SegmentationModel.""" - return v8SegmentationLoss(self) - - -class PoseModel(DetectionModel): - """YOLOv8 pose model.""" - - def __init__(self, cfg="yolov8n-pose.yaml", ch=3, nc=None, data_kpt_shape=(None, None), verbose=True): - """Initialize YOLOv8 Pose model.""" - if not isinstance(cfg, dict): - cfg = yaml_model_load(cfg) # load model YAML - if any(data_kpt_shape) and list(data_kpt_shape) != list(cfg["kpt_shape"]): - LOGGER.info(f"Overriding model.yaml kpt_shape={cfg['kpt_shape']} with kpt_shape={data_kpt_shape}") - cfg["kpt_shape"] = data_kpt_shape - super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose) - - def init_criterion(self): - """Initialize the loss criterion for the PoseModel.""" - return v8PoseLoss(self) - - -class ClassificationModel(BaseModel): - """YOLOv8 classification model.""" - - def __init__(self, cfg="yolov8n-cls.yaml", ch=3, nc=None, verbose=True): - """Init ClassificationModel with YAML, channels, number of classes, verbose flag.""" - super().__init__() - self._from_yaml(cfg, ch, nc, verbose) - - def _from_yaml(self, cfg, ch, nc, verbose): - """Set YOLOv8 model configurations and define the model architecture.""" - self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg) # cfg dict - - # Define model - ch = self.yaml["ch"] = self.yaml.get("ch", ch) # input channels - if nc and nc != self.yaml["nc"]: - LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") - self.yaml["nc"] = nc # override YAML value - elif not nc and not self.yaml.get("nc", None): - raise ValueError("nc not specified. Must specify nc in model.yaml or function arguments.") - self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose) # model, savelist - self.stride = torch.Tensor([1]) # no stride constraints - self.names = {i: f"{i}" for i in range(self.yaml["nc"])} # default names dict - self.info() - - @staticmethod - def reshape_outputs(model, nc): - """Update a TorchVision classification model to class count 'n' if required.""" - name, m = list((model.model if hasattr(model, "model") else model).named_children())[-1] # last module - if isinstance(m, Classify): # YOLO Classify() head - if m.linear.out_features != nc: - m.linear = nn.Linear(m.linear.in_features, nc) - elif isinstance(m, nn.Linear): # ResNet, EfficientNet - if m.out_features != nc: - setattr(model, name, nn.Linear(m.in_features, nc)) - elif isinstance(m, nn.Sequential): - types = [type(x) for x in m] - if nn.Linear in types: - i = types.index(nn.Linear) # nn.Linear index - if m[i].out_features != nc: - m[i] = nn.Linear(m[i].in_features, nc) - elif nn.Conv2d in types: - i = types.index(nn.Conv2d) # nn.Conv2d index - if m[i].out_channels != nc: - m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None) - - def init_criterion(self): - """Initialize the loss criterion for the ClassificationModel.""" - return v8ClassificationLoss() - - -class RTDETRDetectionModel(DetectionModel): - """ - RTDETR (Real-time DEtection and Tracking using Transformers) Detection Model class. - - This class is responsible for constructing the RTDETR architecture, defining loss functions, and facilitating both - the training and inference processes. RTDETR is an object detection and tracking model that extends from the - DetectionModel base class. - - Attributes: - cfg (str): The configuration file path or preset string. Default is 'rtdetr-l.yaml'. - ch (int): Number of input channels. Default is 3 (RGB). - nc (int, optional): Number of classes for object detection. Default is None. - verbose (bool): Specifies if summary statistics are shown during initialization. Default is True. - - Methods: - init_criterion: Initializes the criterion used for loss calculation. - loss: Computes and returns the loss during training. - predict: Performs a forward pass through the network and returns the output. - """ - - def __init__(self, cfg="rtdetr-l.yaml", ch=3, nc=None, verbose=True): - """ - Initialize the RTDETRDetectionModel. - - Args: - cfg (str): Configuration file name or path. - ch (int): Number of input channels. - nc (int, optional): Number of classes. Defaults to None. - verbose (bool, optional): Print additional information during initialization. Defaults to True. - """ - super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose) - - def init_criterion(self): - """Initialize the loss criterion for the RTDETRDetectionModel.""" - from ultralytics.models.utils.loss import RTDETRDetectionLoss - - return RTDETRDetectionLoss(nc=self.nc, use_vfl=True) - - def loss(self, batch, preds=None): - """ - Compute the loss for the given batch of data. - - Args: - batch (dict): Dictionary containing image and label data. - preds (torch.Tensor, optional): Precomputed model predictions. Defaults to None. - - Returns: - (tuple): A tuple containing the total loss and main three losses in a tensor. - """ - if not hasattr(self, "criterion"): - self.criterion = self.init_criterion() - - img = batch["img"] - # NOTE: preprocess gt_bbox and gt_labels to list. - bs = len(img) - batch_idx = batch["batch_idx"] - gt_groups = [(batch_idx == i).sum().item() for i in range(bs)] - targets = { - "cls": batch["cls"].to(img.device, dtype=torch.long).view(-1), - "bboxes": batch["bboxes"].to(device=img.device), - "batch_idx": batch_idx.to(img.device, dtype=torch.long).view(-1), - "gt_groups": gt_groups, - } - - preds = self.predict(img, batch=targets) if preds is None else preds - dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta = preds if self.training else preds[1] - if dn_meta is None: - dn_bboxes, dn_scores = None, None - else: - dn_bboxes, dec_bboxes = torch.split(dec_bboxes, dn_meta["dn_num_split"], dim=2) - dn_scores, dec_scores = torch.split(dec_scores, dn_meta["dn_num_split"], dim=2) - - dec_bboxes = torch.cat([enc_bboxes.unsqueeze(0), dec_bboxes]) # (7, bs, 300, 4) - dec_scores = torch.cat([enc_scores.unsqueeze(0), dec_scores]) - - loss = self.criterion( - (dec_bboxes, dec_scores), targets, dn_bboxes=dn_bboxes, dn_scores=dn_scores, dn_meta=dn_meta - ) - # NOTE: There are like 12 losses in RTDETR, backward with all losses but only show the main three losses. - return sum(loss.values()), torch.as_tensor( - [loss[k].detach() for k in ["loss_giou", "loss_class", "loss_bbox"]], device=img.device - ) - - def predict(self, x, profile=False, visualize=False, batch=None, augment=False, embed=None): - """ - Perform a forward pass through the model. - - Args: - x (torch.Tensor): The input tensor. - profile (bool, optional): If True, profile the computation time for each layer. Defaults to False. - visualize (bool, optional): If True, save feature maps for visualization. Defaults to False. - batch (dict, optional): Ground truth data for evaluation. Defaults to None. - augment (bool, optional): If True, perform data augmentation during inference. Defaults to False. - embed (list, optional): A list of feature vectors/embeddings to return. - - Returns: - (torch.Tensor): Model's output tensor. - """ - y, dt, embeddings = [], [], [] # outputs - for m in self.model[:-1]: # except the head part - if m.f != -1: # if not from previous layer - x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers - if profile: - self._profile_one_layer(m, x, dt) - x = m(x) # run - y.append(x if m.i in self.save else None) # save output - if visualize: - feature_visualization(x, m.type, m.i, save_dir=visualize) - if embed and m.i in embed: - embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten - if m.i == max(embed): - return torch.unbind(torch.cat(embeddings, 1), dim=0) - head = self.model[-1] - x = head([y[j] for j in head.f], batch) # head inference - return x - - -class WorldModel(DetectionModel): - """YOLOv8 World Model.""" - - def __init__(self, cfg="yolov8s-world.yaml", ch=3, nc=None, verbose=True): - """Initialize YOLOv8 world model with given config and parameters.""" - self.txt_feats = torch.randn(1, nc or 80, 512) # placeholder - super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose) - - def set_classes(self, text): - """Perform a forward pass with optional profiling, visualization, and embedding extraction.""" - try: - import clip - except ImportError: - check_requirements("git+https://github.com/openai/CLIP.git") - import clip - - model, _ = clip.load("ViT-B/32") - device = next(model.parameters()).device - text_token = clip.tokenize(text).to(device) - txt_feats = model.encode_text(text_token).to(dtype=torch.float32) - txt_feats = txt_feats / txt_feats.norm(p=2, dim=-1, keepdim=True) - self.txt_feats = txt_feats.reshape(-1, len(text), txt_feats.shape[-1]).detach() - self.model[-1].nc = len(text) - - def init_criterion(self): - """Initialize the loss criterion for the model.""" - raise NotImplementedError - - def predict(self, x, profile=False, visualize=False, augment=False, embed=None): - """ - Perform a forward pass through the model. - - Args: - x (torch.Tensor): The input tensor. - profile (bool, optional): If True, profile the computation time for each layer. Defaults to False. - visualize (bool, optional): If True, save feature maps for visualization. Defaults to False. - augment (bool, optional): If True, perform data augmentation during inference. Defaults to False. - embed (list, optional): A list of feature vectors/embeddings to return. - - Returns: - (torch.Tensor): Model's output tensor. - """ - txt_feats = self.txt_feats.to(device=x.device, dtype=x.dtype) - if len(txt_feats) != len(x): - txt_feats = txt_feats.repeat(len(x), 1, 1) - ori_txt_feats = txt_feats.clone() - y, dt, embeddings = [], [], [] # outputs - for m in self.model: # except the head part - if m.f != -1: # if not from previous layer - x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers - if profile: - self._profile_one_layer(m, x, dt) - if isinstance(m, C2fAttn): - x = m(x, txt_feats) - elif isinstance(m, WorldDetect): - x = m(x, ori_txt_feats) - elif isinstance(m, ImagePoolingAttn): - txt_feats = m(x, txt_feats) - else: - x = m(x) # run - - y.append(x if m.i in self.save else None) # save output - if visualize: - feature_visualization(x, m.type, m.i, save_dir=visualize) - if embed and m.i in embed: - embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten - if m.i == max(embed): - return torch.unbind(torch.cat(embeddings, 1), dim=0) - return x - - -class Ensemble(nn.ModuleList): - """Ensemble of models.""" - - def __init__(self): - """Initialize an ensemble of models.""" - super().__init__() - - def forward(self, x, augment=False, profile=False, visualize=False): - """Function generates the YOLO network's final layer.""" - y = [module(x, augment, profile, visualize)[0] for module in self] - # y = torch.stack(y).max(0)[0] # max ensemble - # y = torch.stack(y).mean(0) # mean ensemble - y = torch.cat(y, 2) # nms ensemble, y shape(B, HW, C) - return y, None # inference, train output - - -# Functions ------------------------------------------------------------------------------------------------------------ - - -@contextlib.contextmanager -def temporary_modules(modules=None): - """ - Context manager for temporarily adding or modifying modules in Python's module cache (`sys.modules`). - - This function can be used to change the module paths during runtime. It's useful when refactoring code, - where you've moved a module from one location to another, but you still want to support the old import - paths for backwards compatibility. - - Args: - modules (dict, optional): A dictionary mapping old module paths to new module paths. - - Example: - ```python - with temporary_modules({'old.module.path': 'new.module.path'}): - import old.module.path # this will now import new.module.path - ``` - - Note: - The changes are only in effect inside the context manager and are undone once the context manager exits. - Be aware that directly manipulating `sys.modules` can lead to unpredictable results, especially in larger - applications or libraries. Use this function with caution. - """ - if not modules: - modules = {} - - import importlib - import sys - - try: - # Set modules in sys.modules under their old name - for old, new in modules.items(): - sys.modules[old] = importlib.import_module(new) - - yield - finally: - # Remove the temporary module paths - for old in modules: - if old in sys.modules: - del sys.modules[old] - - -def torch_safe_load(weight): - """ - This function attempts to load a PyTorch model with the torch.load() function. If a ModuleNotFoundError is raised, - it catches the error, logs a warning message, and attempts to install the missing module via the - check_requirements() function. After installation, the function again attempts to load the model using torch.load(). - - Args: - weight (str): The file path of the PyTorch model. - - Returns: - (dict): The loaded PyTorch model. - """ - from ultralytics.utils.downloads import attempt_download_asset - - check_suffix(file=weight, suffix=".pt") - file = attempt_download_asset(weight) # search online if missing locally - try: - with temporary_modules( - { - "ultralytics.yolo.utils": "ultralytics.utils", - "ultralytics.yolo.v8": "ultralytics.models.yolo", - "ultralytics.yolo.data": "ultralytics.data", - } - ): # for legacy 8.0 Classify and Pose models - ckpt = torch.load(file, map_location="cpu") - - except ModuleNotFoundError as e: # e.name is missing module name - if e.name == "models": - raise TypeError( - emojis( - f"ERROR ❌️ {weight} appears to be an Ultralytics YOLOv5 model originally trained " - f"with https://github.com/ultralytics/yolov5.\nThis model is NOT forwards compatible with " - f"YOLOv8 at https://github.com/ultralytics/ultralytics." - f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to " - f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'" - ) - ) from e - LOGGER.warning( - f"WARNING ⚠️ {weight} appears to require '{e.name}', which is not in ultralytics requirements." - f"\nAutoInstall will run now for '{e.name}' but this feature will be removed in the future." - f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to " - f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'" - ) - check_requirements(e.name) # install missing module - ckpt = torch.load(file, map_location="cpu") - - if not isinstance(ckpt, dict): - # File is likely a YOLO instance saved with i.e. torch.save(model, "saved_model.pt") - LOGGER.warning( - f"WARNING ⚠️ The file '{weight}' appears to be improperly saved or formatted. " - f"For optimal results, use model.save('filename.pt') to correctly save YOLO models." - ) - ckpt = {"model": ckpt.model} - - return ckpt, file # load - - -def attempt_load_weights(weights, device=None, inplace=True, fuse=False): - """Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a.""" - - ensemble = Ensemble() - for w in weights if isinstance(weights, list) else [weights]: - ckpt, w = torch_safe_load(w) # load ckpt - args = {**DEFAULT_CFG_DICT, **ckpt["train_args"]} if "train_args" in ckpt else None # combined args - model = (ckpt.get("ema") or ckpt["model"]).to(device).float() # FP32 model - - # Model compatibility updates - model.args = args # attach args to model - model.pt_path = w # attach *.pt file path to model - model.task = guess_model_task(model) - if not hasattr(model, "stride"): - model.stride = torch.tensor([32.0]) - - # Append - ensemble.append(model.fuse().eval() if fuse and hasattr(model, "fuse") else model.eval()) # model in eval mode - - # Module updates - for m in ensemble.modules(): - if hasattr(m, "inplace"): - m.inplace = inplace - elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"): - m.recompute_scale_factor = None # torch 1.11.0 compatibility - - # Return model - if len(ensemble) == 1: - return ensemble[-1] - - # Return ensemble - LOGGER.info(f"Ensemble created with {weights}\n") - for k in "names", "nc", "yaml": - setattr(ensemble, k, getattr(ensemble[0], k)) - ensemble.stride = ensemble[int(torch.argmax(torch.tensor([m.stride.max() for m in ensemble])))].stride - assert all(ensemble[0].nc == m.nc for m in ensemble), f"Models differ in class counts {[m.nc for m in ensemble]}" - return ensemble - - -def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False): - """Loads a single model weights.""" - ckpt, weight = torch_safe_load(weight) # load ckpt - args = {**DEFAULT_CFG_DICT, **(ckpt.get("train_args", {}))} # combine model and default args, preferring model args - model = (ckpt.get("ema") or ckpt["model"]).to(device).float() # FP32 model - - # Model compatibility updates - model.args = {k: v for k, v in args.items() if k in DEFAULT_CFG_KEYS} # attach args to model - model.pt_path = weight # attach *.pt file path to model - model.task = guess_model_task(model) - if not hasattr(model, "stride"): - model.stride = torch.tensor([32.0]) - - model = model.fuse().eval() if fuse and hasattr(model, "fuse") else model.eval() # model in eval mode - - # Module updates - for m in model.modules(): - if hasattr(m, "inplace"): - m.inplace = inplace - elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"): - m.recompute_scale_factor = None # torch 1.11.0 compatibility - - # Return model and ckpt - return model, ckpt - - -def parse_model(d, ch, verbose=True): # model_dict, input_channels(3) - """Parse a YOLO model.yaml dictionary into a PyTorch model.""" - import ast - - # Args - max_channels = float("inf") - nc, act, scales = (d.get(x) for x in ("nc", "activation", "scales")) - depth, width, kpt_shape = (d.get(x, 1.0) for x in ("depth_multiple", "width_multiple", "kpt_shape")) - if scales: - scale = d.get("scale") - if not scale: - scale = tuple(scales.keys())[0] - LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.") - depth, width, max_channels = scales[scale] - - if act: - Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU() - if verbose: - LOGGER.info(f"{colorstr('activation:')} {act}") # print - - if verbose: - LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}") - ch = [ch] - layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out - for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]): # from, number, module, args - m = getattr(torch.nn, m[3:]) if "nn." in m else globals()[m] # get module - for j, a in enumerate(args): - if isinstance(a, str): - with contextlib.suppress(ValueError): - args[j] = locals()[a] if a in locals() else ast.literal_eval(a) - - n = n_ = max(round(n * depth), 1) if n > 1 else n # depth gain - if m in ( - Classify, - Conv, - ConvTranspose, - GhostConv, - Bottleneck, - GhostBottleneck, - SPP, - SPPF, - DWConv, - Focus, - BottleneckCSP, - C1, - C2, - C2f, - RepNCSPELAN4, - ADown, - SPPELAN, - C2fAttn, - C3, - C3TR, - C3Ghost, - nn.ConvTranspose2d, - DWConvTranspose2d, - C3x, - RepC3, - ): - c1, c2 = ch[f], args[0] - if c2 != nc: # if c2 not equal to number of classes (i.e. for Classify() output) - c2 = make_divisible(min(c2, max_channels) * width, 8) - if m is C2fAttn: - args[1] = make_divisible(min(args[1], max_channels // 2) * width, 8) # embed channels - args[2] = int( - max(round(min(args[2], max_channels // 2 // 32)) * width, 1) if args[2] > 1 else args[2] - ) # num heads - - args = [c1, c2, *args[1:]] - if m in (BottleneckCSP, C1, C2, C2f, C2fAttn, C3, C3TR, C3Ghost, C3x, RepC3): - args.insert(2, n) # number of repeats - n = 1 - elif m is AIFI: - args = [ch[f], *args] - elif m in (HGStem, HGBlock): - c1, cm, c2 = ch[f], args[0], args[1] - args = [c1, cm, c2, *args[2:]] - if m is HGBlock: - args.insert(4, n) # number of repeats - n = 1 - elif m is ResNetLayer: - c2 = args[1] if args[3] else args[1] * 4 - elif m is nn.BatchNorm2d: - args = [ch[f]] - elif m is Concat: - c2 = sum(ch[x] for x in f) - elif m in (Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn): - args.append([ch[x] for x in f]) - if m is Segment: - args[2] = make_divisible(min(args[2], max_channels) * width, 8) - elif m is RTDETRDecoder: # special case, channels arg must be passed in index 1 - args.insert(1, [ch[x] for x in f]) - elif m is CBLinear: - c2 = args[0] - c1 = ch[f] - args = [c1, c2, *args[1:]] - elif m is CBFuse: - c2 = ch[f[-1]] - else: - c2 = ch[f] - - m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module - t = str(m)[8:-2].replace("__main__.", "") # module type - m.np = sum(x.numel() for x in m_.parameters()) # number params - m_.i, m_.f, m_.type = i, f, t # attach index, 'from' index, type - if verbose: - LOGGER.info(f"{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f} {t:<45}{str(args):<30}") # print - save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist - layers.append(m_) - if i == 0: - ch = [] - ch.append(c2) - return nn.Sequential(*layers), sorted(save) - - -def yaml_model_load(path): - """Load a YOLOv8 model from a YAML file.""" - import re - - path = Path(path) - if path.stem in (f"yolov{d}{x}6" for x in "nsmlx" for d in (5, 8)): - new_stem = re.sub(r"(\d+)([nslmx])6(.+)?$", r"\1\2-p6\3", path.stem) - LOGGER.warning(f"WARNING ⚠️ Ultralytics YOLO P6 models now use -p6 suffix. Renaming {path.stem} to {new_stem}.") - path = path.with_name(new_stem + path.suffix) - - unified_path = re.sub(r"(\d+)([nslmx])(.+)?$", r"\1\3", str(path)) # i.e. yolov8x.yaml -> yolov8.yaml - yaml_file = check_yaml(unified_path, hard=False) or check_yaml(path) - d = yaml_load(yaml_file) # model dict - d["scale"] = guess_model_scale(path) - d["yaml_file"] = str(path) - return d - - -def guess_model_scale(model_path): - """ - Takes a path to a YOLO model's YAML file as input and extracts the size character of the model's scale. The function - uses regular expression matching to find the pattern of the model scale in the YAML file name, which is denoted by - n, s, m, l, or x. The function returns the size character of the model scale as a string. - - Args: - model_path (str | Path): The path to the YOLO model's YAML file. - - Returns: - (str): The size character of the model's scale, which can be n, s, m, l, or x. - """ - with contextlib.suppress(AttributeError): - import re - - return re.search(r"yolov\d+([nslmx])", Path(model_path).stem).group(1) # n, s, m, l, or x - return "" - - -def guess_model_task(model): - """ - Guess the task of a PyTorch model from its architecture or configuration. - - Args: - model (nn.Module | dict): PyTorch model or model configuration in YAML format. - - Returns: - (str): Task of the model ('detect', 'segment', 'classify', 'pose'). - - Raises: - SyntaxError: If the task of the model could not be determined. - """ - - def cfg2task(cfg): - """Guess from YAML dictionary.""" - m = cfg["head"][-1][-2].lower() # output module name - if m in ("classify", "classifier", "cls", "fc"): - return "classify" - if m == "detect": - return "detect" - if m == "segment": - return "segment" - if m == "pose": - return "pose" - if m == "obb": - return "obb" - - # Guess from model cfg - if isinstance(model, dict): - with contextlib.suppress(Exception): - return cfg2task(model) - - # Guess from PyTorch model - if isinstance(model, nn.Module): # PyTorch model - for x in "model.args", "model.model.args", "model.model.model.args": - with contextlib.suppress(Exception): - return eval(x)["task"] - for x in "model.yaml", "model.model.yaml", "model.model.model.yaml": - with contextlib.suppress(Exception): - return cfg2task(eval(x)) - - for m in model.modules(): - if isinstance(m, Segment): - return "segment" - elif isinstance(m, Classify): - return "classify" - elif isinstance(m, Pose): - return "pose" - elif isinstance(m, OBB): - return "obb" - elif isinstance(m, (Detect, WorldDetect)): - return "detect" - - # Guess from model filename - if isinstance(model, (str, Path)): - model = Path(model) - if "-seg" in model.stem or "segment" in model.parts: - return "segment" - elif "-cls" in model.stem or "classify" in model.parts: - return "classify" - elif "-pose" in model.stem or "pose" in model.parts: - return "pose" - elif "-obb" in model.stem or "obb" in model.parts: - return "obb" - elif "detect" in model.parts: - return "detect" - - # Unable to determine task from model - LOGGER.warning( - "WARNING ⚠️ Unable to automatically guess model task, assuming 'task=detect'. " - "Explicitly define task for your model, i.e. 'task=detect', 'segment', 'classify','pose' or 'obb'." - ) - return "detect" # assume detect diff --git a/ultralytics-main/ultralytics/solutions/__init__.py b/ultralytics-main/ultralytics/solutions/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/solutions/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/solutions/ai_gym.py b/ultralytics-main/ultralytics/solutions/ai_gym.py deleted file mode 100644 index b089ed0..0000000 --- a/ultralytics-main/ultralytics/solutions/ai_gym.py +++ /dev/null @@ -1,158 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import cv2 - -from ultralytics.utils.checks import check_imshow -from ultralytics.utils.plotting import Annotator - - -class AIGym: - """A class to manage the gym steps of people in a real-time video stream based on their poses.""" - - def __init__(self): - """Initializes the AIGym with default values for Visual and Image parameters.""" - - # Image and line thickness - self.im0 = None - self.tf = None - - # Keypoints and count information - self.keypoints = None - self.poseup_angle = None - self.posedown_angle = None - self.threshold = 0.001 - - # Store stage, count and angle information - self.angle = None - self.count = None - self.stage = None - self.pose_type = "pushup" - self.kpts_to_check = None - - # Visual Information - self.view_img = False - self.annotator = None - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - kpts_to_check, - line_thickness=2, - view_img=False, - pose_up_angle=145.0, - pose_down_angle=90.0, - pose_type="pullup", - ): - """ - Configures the AIGym line_thickness, save image and view image parameters. - - Args: - kpts_to_check (list): 3 keypoints for counting - line_thickness (int): Line thickness for bounding boxes. - view_img (bool): display the im0 - pose_up_angle (float): Angle to set pose position up - pose_down_angle (float): Angle to set pose position down - pose_type (str): "pushup", "pullup" or "abworkout" - """ - self.kpts_to_check = kpts_to_check - self.tf = line_thickness - self.view_img = view_img - self.poseup_angle = pose_up_angle - self.posedown_angle = pose_down_angle - self.pose_type = pose_type - - def start_counting(self, im0, results, frame_count): - """ - Function used to count the gym steps. - - Args: - im0 (ndarray): Current frame from the video stream. - results (list): Pose estimation data - frame_count (int): store current frame count - """ - self.im0 = im0 - if frame_count == 1: - self.count = [0] * len(results[0]) - self.angle = [0] * len(results[0]) - self.stage = ["-" for _ in results[0]] - self.keypoints = results[0].keypoints.data - self.annotator = Annotator(im0, line_width=2) - - num_keypoints = len(results[0]) - - # Resize self.angle, self.count, and self.stage if the number of keypoints has changed - if len(self.angle) != num_keypoints: - self.angle = [0] * num_keypoints - self.count = [0] * num_keypoints - self.stage = ["-" for _ in range(num_keypoints)] - - for ind, k in enumerate(reversed(self.keypoints)): - if self.pose_type in ["pushup", "pullup"]: - self.angle[ind] = self.annotator.estimate_pose_angle( - k[int(self.kpts_to_check[0])].cpu(), - k[int(self.kpts_to_check[1])].cpu(), - k[int(self.kpts_to_check[2])].cpu(), - ) - self.im0 = self.annotator.draw_specific_points(k, self.kpts_to_check, shape=(640, 640), radius=10) - - if self.pose_type == "abworkout": - self.angle[ind] = self.annotator.estimate_pose_angle( - k[int(self.kpts_to_check[0])].cpu(), - k[int(self.kpts_to_check[1])].cpu(), - k[int(self.kpts_to_check[2])].cpu(), - ) - self.im0 = self.annotator.draw_specific_points(k, self.kpts_to_check, shape=(640, 640), radius=10) - if self.angle[ind] > self.poseup_angle: - self.stage[ind] = "down" - if self.angle[ind] < self.posedown_angle and self.stage[ind] == "down": - self.stage[ind] = "up" - self.count[ind] += 1 - self.annotator.plot_angle_and_count_and_stage( - angle_text=self.angle[ind], - count_text=self.count[ind], - stage_text=self.stage[ind], - center_kpt=k[int(self.kpts_to_check[1])], - line_thickness=self.tf, - ) - - if self.pose_type == "pushup": - if self.angle[ind] > self.poseup_angle: - self.stage[ind] = "up" - if self.angle[ind] < self.posedown_angle and self.stage[ind] == "up": - self.stage[ind] = "down" - self.count[ind] += 1 - self.annotator.plot_angle_and_count_and_stage( - angle_text=self.angle[ind], - count_text=self.count[ind], - stage_text=self.stage[ind], - center_kpt=k[int(self.kpts_to_check[1])], - line_thickness=self.tf, - ) - if self.pose_type == "pullup": - if self.angle[ind] > self.poseup_angle: - self.stage[ind] = "down" - if self.angle[ind] < self.posedown_angle and self.stage[ind] == "down": - self.stage[ind] = "up" - self.count[ind] += 1 - self.annotator.plot_angle_and_count_and_stage( - angle_text=self.angle[ind], - count_text=self.count[ind], - stage_text=self.stage[ind], - center_kpt=k[int(self.kpts_to_check[1])], - line_thickness=self.tf, - ) - - self.annotator.kpts(k, shape=(640, 640), radius=1, kpt_line=True) - - if self.env_check and self.view_img: - cv2.imshow("Ultralytics YOLOv8 AI GYM", self.im0) - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - return self.im0 - - -if __name__ == "__main__": - AIGym() diff --git a/ultralytics-main/ultralytics/solutions/distance_calculation.py b/ultralytics-main/ultralytics/solutions/distance_calculation.py deleted file mode 100644 index f09209e..0000000 --- a/ultralytics-main/ultralytics/solutions/distance_calculation.py +++ /dev/null @@ -1,181 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math - -import cv2 - -from ultralytics.utils.checks import check_imshow -from ultralytics.utils.plotting import Annotator, colors - - -class DistanceCalculation: - """A class to calculate distance between two objects in real-time video stream based on their tracks.""" - - def __init__(self): - """Initializes the distance calculation class with default values for Visual, Image, track and distance - parameters. - """ - - # Visual & im0 information - self.im0 = None - self.annotator = None - self.view_img = False - self.line_color = (255, 255, 0) - self.centroid_color = (255, 0, 255) - - # Predict/track information - self.clss = None - self.names = None - self.boxes = None - self.line_thickness = 2 - self.trk_ids = None - - # Distance calculation information - self.centroids = [] - self.pixel_per_meter = 10 - - # Mouse event - self.left_mouse_count = 0 - self.selected_boxes = {} - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - names, - pixels_per_meter=10, - view_img=False, - line_thickness=2, - line_color=(255, 255, 0), - centroid_color=(255, 0, 255), - ): - """ - Configures the distance calculation and display parameters. - - Args: - names (dict): object detection classes names - pixels_per_meter (int): Number of pixels in meter - view_img (bool): Flag indicating frame display - line_thickness (int): Line thickness for bounding boxes. - line_color (RGB): color of centroids line - centroid_color (RGB): colors of bbox centroids - """ - self.names = names - self.pixel_per_meter = pixels_per_meter - self.view_img = view_img - self.line_thickness = line_thickness - self.line_color = line_color - self.centroid_color = centroid_color - - def mouse_event_for_distance(self, event, x, y, flags, param): - """ - This function is designed to move region with mouse events in a real-time video stream. - - Args: - event (int): The type of mouse event (e.g., cv2.EVENT_MOUSEMOVE, cv2.EVENT_LBUTTONDOWN, etc.). - x (int): The x-coordinate of the mouse pointer. - y (int): The y-coordinate of the mouse pointer. - flags (int): Any flags associated with the event (e.g., cv2.EVENT_FLAG_CTRLKEY, - cv2.EVENT_FLAG_SHIFTKEY, etc.). - param (dict): Additional parameters you may want to pass to the function. - """ - global selected_boxes - global left_mouse_count - if event == cv2.EVENT_LBUTTONDOWN: - self.left_mouse_count += 1 - if self.left_mouse_count <= 2: - for box, track_id in zip(self.boxes, self.trk_ids): - if box[0] < x < box[2] and box[1] < y < box[3] and track_id not in self.selected_boxes: - self.selected_boxes[track_id] = [] - self.selected_boxes[track_id] = box - - if event == cv2.EVENT_RBUTTONDOWN: - self.selected_boxes = {} - self.left_mouse_count = 0 - - def extract_tracks(self, tracks): - """ - Extracts results from the provided data. - - Args: - tracks (list): List of tracks obtained from the object tracking process. - """ - self.boxes = tracks[0].boxes.xyxy.cpu() - self.clss = tracks[0].boxes.cls.cpu().tolist() - self.trk_ids = tracks[0].boxes.id.int().cpu().tolist() - - def calculate_centroid(self, box): - """ - Calculate the centroid of bounding box. - - Args: - box (list): Bounding box data - """ - return int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2) - - def calculate_distance(self, centroid1, centroid2): - """ - Calculate distance between two centroids. - - Args: - centroid1 (point): First bounding box data - centroid2 (point): Second bounding box data - """ - pixel_distance = math.sqrt((centroid1[0] - centroid2[0]) ** 2 + (centroid1[1] - centroid2[1]) ** 2) - return pixel_distance / self.pixel_per_meter, (pixel_distance / self.pixel_per_meter) * 1000 - - def start_process(self, im0, tracks): - """ - Calculate distance between two bounding boxes based on tracking data. - - Args: - im0 (nd array): Image - tracks (list): List of tracks obtained from the object tracking process. - """ - self.im0 = im0 - if tracks[0].boxes.id is None: - if self.view_img: - self.display_frames() - return - self.extract_tracks(tracks) - - self.annotator = Annotator(self.im0, line_width=2) - - for box, cls, track_id in zip(self.boxes, self.clss, self.trk_ids): - self.annotator.box_label(box, color=colors(int(cls), True), label=self.names[int(cls)]) - - if len(self.selected_boxes) == 2: - for trk_id, _ in self.selected_boxes.items(): - if trk_id == track_id: - self.selected_boxes[track_id] = box - - if len(self.selected_boxes) == 2: - for trk_id, box in self.selected_boxes.items(): - centroid = self.calculate_centroid(self.selected_boxes[trk_id]) - self.centroids.append(centroid) - - distance_m, distance_mm = self.calculate_distance(self.centroids[0], self.centroids[1]) - self.annotator.plot_distance_and_line( - distance_m, distance_mm, self.centroids, self.line_color, self.centroid_color - ) - - self.centroids = [] - - if self.view_img and self.env_check: - self.display_frames() - - return im0 - - def display_frames(self): - """Display frame.""" - cv2.namedWindow("Ultralytics Distance Estimation") - cv2.setMouseCallback("Ultralytics Distance Estimation", self.mouse_event_for_distance) - cv2.imshow("Ultralytics Distance Estimation", self.im0) - - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - -if __name__ == "__main__": - DistanceCalculation() diff --git a/ultralytics-main/ultralytics/solutions/heatmap.py b/ultralytics-main/ultralytics/solutions/heatmap.py deleted file mode 100644 index f70e62b..0000000 --- a/ultralytics-main/ultralytics/solutions/heatmap.py +++ /dev/null @@ -1,281 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from collections import defaultdict - -import cv2 -import numpy as np - -from ultralytics.utils.checks import check_imshow, check_requirements -from ultralytics.utils.plotting import Annotator - -check_requirements("shapely>=2.0.0") - -from shapely.geometry import LineString, Point, Polygon - - -class Heatmap: - """A class to draw heatmaps in real-time video stream based on their tracks.""" - - def __init__(self): - """Initializes the heatmap class with default values for Visual, Image, track, count and heatmap parameters.""" - - # Visual information - self.annotator = None - self.view_img = False - self.shape = "circle" - - # Image information - self.imw = None - self.imh = None - self.im0 = None - self.view_in_counts = True - self.view_out_counts = True - - # Heatmap colormap and heatmap np array - self.colormap = None - self.heatmap = None - self.heatmap_alpha = 0.5 - - # Predict/track information - self.boxes = None - self.track_ids = None - self.clss = None - self.track_history = defaultdict(list) - - # Region & Line Information - self.count_reg_pts = None - self.counting_region = None - self.line_dist_thresh = 15 - self.region_thickness = 5 - self.region_color = (255, 0, 255) - - # Object Counting Information - self.in_counts = 0 - self.out_counts = 0 - self.counting_list = [] - self.count_txt_thickness = 0 - self.count_txt_color = (0, 0, 0) - self.count_color = (255, 255, 255) - - # Decay factor - self.decay_factor = 0.99 - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - imw, - imh, - colormap=cv2.COLORMAP_JET, - heatmap_alpha=0.5, - view_img=False, - view_in_counts=True, - view_out_counts=True, - count_reg_pts=None, - count_txt_thickness=2, - count_txt_color=(0, 0, 0), - count_color=(255, 255, 255), - count_reg_color=(255, 0, 255), - region_thickness=5, - line_dist_thresh=15, - decay_factor=0.99, - shape="circle", - ): - """ - Configures the heatmap colormap, width, height and display parameters. - - Args: - colormap (cv2.COLORMAP): The colormap to be set. - imw (int): The width of the frame. - imh (int): The height of the frame. - heatmap_alpha (float): alpha value for heatmap display - view_img (bool): Flag indicating frame display - view_in_counts (bool): Flag to control whether to display the incounts on video stream. - view_out_counts (bool): Flag to control whether to display the outcounts on video stream. - count_reg_pts (list): Object counting region points - count_txt_thickness (int): Text thickness for object counting display - count_txt_color (RGB color): count text color value - count_color (RGB color): count text background color value - count_reg_color (RGB color): Color of object counting region - region_thickness (int): Object counting Region thickness - line_dist_thresh (int): Euclidean Distance threshold for line counter - decay_factor (float): value for removing heatmap area after object passed - shape (str): Heatmap shape, rect or circle shape supported - """ - self.imw = imw - self.imh = imh - self.heatmap_alpha = heatmap_alpha - self.view_img = view_img - self.view_in_counts = view_in_counts - self.view_out_counts = view_out_counts - self.colormap = colormap - - # Region and line selection - if count_reg_pts is not None: - if len(count_reg_pts) == 2: - print("Line Counter Initiated.") - self.count_reg_pts = count_reg_pts - self.counting_region = LineString(count_reg_pts) - - elif len(count_reg_pts) == 4: - print("Region Counter Initiated.") - self.count_reg_pts = count_reg_pts - self.counting_region = Polygon(self.count_reg_pts) - - else: - print("Region or line points Invalid, 2 or 4 points supported") - print("Using Line Counter Now") - self.counting_region = Polygon([(20, 400), (1260, 400)]) # dummy points - - # Heatmap new frame - self.heatmap = np.zeros((int(self.imh), int(self.imw)), dtype=np.float32) - - self.count_txt_thickness = count_txt_thickness - self.count_txt_color = count_txt_color - self.count_color = count_color - self.region_color = count_reg_color - self.region_thickness = region_thickness - self.decay_factor = decay_factor - self.line_dist_thresh = line_dist_thresh - self.shape = shape - - # shape of heatmap, if not selected - if self.shape not in ["circle", "rect"]: - print("Unknown shape value provided, 'circle' & 'rect' supported") - print("Using Circular shape now") - self.shape = "circle" - - def extract_results(self, tracks): - """ - Extracts results from the provided data. - - Args: - tracks (list): List of tracks obtained from the object tracking process. - """ - self.boxes = tracks[0].boxes.xyxy.cpu() - self.clss = tracks[0].boxes.cls.cpu().tolist() - self.track_ids = tracks[0].boxes.id.int().cpu().tolist() - - def generate_heatmap(self, im0, tracks): - """ - Generate heatmap based on tracking data. - - Args: - im0 (nd array): Image - tracks (list): List of tracks obtained from the object tracking process. - """ - self.im0 = im0 - if tracks[0].boxes.id is None: - self.heatmap = np.zeros((int(self.imh), int(self.imw)), dtype=np.float32) - if self.view_img and self.env_check: - self.display_frames() - return im0 - self.heatmap *= self.decay_factor # decay factor - self.extract_results(tracks) - self.annotator = Annotator(self.im0, self.count_txt_thickness, None) - - if self.count_reg_pts is not None: - # Draw counting region - if self.view_in_counts or self.view_out_counts: - self.annotator.draw_region( - reg_pts=self.count_reg_pts, color=self.region_color, thickness=self.region_thickness - ) - - for box, cls, track_id in zip(self.boxes, self.clss, self.track_ids): - if self.shape == "circle": - center = (int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2)) - radius = min(int(box[2]) - int(box[0]), int(box[3]) - int(box[1])) // 2 - - y, x = np.ogrid[0 : self.heatmap.shape[0], 0 : self.heatmap.shape[1]] - mask = (x - center[0]) ** 2 + (y - center[1]) ** 2 <= radius**2 - - self.heatmap[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] += ( - 2 * mask[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] - ) - - else: - self.heatmap[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] += 2 - - # Store tracking hist - track_line = self.track_history[track_id] - track_line.append((float((box[0] + box[2]) / 2), float((box[1] + box[3]) / 2))) - if len(track_line) > 30: - track_line.pop(0) - - # Count objects - if len(self.count_reg_pts) == 4: - if self.counting_region.contains(Point(track_line[-1])) and track_id not in self.counting_list: - self.counting_list.append(track_id) - if box[0] < self.counting_region.centroid.x: - self.out_counts += 1 - else: - self.in_counts += 1 - - elif len(self.count_reg_pts) == 2: - distance = Point(track_line[-1]).distance(self.counting_region) - if distance < self.line_dist_thresh and track_id not in self.counting_list: - self.counting_list.append(track_id) - if box[0] < self.counting_region.centroid.x: - self.out_counts += 1 - else: - self.in_counts += 1 - else: - for box, cls in zip(self.boxes, self.clss): - if self.shape == "circle": - center = (int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2)) - radius = min(int(box[2]) - int(box[0]), int(box[3]) - int(box[1])) // 2 - - y, x = np.ogrid[0 : self.heatmap.shape[0], 0 : self.heatmap.shape[1]] - mask = (x - center[0]) ** 2 + (y - center[1]) ** 2 <= radius**2 - - self.heatmap[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] += ( - 2 * mask[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] - ) - - else: - self.heatmap[int(box[1]) : int(box[3]), int(box[0]) : int(box[2])] += 2 - - # Normalize, apply colormap to heatmap and combine with original image - heatmap_normalized = cv2.normalize(self.heatmap, None, 0, 255, cv2.NORM_MINMAX) - heatmap_colored = cv2.applyColorMap(heatmap_normalized.astype(np.uint8), self.colormap) - - incount_label = f"In Count : {self.in_counts}" - outcount_label = f"OutCount : {self.out_counts}" - - # Display counts based on user choice - counts_label = None - if not self.view_in_counts and not self.view_out_counts: - counts_label = None - elif not self.view_in_counts: - counts_label = outcount_label - elif not self.view_out_counts: - counts_label = incount_label - else: - counts_label = f"{incount_label} {outcount_label}" - - if self.count_reg_pts is not None and counts_label is not None: - self.annotator.count_labels( - counts=counts_label, - count_txt_size=self.count_txt_thickness, - txt_color=self.count_txt_color, - color=self.count_color, - ) - - self.im0 = cv2.addWeighted(self.im0, 1 - self.heatmap_alpha, heatmap_colored, self.heatmap_alpha, 0) - - if self.env_check and self.view_img: - self.display_frames() - - return self.im0 - - def display_frames(self): - """Display frame.""" - cv2.imshow("Ultralytics Heatmap", self.im0) - - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - -if __name__ == "__main__": - Heatmap() diff --git a/ultralytics-main/ultralytics/solutions/object_counter.py b/ultralytics-main/ultralytics/solutions/object_counter.py deleted file mode 100644 index 3cb64fd..0000000 --- a/ultralytics-main/ultralytics/solutions/object_counter.py +++ /dev/null @@ -1,278 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from collections import defaultdict - -import cv2 - -from ultralytics.utils.checks import check_imshow, check_requirements -from ultralytics.utils.plotting import Annotator, colors - -check_requirements("shapely>=2.0.0") - -from shapely.geometry import LineString, Point, Polygon - - -class ObjectCounter: - """A class to manage the counting of objects in a real-time video stream based on their tracks.""" - - def __init__(self): - """Initializes the Counter with default values for various tracking and counting parameters.""" - - # Mouse events - self.is_drawing = False - self.selected_point = None - - # Region & Line Information - self.reg_pts = [(20, 400), (1260, 400)] - self.line_dist_thresh = 15 - self.counting_region = None - self.region_color = (255, 0, 255) - self.region_thickness = 5 - - # Image and annotation Information - self.im0 = None - self.tf = None - self.view_img = False - self.view_in_counts = True - self.view_out_counts = True - - self.names = None # Classes names - self.annotator = None # Annotator - self.window_name = "Ultralytics YOLOv8 Object Counter" - - # Object counting Information - self.in_counts = 0 - self.out_counts = 0 - self.counting_dict = {} - self.count_txt_thickness = 0 - self.count_txt_color = (0, 0, 0) - self.count_color = (255, 255, 255) - - # Tracks info - self.track_history = defaultdict(list) - self.track_thickness = 2 - self.draw_tracks = False - self.track_color = (0, 255, 0) - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - classes_names, - reg_pts, - count_reg_color=(255, 0, 255), - line_thickness=2, - track_thickness=2, - view_img=False, - view_in_counts=True, - view_out_counts=True, - draw_tracks=False, - count_txt_thickness=2, - count_txt_color=(0, 0, 0), - count_color=(255, 255, 255), - track_color=(0, 255, 0), - region_thickness=5, - line_dist_thresh=15, - ): - """ - Configures the Counter's image, bounding box line thickness, and counting region points. - - Args: - line_thickness (int): Line thickness for bounding boxes. - view_img (bool): Flag to control whether to display the video stream. - view_in_counts (bool): Flag to control whether to display the incounts on video stream. - view_out_counts (bool): Flag to control whether to display the outcounts on video stream. - reg_pts (list): Initial list of points defining the counting region. - classes_names (dict): Classes names - track_thickness (int): Track thickness - draw_tracks (Bool): draw tracks - count_txt_thickness (int): Text thickness for object counting display - count_txt_color (RGB color): count text color value - count_color (RGB color): count text background color value - count_reg_color (RGB color): Color of object counting region - track_color (RGB color): color for tracks - region_thickness (int): Object counting Region thickness - line_dist_thresh (int): Euclidean Distance threshold for line counter - """ - self.tf = line_thickness - self.view_img = view_img - self.view_in_counts = view_in_counts - self.view_out_counts = view_out_counts - self.track_thickness = track_thickness - self.draw_tracks = draw_tracks - - # Region and line selection - if len(reg_pts) == 2: - print("Line Counter Initiated.") - self.reg_pts = reg_pts - self.counting_region = LineString(self.reg_pts) - elif len(reg_pts) >= 3: - print("Region Counter Initiated.") - self.reg_pts = reg_pts - self.counting_region = Polygon(self.reg_pts) - else: - print("Invalid Region points provided, region_points must be 2 for lines or >= 3 for polygons.") - print("Using Line Counter Now") - self.counting_region = LineString(self.reg_pts) - - self.names = classes_names - self.track_color = track_color - self.count_txt_thickness = count_txt_thickness - self.count_txt_color = count_txt_color - self.count_color = count_color - self.region_color = count_reg_color - self.region_thickness = region_thickness - self.line_dist_thresh = line_dist_thresh - - def mouse_event_for_region(self, event, x, y, flags, params): - """ - This function is designed to move region with mouse events in a real-time video stream. - - Args: - event (int): The type of mouse event (e.g., cv2.EVENT_MOUSEMOVE, cv2.EVENT_LBUTTONDOWN, etc.). - x (int): The x-coordinate of the mouse pointer. - y (int): The y-coordinate of the mouse pointer. - flags (int): Any flags associated with the event (e.g., cv2.EVENT_FLAG_CTRLKEY, - cv2.EVENT_FLAG_SHIFTKEY, etc.). - params (dict): Additional parameters you may want to pass to the function. - """ - if event == cv2.EVENT_LBUTTONDOWN: - for i, point in enumerate(self.reg_pts): - if ( - isinstance(point, (tuple, list)) - and len(point) >= 2 - and (abs(x - point[0]) < 10 and abs(y - point[1]) < 10) - ): - self.selected_point = i - self.is_drawing = True - break - - elif event == cv2.EVENT_MOUSEMOVE: - if self.is_drawing and self.selected_point is not None: - self.reg_pts[self.selected_point] = (x, y) - self.counting_region = Polygon(self.reg_pts) - - elif event == cv2.EVENT_LBUTTONUP: - self.is_drawing = False - self.selected_point = None - - def extract_and_process_tracks(self, tracks): - """Extracts and processes tracks for object counting in a video stream.""" - - # Annotator Init and region drawing - self.annotator = Annotator(self.im0, self.tf, self.names) - - if tracks[0].boxes.id is not None: - boxes = tracks[0].boxes.xyxy.cpu() - clss = tracks[0].boxes.cls.cpu().tolist() - track_ids = tracks[0].boxes.id.int().cpu().tolist() - - # Extract tracks - for box, track_id, cls in zip(boxes, track_ids, clss): - # Draw bounding box - self.annotator.box_label(box, label=f"{track_id}:{self.names[cls]}", color=colors(int(cls), True)) - - # Draw Tracks - track_line = self.track_history[track_id] - track_line.append((float((box[0] + box[2]) / 2), float((box[1] + box[3]) / 2))) - if len(track_line) > 30: - track_line.pop(0) - - # Draw track trails - if self.draw_tracks: - self.annotator.draw_centroid_and_tracks( - track_line, color=self.track_color, track_thickness=self.track_thickness - ) - - prev_position = self.track_history[track_id][-2] if len(self.track_history[track_id]) > 1 else None - centroid = Point((box[:2] + box[2:]) / 2) - - # Count objects - if len(self.reg_pts) >= 3: # any polygon - is_inside = self.counting_region.contains(centroid) - current_position = "in" if is_inside else "out" - - if prev_position is not None: - if self.counting_dict[track_id] != current_position and is_inside: - self.in_counts += 1 - self.counting_dict[track_id] = "in" - elif self.counting_dict[track_id] != current_position and not is_inside: - self.out_counts += 1 - self.counting_dict[track_id] = "out" - else: - self.counting_dict[track_id] = current_position - - else: - self.counting_dict[track_id] = current_position - - elif len(self.reg_pts) == 2: - if prev_position is not None: - is_inside = (box[0] - prev_position[0]) * ( - self.counting_region.centroid.x - prev_position[0] - ) > 0 - current_position = "in" if is_inside else "out" - - if self.counting_dict[track_id] != current_position and is_inside: - self.in_counts += 1 - self.counting_dict[track_id] = "in" - elif self.counting_dict[track_id] != current_position and not is_inside: - self.out_counts += 1 - self.counting_dict[track_id] = "out" - else: - self.counting_dict[track_id] = current_position - else: - self.counting_dict[track_id] = None - - incount_label = f"In Count : {self.in_counts}" - outcount_label = f"OutCount : {self.out_counts}" - - # Display counts based on user choice - counts_label = None - if not self.view_in_counts and not self.view_out_counts: - counts_label = None - elif not self.view_in_counts: - counts_label = outcount_label - elif not self.view_out_counts: - counts_label = incount_label - else: - counts_label = f"{incount_label} {outcount_label}" - - if counts_label is not None: - self.annotator.count_labels( - counts=counts_label, - count_txt_size=self.count_txt_thickness, - txt_color=self.count_txt_color, - color=self.count_color, - ) - - def display_frames(self): - """Display frame.""" - if self.env_check: - self.annotator.draw_region(reg_pts=self.reg_pts, color=self.region_color, thickness=self.region_thickness) - cv2.namedWindow(self.window_name) - if len(self.reg_pts) == 4: # only add mouse event If user drawn region - cv2.setMouseCallback(self.window_name, self.mouse_event_for_region, {"region_points": self.reg_pts}) - cv2.imshow(self.window_name, self.im0) - # Break Window - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - def start_counting(self, im0, tracks): - """ - Main function to start the object counting process. - - Args: - im0 (ndarray): Current frame from the video stream. - tracks (list): List of tracks obtained from the object tracking process. - """ - self.im0 = im0 # store image - self.extract_and_process_tracks(tracks) # draw region even if no objects - - if self.view_img: - self.display_frames() - return self.im0 - - -if __name__ == "__main__": - ObjectCounter() diff --git a/ultralytics-main/ultralytics/solutions/speed.py b/ultralytics-main/ultralytics/solutions/speed.py deleted file mode 100644 index a767710..0000000 --- a/ultralytics-main/ultralytics/solutions/speed.py +++ /dev/null @@ -1,164 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -import math -from collections import defaultdict -from time import time - -import cv2 -import numpy as np - -from ultralytics.utils.checks import check_imshow -from ultralytics.utils.plotting import Annotator, colors -import gol - -class SpeedEstimator: - """A class to estimation speed of objects in real-time video stream based on their tracks.""" - - def __init__(self): - """Initializes the speed-estimator class with default values for Visual, Image, track and speed parameters.""" - - # Visual & im0 information - self.im0 = None - self.annotator = None - self.view_img = False - - # Region information - # self.reg_pts = [(20, 400), (1260, 400)] - self.region_thickness = 3 - - # Predict/track information - self.clss = None - self.names = None - self.boxes = None - self.trk_ids = None - self.trk_pts = None - self.line_thickness = 2 - self.trk_history = defaultdict(list) - - # Speed estimator information - self.current_time = 0 - self.dist_data = {} - self.trk_idslist = [] - self.spdl_dist_thresh = 10 - self.trk_previous_times = {} - self.trk_previous_points = {} - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - # reg_pts, - names, - view_img=False, - line_thickness=2, - region_thickness=5, - spdl_dist_thresh=10, - ): - """ - Configures the speed estimation and display parameters. - - Args: - reg_pts (list): Initial list of points defining the speed calculation region. - names (dict): object detection classes names - view_img (bool): Flag indicating frame display - line_thickness (int): Line thickness for bounding boxes. - region_thickness (int): Speed estimation region thickness - spdl_dist_thresh (int): Euclidean distance threshold for speed line - """ - # if reg_pts is None: - # print("Region points not provided, using default values") - # else: - # self.reg_pts = reg_pts - self.names = names - self.view_img = view_img - self.line_thickness = line_thickness - self.region_thickness = region_thickness - self.spdl_dist_thresh = spdl_dist_thresh - - def extract_tracks(self, tracks): - self.boxes = tracks[0].boxes.xyxy.cpu() - self.clss = tracks[0].boxes.cls.cpu().tolist() - self.trk_ids = tracks[0].boxes.id.int().cpu().tolist() - - def store_track_info(self, track_id, box): - - track = self.trk_history[track_id] - bbox_center = (float((box[0] + box[2]) / 2), float((box[1] + box[3]) / 2)) - x_center = (box[0] + box[2]) / 2 - y_center = (box[1] + box[3]) / 2 - - # points_3d = gol.get_value('points_3d') - # a = points_3d[int(y_center), int(x_center), 0] / 1000 - # b = points_3d[int(y_center), int(x_center), 1] / 1000 - # c = points_3d[int(y_center), int(x_center), 2] / 1000 - a = gol.get_value('a') - b = gol.get_value('b') - c = gol.get_value('c') - bbox_center_3d = (float(a), float(b), float(c)) - - # track.append(bbox_center) - track.append(bbox_center_3d) - if len(track) > 30: - track.pop(0) - self.trk_pts = np.hstack(track).astype(np.int32).reshape((-1, 1, 3)) # 修改 - return track - - def plot_box_and_track(self, track_id, box, cls, track): - speed_label = f"{int(self.dist_data[track_id])}km/ph" if track_id in self.dist_data else self.names[int(cls)] - bbox_color = colors(int(track_id)) if track_id in self.dist_data else (255, 0, 255) - self.annotator.box_label(box, speed_label, bbox_color) - # cv2.polylines(self.im0, [self.trk_pts], isClosed=False, color=(0, 255, 0), thickness=1) - # cv2.circle(self.im0, (int(track[-1][0]), int(track[-1][1])), 5, bbox_color, -1) - # 绘制轨迹 - for i in range(len(track) - 1): - cv2.line(self.im0, (int(track[i][0]), int(track[i][1])), (int(track[i + 1][0]), int(track[i + 1][1])), - (0, 255, 0), 1) - # 绘制最后一个点 - cv2.circle(self.im0, (int(track[-1][0]), int(track[-1][1])), 5, bbox_color, -1) - - def calculate_speed(self, trk_id, track): - - if self.trk_previous_times[trk_id] != 0 and trk_id not in self.trk_idslist: - self.trk_idslist.append(trk_id) - time_difference = time() - self.trk_previous_times[trk_id] - if time_difference > 0: - dist_difference_0 = np.abs(track[-1][0] - self.trk_previous_points[trk_id][0]) - dist_difference_1 = np.abs(track[-1][1] - self.trk_previous_points[trk_id][1]) - dist_difference_2 = np.abs(track[-1][2] - self.trk_previous_points[trk_id][2]) - dist_difference = math.sqrt(dist_difference_0 ** 2 + dist_difference_1 ** 2 + dist_difference_2 ** 2) - speed = dist_difference / time_difference - self.dist_data[trk_id] = speed - self.trk_previous_times[trk_id] = time() - self.trk_previous_points[trk_id] = track[-1] - - def estimate_speed(self, im0, tracks, region_color=(255, 0, 0)): - self.im0 = im0 - if tracks[0].boxes.id is None: - if self.view_img and self.env_check: - self.display_frames() - return im0 - self.extract_tracks(tracks) - self.annotator = Annotator(self.im0, line_width=2) - # self.annotator.draw_region(reg_pts=self.reg_pts, color=region_color, thickness=self.region_thickness) - for box, trk_id, cls in zip(self.boxes, self.trk_ids, self.clss): - track = self.store_track_info(trk_id, box) # 将返回的轨迹信息存储在 track 中 - - if trk_id not in self.trk_previous_times: - self.trk_previous_times[trk_id] = 0 - self.plot_box_and_track(trk_id, box, cls, track) - self.calculate_speed(trk_id, track) # 计算速度 - - if self.view_img and self.env_check: - self.display_frames() - - return im0 - - def display_frames(self): - """Display frame.""" - cv2.imshow("Ultralytics Speed Estimation", self.im0) - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - -if __name__ == "__main__": - SpeedEstimator() diff --git a/ultralytics-main/ultralytics/solutions/speed_estimation.py b/ultralytics-main/ultralytics/solutions/speed_estimation.py deleted file mode 100644 index 9fafb0d..0000000 --- a/ultralytics-main/ultralytics/solutions/speed_estimation.py +++ /dev/null @@ -1,198 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from collections import defaultdict -from time import time - -import cv2 -import numpy as np - -from ultralytics.utils.checks import check_imshow -from ultralytics.utils.plotting import Annotator, colors - - -class SpeedEstimator: - """A class to estimation speed of objects in real-time video stream based on their tracks.""" - - def __init__(self): - """Initializes the speed-estimator class with default values for Visual, Image, track and speed parameters.""" - - # Visual & im0 information - self.im0 = None - self.annotator = None - self.view_img = False - - # Region information - self.reg_pts = [(20, 400), (1260, 400)] - self.region_thickness = 3 - - # Predict/track information - self.clss = None - self.names = None - self.boxes = None - self.trk_ids = None - self.trk_pts = None - self.line_thickness = 2 - self.trk_history = defaultdict(list) - - # Speed estimator information - self.current_time = 0 - self.dist_data = {} - self.trk_idslist = [] - self.spdl_dist_thresh = 10 - self.trk_previous_times = {} - self.trk_previous_points = {} - - # Check if environment support imshow - self.env_check = check_imshow(warn=True) - - def set_args( - self, - reg_pts, - names, - view_img=False, - line_thickness=2, - region_thickness=5, - spdl_dist_thresh=10, - ): - """ - Configures the speed estimation and display parameters. - - Args: - reg_pts (list): Initial list of points defining the speed calculation region. - names (dict): object detection classes names - view_img (bool): Flag indicating frame display - line_thickness (int): Line thickness for bounding boxes. - region_thickness (int): Speed estimation region thickness - spdl_dist_thresh (int): Euclidean distance threshold for speed line - """ - if reg_pts is None: - print("Region points not provided, using default values") - else: - self.reg_pts = reg_pts - self.names = names - self.view_img = view_img - self.line_thickness = line_thickness - self.region_thickness = region_thickness - self.spdl_dist_thresh = spdl_dist_thresh - - def extract_tracks(self, tracks): - """ - Extracts results from the provided data. - - Args: - tracks (list): List of tracks obtained from the object tracking process. - """ - self.boxes = tracks[0].boxes.xyxy.cpu() - self.clss = tracks[0].boxes.cls.cpu().tolist() - self.trk_ids = tracks[0].boxes.id.int().cpu().tolist() - - def store_track_info(self, track_id, box): - """ - Store track data. - - Args: - track_id (int): object track id. - box (list): object bounding box data - """ - track = self.trk_history[track_id] - bbox_center = (float((box[0] + box[2]) / 2), float((box[1] + box[3]) / 2)) - track.append(bbox_center) - - if len(track) > 30: - track.pop(0) - - self.trk_pts = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - return track - - def plot_box_and_track(self, track_id, box, cls, track): - """ - Plot track and bounding box. - - Args: - track_id (int): object track id. - box (list): object bounding box data - cls (str): object class name - track (list): tracking history for tracks path drawing - """ - speed_label = f"{int(self.dist_data[track_id])}km/ph" if track_id in self.dist_data else self.names[int(cls)] - bbox_color = colors(int(track_id)) if track_id in self.dist_data else (255, 0, 255) - - self.annotator.box_label(box, speed_label, bbox_color) - - cv2.polylines(self.im0, [self.trk_pts], isClosed=False, color=(0, 255, 0), thickness=1) - cv2.circle(self.im0, (int(track[-1][0]), int(track[-1][1])), 5, bbox_color, -1) - - def calculate_speed(self, trk_id, track): - """ - Calculation of object speed. - - Args: - trk_id (int): object track id. - track (list): tracking history for tracks path drawing - """ - - if not self.reg_pts[0][0] < track[-1][0] < self.reg_pts[1][0]: - return - if self.reg_pts[1][1] - self.spdl_dist_thresh < track[-1][1] < self.reg_pts[1][1] + self.spdl_dist_thresh: - direction = "known" - - elif self.reg_pts[0][1] - self.spdl_dist_thresh < track[-1][1] < self.reg_pts[0][1] + self.spdl_dist_thresh: - direction = "known" - - else: - direction = "unknown" - - if self.trk_previous_times[trk_id] != 0 and direction != "unknown" and trk_id not in self.trk_idslist: - self.trk_idslist.append(trk_id) - - time_difference = time() - self.trk_previous_times[trk_id] - if time_difference > 0: - dist_difference = np.abs(track[-1][1] - self.trk_previous_points[trk_id][1]) - speed = dist_difference / time_difference - self.dist_data[trk_id] = speed - - self.trk_previous_times[trk_id] = time() - self.trk_previous_points[trk_id] = track[-1] - - def estimate_speed(self, im0, tracks, region_color=(255, 0, 0)): - """ - Calculate object based on tracking data. - - Args: - im0 (nd array): Image - tracks (list): List of tracks obtained from the object tracking process. - region_color (tuple): Color to use when drawing regions. - """ - self.im0 = im0 - if tracks[0].boxes.id is None: - if self.view_img and self.env_check: - self.display_frames() - return im0 - self.extract_tracks(tracks) - - self.annotator = Annotator(self.im0, line_width=2) - self.annotator.draw_region(reg_pts=self.reg_pts, color=region_color, thickness=self.region_thickness) - - for box, trk_id, cls in zip(self.boxes, self.trk_ids, self.clss): - track = self.store_track_info(trk_id, box) # 将返回的轨迹信息存储在 track 中 - - if trk_id not in self.trk_previous_times: - self.trk_previous_times[trk_id] = 0 - - self.plot_box_and_track(trk_id, box, cls, track) - self.calculate_speed(trk_id, track) # 计算速度 - - if self.view_img and self.env_check: - self.display_frames() - - return im0 - - def display_frames(self): - """Display frame.""" - cv2.imshow("Ultralytics Speed Estimation", self.im0) - if cv2.waitKey(1) & 0xFF == ord("q"): - return - - -if __name__ == "__main__": - SpeedEstimator() diff --git a/ultralytics-main/ultralytics/trackers/README.md b/ultralytics-main/ultralytics/trackers/README.md deleted file mode 100644 index 2cab3c0..0000000 --- a/ultralytics-main/ultralytics/trackers/README.md +++ /dev/null @@ -1,321 +0,0 @@ -# Multi-Object Tracking with Ultralytics YOLO - -YOLOv8 trackers visualization - -Object tracking in the realm of video analytics is a critical task that not only identifies the location and class of objects within the frame but also maintains a unique ID for each detected object as the video progresses. The applications are limitless—ranging from surveillance and security to real-time sports analytics. - -## Why Choose Ultralytics YOLO for Object Tracking? - -The output from Ultralytics trackers is consistent with standard object detection but has the added value of object IDs. This makes it easy to track objects in video streams and perform subsequent analytics. Here's why you should consider using Ultralytics YOLO for your object tracking needs: - -- **Efficiency:** Process video streams in real-time without compromising accuracy. -- **Flexibility:** Supports multiple tracking algorithms and configurations. -- **Ease of Use:** Simple Python API and CLI options for quick integration and deployment. -- **Customizability:** Easy to use with custom trained YOLO models, allowing integration into domain-specific applications. - -**Video Tutorial:** [Object Detection and Tracking with Ultralytics YOLOv8](https://www.youtube.com/embed/hHyHmOtmEgs?si=VNZtXmm45Nb9s-N-). - -## Features at a Glance - -Ultralytics YOLO extends its object detection features to provide robust and versatile object tracking: - -- **Real-Time Tracking:** Seamlessly track objects in high-frame-rate videos. -- **Multiple Tracker Support:** Choose from a variety of established tracking algorithms. -- **Customizable Tracker Configurations:** Tailor the tracking algorithm to meet specific requirements by adjusting various parameters. - -## Available Trackers - -Ultralytics YOLO supports the following tracking algorithms. They can be enabled by passing the relevant YAML configuration file such as `tracker=tracker_type.yaml`: - -- [BoT-SORT](https://github.com/NirAharon/BoT-SORT) - Use `botsort.yaml` to enable this tracker. -- [ByteTrack](https://github.com/ifzhang/ByteTrack) - Use `bytetrack.yaml` to enable this tracker. - -The default tracker is BoT-SORT. - -## Tracking - -To run the tracker on video streams, use a trained Detect, Segment or Pose model such as YOLOv8n, YOLOv8n-seg and YOLOv8n-pose. - -#### Python - -```python -from ultralytics import YOLO - -# Load an official or custom model -model = YOLO("yolov8n.pt") # Load an official Detect model -model = YOLO("yolov8n-seg.pt") # Load an official Segment model -model = YOLO("yolov8n-pose.pt") # Load an official Pose model -model = YOLO("path/to/best.pt") # Load a custom trained model - -# Perform tracking with the model -results = model.track( - source="https://youtu.be/LNwODJXcvt4", show=True -) # Tracking with default tracker -results = model.track( - source="https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml" -) # Tracking with ByteTrack tracker -``` - -#### CLI - -```bash -# Perform tracking with various models using the command line interface -yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" # Official Detect model -yolo track model=yolov8n-seg.pt source="https://youtu.be/LNwODJXcvt4" # Official Segment model -yolo track model=yolov8n-pose.pt source="https://youtu.be/LNwODJXcvt4" # Official Pose model -yolo track model=path/to/best.pt source="https://youtu.be/LNwODJXcvt4" # Custom trained model - -# Track using ByteTrack tracker -yolo track model=path/to/best.pt tracker="bytetrack.yaml" -``` - -As can be seen in the above usage, tracking is available for all Detect, Segment and Pose models run on videos or streaming sources. - -## Configuration - -### Tracking Arguments - -Tracking configuration shares properties with Predict mode, such as `conf`, `iou`, and `show`. For further configurations, refer to the [Predict](https://docs.ultralytics.com/modes/predict/) model page. - -#### Python - -```python -from ultralytics import YOLO - -# Configure the tracking parameters and run the tracker -model = YOLO("yolov8n.pt") -results = model.track( - source="https://youtu.be/LNwODJXcvt4", conf=0.3, iou=0.5, show=True -) -``` - -#### CLI - -```bash -# Configure tracking parameters and run the tracker using the command line interface -yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" conf=0.3, iou=0.5 show -``` - -### Tracker Selection - -Ultralytics also allows you to use a modified tracker configuration file. To do this, simply make a copy of a tracker config file (for example, `custom_tracker.yaml`) from [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) and modify any configurations (except the `tracker_type`) as per your needs. - -#### Python - -```python -from ultralytics import YOLO - -# Load the model and run the tracker with a custom configuration file -model = YOLO("yolov8n.pt") -results = model.track( - source="https://youtu.be/LNwODJXcvt4", tracker="custom_tracker.yaml" -) -``` - -#### CLI - -```bash -# Load the model and run the tracker with a custom configuration file using the command line interface -yolo track model=yolov8n.pt source="https://youtu.be/LNwODJXcvt4" tracker='custom_tracker.yaml' -``` - -For a comprehensive list of tracking arguments, refer to the [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) page. - -## Python Examples - -### Persisting Tracks Loop - -Here is a Python script using OpenCV (`cv2`) and YOLOv8 to run object tracking on video frames. This script still assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`). The `persist=True` argument tells the tracker than the current image or frame is the next in a sequence and to expect tracks from the previous image in the current image. - -#### Python - -```python -import cv2 -from ultralytics import YOLO - -# Load the YOLOv8 model -model = YOLO("yolov8n.pt") - -# Open the video file -video_path = "path/to/video.mp4" -cap = cv2.VideoCapture(video_path) - -# Loop through the video frames -while cap.isOpened(): - # Read a frame from the video - success, frame = cap.read() - - if success: - # Run YOLOv8 tracking on the frame, persisting tracks between frames - results = model.track(frame, persist=True) - - # Visualize the results on the frame - annotated_frame = results[0].plot() - - # Display the annotated frame - cv2.imshow("YOLOv8 Tracking", annotated_frame) - - # Break the loop if 'q' is pressed - if cv2.waitKey(1) & 0xFF == ord("q"): - break - else: - # Break the loop if the end of the video is reached - break - -# Release the video capture object and close the display window -cap.release() -cv2.destroyAllWindows() -``` - -Please note the change from `model(frame)` to `model.track(frame)`, which enables object tracking instead of simple detection. This modified script will run the tracker on each frame of the video, visualize the results, and display them in a window. The loop can be exited by pressing 'q'. - -### Plotting Tracks Over Time - -Visualizing object tracks over consecutive frames can provide valuable insights into the movement patterns and behavior of detected objects within a video. With Ultralytics YOLOv8, plotting these tracks is a seamless and efficient process. - -In the following example, we demonstrate how to utilize YOLOv8's tracking capabilities to plot the movement of detected objects across multiple video frames. This script involves opening a video file, reading it frame by frame, and utilizing the YOLO model to identify and track various objects. By retaining the center points of the detected bounding boxes and connecting them, we can draw lines that represent the paths followed by the tracked objects. - -#### Python - -```python -from collections import defaultdict - -import cv2 -import numpy as np - -from ultralytics import YOLO - -# Load the YOLOv8 model -model = YOLO("yolov8n.pt") - -# Open the video file -video_path = "path/to/video.mp4" -cap = cv2.VideoCapture(video_path) - -# Store the track history -track_history = defaultdict(lambda: []) - -# Loop through the video frames -while cap.isOpened(): - # Read a frame from the video - success, frame = cap.read() - - if success: - # Run YOLOv8 tracking on the frame, persisting tracks between frames - results = model.track(frame, persist=True) - - # Get the boxes and track IDs - boxes = results[0].boxes.xywh.cpu() - track_ids = results[0].boxes.id.int().cpu().tolist() - - # Visualize the results on the frame - annotated_frame = results[0].plot() - - # Plot the tracks - for box, track_id in zip(boxes, track_ids): - x, y, w, h = box - track = track_history[track_id] - track.append((float(x), float(y))) # x, y center point - if len(track) > 30: # retain 90 tracks for 90 frames - track.pop(0) - - # Draw the tracking lines - points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines( - annotated_frame, - [points], - isClosed=False, - color=(230, 230, 230), - thickness=10, - ) - - # Display the annotated frame - cv2.imshow("YOLOv8 Tracking", annotated_frame) - - # Break the loop if 'q' is pressed - if cv2.waitKey(1) & 0xFF == ord("q"): - break - else: - # Break the loop if the end of the video is reached - break - -# Release the video capture object and close the display window -cap.release() -cv2.destroyAllWindows() -``` - -### Multithreaded Tracking - -Multithreaded tracking provides the capability to run object tracking on multiple video streams simultaneously. This is particularly useful when handling multiple video inputs, such as from multiple surveillance cameras, where concurrent processing can greatly enhance efficiency and performance. - -In the provided Python script, we make use of Python's `threading` module to run multiple instances of the tracker concurrently. Each thread is responsible for running the tracker on one video file, and all the threads run simultaneously in the background. - -To ensure that each thread receives the correct parameters (the video file and the model to use), we define a function `run_tracker_in_thread` that accepts these parameters and contains the main tracking loop. This function reads the video frame by frame, runs the tracker, and displays the results. - -Two different models are used in this example: `yolov8n.pt` and `yolov8n-seg.pt`, each tracking objects in a different video file. The video files are specified in `video_file1` and `video_file2`. - -The `daemon=True` parameter in `threading.Thread` means that these threads will be closed as soon as the main program finishes. We then start the threads with `start()` and use `join()` to make the main thread wait until both tracker threads have finished. - -Finally, after all threads have completed their task, the windows displaying the results are closed using `cv2.destroyAllWindows()`. - -#### Python - -```python -import threading - -import cv2 -from ultralytics import YOLO - - -def run_tracker_in_thread(filename, model): - video = cv2.VideoCapture(filename) - frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT)) - for _ in range(frames): - ret, frame = video.read() - if ret: - results = model.track(source=frame, persist=True) - res_plotted = results[0].plot() - cv2.imshow("p", res_plotted) - if cv2.waitKey(1) == ord("q"): - break - - -# Load the models -model1 = YOLO("yolov8n.pt") -model2 = YOLO("yolov8n-seg.pt") - -# Define the video files for the trackers -video_file1 = "path/to/video1.mp4" -video_file2 = "path/to/video2.mp4" - -# Create the tracker threads -tracker_thread1 = threading.Thread( - target=run_tracker_in_thread, args=(video_file1, model1), daemon=True -) -tracker_thread2 = threading.Thread( - target=run_tracker_in_thread, args=(video_file2, model2), daemon=True -) - -# Start the tracker threads -tracker_thread1.start() -tracker_thread2.start() - -# Wait for the tracker threads to finish -tracker_thread1.join() -tracker_thread2.join() - -# Clean up and close windows -cv2.destroyAllWindows() -``` - -This example can easily be extended to handle more video files and models by creating more threads and applying the same methodology. - -## Contribute New Trackers - -Are you proficient in multi-object tracking and have successfully implemented or adapted a tracking algorithm with Ultralytics YOLO? We invite you to contribute to our Trackers section in [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers)! Your real-world applications and solutions could be invaluable for users working on tracking tasks. - -By contributing to this section, you help expand the scope of tracking solutions available within the Ultralytics YOLO framework, adding another layer of functionality and utility for the community. - -To initiate your contribution, please refer to our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for comprehensive instructions on submitting a Pull Request (PR) 🛠️. We are excited to see what you bring to the table! - -Together, let's enhance the tracking capabilities of the Ultralytics YOLO ecosystem 🙏! diff --git a/ultralytics-main/ultralytics/trackers/__init__.py b/ultralytics-main/ultralytics/trackers/__init__.py deleted file mode 100644 index bf51b8d..0000000 --- a/ultralytics-main/ultralytics/trackers/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .bot_sort import BOTSORT -from .byte_tracker import BYTETracker -from .track import register_tracker - -__all__ = "register_tracker", "BOTSORT", "BYTETracker" # allow simpler import diff --git a/ultralytics-main/ultralytics/trackers/basetrack.py b/ultralytics-main/ultralytics/trackers/basetrack.py deleted file mode 100644 index c900cac..0000000 --- a/ultralytics-main/ultralytics/trackers/basetrack.py +++ /dev/null @@ -1,105 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""This module defines the base classes and structures for object tracking in YOLO.""" - -from collections import OrderedDict - -import numpy as np - - -class TrackState: - """ - Enumeration class representing the possible states of an object being tracked. - - Attributes: - New (int): State when the object is newly detected. - Tracked (int): State when the object is successfully tracked in subsequent frames. - Lost (int): State when the object is no longer tracked. - Removed (int): State when the object is removed from tracking. - """ - - New = 0 - Tracked = 1 - Lost = 2 - Removed = 3 - - -class BaseTrack: - """ - Base class for object tracking, providing foundational attributes and methods. - - Attributes: - _count (int): Class-level counter for unique track IDs. - track_id (int): Unique identifier for the track. - is_activated (bool): Flag indicating whether the track is currently active. - state (TrackState): Current state of the track. - history (OrderedDict): Ordered history of the track's states. - features (list): List of features extracted from the object for tracking. - curr_feature (any): The current feature of the object being tracked. - score (float): The confidence score of the tracking. - start_frame (int): The frame number where tracking started. - frame_id (int): The most recent frame ID processed by the track. - time_since_update (int): Frames passed since the last update. - location (tuple): The location of the object in the context of multi-camera tracking. - - Methods: - end_frame: Returns the ID of the last frame where the object was tracked. - next_id: Increments and returns the next global track ID. - activate: Abstract method to activate the track. - predict: Abstract method to predict the next state of the track. - update: Abstract method to update the track with new data. - mark_lost: Marks the track as lost. - mark_removed: Marks the track as removed. - reset_id: Resets the global track ID counter. - """ - - _count = 0 - - def __init__(self): - """Initializes a new track with unique ID and foundational tracking attributes.""" - self.track_id = 0 - self.is_activated = False - self.state = TrackState.New - self.history = OrderedDict() - self.features = [] - self.curr_feature = None - self.score = 0 - self.start_frame = 0 - self.frame_id = 0 - self.time_since_update = 0 - self.location = (np.inf, np.inf) - - @property - def end_frame(self): - """Return the last frame ID of the track.""" - return self.frame_id - - @staticmethod - def next_id(): - """Increment and return the global track ID counter.""" - BaseTrack._count += 1 - return BaseTrack._count - - def activate(self, *args): - """Abstract method to activate the track with provided arguments.""" - raise NotImplementedError - - def predict(self): - """Abstract method to predict the next state of the track.""" - raise NotImplementedError - - def update(self, *args, **kwargs): - """Abstract method to update the track with new observations.""" - raise NotImplementedError - - def mark_lost(self): - """Mark the track as lost.""" - self.state = TrackState.Lost - - def mark_removed(self): - """Mark the track as removed.""" - self.state = TrackState.Removed - - @staticmethod - def reset_id(): - """Reset the global track ID counter.""" - BaseTrack._count = 0 diff --git a/ultralytics-main/ultralytics/trackers/bot_sort.py b/ultralytics-main/ultralytics/trackers/bot_sort.py deleted file mode 100644 index 31d5e1b..0000000 --- a/ultralytics-main/ultralytics/trackers/bot_sort.py +++ /dev/null @@ -1,200 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from collections import deque - -import numpy as np - -from .basetrack import TrackState -from .byte_tracker import BYTETracker, STrack -from .utils import matching -from .utils.gmc import GMC -from .utils.kalman_filter import KalmanFilterXYWH - - -class BOTrack(STrack): - """ - An extended version of the STrack class for YOLOv8, adding object tracking features. - - Attributes: - shared_kalman (KalmanFilterXYWH): A shared Kalman filter for all instances of BOTrack. - smooth_feat (np.ndarray): Smoothed feature vector. - curr_feat (np.ndarray): Current feature vector. - features (deque): A deque to store feature vectors with a maximum length defined by `feat_history`. - alpha (float): Smoothing factor for the exponential moving average of features. - mean (np.ndarray): The mean state of the Kalman filter. - covariance (np.ndarray): The covariance matrix of the Kalman filter. - - Methods: - update_features(feat): Update features vector and smooth it using exponential moving average. - predict(): Predicts the mean and covariance using Kalman filter. - re_activate(new_track, frame_id, new_id): Reactivates a track with updated features and optionally new ID. - update(new_track, frame_id): Update the YOLOv8 instance with new track and frame ID. - tlwh: Property that gets the current position in tlwh format `(top left x, top left y, width, height)`. - multi_predict(stracks): Predicts the mean and covariance of multiple object tracks using shared Kalman filter. - convert_coords(tlwh): Converts tlwh bounding box coordinates to xywh format. - tlwh_to_xywh(tlwh): Convert bounding box to xywh format `(center x, center y, width, height)`. - - Usage: - bo_track = BOTrack(tlwh, score, cls, feat) - bo_track.predict() - bo_track.update(new_track, frame_id) - """ - - shared_kalman = KalmanFilterXYWH() - - def __init__(self, tlwh, score, cls, feat=None, feat_history=50): - """Initialize YOLOv8 object with temporal parameters, such as feature history, alpha and current features.""" - super().__init__(tlwh, score, cls) - - self.smooth_feat = None - self.curr_feat = None - if feat is not None: - self.update_features(feat) - self.features = deque([], maxlen=feat_history) - self.alpha = 0.9 - - def update_features(self, feat): - """Update features vector and smooth it using exponential moving average.""" - feat /= np.linalg.norm(feat) - self.curr_feat = feat - if self.smooth_feat is None: - self.smooth_feat = feat - else: - self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat - self.features.append(feat) - self.smooth_feat /= np.linalg.norm(self.smooth_feat) - - def predict(self): - """Predicts the mean and covariance using Kalman filter.""" - mean_state = self.mean.copy() - if self.state != TrackState.Tracked: - mean_state[6] = 0 - mean_state[7] = 0 - - self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance) - - def re_activate(self, new_track, frame_id, new_id=False): - """Reactivates a track with updated features and optionally assigns a new ID.""" - if new_track.curr_feat is not None: - self.update_features(new_track.curr_feat) - super().re_activate(new_track, frame_id, new_id) - - def update(self, new_track, frame_id): - """Update the YOLOv8 instance with new track and frame ID.""" - if new_track.curr_feat is not None: - self.update_features(new_track.curr_feat) - super().update(new_track, frame_id) - - @property - def tlwh(self): - """Get current position in bounding box format `(top left x, top left y, width, height)`.""" - if self.mean is None: - return self._tlwh.copy() - ret = self.mean[:4].copy() - ret[:2] -= ret[2:] / 2 - return ret - - @staticmethod - def multi_predict(stracks): - """Predicts the mean and covariance of multiple object tracks using shared Kalman filter.""" - if len(stracks) <= 0: - return - multi_mean = np.asarray([st.mean.copy() for st in stracks]) - multi_covariance = np.asarray([st.covariance for st in stracks]) - for i, st in enumerate(stracks): - if st.state != TrackState.Tracked: - multi_mean[i][6] = 0 - multi_mean[i][7] = 0 - multi_mean, multi_covariance = BOTrack.shared_kalman.multi_predict(multi_mean, multi_covariance) - for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): - stracks[i].mean = mean - stracks[i].covariance = cov - - def convert_coords(self, tlwh): - """Converts Top-Left-Width-Height bounding box coordinates to X-Y-Width-Height format.""" - return self.tlwh_to_xywh(tlwh) - - @staticmethod - def tlwh_to_xywh(tlwh): - """Convert bounding box to format `(center x, center y, width, height)`.""" - ret = np.asarray(tlwh).copy() - ret[:2] += ret[2:] / 2 - return ret - - -class BOTSORT(BYTETracker): - """ - An extended version of the BYTETracker class for YOLOv8, designed for object tracking with ReID and GMC algorithm. - - Attributes: - proximity_thresh (float): Threshold for spatial proximity (IoU) between tracks and detections. - appearance_thresh (float): Threshold for appearance similarity (ReID embeddings) between tracks and detections. - encoder (object): Object to handle ReID embeddings, set to None if ReID is not enabled. - gmc (GMC): An instance of the GMC algorithm for data association. - args (object): Parsed command-line arguments containing tracking parameters. - - Methods: - get_kalmanfilter(): Returns an instance of KalmanFilterXYWH for object tracking. - init_track(dets, scores, cls, img): Initialize track with detections, scores, and classes. - get_dists(tracks, detections): Get distances between tracks and detections using IoU and (optionally) ReID. - multi_predict(tracks): Predict and track multiple objects with YOLOv8 model. - - Usage: - bot_sort = BOTSORT(args, frame_rate) - bot_sort.init_track(dets, scores, cls, img) - bot_sort.multi_predict(tracks) - - Note: - The class is designed to work with the YOLOv8 object detection model and supports ReID only if enabled via args. - """ - - def __init__(self, args, frame_rate=30): - """Initialize YOLOv8 object with ReID module and GMC algorithm.""" - super().__init__(args, frame_rate) - # ReID module - self.proximity_thresh = args.proximity_thresh - self.appearance_thresh = args.appearance_thresh - - if args.with_reid: - # Haven't supported BoT-SORT(reid) yet - self.encoder = None - self.gmc = GMC(method=args.gmc_method) - - def get_kalmanfilter(self): - """Returns an instance of KalmanFilterXYWH for object tracking.""" - return KalmanFilterXYWH() - - def init_track(self, dets, scores, cls, img=None): - """Initialize track with detections, scores, and classes.""" - if len(dets) == 0: - return [] - if self.args.with_reid and self.encoder is not None: - features_keep = self.encoder.inference(img, dets) - return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)] # detections - else: - return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] # detections - - def get_dists(self, tracks, detections): - """Get distances between tracks and detections using IoU and (optionally) ReID embeddings.""" - dists = matching.iou_distance(tracks, detections) - dists_mask = dists > self.proximity_thresh - - # TODO: mot20 - # if not self.args.mot20: - dists = matching.fuse_score(dists, detections) - - if self.args.with_reid and self.encoder is not None: - emb_dists = matching.embedding_distance(tracks, detections) / 2.0 - emb_dists[emb_dists > self.appearance_thresh] = 1.0 - emb_dists[dists_mask] = 1.0 - dists = np.minimum(dists, emb_dists) - return dists - - def multi_predict(self, tracks): - """Predict and track multiple objects with YOLOv8 model.""" - BOTrack.multi_predict(tracks) - - def reset(self): - """Reset tracker.""" - super().reset() - self.gmc.reset_params() diff --git a/ultralytics-main/ultralytics/trackers/byte_tracker.py b/ultralytics-main/ultralytics/trackers/byte_tracker.py deleted file mode 100644 index 01cbca9..0000000 --- a/ultralytics-main/ultralytics/trackers/byte_tracker.py +++ /dev/null @@ -1,444 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import numpy as np - -from .basetrack import BaseTrack, TrackState -from .utils import matching -from .utils.kalman_filter import KalmanFilterXYAH -from ..utils.ops import xywh2ltwh -from ..utils import LOGGER - - -class STrack(BaseTrack): - """ - Single object tracking representation that uses Kalman filtering for state estimation. - - This class is responsible for storing all the information regarding individual tracklets and performs state updates - and predictions based on Kalman filter. - - Attributes: - shared_kalman (KalmanFilterXYAH): Shared Kalman filter that is used across all STrack instances for prediction. - _tlwh (np.ndarray): Private attribute to store top-left corner coordinates and width and height of bounding box. - kalman_filter (KalmanFilterXYAH): Instance of Kalman filter used for this particular object track. - mean (np.ndarray): Mean state estimate vector. - covariance (np.ndarray): Covariance of state estimate. - is_activated (bool): Boolean flag indicating if the track has been activated. - score (float): Confidence score of the track. - tracklet_len (int): Length of the tracklet. - cls (any): Class label for the object. - idx (int): Index or identifier for the object. - frame_id (int): Current frame ID. - start_frame (int): Frame where the object was first detected. - - Methods: - predict(): Predict the next state of the object using Kalman filter. - multi_predict(stracks): Predict the next states for multiple tracks. - multi_gmc(stracks, H): Update multiple track states using a homography matrix. - activate(kalman_filter, frame_id): Activate a new tracklet. - re_activate(new_track, frame_id, new_id): Reactivate a previously lost tracklet. - update(new_track, frame_id): Update the state of a matched track. - convert_coords(tlwh): Convert bounding box to x-y-aspect-height format. - tlwh_to_xyah(tlwh): Convert tlwh bounding box to xyah format. - """ - - shared_kalman = KalmanFilterXYAH() - - def __init__(self, xywh, score, cls): - """Initialize new STrack instance.""" - super().__init__() - # xywh+idx or xywha+idx - assert len(xywh) in [5, 6], f"expected 5 or 6 values but got {len(xywh)}" - self._tlwh = np.asarray(xywh2ltwh(xywh[:4]), dtype=np.float32) - self.kalman_filter = None - self.mean, self.covariance = None, None - self.is_activated = False - - self.score = score - self.tracklet_len = 0 - self.cls = cls - self.idx = xywh[-1] - self.angle = xywh[4] if len(xywh) == 6 else None - - def predict(self): - """Predicts mean and covariance using Kalman filter.""" - mean_state = self.mean.copy() - if self.state != TrackState.Tracked: - mean_state[7] = 0 - self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance) - - @staticmethod - def multi_predict(stracks): - """Perform multi-object predictive tracking using Kalman filter for given stracks.""" - if len(stracks) <= 0: - return - multi_mean = np.asarray([st.mean.copy() for st in stracks]) - multi_covariance = np.asarray([st.covariance for st in stracks]) - for i, st in enumerate(stracks): - if st.state != TrackState.Tracked: - multi_mean[i][7] = 0 - multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance) - for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): - stracks[i].mean = mean - stracks[i].covariance = cov - - @staticmethod - def multi_gmc(stracks, H=np.eye(2, 3)): - """Update state tracks positions and covariances using a homography matrix.""" - if len(stracks) > 0: - multi_mean = np.asarray([st.mean.copy() for st in stracks]) - multi_covariance = np.asarray([st.covariance for st in stracks]) - - R = H[:2, :2] - R8x8 = np.kron(np.eye(4, dtype=float), R) - t = H[:2, 2] - - for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)): - mean = R8x8.dot(mean) - mean[:2] += t - cov = R8x8.dot(cov).dot(R8x8.transpose()) - - stracks[i].mean = mean - stracks[i].covariance = cov - - def activate(self, kalman_filter, frame_id): - """Start a new tracklet.""" - self.kalman_filter = kalman_filter - self.track_id = self.next_id() - self.mean, self.covariance = self.kalman_filter.initiate(self.convert_coords(self._tlwh)) - - self.tracklet_len = 0 - self.state = TrackState.Tracked - if frame_id == 1: - self.is_activated = True - self.frame_id = frame_id - self.start_frame = frame_id - - def re_activate(self, new_track, frame_id, new_id=False): - """Reactivates a previously lost track with a new detection.""" - self.mean, self.covariance = self.kalman_filter.update( - self.mean, self.covariance, self.convert_coords(new_track.tlwh) - ) - self.tracklet_len = 0 - self.state = TrackState.Tracked - self.is_activated = True - self.frame_id = frame_id - if new_id: - self.track_id = self.next_id() - self.score = new_track.score - self.cls = new_track.cls - self.angle = new_track.angle - self.idx = new_track.idx - - def update(self, new_track, frame_id): - """ - Update the state of a matched track. - - Args: - new_track (STrack): The new track containing updated information. - frame_id (int): The ID of the current frame. - """ - self.frame_id = frame_id - self.tracklet_len += 1 - - new_tlwh = new_track.tlwh - self.mean, self.covariance = self.kalman_filter.update( - self.mean, self.covariance, self.convert_coords(new_tlwh) - ) - self.state = TrackState.Tracked - self.is_activated = True - - self.score = new_track.score - self.cls = new_track.cls - self.angle = new_track.angle - self.idx = new_track.idx - - def convert_coords(self, tlwh): - """Convert a bounding box's top-left-width-height format to its x-y-aspect-height equivalent.""" - return self.tlwh_to_xyah(tlwh) - - @property - def tlwh(self): - """Get current position in bounding box format (top left x, top left y, width, height).""" - if self.mean is None: - return self._tlwh.copy() - ret = self.mean[:4].copy() - ret[2] *= ret[3] - ret[:2] -= ret[2:] / 2 - return ret - - @property - def xyxy(self): - """Convert bounding box to format (min x, min y, max x, max y), i.e., (top left, bottom right).""" - ret = self.tlwh.copy() - ret[2:] += ret[:2] - return ret - - @staticmethod - def tlwh_to_xyah(tlwh): - """Convert bounding box to format (center x, center y, aspect ratio, height), where the aspect ratio is width / - height. - """ - ret = np.asarray(tlwh).copy() - ret[:2] += ret[2:] / 2 - ret[2] /= ret[3] - return ret - - @property - def xywh(self): - """Get current position in bounding box format (center x, center y, width, height).""" - ret = np.asarray(self.tlwh).copy() - ret[:2] += ret[2:] / 2 - return ret - - @property - def xywha(self): - """Get current position in bounding box format (center x, center y, width, height, angle).""" - if self.angle is None: - LOGGER.warning("WARNING ⚠️ `angle` attr not found, returning `xywh` instead.") - return self.xywh - return np.concatenate([self.xywh, self.angle[None]]) - - @property - def result(self): - """Get current tracking results.""" - coords = self.xyxy if self.angle is None else self.xywha - return coords.tolist() + [self.track_id, self.score, self.cls, self.idx] - - def __repr__(self): - """Return a string representation of the BYTETracker object with start and end frames and track ID.""" - return f"OT_{self.track_id}_({self.start_frame}-{self.end_frame})" - - -class BYTETracker: - """ - BYTETracker: A tracking algorithm built on top of YOLOv8 for object detection and tracking. - - The class is responsible for initializing, updating, and managing the tracks for detected objects in a video - sequence. It maintains the state of tracked, lost, and removed tracks over frames, utilizes Kalman filtering for - predicting the new object locations, and performs data association. - - Attributes: - tracked_stracks (list[STrack]): List of successfully activated tracks. - lost_stracks (list[STrack]): List of lost tracks. - removed_stracks (list[STrack]): List of removed tracks. - frame_id (int): The current frame ID. - args (namespace): Command-line arguments. - max_time_lost (int): The maximum frames for a track to be considered as 'lost'. - kalman_filter (object): Kalman Filter object. - - Methods: - update(results, img=None): Updates object tracker with new detections. - get_kalmanfilter(): Returns a Kalman filter object for tracking bounding boxes. - init_track(dets, scores, cls, img=None): Initialize object tracking with detections. - get_dists(tracks, detections): Calculates the distance between tracks and detections. - multi_predict(tracks): Predicts the location of tracks. - reset_id(): Resets the ID counter of STrack. - joint_stracks(tlista, tlistb): Combines two lists of stracks. - sub_stracks(tlista, tlistb): Filters out the stracks present in the second list from the first list. - remove_duplicate_stracks(stracksa, stracksb): Removes duplicate stracks based on IoU. - """ - - def __init__(self, args, frame_rate=30): - """Initialize a YOLOv8 object to track objects with given arguments and frame rate.""" - self.tracked_stracks = [] # type: list[STrack] - self.lost_stracks = [] # type: list[STrack] - self.removed_stracks = [] # type: list[STrack] - - self.frame_id = 0 - self.args = args - self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer) - self.kalman_filter = self.get_kalmanfilter() - self.reset_id() - - def update(self, results, img=None): - """Updates object tracker with new detections and returns tracked object bounding boxes.""" - self.frame_id += 1 - activated_stracks = [] - refind_stracks = [] - lost_stracks = [] - removed_stracks = [] - - scores = results.conf - bboxes = results.xywhr if hasattr(results, "xywhr") else results.xywh - # Add index - bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1) - cls = results.cls - - remain_inds = scores > self.args.track_high_thresh - inds_low = scores > self.args.track_low_thresh - inds_high = scores < self.args.track_high_thresh - - inds_second = np.logical_and(inds_low, inds_high) - dets_second = bboxes[inds_second] - dets = bboxes[remain_inds] - scores_keep = scores[remain_inds] - scores_second = scores[inds_second] - cls_keep = cls[remain_inds] - cls_second = cls[inds_second] - - detections = self.init_track(dets, scores_keep, cls_keep, img) - # Add newly detected tracklets to tracked_stracks - unconfirmed = [] - tracked_stracks = [] # type: list[STrack] - for track in self.tracked_stracks: - if not track.is_activated: - unconfirmed.append(track) - else: - tracked_stracks.append(track) - # Step 2: First association, with high score detection boxes - strack_pool = self.joint_stracks(tracked_stracks, self.lost_stracks) - # Predict the current location with KF - self.multi_predict(strack_pool) - if hasattr(self, "gmc") and img is not None: - warp = self.gmc.apply(img, dets) - STrack.multi_gmc(strack_pool, warp) - STrack.multi_gmc(unconfirmed, warp) - - dists = self.get_dists(strack_pool, detections) - matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh) - - for itracked, idet in matches: - track = strack_pool[itracked] - det = detections[idet] - if track.state == TrackState.Tracked: - track.update(det, self.frame_id) - activated_stracks.append(track) - else: - track.re_activate(det, self.frame_id, new_id=False) - refind_stracks.append(track) - # Step 3: Second association, with low score detection boxes association the untrack to the low score detections - detections_second = self.init_track(dets_second, scores_second, cls_second, img) - r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked] - # TODO - dists = matching.iou_distance(r_tracked_stracks, detections_second) - matches, u_track, u_detection_second = matching.linear_assignment(dists, thresh=0.5) - for itracked, idet in matches: - track = r_tracked_stracks[itracked] - det = detections_second[idet] - if track.state == TrackState.Tracked: - track.update(det, self.frame_id) - activated_stracks.append(track) - else: - track.re_activate(det, self.frame_id, new_id=False) - refind_stracks.append(track) - - for it in u_track: - track = r_tracked_stracks[it] - if track.state != TrackState.Lost: - track.mark_lost() - lost_stracks.append(track) - # Deal with unconfirmed tracks, usually tracks with only one beginning frame - detections = [detections[i] for i in u_detection] - dists = self.get_dists(unconfirmed, detections) - matches, u_unconfirmed, u_detection = matching.linear_assignment(dists, thresh=0.7) - for itracked, idet in matches: - unconfirmed[itracked].update(detections[idet], self.frame_id) - activated_stracks.append(unconfirmed[itracked]) - for it in u_unconfirmed: - track = unconfirmed[it] - track.mark_removed() - removed_stracks.append(track) - # Step 4: Init new stracks - for inew in u_detection: - track = detections[inew] - if track.score < self.args.new_track_thresh: - continue - track.activate(self.kalman_filter, self.frame_id) - activated_stracks.append(track) - # Step 5: Update state - for track in self.lost_stracks: - if self.frame_id - track.end_frame > self.max_time_lost: - track.mark_removed() - removed_stracks.append(track) - - self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked] - self.tracked_stracks = self.joint_stracks(self.tracked_stracks, activated_stracks) - self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks) - self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks) - self.lost_stracks.extend(lost_stracks) - self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks) - self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks) - self.removed_stracks.extend(removed_stracks) - if len(self.removed_stracks) > 1000: - self.removed_stracks = self.removed_stracks[-999:] # clip remove stracks to 1000 maximum - - return np.asarray([x.result for x in self.tracked_stracks if x.is_activated], dtype=np.float32) - - def get_kalmanfilter(self): - """Returns a Kalman filter object for tracking bounding boxes.""" - return KalmanFilterXYAH() - - def init_track(self, dets, scores, cls, img=None): - """Initialize object tracking with detections and scores using STrack algorithm.""" - return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else [] # detections - - def get_dists(self, tracks, detections): - """Calculates the distance between tracks and detections using IoU and fuses scores.""" - dists = matching.iou_distance(tracks, detections) - # TODO: mot20 - # if not self.args.mot20: - dists = matching.fuse_score(dists, detections) - return dists - - def multi_predict(self, tracks): - """Returns the predicted tracks using the YOLOv8 network.""" - STrack.multi_predict(tracks) - - @staticmethod - def reset_id(): - """Resets the ID counter of STrack.""" - STrack.reset_id() - - def reset(self): - """Reset tracker.""" - self.tracked_stracks = [] # type: list[STrack] - self.lost_stracks = [] # type: list[STrack] - self.removed_stracks = [] # type: list[STrack] - self.frame_id = 0 - self.kalman_filter = self.get_kalmanfilter() - self.reset_id() - - @staticmethod - def joint_stracks(tlista, tlistb): - """Combine two lists of stracks into a single one.""" - exists = {} - res = [] - for t in tlista: - exists[t.track_id] = 1 - res.append(t) - for t in tlistb: - tid = t.track_id - if not exists.get(tid, 0): - exists[tid] = 1 - res.append(t) - return res - - @staticmethod - def sub_stracks(tlista, tlistb): - """DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/ - stracks = {t.track_id: t for t in tlista} - for t in tlistb: - tid = t.track_id - if stracks.get(tid, 0): - del stracks[tid] - return list(stracks.values()) - """ - track_ids_b = {t.track_id for t in tlistb} - return [t for t in tlista if t.track_id not in track_ids_b] - - @staticmethod - def remove_duplicate_stracks(stracksa, stracksb): - """Remove duplicate stracks with non-maximum IoU distance.""" - pdist = matching.iou_distance(stracksa, stracksb) - pairs = np.where(pdist < 0.15) - dupa, dupb = [], [] - for p, q in zip(*pairs): - timep = stracksa[p].frame_id - stracksa[p].start_frame - timeq = stracksb[q].frame_id - stracksb[q].start_frame - if timep > timeq: - dupb.append(q) - else: - dupa.append(p) - resa = [t for i, t in enumerate(stracksa) if i not in dupa] - resb = [t for i, t in enumerate(stracksb) if i not in dupb] - return resa, resb diff --git a/ultralytics-main/ultralytics/trackers/track.py b/ultralytics-main/ultralytics/trackers/track.py deleted file mode 100644 index 7146a40..0000000 --- a/ultralytics-main/ultralytics/trackers/track.py +++ /dev/null @@ -1,89 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from functools import partial -from pathlib import Path - -import torch - -from ultralytics.utils import IterableSimpleNamespace, yaml_load -from ultralytics.utils.checks import check_yaml -from .bot_sort import BOTSORT -from .byte_tracker import BYTETracker - -# A mapping of tracker types to corresponding tracker classes -TRACKER_MAP = {"bytetrack": BYTETracker, "botsort": BOTSORT} - - -def on_predict_start(predictor: object, persist: bool = False) -> None: - """ - Initialize trackers for object tracking during prediction. - - Args: - predictor (object): The predictor object to initialize trackers for. - persist (bool, optional): Whether to persist the trackers if they already exist. Defaults to False. - - Raises: - AssertionError: If the tracker_type is not 'bytetrack' or 'botsort'. - """ - if hasattr(predictor, "trackers") and persist: - return - - tracker = check_yaml(predictor.args.tracker) - cfg = IterableSimpleNamespace(**yaml_load(tracker)) - - if cfg.tracker_type not in ["bytetrack", "botsort"]: - raise AssertionError(f"Only 'bytetrack' and 'botsort' are supported for now, but got '{cfg.tracker_type}'") - - trackers = [] - for _ in range(predictor.dataset.bs): - tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30) - trackers.append(tracker) - if predictor.dataset.mode != "stream": # only need one tracker for other modes. - break - predictor.trackers = trackers - predictor.vid_path = [None] * predictor.dataset.bs # for determining when to reset tracker on new video - - -def on_predict_postprocess_end(predictor: object, persist: bool = False) -> None: - """ - Postprocess detected boxes and update with object tracking. - - Args: - predictor (object): The predictor object containing the predictions. - persist (bool, optional): Whether to persist the trackers if they already exist. Defaults to False. - """ - path, im0s = predictor.batch[:2] - - is_obb = predictor.args.task == "obb" - is_stream = predictor.dataset.mode == "stream" - for i in range(len(im0s)): - tracker = predictor.trackers[i if is_stream else 0] - vid_path = predictor.save_dir / Path(path[i]).name - if not persist and predictor.vid_path[i if is_stream else 0] != vid_path: - tracker.reset() - predictor.vid_path[i if is_stream else 0] = vid_path - - det = (predictor.results[i].obb if is_obb else predictor.results[i].boxes).cpu().numpy() - if len(det) == 0: - continue - tracks = tracker.update(det, im0s[i]) - if len(tracks) == 0: - continue - idx = tracks[:, -1].astype(int) - predictor.results[i] = predictor.results[i][idx] - - update_args = dict() - update_args["obb" if is_obb else "boxes"] = torch.as_tensor(tracks[:, :-1]) - predictor.results[i].update(**update_args) - - -def register_tracker(model: object, persist: bool) -> None: - """ - Register tracking callbacks to the model for object tracking during prediction. - - Args: - model (object): The model object to register tracking callbacks for. - persist (bool): Whether to persist the trackers if they already exist. - """ - model.add_callback("on_predict_start", partial(on_predict_start, persist=persist)) - model.add_callback("on_predict_postprocess_end", partial(on_predict_postprocess_end, persist=persist)) diff --git a/ultralytics-main/ultralytics/trackers/utils/__init__.py b/ultralytics-main/ultralytics/trackers/utils/__init__.py deleted file mode 100644 index 9e68dc1..0000000 --- a/ultralytics-main/ultralytics/trackers/utils/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license diff --git a/ultralytics-main/ultralytics/trackers/utils/gmc.py b/ultralytics-main/ultralytics/trackers/utils/gmc.py deleted file mode 100644 index 806f1b5..0000000 --- a/ultralytics-main/ultralytics/trackers/utils/gmc.py +++ /dev/null @@ -1,363 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import copy - -import cv2 -import numpy as np - -from ultralytics.utils import LOGGER - - -class GMC: - """ - Generalized Motion Compensation (GMC) class for tracking and object detection in video frames. - - This class provides methods for tracking and detecting objects based on several tracking algorithms including ORB, - SIFT, ECC, and Sparse Optical Flow. It also supports downscaling of frames for computational efficiency. - - Attributes: - method (str): The method used for tracking. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'. - downscale (int): Factor by which to downscale the frames for processing. - prevFrame (np.ndarray): Stores the previous frame for tracking. - prevKeyPoints (list): Stores the keypoints from the previous frame. - prevDescriptors (np.ndarray): Stores the descriptors from the previous frame. - initializedFirstFrame (bool): Flag to indicate if the first frame has been processed. - - Methods: - __init__(self, method='sparseOptFlow', downscale=2): Initializes a GMC object with the specified method - and downscale factor. - apply(self, raw_frame, detections=None): Applies the chosen method to a raw frame and optionally uses - provided detections. - applyEcc(self, raw_frame, detections=None): Applies the ECC algorithm to a raw frame. - applyFeatures(self, raw_frame, detections=None): Applies feature-based methods like ORB or SIFT to a raw frame. - applySparseOptFlow(self, raw_frame, detections=None): Applies the Sparse Optical Flow method to a raw frame. - """ - - def __init__(self, method: str = "sparseOptFlow", downscale: int = 2) -> None: - """ - Initialize a video tracker with specified parameters. - - Args: - method (str): The method used for tracking. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'. - downscale (int): Downscale factor for processing frames. - """ - super().__init__() - - self.method = method - self.downscale = max(1, int(downscale)) - - if self.method == "orb": - self.detector = cv2.FastFeatureDetector_create(20) - self.extractor = cv2.ORB_create() - self.matcher = cv2.BFMatcher(cv2.NORM_HAMMING) - - elif self.method == "sift": - self.detector = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20) - self.extractor = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20) - self.matcher = cv2.BFMatcher(cv2.NORM_L2) - - elif self.method == "ecc": - number_of_iterations = 5000 - termination_eps = 1e-6 - self.warp_mode = cv2.MOTION_EUCLIDEAN - self.criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, number_of_iterations, termination_eps) - - elif self.method == "sparseOptFlow": - self.feature_params = dict( - maxCorners=1000, qualityLevel=0.01, minDistance=1, blockSize=3, useHarrisDetector=False, k=0.04 - ) - - elif self.method in {"none", "None", None}: - self.method = None - else: - raise ValueError(f"Error: Unknown GMC method:{method}") - - self.prevFrame = None - self.prevKeyPoints = None - self.prevDescriptors = None - self.initializedFirstFrame = False - - def apply(self, raw_frame: np.array, detections: list = None) -> np.array: - """ - Apply object detection on a raw frame using specified method. - - Args: - raw_frame (np.ndarray): The raw frame to be processed. - detections (list): List of detections to be used in the processing. - - Returns: - (np.ndarray): Processed frame. - - Examples: - >>> gmc = GMC() - >>> gmc.apply(np.array([[1, 2, 3], [4, 5, 6]])) - array([[1, 2, 3], - [4, 5, 6]]) - """ - if self.method in ["orb", "sift"]: - return self.applyFeatures(raw_frame, detections) - elif self.method == "ecc": - return self.applyEcc(raw_frame) - elif self.method == "sparseOptFlow": - return self.applySparseOptFlow(raw_frame) - else: - return np.eye(2, 3) - - def applyEcc(self, raw_frame: np.array) -> np.array: - """ - Apply ECC algorithm to a raw frame. - - Args: - raw_frame (np.ndarray): The raw frame to be processed. - - Returns: - (np.ndarray): Processed frame. - - Examples: - >>> gmc = GMC() - >>> gmc.applyEcc(np.array([[1, 2, 3], [4, 5, 6]])) - array([[1, 2, 3], - [4, 5, 6]]) - """ - height, width, _ = raw_frame.shape - frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY) - H = np.eye(2, 3, dtype=np.float32) - - # Downscale image - if self.downscale > 1.0: - frame = cv2.GaussianBlur(frame, (3, 3), 1.5) - frame = cv2.resize(frame, (width // self.downscale, height // self.downscale)) - width = width // self.downscale - height = height // self.downscale - - # Handle first frame - if not self.initializedFirstFrame: - # Initialize data - self.prevFrame = frame.copy() - - # Initialization done - self.initializedFirstFrame = True - - return H - - # Run the ECC algorithm. The results are stored in warp_matrix. - # (cc, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria) - try: - (_, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria, None, 1) - except Exception as e: - LOGGER.warning(f"WARNING: find transform failed. Set warp as identity {e}") - - return H - - def applyFeatures(self, raw_frame: np.array, detections: list = None) -> np.array: - """ - Apply feature-based methods like ORB or SIFT to a raw frame. - - Args: - raw_frame (np.ndarray): The raw frame to be processed. - detections (list): List of detections to be used in the processing. - - Returns: - (np.ndarray): Processed frame. - - Examples: - >>> gmc = GMC() - >>> gmc.applyFeatures(np.array([[1, 2, 3], [4, 5, 6]])) - array([[1, 2, 3], - [4, 5, 6]]) - """ - height, width, _ = raw_frame.shape - frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY) - H = np.eye(2, 3) - - # Downscale image - if self.downscale > 1.0: - frame = cv2.resize(frame, (width // self.downscale, height // self.downscale)) - width = width // self.downscale - height = height // self.downscale - - # Find the keypoints - mask = np.zeros_like(frame) - mask[int(0.02 * height) : int(0.98 * height), int(0.02 * width) : int(0.98 * width)] = 255 - if detections is not None: - for det in detections: - tlbr = (det[:4] / self.downscale).astype(np.int_) - mask[tlbr[1] : tlbr[3], tlbr[0] : tlbr[2]] = 0 - - keypoints = self.detector.detect(frame, mask) - - # Compute the descriptors - keypoints, descriptors = self.extractor.compute(frame, keypoints) - - # Handle first frame - if not self.initializedFirstFrame: - # Initialize data - self.prevFrame = frame.copy() - self.prevKeyPoints = copy.copy(keypoints) - self.prevDescriptors = copy.copy(descriptors) - - # Initialization done - self.initializedFirstFrame = True - - return H - - # Match descriptors - knnMatches = self.matcher.knnMatch(self.prevDescriptors, descriptors, 2) - - # Filter matches based on smallest spatial distance - matches = [] - spatialDistances = [] - - maxSpatialDistance = 0.25 * np.array([width, height]) - - # Handle empty matches case - if len(knnMatches) == 0: - # Store to next iteration - self.prevFrame = frame.copy() - self.prevKeyPoints = copy.copy(keypoints) - self.prevDescriptors = copy.copy(descriptors) - - return H - - for m, n in knnMatches: - if m.distance < 0.9 * n.distance: - prevKeyPointLocation = self.prevKeyPoints[m.queryIdx].pt - currKeyPointLocation = keypoints[m.trainIdx].pt - - spatialDistance = ( - prevKeyPointLocation[0] - currKeyPointLocation[0], - prevKeyPointLocation[1] - currKeyPointLocation[1], - ) - - if (np.abs(spatialDistance[0]) < maxSpatialDistance[0]) and ( - np.abs(spatialDistance[1]) < maxSpatialDistance[1] - ): - spatialDistances.append(spatialDistance) - matches.append(m) - - meanSpatialDistances = np.mean(spatialDistances, 0) - stdSpatialDistances = np.std(spatialDistances, 0) - - inliers = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances - - goodMatches = [] - prevPoints = [] - currPoints = [] - for i in range(len(matches)): - if inliers[i, 0] and inliers[i, 1]: - goodMatches.append(matches[i]) - prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt) - currPoints.append(keypoints[matches[i].trainIdx].pt) - - prevPoints = np.array(prevPoints) - currPoints = np.array(currPoints) - - # Draw the keypoint matches on the output image - # if False: - # import matplotlib.pyplot as plt - # matches_img = np.hstack((self.prevFrame, frame)) - # matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR) - # W = self.prevFrame.shape[1] - # for m in goodMatches: - # prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_) - # curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_) - # curr_pt[0] += W - # color = np.random.randint(0, 255, 3) - # color = (int(color[0]), int(color[1]), int(color[2])) - # - # matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA) - # matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1) - # matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1) - # - # plt.figure() - # plt.imshow(matches_img) - # plt.show() - - # Find rigid matrix - if prevPoints.shape[0] > 4: - H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC) - - # Handle downscale - if self.downscale > 1.0: - H[0, 2] *= self.downscale - H[1, 2] *= self.downscale - else: - LOGGER.warning("WARNING: not enough matching points") - - # Store to next iteration - self.prevFrame = frame.copy() - self.prevKeyPoints = copy.copy(keypoints) - self.prevDescriptors = copy.copy(descriptors) - - return H - - def applySparseOptFlow(self, raw_frame: np.array) -> np.array: - """ - Apply Sparse Optical Flow method to a raw frame. - - Args: - raw_frame (np.ndarray): The raw frame to be processed. - - Returns: - (np.ndarray): Processed frame. - - Examples: - >>> gmc = GMC() - >>> gmc.applySparseOptFlow(np.array([[1, 2, 3], [4, 5, 6]])) - array([[1, 2, 3], - [4, 5, 6]]) - """ - height, width, _ = raw_frame.shape - frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY) - H = np.eye(2, 3) - - # Downscale image - if self.downscale > 1.0: - frame = cv2.resize(frame, (width // self.downscale, height // self.downscale)) - - # Find the keypoints - keypoints = cv2.goodFeaturesToTrack(frame, mask=None, **self.feature_params) - - # Handle first frame - if not self.initializedFirstFrame: - self.prevFrame = frame.copy() - self.prevKeyPoints = copy.copy(keypoints) - self.initializedFirstFrame = True - return H - - # Find correspondences - matchedKeypoints, status, _ = cv2.calcOpticalFlowPyrLK(self.prevFrame, frame, self.prevKeyPoints, None) - - # Leave good correspondences only - prevPoints = [] - currPoints = [] - - for i in range(len(status)): - if status[i]: - prevPoints.append(self.prevKeyPoints[i]) - currPoints.append(matchedKeypoints[i]) - - prevPoints = np.array(prevPoints) - currPoints = np.array(currPoints) - - # Find rigid matrix - if (prevPoints.shape[0] > 4) and (prevPoints.shape[0] == prevPoints.shape[0]): - H, _ = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC) - - if self.downscale > 1.0: - H[0, 2] *= self.downscale - H[1, 2] *= self.downscale - else: - LOGGER.warning("WARNING: not enough matching points") - - self.prevFrame = frame.copy() - self.prevKeyPoints = copy.copy(keypoints) - - return H - - def reset_params(self) -> None: - """Reset parameters.""" - self.prevFrame = None - self.prevKeyPoints = None - self.prevDescriptors = None - self.initializedFirstFrame = False diff --git a/ultralytics-main/ultralytics/trackers/utils/kalman_filter.py b/ultralytics-main/ultralytics/trackers/utils/kalman_filter.py deleted file mode 100644 index 4ae68be..0000000 --- a/ultralytics-main/ultralytics/trackers/utils/kalman_filter.py +++ /dev/null @@ -1,360 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import numpy as np -import scipy.linalg - - -class KalmanFilterXYAH: - """ - For bytetrack. A simple Kalman filter for tracking bounding boxes in image space. - - The 8-dimensional state space (x, y, a, h, vx, vy, va, vh) contains the bounding box center position (x, y), aspect - ratio a, height h, and their respective velocities. - - Object motion follows a constant velocity model. The bounding box location (x, y, a, h) is taken as direct - observation of the state space (linear observation model). - """ - - def __init__(self): - """Initialize Kalman filter model matrices with motion and observation uncertainty weights.""" - ndim, dt = 4, 1.0 - - # Create Kalman filter model matrices - self._motion_mat = np.eye(2 * ndim, 2 * ndim) - for i in range(ndim): - self._motion_mat[i, ndim + i] = dt - self._update_mat = np.eye(ndim, 2 * ndim) - - # Motion and observation uncertainty are chosen relative to the current state estimate. These weights control - # the amount of uncertainty in the model. - self._std_weight_position = 1.0 / 20 - self._std_weight_velocity = 1.0 / 160 - - def initiate(self, measurement: np.ndarray) -> tuple: - """ - Create track from unassociated measurement. - - Args: - measurement (ndarray): Bounding box coordinates (x, y, a, h) with center position (x, y), aspect ratio a, - and height h. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector (8 dimensional) and covariance matrix (8x8 dimensional) of - the new track. Unobserved velocities are initialized to 0 mean. - """ - mean_pos = measurement - mean_vel = np.zeros_like(mean_pos) - mean = np.r_[mean_pos, mean_vel] - - std = [ - 2 * self._std_weight_position * measurement[3], - 2 * self._std_weight_position * measurement[3], - 1e-2, - 2 * self._std_weight_position * measurement[3], - 10 * self._std_weight_velocity * measurement[3], - 10 * self._std_weight_velocity * measurement[3], - 1e-5, - 10 * self._std_weight_velocity * measurement[3], - ] - covariance = np.diag(np.square(std)) - return mean, covariance - - def predict(self, mean: np.ndarray, covariance: np.ndarray) -> tuple: - """ - Run Kalman filter prediction step. - - Args: - mean (ndarray): The 8 dimensional mean vector of the object state at the previous time step. - covariance (ndarray): The 8x8 dimensional covariance matrix of the object state at the previous time step. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector and covariance matrix of the predicted state. Unobserved - velocities are initialized to 0 mean. - """ - std_pos = [ - self._std_weight_position * mean[3], - self._std_weight_position * mean[3], - 1e-2, - self._std_weight_position * mean[3], - ] - std_vel = [ - self._std_weight_velocity * mean[3], - self._std_weight_velocity * mean[3], - 1e-5, - self._std_weight_velocity * mean[3], - ] - motion_cov = np.diag(np.square(np.r_[std_pos, std_vel])) - - mean = np.dot(mean, self._motion_mat.T) - covariance = np.linalg.multi_dot((self._motion_mat, covariance, self._motion_mat.T)) + motion_cov - - return mean, covariance - - def project(self, mean: np.ndarray, covariance: np.ndarray) -> tuple: - """ - Project state distribution to measurement space. - - Args: - mean (ndarray): The state's mean vector (8 dimensional array). - covariance (ndarray): The state's covariance matrix (8x8 dimensional). - - Returns: - (tuple[ndarray, ndarray]): Returns the projected mean and covariance matrix of the given state estimate. - """ - std = [ - self._std_weight_position * mean[3], - self._std_weight_position * mean[3], - 1e-1, - self._std_weight_position * mean[3], - ] - innovation_cov = np.diag(np.square(std)) - - mean = np.dot(self._update_mat, mean) - covariance = np.linalg.multi_dot((self._update_mat, covariance, self._update_mat.T)) - return mean, covariance + innovation_cov - - def multi_predict(self, mean: np.ndarray, covariance: np.ndarray) -> tuple: - """ - Run Kalman filter prediction step (Vectorized version). - - Args: - mean (ndarray): The Nx8 dimensional mean matrix of the object states at the previous time step. - covariance (ndarray): The Nx8x8 covariance matrix of the object states at the previous time step. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector and covariance matrix of the predicted state. Unobserved - velocities are initialized to 0 mean. - """ - std_pos = [ - self._std_weight_position * mean[:, 3], - self._std_weight_position * mean[:, 3], - 1e-2 * np.ones_like(mean[:, 3]), - self._std_weight_position * mean[:, 3], - ] - std_vel = [ - self._std_weight_velocity * mean[:, 3], - self._std_weight_velocity * mean[:, 3], - 1e-5 * np.ones_like(mean[:, 3]), - self._std_weight_velocity * mean[:, 3], - ] - sqr = np.square(np.r_[std_pos, std_vel]).T - - motion_cov = [np.diag(sqr[i]) for i in range(len(mean))] - motion_cov = np.asarray(motion_cov) - - mean = np.dot(mean, self._motion_mat.T) - left = np.dot(self._motion_mat, covariance).transpose((1, 0, 2)) - covariance = np.dot(left, self._motion_mat.T) + motion_cov - - return mean, covariance - - def update(self, mean: np.ndarray, covariance: np.ndarray, measurement: np.ndarray) -> tuple: - """ - Run Kalman filter correction step. - - Args: - mean (ndarray): The predicted state's mean vector (8 dimensional). - covariance (ndarray): The state's covariance matrix (8x8 dimensional). - measurement (ndarray): The 4 dimensional measurement vector (x, y, a, h), where (x, y) is the center - position, a the aspect ratio, and h the height of the bounding box. - - Returns: - (tuple[ndarray, ndarray]): Returns the measurement-corrected state distribution. - """ - projected_mean, projected_cov = self.project(mean, covariance) - - chol_factor, lower = scipy.linalg.cho_factor(projected_cov, lower=True, check_finite=False) - kalman_gain = scipy.linalg.cho_solve( - (chol_factor, lower), np.dot(covariance, self._update_mat.T).T, check_finite=False - ).T - innovation = measurement - projected_mean - - new_mean = mean + np.dot(innovation, kalman_gain.T) - new_covariance = covariance - np.linalg.multi_dot((kalman_gain, projected_cov, kalman_gain.T)) - return new_mean, new_covariance - - def gating_distance( - self, - mean: np.ndarray, - covariance: np.ndarray, - measurements: np.ndarray, - only_position: bool = False, - metric: str = "maha", - ) -> np.ndarray: - """ - Compute gating distance between state distribution and measurements. A suitable distance threshold can be - obtained from `chi2inv95`. If `only_position` is False, the chi-square distribution has 4 degrees of freedom, - otherwise 2. - - Args: - mean (ndarray): Mean vector over the state distribution (8 dimensional). - covariance (ndarray): Covariance of the state distribution (8x8 dimensional). - measurements (ndarray): An Nx4 matrix of N measurements, each in format (x, y, a, h) where (x, y) - is the bounding box center position, a the aspect ratio, and h the height. - only_position (bool, optional): If True, distance computation is done with respect to the bounding box - center position only. Defaults to False. - metric (str, optional): The metric to use for calculating the distance. Options are 'gaussian' for the - squared Euclidean distance and 'maha' for the squared Mahalanobis distance. Defaults to 'maha'. - - Returns: - (np.ndarray): Returns an array of length N, where the i-th element contains the squared distance between - (mean, covariance) and `measurements[i]`. - """ - mean, covariance = self.project(mean, covariance) - if only_position: - mean, covariance = mean[:2], covariance[:2, :2] - measurements = measurements[:, :2] - - d = measurements - mean - if metric == "gaussian": - return np.sum(d * d, axis=1) - elif metric == "maha": - cholesky_factor = np.linalg.cholesky(covariance) - z = scipy.linalg.solve_triangular(cholesky_factor, d.T, lower=True, check_finite=False, overwrite_b=True) - return np.sum(z * z, axis=0) # square maha - else: - raise ValueError("Invalid distance metric") - - -class KalmanFilterXYWH(KalmanFilterXYAH): - """ - For BoT-SORT. A simple Kalman filter for tracking bounding boxes in image space. - - The 8-dimensional state space (x, y, w, h, vx, vy, vw, vh) contains the bounding box center position (x, y), width - w, height h, and their respective velocities. - - Object motion follows a constant velocity model. The bounding box location (x, y, w, h) is taken as direct - observation of the state space (linear observation model). - """ - - def initiate(self, measurement: np.ndarray) -> tuple: - """ - Create track from unassociated measurement. - - Args: - measurement (ndarray): Bounding box coordinates (x, y, w, h) with center position (x, y), width, and height. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector (8 dimensional) and covariance matrix (8x8 dimensional) of - the new track. Unobserved velocities are initialized to 0 mean. - """ - mean_pos = measurement - mean_vel = np.zeros_like(mean_pos) - mean = np.r_[mean_pos, mean_vel] - - std = [ - 2 * self._std_weight_position * measurement[2], - 2 * self._std_weight_position * measurement[3], - 2 * self._std_weight_position * measurement[2], - 2 * self._std_weight_position * measurement[3], - 10 * self._std_weight_velocity * measurement[2], - 10 * self._std_weight_velocity * measurement[3], - 10 * self._std_weight_velocity * measurement[2], - 10 * self._std_weight_velocity * measurement[3], - ] - covariance = np.diag(np.square(std)) - return mean, covariance - - def predict(self, mean, covariance) -> tuple: - """ - Run Kalman filter prediction step. - - Args: - mean (ndarray): The 8 dimensional mean vector of the object state at the previous time step. - covariance (ndarray): The 8x8 dimensional covariance matrix of the object state at the previous time step. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector and covariance matrix of the predicted state. Unobserved - velocities are initialized to 0 mean. - """ - std_pos = [ - self._std_weight_position * mean[2], - self._std_weight_position * mean[3], - self._std_weight_position * mean[2], - self._std_weight_position * mean[3], - ] - std_vel = [ - self._std_weight_velocity * mean[2], - self._std_weight_velocity * mean[3], - self._std_weight_velocity * mean[2], - self._std_weight_velocity * mean[3], - ] - motion_cov = np.diag(np.square(np.r_[std_pos, std_vel])) - - mean = np.dot(mean, self._motion_mat.T) - covariance = np.linalg.multi_dot((self._motion_mat, covariance, self._motion_mat.T)) + motion_cov - - return mean, covariance - - def project(self, mean, covariance) -> tuple: - """ - Project state distribution to measurement space. - - Args: - mean (ndarray): The state's mean vector (8 dimensional array). - covariance (ndarray): The state's covariance matrix (8x8 dimensional). - - Returns: - (tuple[ndarray, ndarray]): Returns the projected mean and covariance matrix of the given state estimate. - """ - std = [ - self._std_weight_position * mean[2], - self._std_weight_position * mean[3], - self._std_weight_position * mean[2], - self._std_weight_position * mean[3], - ] - innovation_cov = np.diag(np.square(std)) - - mean = np.dot(self._update_mat, mean) - covariance = np.linalg.multi_dot((self._update_mat, covariance, self._update_mat.T)) - return mean, covariance + innovation_cov - - def multi_predict(self, mean, covariance) -> tuple: - """ - Run Kalman filter prediction step (Vectorized version). - - Args: - mean (ndarray): The Nx8 dimensional mean matrix of the object states at the previous time step. - covariance (ndarray): The Nx8x8 covariance matrix of the object states at the previous time step. - - Returns: - (tuple[ndarray, ndarray]): Returns the mean vector and covariance matrix of the predicted state. Unobserved - velocities are initialized to 0 mean. - """ - std_pos = [ - self._std_weight_position * mean[:, 2], - self._std_weight_position * mean[:, 3], - self._std_weight_position * mean[:, 2], - self._std_weight_position * mean[:, 3], - ] - std_vel = [ - self._std_weight_velocity * mean[:, 2], - self._std_weight_velocity * mean[:, 3], - self._std_weight_velocity * mean[:, 2], - self._std_weight_velocity * mean[:, 3], - ] - sqr = np.square(np.r_[std_pos, std_vel]).T - - motion_cov = [np.diag(sqr[i]) for i in range(len(mean))] - motion_cov = np.asarray(motion_cov) - - mean = np.dot(mean, self._motion_mat.T) - left = np.dot(self._motion_mat, covariance).transpose((1, 0, 2)) - covariance = np.dot(left, self._motion_mat.T) + motion_cov - - return mean, covariance - - def update(self, mean, covariance, measurement) -> tuple: - """ - Run Kalman filter correction step. - - Args: - mean (ndarray): The predicted state's mean vector (8 dimensional). - covariance (ndarray): The state's covariance matrix (8x8 dimensional). - measurement (ndarray): The 4 dimensional measurement vector (x, y, w, h), where (x, y) is the center - position, w the width, and h the height of the bounding box. - - Returns: - (tuple[ndarray, ndarray]): Returns the measurement-corrected state distribution. - """ - return super().update(mean, covariance, measurement) diff --git a/ultralytics-main/ultralytics/trackers/utils/matching.py b/ultralytics-main/ultralytics/trackers/utils/matching.py deleted file mode 100644 index fa72b8b..0000000 --- a/ultralytics-main/ultralytics/trackers/utils/matching.py +++ /dev/null @@ -1,138 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import numpy as np -import scipy -from scipy.spatial.distance import cdist - -from ultralytics.utils.metrics import bbox_ioa, batch_probiou - -try: - import lap # for linear_assignment - - assert lap.__version__ # verify package is not directory -except (ImportError, AssertionError, AttributeError): - from ultralytics.utils.checks import check_requirements - - check_requirements("lapx>=0.5.2") # update to lap package from https://github.com/rathaROG/lapx - import lap - - -def linear_assignment(cost_matrix: np.ndarray, thresh: float, use_lap: bool = True) -> tuple: - """ - Perform linear assignment using scipy or lap.lapjv. - - Args: - cost_matrix (np.ndarray): The matrix containing cost values for assignments. - thresh (float): Threshold for considering an assignment valid. - use_lap (bool, optional): Whether to use lap.lapjv. Defaults to True. - - Returns: - Tuple with: - - matched indices - - unmatched indices from 'a' - - unmatched indices from 'b' - """ - - if cost_matrix.size == 0: - return np.empty((0, 2), dtype=int), tuple(range(cost_matrix.shape[0])), tuple(range(cost_matrix.shape[1])) - - if use_lap: - # Use lap.lapjv - # https://github.com/gatagat/lap - _, x, y = lap.lapjv(cost_matrix, extend_cost=True, cost_limit=thresh) - matches = [[ix, mx] for ix, mx in enumerate(x) if mx >= 0] - unmatched_a = np.where(x < 0)[0] - unmatched_b = np.where(y < 0)[0] - else: - # Use scipy.optimize.linear_sum_assignment - # https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.linear_sum_assignment.html - x, y = scipy.optimize.linear_sum_assignment(cost_matrix) # row x, col y - matches = np.asarray([[x[i], y[i]] for i in range(len(x)) if cost_matrix[x[i], y[i]] <= thresh]) - if len(matches) == 0: - unmatched_a = list(np.arange(cost_matrix.shape[0])) - unmatched_b = list(np.arange(cost_matrix.shape[1])) - else: - unmatched_a = list(set(np.arange(cost_matrix.shape[0])) - set(matches[:, 0])) - unmatched_b = list(set(np.arange(cost_matrix.shape[1])) - set(matches[:, 1])) - - return matches, unmatched_a, unmatched_b - - -def iou_distance(atracks: list, btracks: list) -> np.ndarray: - """ - Compute cost based on Intersection over Union (IoU) between tracks. - - Args: - atracks (list[STrack] | list[np.ndarray]): List of tracks 'a' or bounding boxes. - btracks (list[STrack] | list[np.ndarray]): List of tracks 'b' or bounding boxes. - - Returns: - (np.ndarray): Cost matrix computed based on IoU. - """ - - if atracks and isinstance(atracks[0], np.ndarray) or btracks and isinstance(btracks[0], np.ndarray): - atlbrs = atracks - btlbrs = btracks - else: - atlbrs = [track.xywha if track.angle is not None else track.xyxy for track in atracks] - btlbrs = [track.xywha if track.angle is not None else track.xyxy for track in btracks] - - ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float32) - if len(atlbrs) and len(btlbrs): - if len(atlbrs[0]) == 5 and len(btlbrs[0]) == 5: - ious = batch_probiou( - np.ascontiguousarray(atlbrs, dtype=np.float32), - np.ascontiguousarray(btlbrs, dtype=np.float32), - ).numpy() - else: - ious = bbox_ioa( - np.ascontiguousarray(atlbrs, dtype=np.float32), - np.ascontiguousarray(btlbrs, dtype=np.float32), - iou=True, - ) - return 1 - ious # cost matrix - - -def embedding_distance(tracks: list, detections: list, metric: str = "cosine") -> np.ndarray: - """ - Compute distance between tracks and detections based on embeddings. - - Args: - tracks (list[STrack]): List of tracks. - detections (list[BaseTrack]): List of detections. - metric (str, optional): Metric for distance computation. Defaults to 'cosine'. - - Returns: - (np.ndarray): Cost matrix computed based on embeddings. - """ - - cost_matrix = np.zeros((len(tracks), len(detections)), dtype=np.float32) - if cost_matrix.size == 0: - return cost_matrix - det_features = np.asarray([track.curr_feat for track in detections], dtype=np.float32) - # for i, track in enumerate(tracks): - # cost_matrix[i, :] = np.maximum(0.0, cdist(track.smooth_feat.reshape(1,-1), det_features, metric)) - track_features = np.asarray([track.smooth_feat for track in tracks], dtype=np.float32) - cost_matrix = np.maximum(0.0, cdist(track_features, det_features, metric)) # Normalized features - return cost_matrix - - -def fuse_score(cost_matrix: np.ndarray, detections: list) -> np.ndarray: - """ - Fuses cost matrix with detection scores to produce a single similarity matrix. - - Args: - cost_matrix (np.ndarray): The matrix containing cost values for assignments. - detections (list[BaseTrack]): List of detections with scores. - - Returns: - (np.ndarray): Fused similarity matrix. - """ - - if cost_matrix.size == 0: - return cost_matrix - iou_sim = 1 - cost_matrix - det_scores = np.array([det.score for det in detections]) - det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0) - fuse_sim = iou_sim * det_scores - return 1 - fuse_sim # fuse_cost diff --git a/ultralytics-main/ultralytics/utils/__init__.py b/ultralytics-main/ultralytics/utils/__init__.py deleted file mode 100644 index befa081..0000000 --- a/ultralytics-main/ultralytics/utils/__init__.py +++ /dev/null @@ -1,1049 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import inspect -import logging.config -import os -import platform -import re -import subprocess -import sys -import threading -import time -import urllib -import uuid -from pathlib import Path -from types import SimpleNamespace -from typing import Union - -import cv2 -import matplotlib.pyplot as plt -import numpy as np -import torch -import yaml -from tqdm import tqdm as tqdm_original - -from ultralytics import __version__ - -# PyTorch Multi-GPU DDP Constants -RANK = int(os.getenv("RANK", -1)) -LOCAL_RANK = int(os.getenv("LOCAL_RANK", -1)) # https://pytorch.org/docs/stable/elastic/run.html - -# Other Constants -FILE = Path(__file__).resolve() -ROOT = FILE.parents[1] # YOLO -ASSETS = ROOT / "assets" # default images -DEFAULT_CFG_PATH = ROOT / "cfg/default.yaml" -NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiprocessing threads -AUTOINSTALL = str(os.getenv("YOLO_AUTOINSTALL", True)).lower() == "true" # global auto-install mode -VERBOSE = str(os.getenv("YOLO_VERBOSE", True)).lower() == "true" # global verbose mode -TQDM_BAR_FORMAT = "{l_bar}{bar:10}{r_bar}" if VERBOSE else None # tqdm bar format -LOGGING_NAME = "ultralytics" -MACOS, LINUX, WINDOWS = (platform.system() == x for x in ["Darwin", "Linux", "Windows"]) # environment booleans -ARM64 = platform.machine() in ("arm64", "aarch64") # ARM64 booleans -HELP_MSG = """ - Usage examples for running YOLOv8: - - 1. Install the ultralytics package: - - pip install ultralytics - - 2. Use the Python SDK: - - from ultralytics import YOLO - - # Load a model - model = YOLO('yolov8n.yaml') # build a new model from scratch - model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training) - - # Use the model - results = model.train(data="coco128.yaml", epochs=3) # train the model - results = model.val() # evaluate model performance on the validation set - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - success = model.export(format='onnx') # export the model to ONNX format - - 3. Use the command line interface (CLI): - - YOLOv8 'yolo' CLI commands use the following syntax: - - yolo TASK MODE ARGS - - Where TASK (optional) is one of [detect, segment, classify] - MODE (required) is one of [train, val, predict, export] - ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults. - See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg' - - - Train a detection model for 10 epochs with an initial learning_rate of 0.01 - yolo detect train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 - - - Predict a YouTube video using a pretrained segmentation model at image size 320: - yolo segment predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 - - - Val a pretrained detection model at batch-size 1 and image size 640: - yolo detect val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 - - - Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required) - yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128 - - - Run special commands: - yolo help - yolo checks - yolo version - yolo settings - yolo copy-cfg - yolo cfg - - Docs: https://docs.ultralytics.com - Community: https://community.ultralytics.com - GitHub: https://github.com/ultralytics/ultralytics - """ - -# Settings -torch.set_printoptions(linewidth=320, precision=4, profile="default") -np.set_printoptions(linewidth=320, formatter={"float_kind": "{:11.5g}".format}) # format short g, %precision=5 -cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader) -os.environ["NUMEXPR_MAX_THREADS"] = str(NUM_THREADS) # NumExpr max threads -os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8" # for deterministic training -os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" # suppress verbose TF compiler warnings in Colab - - -class TQDM(tqdm_original): - """ - Custom Ultralytics tqdm class with different default arguments. - - Args: - *args (list): Positional arguments passed to original tqdm. - **kwargs (any): Keyword arguments, with custom defaults applied. - """ - - def __init__(self, *args, **kwargs): - """ - Initialize custom Ultralytics tqdm class with different default arguments. - - Note these can still be overridden when calling TQDM. - """ - kwargs["disable"] = not VERBOSE or kwargs.get("disable", False) # logical 'and' with default value if passed - kwargs.setdefault("bar_format", TQDM_BAR_FORMAT) # override default value if passed - super().__init__(*args, **kwargs) - - -class SimpleClass: - """Ultralytics SimpleClass is a base class providing helpful string representation, error reporting, and attribute - access methods for easier debugging and usage. - """ - - def __str__(self): - """Return a human-readable string representation of the object.""" - attr = [] - for a in dir(self): - v = getattr(self, a) - if not callable(v) and not a.startswith("_"): - if isinstance(v, SimpleClass): - # Display only the module and class name for subclasses - s = f"{a}: {v.__module__}.{v.__class__.__name__} object" - else: - s = f"{a}: {repr(v)}" - attr.append(s) - return f"{self.__module__}.{self.__class__.__name__} object with attributes:\n\n" + "\n".join(attr) - - def __repr__(self): - """Return a machine-readable string representation of the object.""" - return self.__str__() - - def __getattr__(self, attr): - """Custom attribute access error message with helpful information.""" - name = self.__class__.__name__ - raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}") - - -class IterableSimpleNamespace(SimpleNamespace): - """Ultralytics IterableSimpleNamespace is an extension class of SimpleNamespace that adds iterable functionality and - enables usage with dict() and for loops. - """ - - def __iter__(self): - """Return an iterator of key-value pairs from the namespace's attributes.""" - return iter(vars(self).items()) - - def __str__(self): - """Return a human-readable string representation of the object.""" - return "\n".join(f"{k}={v}" for k, v in vars(self).items()) - - def __getattr__(self, attr): - """Custom attribute access error message with helpful information.""" - name = self.__class__.__name__ - raise AttributeError( - f""" - '{name}' object has no attribute '{attr}'. This may be caused by a modified or out of date ultralytics - 'default.yaml' file.\nPlease update your code with 'pip install -U ultralytics' and if necessary replace - {DEFAULT_CFG_PATH} with the latest version from - https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/default.yaml - """ - ) - - def get(self, key, default=None): - """Return the value of the specified key if it exists; otherwise, return the default value.""" - return getattr(self, key, default) - - -def plt_settings(rcparams=None, backend="Agg"): - """ - Decorator to temporarily set rc parameters and the backend for a plotting function. - - Example: - decorator: @plt_settings({"font.size": 12}) - context manager: with plt_settings({"font.size": 12}): - - Args: - rcparams (dict): Dictionary of rc parameters to set. - backend (str, optional): Name of the backend to use. Defaults to 'Agg'. - - Returns: - (Callable): Decorated function with temporarily set rc parameters and backend. This decorator can be - applied to any function that needs to have specific matplotlib rc parameters and backend for its execution. - """ - - if rcparams is None: - rcparams = {"font.size": 11} - - def decorator(func): - """Decorator to apply temporary rc parameters and backend to a function.""" - - def wrapper(*args, **kwargs): - """Sets rc parameters and backend, calls the original function, and restores the settings.""" - original_backend = plt.get_backend() - if backend.lower() != original_backend.lower(): - plt.close("all") # auto-close()ing of figures upon backend switching is deprecated since 3.8 - plt.switch_backend(backend) - - with plt.rc_context(rcparams): - result = func(*args, **kwargs) - - if backend != original_backend: - plt.close("all") - plt.switch_backend(original_backend) - return result - - return wrapper - - return decorator - - -def set_logging(name=LOGGING_NAME, verbose=True): - """Sets up logging for the given name with UTF-8 encoding support.""" - level = logging.INFO if verbose and RANK in {-1, 0} else logging.ERROR # rank in world for Multi-GPU trainings - - # Configure the console (stdout) encoding to UTF-8 - formatter = logging.Formatter("%(message)s") # Default formatter - if WINDOWS and sys.stdout.encoding != "utf-8": - try: - if hasattr(sys.stdout, "reconfigure"): - sys.stdout.reconfigure(encoding="utf-8") - elif hasattr(sys.stdout, "buffer"): - import io - - sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8") - else: - sys.stdout.encoding = "utf-8" - except Exception as e: - print(f"Creating custom formatter for non UTF-8 environments due to {e}") - - class CustomFormatter(logging.Formatter): - def format(self, record): - """Sets up logging with UTF-8 encoding and configurable verbosity.""" - return emojis(super().format(record)) - - formatter = CustomFormatter("%(message)s") # Use CustomFormatter to eliminate UTF-8 output as last recourse - - # Create and configure the StreamHandler - stream_handler = logging.StreamHandler(sys.stdout) - stream_handler.setFormatter(formatter) - stream_handler.setLevel(level) - - logger = logging.getLogger(name) - logger.setLevel(level) - logger.addHandler(stream_handler) - logger.propagate = False - return logger - - -# Set logger -LOGGER = set_logging(LOGGING_NAME, verbose=VERBOSE) # define globally (used in train.py, val.py, predict.py, etc.) -for logger in "sentry_sdk", "urllib3.connectionpool": - logging.getLogger(logger).setLevel(logging.CRITICAL + 1) - - -def emojis(string=""): - """Return platform-dependent emoji-safe version of string.""" - return string.encode().decode("ascii", "ignore") if WINDOWS else string - - -class ThreadingLocked: - """ - A decorator class for ensuring thread-safe execution of a function or method. This class can be used as a decorator - to make sure that if the decorated function is called from multiple threads, only one thread at a time will be able - to execute the function. - - Attributes: - lock (threading.Lock): A lock object used to manage access to the decorated function. - - Example: - ```python - from ultralytics.utils import ThreadingLocked - - @ThreadingLocked() - def my_function(): - # Your code here - pass - ``` - """ - - def __init__(self): - """Initializes the decorator class for thread-safe execution of a function or method.""" - self.lock = threading.Lock() - - def __call__(self, f): - """Run thread-safe execution of function or method.""" - from functools import wraps - - @wraps(f) - def decorated(*args, **kwargs): - """Applies thread-safety to the decorated function or method.""" - with self.lock: - return f(*args, **kwargs) - - return decorated - - -def yaml_save(file="data.yaml", data=None, header=""): - """ - Save YAML data to a file. - - Args: - file (str, optional): File name. Default is 'data.yaml'. - data (dict): Data to save in YAML format. - header (str, optional): YAML header to add. - - Returns: - (None): Data is saved to the specified file. - """ - if data is None: - data = {} - file = Path(file) - if not file.parent.exists(): - # Create parent directories if they don't exist - file.parent.mkdir(parents=True, exist_ok=True) - - # Convert Path objects to strings - valid_types = int, float, str, bool, list, tuple, dict, type(None) - for k, v in data.items(): - if not isinstance(v, valid_types): - data[k] = str(v) - - # Dump data to file in YAML format - with open(file, "w", errors="ignore", encoding="utf-8") as f: - if header: - f.write(header) - yaml.safe_dump(data, f, sort_keys=False, allow_unicode=True) - - -def yaml_load(file="data.yaml", append_filename=False): - """ - Load YAML data from a file. - - Args: - file (str, optional): File name. Default is 'data.yaml'. - append_filename (bool): Add the YAML filename to the YAML dictionary. Default is False. - - Returns: - (dict): YAML data and file name. - """ - assert Path(file).suffix in (".yaml", ".yml"), f"Attempting to load non-YAML file {file} with yaml_load()" - with open(file, errors="ignore", encoding="utf-8") as f: - s = f.read() # string - - # Remove special characters - if not s.isprintable(): - s = re.sub(r"[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]+", "", s) - - # Add YAML filename to dict and return - data = yaml.safe_load(s) or {} # always return a dict (yaml.safe_load() may return None for empty files) - if append_filename: - data["yaml_file"] = str(file) - return data - - -def yaml_print(yaml_file: Union[str, Path, dict]) -> None: - """ - Pretty prints a YAML file or a YAML-formatted dictionary. - - Args: - yaml_file: The file path of the YAML file or a YAML-formatted dictionary. - - Returns: - (None) - """ - yaml_dict = yaml_load(yaml_file) if isinstance(yaml_file, (str, Path)) else yaml_file - dump = yaml.dump(yaml_dict, sort_keys=False, allow_unicode=True) - LOGGER.info(f"Printing '{colorstr('bold', 'black', yaml_file)}'\n\n{dump}") - - -# Default configuration -DEFAULT_CFG_DICT = yaml_load(DEFAULT_CFG_PATH) -for k, v in DEFAULT_CFG_DICT.items(): - if isinstance(v, str) and v.lower() == "none": - DEFAULT_CFG_DICT[k] = None -DEFAULT_CFG_KEYS = DEFAULT_CFG_DICT.keys() -DEFAULT_CFG = IterableSimpleNamespace(**DEFAULT_CFG_DICT) - - -def is_ubuntu() -> bool: - """ - Check if the OS is Ubuntu. - - Returns: - (bool): True if OS is Ubuntu, False otherwise. - """ - with contextlib.suppress(FileNotFoundError): - with open("/etc/os-release") as f: - return "ID=ubuntu" in f.read() - return False - - -def is_colab(): - """ - Check if the current script is running inside a Google Colab notebook. - - Returns: - (bool): True if running inside a Colab notebook, False otherwise. - """ - return "COLAB_RELEASE_TAG" in os.environ or "COLAB_BACKEND_VERSION" in os.environ - - -def is_kaggle(): - """ - Check if the current script is running inside a Kaggle kernel. - - Returns: - (bool): True if running inside a Kaggle kernel, False otherwise. - """ - return os.environ.get("PWD") == "/kaggle/working" and os.environ.get("KAGGLE_URL_BASE") == "https://www.kaggle.com" - - -def is_jupyter(): - """ - Check if the current script is running inside a Jupyter Notebook. Verified on Colab, Jupyterlab, Kaggle, Paperspace. - - Returns: - (bool): True if running inside a Jupyter Notebook, False otherwise. - """ - with contextlib.suppress(Exception): - from IPython import get_ipython - - return get_ipython() is not None - return False - - -def is_docker() -> bool: - """ - Determine if the script is running inside a Docker container. - - Returns: - (bool): True if the script is running inside a Docker container, False otherwise. - """ - file = Path("/proc/self/cgroup") - if file.exists(): - with open(file) as f: - return "docker" in f.read() - else: - return False - - -def is_online() -> bool: - """ - Check internet connectivity by attempting to connect to a known online host. - - Returns: - (bool): True if connection is successful, False otherwise. - """ - import socket - - for host in "1.1.1.1", "8.8.8.8", "223.5.5.5": # Cloudflare, Google, AliDNS: - try: - test_connection = socket.create_connection(address=(host, 53), timeout=2) - except (socket.timeout, socket.gaierror, OSError): - continue - else: - # If the connection was successful, close it to avoid a ResourceWarning - test_connection.close() - return True - return False - - -ONLINE = is_online() - - -def is_pip_package(filepath: str = __name__) -> bool: - """ - Determines if the file at the given filepath is part of a pip package. - - Args: - filepath (str): The filepath to check. - - Returns: - (bool): True if the file is part of a pip package, False otherwise. - """ - import importlib.util - - # Get the spec for the module - spec = importlib.util.find_spec(filepath) - - # Return whether the spec is not None and the origin is not None (indicating it is a package) - return spec is not None and spec.origin is not None - - -def is_dir_writeable(dir_path: Union[str, Path]) -> bool: - """ - Check if a directory is writeable. - - Args: - dir_path (str | Path): The path to the directory. - - Returns: - (bool): True if the directory is writeable, False otherwise. - """ - return os.access(str(dir_path), os.W_OK) - - -def is_pytest_running(): - """ - Determines whether pytest is currently running or not. - - Returns: - (bool): True if pytest is running, False otherwise. - """ - return ("PYTEST_CURRENT_TEST" in os.environ) or ("pytest" in sys.modules) or ("pytest" in Path(sys.argv[0]).stem) - - -def is_github_action_running() -> bool: - """ - Determine if the current environment is a GitHub Actions runner. - - Returns: - (bool): True if the current environment is a GitHub Actions runner, False otherwise. - """ - return "GITHUB_ACTIONS" in os.environ and "GITHUB_WORKFLOW" in os.environ and "RUNNER_OS" in os.environ - - -def is_git_dir(): - """ - Determines whether the current file is part of a git repository. If the current file is not part of a git - repository, returns None. - - Returns: - (bool): True if current file is part of a git repository. - """ - return get_git_dir() is not None - - -def get_git_dir(): - """ - Determines whether the current file is part of a git repository and if so, returns the repository root directory. If - the current file is not part of a git repository, returns None. - - Returns: - (Path | None): Git root directory if found or None if not found. - """ - for d in Path(__file__).parents: - if (d / ".git").is_dir(): - return d - - -def get_git_origin_url(): - """ - Retrieves the origin URL of a git repository. - - Returns: - (str | None): The origin URL of the git repository or None if not git directory. - """ - if is_git_dir(): - with contextlib.suppress(subprocess.CalledProcessError): - origin = subprocess.check_output(["git", "config", "--get", "remote.origin.url"]) - return origin.decode().strip() - - -def get_git_branch(): - """ - Returns the current git branch name. If not in a git repository, returns None. - - Returns: - (str | None): The current git branch name or None if not a git directory. - """ - if is_git_dir(): - with contextlib.suppress(subprocess.CalledProcessError): - origin = subprocess.check_output(["git", "rev-parse", "--abbrev-ref", "HEAD"]) - return origin.decode().strip() - - -def get_default_args(func): - """ - Returns a dictionary of default arguments for a function. - - Args: - func (callable): The function to inspect. - - Returns: - (dict): A dictionary where each key is a parameter name, and each value is the default value of that parameter. - """ - signature = inspect.signature(func) - return {k: v.default for k, v in signature.parameters.items() if v.default is not inspect.Parameter.empty} - - -def get_ubuntu_version(): - """ - Retrieve the Ubuntu version if the OS is Ubuntu. - - Returns: - (str): Ubuntu version or None if not an Ubuntu OS. - """ - if is_ubuntu(): - with contextlib.suppress(FileNotFoundError, AttributeError): - with open("/etc/os-release") as f: - return re.search(r'VERSION_ID="(\d+\.\d+)"', f.read())[1] - - -def get_user_config_dir(sub_dir="Ultralytics"): - """ - Return the appropriate config directory based on the environment operating system. - - Args: - sub_dir (str): The name of the subdirectory to create. - - Returns: - (Path): The path to the user config directory. - """ - if WINDOWS: - path = Path.home() / "AppData" / "Roaming" / sub_dir - elif MACOS: # macOS - path = Path.home() / "Library" / "Application Support" / sub_dir - elif LINUX: - path = Path.home() / ".config" / sub_dir - else: - raise ValueError(f"Unsupported operating system: {platform.system()}") - - # GCP and AWS lambda fix, only /tmp is writeable - if not is_dir_writeable(path.parent): - LOGGER.warning( - f"WARNING ⚠️ user config directory '{path}' is not writeable, defaulting to '/tmp' or CWD." - "Alternatively you can define a YOLO_CONFIG_DIR environment variable for this path." - ) - path = Path("/tmp") / sub_dir if is_dir_writeable("/tmp") else Path().cwd() / sub_dir - - # Create the subdirectory if it does not exist - path.mkdir(parents=True, exist_ok=True) - - return path - - -USER_CONFIG_DIR = Path(os.getenv("YOLO_CONFIG_DIR") or get_user_config_dir()) # Ultralytics settings dir -SETTINGS_YAML = USER_CONFIG_DIR / "settings.yaml" - - -def colorstr(*input): - """ - Colors a string based on the provided color and style arguments. Utilizes ANSI escape codes. - See https://en.wikipedia.org/wiki/ANSI_escape_code for more details. - - This function can be called in two ways: - - colorstr('color', 'style', 'your string') - - colorstr('your string') - - In the second form, 'blue' and 'bold' will be applied by default. - - Args: - *input (str): A sequence of strings where the first n-1 strings are color and style arguments, - and the last string is the one to be colored. - - Supported Colors and Styles: - Basic Colors: 'black', 'red', 'green', 'yellow', 'blue', 'magenta', 'cyan', 'white' - Bright Colors: 'bright_black', 'bright_red', 'bright_green', 'bright_yellow', - 'bright_blue', 'bright_magenta', 'bright_cyan', 'bright_white' - Misc: 'end', 'bold', 'underline' - - Returns: - (str): The input string wrapped with ANSI escape codes for the specified color and style. - - Examples: - >>> colorstr('blue', 'bold', 'hello world') - >>> '\033[34m\033[1mhello world\033[0m' - """ - *args, string = input if len(input) > 1 else ("blue", "bold", input[0]) # color arguments, string - colors = { - "black": "\033[30m", # basic colors - "red": "\033[31m", - "green": "\033[32m", - "yellow": "\033[33m", - "blue": "\033[34m", - "magenta": "\033[35m", - "cyan": "\033[36m", - "white": "\033[37m", - "bright_black": "\033[90m", # bright colors - "bright_red": "\033[91m", - "bright_green": "\033[92m", - "bright_yellow": "\033[93m", - "bright_blue": "\033[94m", - "bright_magenta": "\033[95m", - "bright_cyan": "\033[96m", - "bright_white": "\033[97m", - "end": "\033[0m", # misc - "bold": "\033[1m", - "underline": "\033[4m", - } - return "".join(colors[x] for x in args) + f"{string}" + colors["end"] - - -def remove_colorstr(input_string): - """ - Removes ANSI escape codes from a string, effectively un-coloring it. - - Args: - input_string (str): The string to remove color and style from. - - Returns: - (str): A new string with all ANSI escape codes removed. - - Examples: - >>> remove_colorstr(colorstr('blue', 'bold', 'hello world')) - >>> 'hello world' - """ - ansi_escape = re.compile(r"\x1B\[[0-9;]*[A-Za-z]") - return ansi_escape.sub("", input_string) - - -class TryExcept(contextlib.ContextDecorator): - """ - Ultralytics TryExcept class. Use as @TryExcept() decorator or 'with TryExcept():' context manager. - - Examples: - As a decorator: - >>> @TryExcept(msg="Error occurred in func", verbose=True) - >>> def func(): - >>> # Function logic here - >>> pass - - As a context manager: - >>> with TryExcept(msg="Error occurred in block", verbose=True): - >>> # Code block here - >>> pass - """ - - def __init__(self, msg="", verbose=True): - """Initialize TryExcept class with optional message and verbosity settings.""" - self.msg = msg - self.verbose = verbose - - def __enter__(self): - """Executes when entering TryExcept context, initializes instance.""" - pass - - def __exit__(self, exc_type, value, traceback): - """Defines behavior when exiting a 'with' block, prints error message if necessary.""" - if self.verbose and value: - print(emojis(f"{self.msg}{': ' if self.msg else ''}{value}")) - return True - - -class Retry(contextlib.ContextDecorator): - """ - Retry class for function execution with exponential backoff. - - Can be used as a decorator or a context manager to retry a function or block of code on exceptions, up to a - specified number of times with an exponentially increasing delay between retries. - - Examples: - Example usage as a decorator: - >>> @Retry(times=3, delay=2) - >>> def test_func(): - >>> # Replace with function logic that may raise exceptions - >>> return True - - Example usage as a context manager: - >>> with Retry(times=3, delay=2): - >>> # Replace with code block that may raise exceptions - >>> pass - """ - - def __init__(self, times=3, delay=2): - """Initialize Retry class with specified number of retries and delay.""" - self.times = times - self.delay = delay - self._attempts = 0 - - def __call__(self, func): - """Decorator implementation for Retry with exponential backoff.""" - - def wrapped_func(*args, **kwargs): - """Applies retries to the decorated function or method.""" - self._attempts = 0 - while self._attempts < self.times: - try: - return func(*args, **kwargs) - except Exception as e: - self._attempts += 1 - print(f"Retry {self._attempts}/{self.times} failed: {e}") - if self._attempts >= self.times: - raise e - time.sleep(self.delay * (2**self._attempts)) # exponential backoff delay - - return wrapped_func - - def __enter__(self): - """Enter the runtime context related to this object.""" - self._attempts = 0 - - def __exit__(self, exc_type, exc_value, traceback): - """Exit the runtime context related to this object with exponential backoff.""" - if exc_type is not None: - self._attempts += 1 - if self._attempts < self.times: - print(f"Retry {self._attempts}/{self.times} failed: {exc_value}") - time.sleep(self.delay * (2**self._attempts)) # exponential backoff delay - return True # Suppresses the exception and retries - return False # Re-raises the exception if retries are exhausted - - -def threaded(func): - """ - Multi-threads a target function by default and returns the thread or function result. - - Use as @threaded decorator. The function runs in a separate thread unless 'threaded=False' is passed. - """ - - def wrapper(*args, **kwargs): - """Multi-threads a given function based on 'threaded' kwarg and returns the thread or function result.""" - if kwargs.pop("threaded", True): # run in thread - thread = threading.Thread(target=func, args=args, kwargs=kwargs, daemon=True) - thread.start() - return thread - else: - return func(*args, **kwargs) - - return wrapper - - -def set_sentry(): - """ - Initialize the Sentry SDK for error tracking and reporting. Only used if sentry_sdk package is installed and - sync=True in settings. Run 'yolo settings' to see and update settings YAML file. - - Conditions required to send errors (ALL conditions must be met or no errors will be reported): - - sentry_sdk package is installed - - sync=True in YOLO settings - - pytest is not running - - running in a pip package installation - - running in a non-git directory - - running with rank -1 or 0 - - online environment - - CLI used to run package (checked with 'yolo' as the name of the main CLI command) - - The function also configures Sentry SDK to ignore KeyboardInterrupt and FileNotFoundError - exceptions and to exclude events with 'out of memory' in their exception message. - - Additionally, the function sets custom tags and user information for Sentry events. - """ - - def before_send(event, hint): - """ - Modify the event before sending it to Sentry based on specific exception types and messages. - - Args: - event (dict): The event dictionary containing information about the error. - hint (dict): A dictionary containing additional information about the error. - - Returns: - dict: The modified event or None if the event should not be sent to Sentry. - """ - if "exc_info" in hint: - exc_type, exc_value, tb = hint["exc_info"] - if exc_type in (KeyboardInterrupt, FileNotFoundError) or "out of memory" in str(exc_value): - return None # do not send event - - event["tags"] = { - "sys_argv": sys.argv[0], - "sys_argv_name": Path(sys.argv[0]).name, - "install": "git" if is_git_dir() else "pip" if is_pip_package() else "other", - "os": ENVIRONMENT, - } - return event - - if ( - SETTINGS["sync"] - and RANK in (-1, 0) - and Path(sys.argv[0]).name == "yolo" - and not TESTS_RUNNING - and ONLINE - and is_pip_package() - and not is_git_dir() - ): - # If sentry_sdk package is not installed then return and do not use Sentry - try: - import sentry_sdk # noqa - except ImportError: - return - - sentry_sdk.init( - dsn="https://5ff1556b71594bfea135ff0203a0d290@o4504521589325824.ingest.sentry.io/4504521592406016", - debug=False, - traces_sample_rate=1.0, - release=__version__, - environment="production", # 'dev' or 'production' - before_send=before_send, - ignore_errors=[KeyboardInterrupt, FileNotFoundError], - ) - sentry_sdk.set_user({"id": SETTINGS["uuid"]}) # SHA-256 anonymized UUID hash - - -class SettingsManager(dict): - """ - Manages Ultralytics settings stored in a YAML file. - - Args: - file (str | Path): Path to the Ultralytics settings YAML file. Default is USER_CONFIG_DIR / 'settings.yaml'. - version (str): Settings version. In case of local version mismatch, new default settings will be saved. - """ - - def __init__(self, file=SETTINGS_YAML, version="0.0.4"): - """Initialize the SettingsManager with default settings, load and validate current settings from the YAML - file. - """ - import copy - import hashlib - - from ultralytics.utils.checks import check_version - from ultralytics.utils.torch_utils import torch_distributed_zero_first - - git_dir = get_git_dir() - root = git_dir or Path() - datasets_root = (root.parent if git_dir and is_dir_writeable(root.parent) else root).resolve() - - self.file = Path(file) - self.version = version - self.defaults = { - "settings_version": version, - "datasets_dir": str(datasets_root / "datasets"), - "weights_dir": str(root / "weights"), - "runs_dir": str(root / "runs"), - "uuid": hashlib.sha256(str(uuid.getnode()).encode()).hexdigest(), - "sync": True, - "api_key": "", - "openai_api_key": "", - "clearml": True, # integrations - "comet": True, - "dvc": True, - "hub": True, - "mlflow": True, - "neptune": True, - "raytune": True, - "tensorboard": True, - "wandb": True, - } - - super().__init__(copy.deepcopy(self.defaults)) - - with torch_distributed_zero_first(RANK): - if not self.file.exists(): - self.save() - - self.load() - correct_keys = self.keys() == self.defaults.keys() - correct_types = all(type(a) is type(b) for a, b in zip(self.values(), self.defaults.values())) - correct_version = check_version(self["settings_version"], self.version) - help_msg = ( - f"\nView settings with 'yolo settings' or at '{self.file}'" - "\nUpdate settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. " - "For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings." - ) - if not (correct_keys and correct_types and correct_version): - LOGGER.warning( - "WARNING ⚠️ Ultralytics settings reset to default values. This may be due to a possible problem " - f"with your settings or a recent ultralytics package update. {help_msg}" - ) - self.reset() - - if self.get("datasets_dir") == self.get("runs_dir"): - LOGGER.warning( - f"WARNING ⚠️ Ultralytics setting 'datasets_dir: {self.get('datasets_dir')}' " - f"must be different than 'runs_dir: {self.get('runs_dir')}'. " - f"Please change one to avoid possible issues during training. {help_msg}" - ) - - def load(self): - """Loads settings from the YAML file.""" - super().update(yaml_load(self.file)) - - def save(self): - """Saves the current settings to the YAML file.""" - yaml_save(self.file, dict(self)) - - def update(self, *args, **kwargs): - """Updates a setting value in the current settings.""" - super().update(*args, **kwargs) - self.save() - - def reset(self): - """Resets the settings to default and saves them.""" - self.clear() - self.update(self.defaults) - self.save() - - -def deprecation_warn(arg, new_arg, version=None): - """Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument.""" - if not version: - version = float(__version__[:3]) + 0.2 # deprecate after 2nd major release - LOGGER.warning( - f"WARNING ⚠️ '{arg}' is deprecated and will be removed in 'ultralytics {version}' in the future. " - f"Please use '{new_arg}' instead." - ) - - -def clean_url(url): - """Strip auth from URL, i.e. https://url.com/file.txt?auth -> https://url.com/file.txt.""" - url = Path(url).as_posix().replace(":/", "://") # Pathlib turns :// -> :/, as_posix() for Windows - return urllib.parse.unquote(url).split("?")[0] # '%2F' to '/', split https://url.com/file.txt?auth - - -def url2file(url): - """Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt.""" - return Path(clean_url(url)).name - - -# Run below code on utils init ------------------------------------------------------------------------------------ - -# Check first-install steps -PREFIX = colorstr("Ultralytics: ") -SETTINGS = SettingsManager() # initialize settings -DATASETS_DIR = Path(SETTINGS["datasets_dir"]) # global datasets directory -WEIGHTS_DIR = Path(SETTINGS["weights_dir"]) # global weights directory -RUNS_DIR = Path(SETTINGS["runs_dir"]) # global runs directory -ENVIRONMENT = ( - "Colab" - if is_colab() - else "Kaggle" - if is_kaggle() - else "Jupyter" - if is_jupyter() - else "Docker" - if is_docker() - else platform.system() -) -TESTS_RUNNING = is_pytest_running() or is_github_action_running() -set_sentry() - -# Apply monkey patches -from .patches import imread, imshow, imwrite, torch_save - -torch.save = torch_save -if WINDOWS: - # Apply cv2 patches for non-ASCII and non-UTF characters in image paths - cv2.imread, cv2.imwrite, cv2.imshow = imread, imwrite, imshow diff --git a/ultralytics-main/ultralytics/utils/autobatch.py b/ultralytics-main/ultralytics/utils/autobatch.py deleted file mode 100644 index daea14e..0000000 --- a/ultralytics-main/ultralytics/utils/autobatch.py +++ /dev/null @@ -1,88 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Functions for estimating the best YOLO batch size to use a fraction of the available CUDA memory in PyTorch.""" - -from copy import deepcopy - -import numpy as np -import torch - -from ultralytics.utils import DEFAULT_CFG, LOGGER, colorstr -from ultralytics.utils.torch_utils import profile - - -def check_train_batch_size(model, imgsz=640, amp=True): - """ - Check YOLO training batch size using the autobatch() function. - - Args: - model (torch.nn.Module): YOLO model to check batch size for. - imgsz (int): Image size used for training. - amp (bool): If True, use automatic mixed precision (AMP) for training. - - Returns: - (int): Optimal batch size computed using the autobatch() function. - """ - - with torch.cuda.amp.autocast(amp): - return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size - - -def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch): - """ - Automatically estimate the best YOLO batch size to use a fraction of the available CUDA memory. - - Args: - model (torch.nn.module): YOLO model to compute batch size for. - imgsz (int, optional): The image size used as input for the YOLO model. Defaults to 640. - fraction (float, optional): The fraction of available CUDA memory to use. Defaults to 0.60. - batch_size (int, optional): The default batch size to use if an error is detected. Defaults to 16. - - Returns: - (int): The optimal batch size. - """ - - # Check device - prefix = colorstr("AutoBatch: ") - LOGGER.info(f"{prefix}Computing optimal batch size for imgsz={imgsz}") - device = next(model.parameters()).device # get model device - if device.type == "cpu": - LOGGER.info(f"{prefix}CUDA not detected, using default CPU batch-size {batch_size}") - return batch_size - if torch.backends.cudnn.benchmark: - LOGGER.info(f"{prefix} ⚠️ Requires torch.backends.cudnn.benchmark=False, using default batch-size {batch_size}") - return batch_size - - # Inspect CUDA memory - gb = 1 << 30 # bytes to GiB (1024 ** 3) - d = str(device).upper() # 'CUDA:0' - properties = torch.cuda.get_device_properties(device) # device properties - t = properties.total_memory / gb # GiB total - r = torch.cuda.memory_reserved(device) / gb # GiB reserved - a = torch.cuda.memory_allocated(device) / gb # GiB allocated - f = t - (r + a) # GiB free - LOGGER.info(f"{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free") - - # Profile batch sizes - batch_sizes = [1, 2, 4, 8, 16] - try: - img = [torch.empty(b, 3, imgsz, imgsz) for b in batch_sizes] - results = profile(img, model, n=3, device=device) - - # Fit a solution - y = [x[2] for x in results if x] # memory [2] - p = np.polyfit(batch_sizes[: len(y)], y, deg=1) # first degree polynomial fit - b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) - if None in results: # some sizes failed - i = results.index(None) # first fail index - if b >= batch_sizes[i]: # y intercept above failure point - b = batch_sizes[max(i - 1, 0)] # select prior safe point - if b < 1 or b > 1024: # b outside of safe range - b = batch_size - LOGGER.info(f"{prefix}WARNING ⚠️ CUDA anomaly detected, using default batch-size {batch_size}.") - - fraction = (np.polyval(p, b) + r + a) / t # actual fraction predicted - LOGGER.info(f"{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅") - return b - except Exception as e: - LOGGER.warning(f"{prefix}WARNING ⚠️ error detected: {e}, using default batch-size {batch_size}.") - return batch_size diff --git a/ultralytics-main/ultralytics/utils/benchmarks.py b/ultralytics-main/ultralytics/utils/benchmarks.py deleted file mode 100644 index 3bc6351..0000000 --- a/ultralytics-main/ultralytics/utils/benchmarks.py +++ /dev/null @@ -1,402 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -Benchmark a YOLO model formats for speed and accuracy. - -Usage: - from ultralytics.utils.benchmarks import ProfileModels, benchmark - ProfileModels(['yolov8n.yaml', 'yolov8s.yaml']).profile() - benchmark(model='yolov8n.pt', imgsz=160) - -Format | `format=argument` | Model ---- | --- | --- -PyTorch | - | yolov8n.pt -TorchScript | `torchscript` | yolov8n.torchscript -ONNX | `onnx` | yolov8n.onnx -OpenVINO | `openvino` | yolov8n_openvino_model/ -TensorRT | `engine` | yolov8n.engine -CoreML | `coreml` | yolov8n.mlpackage -TensorFlow SavedModel | `saved_model` | yolov8n_saved_model/ -TensorFlow GraphDef | `pb` | yolov8n.pb -TensorFlow Lite | `tflite` | yolov8n.tflite -TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite -TensorFlow.js | `tfjs` | yolov8n_web_model/ -PaddlePaddle | `paddle` | yolov8n_paddle_model/ -NCNN | `ncnn` | yolov8n_ncnn_model/ -""" - -import glob -import platform -import time -from pathlib import Path - -import numpy as np -import torch.cuda - -from ultralytics import YOLO, YOLOWorld -from ultralytics.cfg import TASK2DATA, TASK2METRIC -from ultralytics.engine.exporter import export_formats -from ultralytics.utils import ASSETS, LINUX, LOGGER, MACOS, TQDM, WEIGHTS_DIR -from ultralytics.utils.checks import IS_PYTHON_3_12, check_requirements, check_yolo -from ultralytics.utils.files import file_size -from ultralytics.utils.torch_utils import select_device - - -def benchmark( - model=WEIGHTS_DIR / "yolov8n.pt", data=None, imgsz=160, half=False, int8=False, device="cpu", verbose=False -): - """ - Benchmark a YOLO model across different formats for speed and accuracy. - - Args: - model (str | Path | optional): Path to the model file or directory. Default is - Path(SETTINGS['weights_dir']) / 'yolov8n.pt'. - data (str, optional): Dataset to evaluate on, inherited from TASK2DATA if not passed. Default is None. - imgsz (int, optional): Image size for the benchmark. Default is 160. - half (bool, optional): Use half-precision for the model if True. Default is False. - int8 (bool, optional): Use int8-precision for the model if True. Default is False. - device (str, optional): Device to run the benchmark on, either 'cpu' or 'cuda'. Default is 'cpu'. - verbose (bool | float | optional): If True or a float, assert benchmarks pass with given metric. - Default is False. - - Returns: - df (pandas.DataFrame): A pandas DataFrame with benchmark results for each format, including file size, - metric, and inference time. - - Example: - ```python - from ultralytics.utils.benchmarks import benchmark - - benchmark(model='yolov8n.pt', imgsz=640) - ``` - """ - - import pandas as pd - - pd.options.display.max_columns = 10 - pd.options.display.width = 120 - device = select_device(device, verbose=False) - if isinstance(model, (str, Path)): - model = YOLO(model) - - y = [] - t0 = time.time() - for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU) - emoji, filename = "❌", None # export defaults - try: - # Checks - if i == 9: # Edge TPU - assert LINUX, "Edge TPU export only supported on Linux" - elif i == 7: # TF GraphDef - assert model.task != "obb", "TensorFlow GraphDef not supported for OBB task" - elif i in {5, 10}: # CoreML and TF.js - assert MACOS or LINUX, "export only supported on macOS and Linux" - if i in {3, 5}: # CoreML and OpenVINO - assert not IS_PYTHON_3_12, "CoreML and OpenVINO not supported on Python 3.12" - if i in {6, 7, 8, 9, 10}: # All TF formats - assert not isinstance(model, YOLOWorld), "YOLOWorldv2 TensorFlow exports not supported by onnx2tf yet" - if i in {11}: # Paddle - assert not isinstance(model, YOLOWorld), "YOLOWorldv2 Paddle exports not supported yet" - if i in {12}: # NCNN - assert not isinstance(model, YOLOWorld), "YOLOWorldv2 NCNN exports not supported yet" - if "cpu" in device.type: - assert cpu, "inference not supported on CPU" - if "cuda" in device.type: - assert gpu, "inference not supported on GPU" - - # Export - if format == "-": - filename = model.ckpt_path or model.cfg - exported_model = model # PyTorch format - else: - filename = model.export(imgsz=imgsz, format=format, half=half, int8=int8, device=device, verbose=False) - exported_model = YOLO(filename, task=model.task) - assert suffix in str(filename), "export failed" - emoji = "❎" # indicates export succeeded - - # Predict - assert model.task != "pose" or i != 7, "GraphDef Pose inference is not supported" - assert i not in (9, 10), "inference not supported" # Edge TPU and TF.js are unsupported - assert i != 5 or platform.system() == "Darwin", "inference only supported on macOS>=10.13" # CoreML - exported_model.predict(ASSETS / "bus.jpg", imgsz=imgsz, device=device, half=half) - - # Validate - data = data or TASK2DATA[model.task] # task to dataset, i.e. coco8.yaml for task=detect - key = TASK2METRIC[model.task] # task to metric, i.e. metrics/mAP50-95(B) for task=detect - results = exported_model.val( - data=data, batch=1, imgsz=imgsz, plots=False, device=device, half=half, int8=int8, verbose=False - ) - metric, speed = results.results_dict[key], results.speed["inference"] - y.append([name, "✅", round(file_size(filename), 1), round(metric, 4), round(speed, 2)]) - except Exception as e: - if verbose: - assert type(e) is AssertionError, f"Benchmark failure for {name}: {e}" - LOGGER.warning(f"ERROR ❌️ Benchmark failure for {name}: {e}") - y.append([name, emoji, round(file_size(filename), 1), None, None]) # mAP, t_inference - - # Print results - check_yolo(device=device) # print system info - df = pd.DataFrame(y, columns=["Format", "Status❔", "Size (MB)", key, "Inference time (ms/im)"]) - - name = Path(model.ckpt_path).name - s = f"\nBenchmarks complete for {name} on {data} at imgsz={imgsz} ({time.time() - t0:.2f}s)\n{df}\n" - LOGGER.info(s) - with open("benchmarks.log", "a", errors="ignore", encoding="utf-8") as f: - f.write(s) - - if verbose and isinstance(verbose, float): - metrics = df[key].array # values to compare to floor - floor = verbose # minimum metric floor to pass, i.e. = 0.29 mAP for YOLOv5n - assert all(x > floor for x in metrics if pd.notna(x)), f"Benchmark failure: metric(s) < floor {floor}" - - return df - - -class ProfileModels: - """ - ProfileModels class for profiling different models on ONNX and TensorRT. - - This class profiles the performance of different models, returning results such as model speed and FLOPs. - - Attributes: - paths (list): Paths of the models to profile. - num_timed_runs (int): Number of timed runs for the profiling. Default is 100. - num_warmup_runs (int): Number of warmup runs before profiling. Default is 10. - min_time (float): Minimum number of seconds to profile for. Default is 60. - imgsz (int): Image size used in the models. Default is 640. - - Methods: - profile(): Profiles the models and prints the result. - - Example: - ```python - from ultralytics.utils.benchmarks import ProfileModels - - ProfileModels(['yolov8n.yaml', 'yolov8s.yaml'], imgsz=640).profile() - ``` - """ - - def __init__( - self, - paths: list, - num_timed_runs=100, - num_warmup_runs=10, - min_time=60, - imgsz=640, - half=True, - trt=True, - device=None, - ): - """ - Initialize the ProfileModels class for profiling models. - - Args: - paths (list): List of paths of the models to be profiled. - num_timed_runs (int, optional): Number of timed runs for the profiling. Default is 100. - num_warmup_runs (int, optional): Number of warmup runs before the actual profiling starts. Default is 10. - min_time (float, optional): Minimum time in seconds for profiling a model. Default is 60. - imgsz (int, optional): Size of the image used during profiling. Default is 640. - half (bool, optional): Flag to indicate whether to use half-precision floating point for profiling. - trt (bool, optional): Flag to indicate whether to profile using TensorRT. Default is True. - device (torch.device, optional): Device used for profiling. If None, it is determined automatically. - """ - self.paths = paths - self.num_timed_runs = num_timed_runs - self.num_warmup_runs = num_warmup_runs - self.min_time = min_time - self.imgsz = imgsz - self.half = half - self.trt = trt # run TensorRT profiling - self.device = device or torch.device(0 if torch.cuda.is_available() else "cpu") - - def profile(self): - """Logs the benchmarking results of a model, checks metrics against floor and returns the results.""" - files = self.get_files() - - if not files: - print("No matching *.pt or *.onnx files found.") - return - - table_rows = [] - output = [] - for file in files: - engine_file = file.with_suffix(".engine") - if file.suffix in (".pt", ".yaml", ".yml"): - model = YOLO(str(file)) - model.fuse() # to report correct params and GFLOPs in model.info() - model_info = model.info() - if self.trt and self.device.type != "cpu" and not engine_file.is_file(): - engine_file = model.export( - format="engine", half=self.half, imgsz=self.imgsz, device=self.device, verbose=False - ) - onnx_file = model.export( - format="onnx", half=self.half, imgsz=self.imgsz, simplify=True, device=self.device, verbose=False - ) - elif file.suffix == ".onnx": - model_info = self.get_onnx_model_info(file) - onnx_file = file - else: - continue - - t_engine = self.profile_tensorrt_model(str(engine_file)) - t_onnx = self.profile_onnx_model(str(onnx_file)) - table_rows.append(self.generate_table_row(file.stem, t_onnx, t_engine, model_info)) - output.append(self.generate_results_dict(file.stem, t_onnx, t_engine, model_info)) - - self.print_table(table_rows) - return output - - def get_files(self): - """Returns a list of paths for all relevant model files given by the user.""" - files = [] - for path in self.paths: - path = Path(path) - if path.is_dir(): - extensions = ["*.pt", "*.onnx", "*.yaml"] - files.extend([file for ext in extensions for file in glob.glob(str(path / ext))]) - elif path.suffix in {".pt", ".yaml", ".yml"}: # add non-existing - files.append(str(path)) - else: - files.extend(glob.glob(str(path))) - - print(f"Profiling: {sorted(files)}") - return [Path(file) for file in sorted(files)] - - def get_onnx_model_info(self, onnx_file: str): - """Retrieves the information including number of layers, parameters, gradients and FLOPs for an ONNX model - file. - """ - return 0.0, 0.0, 0.0, 0.0 # return (num_layers, num_params, num_gradients, num_flops) - - @staticmethod - def iterative_sigma_clipping(data, sigma=2, max_iters=3): - """Applies an iterative sigma clipping algorithm to the given data times number of iterations.""" - data = np.array(data) - for _ in range(max_iters): - mean, std = np.mean(data), np.std(data) - clipped_data = data[(data > mean - sigma * std) & (data < mean + sigma * std)] - if len(clipped_data) == len(data): - break - data = clipped_data - return data - - def profile_tensorrt_model(self, engine_file: str, eps: float = 1e-3): - """Profiles the TensorRT model, measuring average run time and standard deviation among runs.""" - if not self.trt or not Path(engine_file).is_file(): - return 0.0, 0.0 - - # Model and input - model = YOLO(engine_file) - input_data = np.random.rand(self.imgsz, self.imgsz, 3).astype(np.float32) # must be FP32 - - # Warmup runs - elapsed = 0.0 - for _ in range(3): - start_time = time.time() - for _ in range(self.num_warmup_runs): - model(input_data, imgsz=self.imgsz, verbose=False) - elapsed = time.time() - start_time - - # Compute number of runs as higher of min_time or num_timed_runs - num_runs = max(round(self.min_time / (elapsed + eps) * self.num_warmup_runs), self.num_timed_runs * 50) - - # Timed runs - run_times = [] - for _ in TQDM(range(num_runs), desc=engine_file): - results = model(input_data, imgsz=self.imgsz, verbose=False) - run_times.append(results[0].speed["inference"]) # Convert to milliseconds - - run_times = self.iterative_sigma_clipping(np.array(run_times), sigma=2, max_iters=3) # sigma clipping - return np.mean(run_times), np.std(run_times) - - def profile_onnx_model(self, onnx_file: str, eps: float = 1e-3): - """Profiles an ONNX model by executing it multiple times and returns the mean and standard deviation of run - times. - """ - check_requirements("onnxruntime") - import onnxruntime as ort - - # Session with either 'TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider' - sess_options = ort.SessionOptions() - sess_options.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL - sess_options.intra_op_num_threads = 8 # Limit the number of threads - sess = ort.InferenceSession(onnx_file, sess_options, providers=["CPUExecutionProvider"]) - - input_tensor = sess.get_inputs()[0] - input_type = input_tensor.type - - # Mapping ONNX datatype to numpy datatype - if "float16" in input_type: - input_dtype = np.float16 - elif "float" in input_type: - input_dtype = np.float32 - elif "double" in input_type: - input_dtype = np.float64 - elif "int64" in input_type: - input_dtype = np.int64 - elif "int32" in input_type: - input_dtype = np.int32 - else: - raise ValueError(f"Unsupported ONNX datatype {input_type}") - - input_data = np.random.rand(*input_tensor.shape).astype(input_dtype) - input_name = input_tensor.name - output_name = sess.get_outputs()[0].name - - # Warmup runs - elapsed = 0.0 - for _ in range(3): - start_time = time.time() - for _ in range(self.num_warmup_runs): - sess.run([output_name], {input_name: input_data}) - elapsed = time.time() - start_time - - # Compute number of runs as higher of min_time or num_timed_runs - num_runs = max(round(self.min_time / (elapsed + eps) * self.num_warmup_runs), self.num_timed_runs) - - # Timed runs - run_times = [] - for _ in TQDM(range(num_runs), desc=onnx_file): - start_time = time.time() - sess.run([output_name], {input_name: input_data}) - run_times.append((time.time() - start_time) * 1000) # Convert to milliseconds - - run_times = self.iterative_sigma_clipping(np.array(run_times), sigma=2, max_iters=5) # sigma clipping - return np.mean(run_times), np.std(run_times) - - def generate_table_row(self, model_name, t_onnx, t_engine, model_info): - """Generates a formatted string for a table row that includes model performance and metric details.""" - layers, params, gradients, flops = model_info - return ( - f"| {model_name:18s} | {self.imgsz} | - | {t_onnx[0]:.2f} ± {t_onnx[1]:.2f} ms | {t_engine[0]:.2f} ± " - f"{t_engine[1]:.2f} ms | {params / 1e6:.1f} | {flops:.1f} |" - ) - - @staticmethod - def generate_results_dict(model_name, t_onnx, t_engine, model_info): - """Generates a dictionary of model details including name, parameters, GFLOPS and speed metrics.""" - layers, params, gradients, flops = model_info - return { - "model/name": model_name, - "model/parameters": params, - "model/GFLOPs": round(flops, 3), - "model/speed_ONNX(ms)": round(t_onnx[0], 3), - "model/speed_TensorRT(ms)": round(t_engine[0], 3), - } - - @staticmethod - def print_table(table_rows): - """Formats and prints a comparison table for different models with given statistics and performance data.""" - gpu = torch.cuda.get_device_name(0) if torch.cuda.is_available() else "GPU" - header = ( - f"| Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | " - f"Speed
{gpu} TensorRT
(ms) | params
(M) | FLOPs
(B) |" - ) - separator = ( - "|-------------|---------------------|--------------------|------------------------------|" - "-----------------------------------|------------------|-----------------|" - ) - - print(f"\n\n{header}") - print(separator) - for row in table_rows: - print(row) diff --git a/ultralytics-main/ultralytics/utils/callbacks/__init__.py b/ultralytics-main/ultralytics/utils/callbacks/__init__.py deleted file mode 100644 index 116babe..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from .base import add_integration_callbacks, default_callbacks, get_default_callbacks - -__all__ = "add_integration_callbacks", "default_callbacks", "get_default_callbacks" diff --git a/ultralytics-main/ultralytics/utils/callbacks/base.py b/ultralytics-main/ultralytics/utils/callbacks/base.py deleted file mode 100644 index d015457..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/base.py +++ /dev/null @@ -1,219 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Base callbacks.""" - -from collections import defaultdict -from copy import deepcopy - - -# Trainer callbacks ---------------------------------------------------------------------------------------------------- - - -def on_pretrain_routine_start(trainer): - """Called before the pretraining routine starts.""" - pass - - -def on_pretrain_routine_end(trainer): - """Called after the pretraining routine ends.""" - pass - - -def on_train_start(trainer): - """Called when the training starts.""" - pass - - -def on_train_epoch_start(trainer): - """Called at the start of each training epoch.""" - pass - - -def on_train_batch_start(trainer): - """Called at the start of each training batch.""" - pass - - -def optimizer_step(trainer): - """Called when the optimizer takes a step.""" - pass - - -def on_before_zero_grad(trainer): - """Called before the gradients are set to zero.""" - pass - - -def on_train_batch_end(trainer): - """Called at the end of each training batch.""" - pass - - -def on_train_epoch_end(trainer): - """Called at the end of each training epoch.""" - pass - - -def on_fit_epoch_end(trainer): - """Called at the end of each fit epoch (train + val).""" - pass - - -def on_model_save(trainer): - """Called when the model is saved.""" - pass - - -def on_train_end(trainer): - """Called when the training ends.""" - pass - - -def on_params_update(trainer): - """Called when the model parameters are updated.""" - pass - - -def teardown(trainer): - """Called during the teardown of the training process.""" - pass - - -# Validator callbacks -------------------------------------------------------------------------------------------------- - - -def on_val_start(validator): - """Called when the validation starts.""" - pass - - -def on_val_batch_start(validator): - """Called at the start of each validation batch.""" - pass - - -def on_val_batch_end(validator): - """Called at the end of each validation batch.""" - pass - - -def on_val_end(validator): - """Called when the validation ends.""" - pass - - -# Predictor callbacks -------------------------------------------------------------------------------------------------- - - -def on_predict_start(predictor): - """Called when the prediction starts.""" - pass - - -def on_predict_batch_start(predictor): - """Called at the start of each prediction batch.""" - pass - - -def on_predict_batch_end(predictor): - """Called at the end of each prediction batch.""" - pass - - -def on_predict_postprocess_end(predictor): - """Called after the post-processing of the prediction ends.""" - pass - - -def on_predict_end(predictor): - """Called when the prediction ends.""" - pass - - -# Exporter callbacks --------------------------------------------------------------------------------------------------- - - -def on_export_start(exporter): - """Called when the model export starts.""" - pass - - -def on_export_end(exporter): - """Called when the model export ends.""" - pass - - -default_callbacks = { - # Run in trainer - "on_pretrain_routine_start": [on_pretrain_routine_start], - "on_pretrain_routine_end": [on_pretrain_routine_end], - "on_train_start": [on_train_start], - "on_train_epoch_start": [on_train_epoch_start], - "on_train_batch_start": [on_train_batch_start], - "optimizer_step": [optimizer_step], - "on_before_zero_grad": [on_before_zero_grad], - "on_train_batch_end": [on_train_batch_end], - "on_train_epoch_end": [on_train_epoch_end], - "on_fit_epoch_end": [on_fit_epoch_end], # fit = train + val - "on_model_save": [on_model_save], - "on_train_end": [on_train_end], - "on_params_update": [on_params_update], - "teardown": [teardown], - # Run in validator - "on_val_start": [on_val_start], - "on_val_batch_start": [on_val_batch_start], - "on_val_batch_end": [on_val_batch_end], - "on_val_end": [on_val_end], - # Run in predictor - "on_predict_start": [on_predict_start], - "on_predict_batch_start": [on_predict_batch_start], - "on_predict_postprocess_end": [on_predict_postprocess_end], - "on_predict_batch_end": [on_predict_batch_end], - "on_predict_end": [on_predict_end], - # Run in exporter - "on_export_start": [on_export_start], - "on_export_end": [on_export_end], -} - - -def get_default_callbacks(): - """ - Return a copy of the default_callbacks dictionary with lists as default values. - - Returns: - (defaultdict): A defaultdict with keys from default_callbacks and empty lists as default values. - """ - return defaultdict(list, deepcopy(default_callbacks)) - - -def add_integration_callbacks(instance): - """ - Add integration callbacks from various sources to the instance's callbacks. - - Args: - instance (Trainer, Predictor, Validator, Exporter): An object with a 'callbacks' attribute that is a dictionary - of callback lists. - """ - - # Load HUB callbacks - from .hub import callbacks as hub_cb - - callbacks_list = [hub_cb] - - # Load training callbacks - if "Trainer" in instance.__class__.__name__: - from .clearml import callbacks as clear_cb - from .comet import callbacks as comet_cb - from .dvc import callbacks as dvc_cb - from .mlflow import callbacks as mlflow_cb - from .neptune import callbacks as neptune_cb - from .raytune import callbacks as tune_cb - from .tensorboard import callbacks as tb_cb - from .wb import callbacks as wb_cb - - callbacks_list.extend([clear_cb, comet_cb, dvc_cb, mlflow_cb, neptune_cb, tune_cb, tb_cb, wb_cb]) - - # Add the callbacks to the callbacks dictionary - for callbacks in callbacks_list: - for k, v in callbacks.items(): - if v not in instance.callbacks[k]: - instance.callbacks[k].append(v) diff --git a/ultralytics-main/ultralytics/utils/callbacks/clearml.py b/ultralytics-main/ultralytics/utils/callbacks/clearml.py deleted file mode 100644 index a030fc5..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/clearml.py +++ /dev/null @@ -1,152 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING - -try: - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["clearml"] is True # verify integration is enabled - import clearml - from clearml import Task - from clearml.binding.frameworks.pytorch_bind import PatchPyTorchModelIO - from clearml.binding.matplotlib_bind import PatchedMatplotlib - - assert hasattr(clearml, "__version__") # verify package is not directory - -except (ImportError, AssertionError): - clearml = None - - -def _log_debug_samples(files, title="Debug Samples") -> None: - """ - Log files (images) as debug samples in the ClearML task. - - Args: - files (list): A list of file paths in PosixPath format. - title (str): A title that groups together images with the same values. - """ - import re - - if task := Task.current_task(): - for f in files: - if f.exists(): - it = re.search(r"_batch(\d+)", f.name) - iteration = int(it.groups()[0]) if it else 0 - task.get_logger().report_image( - title=title, series=f.name.replace(it.group(), ""), local_path=str(f), iteration=iteration - ) - - -def _log_plot(title, plot_path) -> None: - """ - Log an image as a plot in the plot section of ClearML. - - Args: - title (str): The title of the plot. - plot_path (str): The path to the saved image file. - """ - import matplotlib.image as mpimg - import matplotlib.pyplot as plt - - img = mpimg.imread(plot_path) - fig = plt.figure() - ax = fig.add_axes([0, 0, 1, 1], frameon=False, aspect="auto", xticks=[], yticks=[]) # no ticks - ax.imshow(img) - - Task.current_task().get_logger().report_matplotlib_figure( - title=title, series="", figure=fig, report_interactive=False - ) - - -def on_pretrain_routine_start(trainer): - """Runs at start of pretraining routine; initializes and connects/ logs task to ClearML.""" - try: - if task := Task.current_task(): - # Make sure the automatic pytorch and matplotlib bindings are disabled! - # We are logging these plots and model files manually in the integration - PatchPyTorchModelIO.update_current_task(None) - PatchedMatplotlib.update_current_task(None) - else: - task = Task.init( - project_name=trainer.args.project or "YOLOv8", - task_name=trainer.args.name, - tags=["YOLOv8"], - output_uri=True, - reuse_last_task_id=False, - auto_connect_frameworks={"pytorch": False, "matplotlib": False}, - ) - LOGGER.warning( - "ClearML Initialized a new task. If you want to run remotely, " - "please add clearml-init and connect your arguments before initializing YOLO." - ) - task.connect(vars(trainer.args), name="General") - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ ClearML installed but not initialized correctly, not logging this run. {e}") - - -def on_train_epoch_end(trainer): - """Logs debug samples for the first epoch of YOLO training and report current training progress.""" - if task := Task.current_task(): - # Log debug samples - if trainer.epoch == 1: - _log_debug_samples(sorted(trainer.save_dir.glob("train_batch*.jpg")), "Mosaic") - # Report the current training progress - for k, v in trainer.label_loss_items(trainer.tloss, prefix="train").items(): - task.get_logger().report_scalar("train", k, v, iteration=trainer.epoch) - for k, v in trainer.lr.items(): - task.get_logger().report_scalar("lr", k, v, iteration=trainer.epoch) - - -def on_fit_epoch_end(trainer): - """Reports model information to logger at the end of an epoch.""" - if task := Task.current_task(): - # You should have access to the validation bboxes under jdict - task.get_logger().report_scalar( - title="Epoch Time", series="Epoch Time", value=trainer.epoch_time, iteration=trainer.epoch - ) - for k, v in trainer.metrics.items(): - task.get_logger().report_scalar("val", k, v, iteration=trainer.epoch) - if trainer.epoch == 0: - from ultralytics.utils.torch_utils import model_info_for_loggers - - for k, v in model_info_for_loggers(trainer).items(): - task.get_logger().report_single_value(k, v) - - -def on_val_end(validator): - """Logs validation results including labels and predictions.""" - if Task.current_task(): - # Log val_labels and val_pred - _log_debug_samples(sorted(validator.save_dir.glob("val*.jpg")), "Validation") - - -def on_train_end(trainer): - """Logs final model and its name on training completion.""" - if task := Task.current_task(): - # Log final results, CM matrix + PR plots - files = [ - "results.png", - "confusion_matrix.png", - "confusion_matrix_normalized.png", - *(f"{x}_curve.png" for x in ("F1", "PR", "P", "R")), - ] - files = [(trainer.save_dir / f) for f in files if (trainer.save_dir / f).exists()] # filter - for f in files: - _log_plot(title=f.stem, plot_path=f) - # Report final metrics - for k, v in trainer.validator.metrics.results_dict.items(): - task.get_logger().report_single_value(k, v) - # Log the final model - task.update_output_model(model_path=str(trainer.best), model_name=trainer.args.name, auto_delete_file=False) - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_train_epoch_end": on_train_epoch_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_val_end": on_val_end, - "on_train_end": on_train_end, - } - if clearml - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/comet.py b/ultralytics-main/ultralytics/utils/callbacks/comet.py deleted file mode 100644 index 1c5f585..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/comet.py +++ /dev/null @@ -1,375 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import LOGGER, RANK, SETTINGS, TESTS_RUNNING, ops - -try: - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["comet"] is True # verify integration is enabled - import comet_ml - - assert hasattr(comet_ml, "__version__") # verify package is not directory - - import os - from pathlib import Path - - # Ensures certain logging functions only run for supported tasks - COMET_SUPPORTED_TASKS = ["detect"] - - # Names of plots created by YOLOv8 that are logged to Comet - EVALUATION_PLOT_NAMES = "F1_curve", "P_curve", "R_curve", "PR_curve", "confusion_matrix" - LABEL_PLOT_NAMES = "labels", "labels_correlogram" - - _comet_image_prediction_count = 0 - -except (ImportError, AssertionError): - comet_ml = None - - -def _get_comet_mode(): - """Returns the mode of comet set in the environment variables, defaults to 'online' if not set.""" - return os.getenv("COMET_MODE", "online") - - -def _get_comet_model_name(): - """Returns the model name for Comet from the environment variable 'COMET_MODEL_NAME' or defaults to 'YOLOv8'.""" - return os.getenv("COMET_MODEL_NAME", "YOLOv8") - - -def _get_eval_batch_logging_interval(): - """Get the evaluation batch logging interval from environment variable or use default value 1.""" - return int(os.getenv("COMET_EVAL_BATCH_LOGGING_INTERVAL", 1)) - - -def _get_max_image_predictions_to_log(): - """Get the maximum number of image predictions to log from the environment variables.""" - return int(os.getenv("COMET_MAX_IMAGE_PREDICTIONS", 100)) - - -def _scale_confidence_score(score): - """Scales the given confidence score by a factor specified in an environment variable.""" - scale = float(os.getenv("COMET_MAX_CONFIDENCE_SCORE", 100.0)) - return score * scale - - -def _should_log_confusion_matrix(): - """Determines if the confusion matrix should be logged based on the environment variable settings.""" - return os.getenv("COMET_EVAL_LOG_CONFUSION_MATRIX", "false").lower() == "true" - - -def _should_log_image_predictions(): - """Determines whether to log image predictions based on a specified environment variable.""" - return os.getenv("COMET_EVAL_LOG_IMAGE_PREDICTIONS", "true").lower() == "true" - - -def _get_experiment_type(mode, project_name): - """Return an experiment based on mode and project name.""" - if mode == "offline": - return comet_ml.OfflineExperiment(project_name=project_name) - - return comet_ml.Experiment(project_name=project_name) - - -def _create_experiment(args): - """Ensures that the experiment object is only created in a single process during distributed training.""" - if RANK not in (-1, 0): - return - try: - comet_mode = _get_comet_mode() - _project_name = os.getenv("COMET_PROJECT_NAME", args.project) - experiment = _get_experiment_type(comet_mode, _project_name) - experiment.log_parameters(vars(args)) - experiment.log_others( - { - "eval_batch_logging_interval": _get_eval_batch_logging_interval(), - "log_confusion_matrix_on_eval": _should_log_confusion_matrix(), - "log_image_predictions": _should_log_image_predictions(), - "max_image_predictions": _get_max_image_predictions_to_log(), - } - ) - experiment.log_other("Created from", "yolov8") - - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ Comet installed but not initialized correctly, not logging this run. {e}") - - -def _fetch_trainer_metadata(trainer): - """Returns metadata for YOLO training including epoch and asset saving status.""" - curr_epoch = trainer.epoch + 1 - - train_num_steps_per_epoch = len(trainer.train_loader.dataset) // trainer.batch_size - curr_step = curr_epoch * train_num_steps_per_epoch - final_epoch = curr_epoch == trainer.epochs - - save = trainer.args.save - save_period = trainer.args.save_period - save_interval = curr_epoch % save_period == 0 - save_assets = save and save_period > 0 and save_interval and not final_epoch - - return dict(curr_epoch=curr_epoch, curr_step=curr_step, save_assets=save_assets, final_epoch=final_epoch) - - -def _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad): - """ - YOLOv8 resizes images during training and the label values are normalized based on this resized shape. - - This function rescales the bounding box labels to the original image shape. - """ - - resized_image_height, resized_image_width = resized_image_shape - - # Convert normalized xywh format predictions to xyxy in resized scale format - box = ops.xywhn2xyxy(box, h=resized_image_height, w=resized_image_width) - # Scale box predictions from resized image scale back to original image scale - box = ops.scale_boxes(resized_image_shape, box, original_image_shape, ratio_pad) - # Convert bounding box format from xyxy to xywh for Comet logging - box = ops.xyxy2xywh(box) - # Adjust xy center to correspond top-left corner - box[:2] -= box[2:] / 2 - box = box.tolist() - - return box - - -def _format_ground_truth_annotations_for_detection(img_idx, image_path, batch, class_name_map=None): - """Format ground truth annotations for detection.""" - indices = batch["batch_idx"] == img_idx - bboxes = batch["bboxes"][indices] - if len(bboxes) == 0: - LOGGER.debug(f"COMET WARNING: Image: {image_path} has no bounding boxes labels") - return None - - cls_labels = batch["cls"][indices].squeeze(1).tolist() - if class_name_map: - cls_labels = [str(class_name_map[label]) for label in cls_labels] - - original_image_shape = batch["ori_shape"][img_idx] - resized_image_shape = batch["resized_shape"][img_idx] - ratio_pad = batch["ratio_pad"][img_idx] - - data = [] - for box, label in zip(bboxes, cls_labels): - box = _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad) - data.append( - { - "boxes": [box], - "label": f"gt_{label}", - "score": _scale_confidence_score(1.0), - } - ) - - return {"name": "ground_truth", "data": data} - - -def _format_prediction_annotations_for_detection(image_path, metadata, class_label_map=None): - """Format YOLO predictions for object detection visualization.""" - stem = image_path.stem - image_id = int(stem) if stem.isnumeric() else stem - - predictions = metadata.get(image_id) - if not predictions: - LOGGER.debug(f"COMET WARNING: Image: {image_path} has no bounding boxes predictions") - return None - - data = [] - for prediction in predictions: - boxes = prediction["bbox"] - score = _scale_confidence_score(prediction["score"]) - cls_label = prediction["category_id"] - if class_label_map: - cls_label = str(class_label_map[cls_label]) - - data.append({"boxes": [boxes], "label": cls_label, "score": score}) - - return {"name": "prediction", "data": data} - - -def _fetch_annotations(img_idx, image_path, batch, prediction_metadata_map, class_label_map): - """Join the ground truth and prediction annotations if they exist.""" - ground_truth_annotations = _format_ground_truth_annotations_for_detection( - img_idx, image_path, batch, class_label_map - ) - prediction_annotations = _format_prediction_annotations_for_detection( - image_path, prediction_metadata_map, class_label_map - ) - - annotations = [ - annotation for annotation in [ground_truth_annotations, prediction_annotations] if annotation is not None - ] - return [annotations] if annotations else None - - -def _create_prediction_metadata_map(model_predictions): - """Create metadata map for model predictions by groupings them based on image ID.""" - pred_metadata_map = {} - for prediction in model_predictions: - pred_metadata_map.setdefault(prediction["image_id"], []) - pred_metadata_map[prediction["image_id"]].append(prediction) - - return pred_metadata_map - - -def _log_confusion_matrix(experiment, trainer, curr_step, curr_epoch): - """Log the confusion matrix to Comet experiment.""" - conf_mat = trainer.validator.confusion_matrix.matrix - names = list(trainer.data["names"].values()) + ["background"] - experiment.log_confusion_matrix( - matrix=conf_mat, labels=names, max_categories=len(names), epoch=curr_epoch, step=curr_step - ) - - -def _log_images(experiment, image_paths, curr_step, annotations=None): - """Logs images to the experiment with optional annotations.""" - if annotations: - for image_path, annotation in zip(image_paths, annotations): - experiment.log_image(image_path, name=image_path.stem, step=curr_step, annotations=annotation) - - else: - for image_path in image_paths: - experiment.log_image(image_path, name=image_path.stem, step=curr_step) - - -def _log_image_predictions(experiment, validator, curr_step): - """Logs predicted boxes for a single image during training.""" - global _comet_image_prediction_count - - task = validator.args.task - if task not in COMET_SUPPORTED_TASKS: - return - - jdict = validator.jdict - if not jdict: - return - - predictions_metadata_map = _create_prediction_metadata_map(jdict) - dataloader = validator.dataloader - class_label_map = validator.names - - batch_logging_interval = _get_eval_batch_logging_interval() - max_image_predictions = _get_max_image_predictions_to_log() - - for batch_idx, batch in enumerate(dataloader): - if (batch_idx + 1) % batch_logging_interval != 0: - continue - - image_paths = batch["im_file"] - for img_idx, image_path in enumerate(image_paths): - if _comet_image_prediction_count >= max_image_predictions: - return - - image_path = Path(image_path) - annotations = _fetch_annotations( - img_idx, - image_path, - batch, - predictions_metadata_map, - class_label_map, - ) - _log_images( - experiment, - [image_path], - curr_step, - annotations=annotations, - ) - _comet_image_prediction_count += 1 - - -def _log_plots(experiment, trainer): - """Logs evaluation plots and label plots for the experiment.""" - plot_filenames = [trainer.save_dir / f"{plots}.png" for plots in EVALUATION_PLOT_NAMES] - _log_images(experiment, plot_filenames, None) - - label_plot_filenames = [trainer.save_dir / f"{labels}.jpg" for labels in LABEL_PLOT_NAMES] - _log_images(experiment, label_plot_filenames, None) - - -def _log_model(experiment, trainer): - """Log the best-trained model to Comet.ml.""" - model_name = _get_comet_model_name() - experiment.log_model(model_name, file_or_folder=str(trainer.best), file_name="best.pt", overwrite=True) - - -def on_pretrain_routine_start(trainer): - """Creates or resumes a CometML experiment at the start of a YOLO pre-training routine.""" - experiment = comet_ml.get_global_experiment() - is_alive = getattr(experiment, "alive", False) - if not experiment or not is_alive: - _create_experiment(trainer.args) - - -def on_train_epoch_end(trainer): - """Log metrics and save batch images at the end of training epochs.""" - experiment = comet_ml.get_global_experiment() - if not experiment: - return - - metadata = _fetch_trainer_metadata(trainer) - curr_epoch = metadata["curr_epoch"] - curr_step = metadata["curr_step"] - - experiment.log_metrics(trainer.label_loss_items(trainer.tloss, prefix="train"), step=curr_step, epoch=curr_epoch) - - if curr_epoch == 1: - _log_images(experiment, trainer.save_dir.glob("train_batch*.jpg"), curr_step) - - -def on_fit_epoch_end(trainer): - """Logs model assets at the end of each epoch.""" - experiment = comet_ml.get_global_experiment() - if not experiment: - return - - metadata = _fetch_trainer_metadata(trainer) - curr_epoch = metadata["curr_epoch"] - curr_step = metadata["curr_step"] - save_assets = metadata["save_assets"] - - experiment.log_metrics(trainer.metrics, step=curr_step, epoch=curr_epoch) - experiment.log_metrics(trainer.lr, step=curr_step, epoch=curr_epoch) - if curr_epoch == 1: - from ultralytics.utils.torch_utils import model_info_for_loggers - - experiment.log_metrics(model_info_for_loggers(trainer), step=curr_step, epoch=curr_epoch) - - if not save_assets: - return - - _log_model(experiment, trainer) - if _should_log_confusion_matrix(): - _log_confusion_matrix(experiment, trainer, curr_step, curr_epoch) - if _should_log_image_predictions(): - _log_image_predictions(experiment, trainer.validator, curr_step) - - -def on_train_end(trainer): - """Perform operations at the end of training.""" - experiment = comet_ml.get_global_experiment() - if not experiment: - return - - metadata = _fetch_trainer_metadata(trainer) - curr_epoch = metadata["curr_epoch"] - curr_step = metadata["curr_step"] - plots = trainer.args.plots - - _log_model(experiment, trainer) - if plots: - _log_plots(experiment, trainer) - - _log_confusion_matrix(experiment, trainer, curr_step, curr_epoch) - _log_image_predictions(experiment, trainer.validator, curr_step) - experiment.end() - - global _comet_image_prediction_count - _comet_image_prediction_count = 0 - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_train_epoch_end": on_train_epoch_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_train_end": on_train_end, - } - if comet_ml - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/dvc.py b/ultralytics-main/ultralytics/utils/callbacks/dvc.py deleted file mode 100644 index ab51dc5..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/dvc.py +++ /dev/null @@ -1,145 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING, checks - -try: - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["dvc"] is True # verify integration is enabled - import dvclive - - assert checks.check_version("dvclive", "2.11.0", verbose=True) - - import os - import re - from pathlib import Path - - # DVCLive logger instance - live = None - _processed_plots = {} - - # `on_fit_epoch_end` is called on final validation (probably need to be fixed) for now this is the way we - # distinguish final evaluation of the best model vs last epoch validation - _training_epoch = False - -except (ImportError, AssertionError, TypeError): - dvclive = None - - -def _log_images(path, prefix=""): - """Logs images at specified path with an optional prefix using DVCLive.""" - if live: - name = path.name - - # Group images by batch to enable sliders in UI - if m := re.search(r"_batch(\d+)", name): - ni = m[1] - new_stem = re.sub(r"_batch(\d+)", "_batch", path.stem) - name = (Path(new_stem) / ni).with_suffix(path.suffix) - - live.log_image(os.path.join(prefix, name), path) - - -def _log_plots(plots, prefix=""): - """Logs plot images for training progress if they have not been previously processed.""" - for name, params in plots.items(): - timestamp = params["timestamp"] - if _processed_plots.get(name) != timestamp: - _log_images(name, prefix) - _processed_plots[name] = timestamp - - -def _log_confusion_matrix(validator): - """Logs the confusion matrix for the given validator using DVCLive.""" - targets = [] - preds = [] - matrix = validator.confusion_matrix.matrix - names = list(validator.names.values()) - if validator.confusion_matrix.task == "detect": - names += ["background"] - - for ti, pred in enumerate(matrix.T.astype(int)): - for pi, num in enumerate(pred): - targets.extend([names[ti]] * num) - preds.extend([names[pi]] * num) - - live.log_sklearn_plot("confusion_matrix", targets, preds, name="cf.json", normalized=True) - - -def on_pretrain_routine_start(trainer): - """Initializes DVCLive logger for training metadata during pre-training routine.""" - try: - global live - live = dvclive.Live(save_dvc_exp=True, cache_images=True) - LOGGER.info("DVCLive is detected and auto logging is enabled (run 'yolo settings dvc=False' to disable).") - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ DVCLive installed but not initialized correctly, not logging this run. {e}") - - -def on_pretrain_routine_end(trainer): - """Logs plots related to the training process at the end of the pretraining routine.""" - _log_plots(trainer.plots, "train") - - -def on_train_start(trainer): - """Logs the training parameters if DVCLive logging is active.""" - if live: - live.log_params(trainer.args) - - -def on_train_epoch_start(trainer): - """Sets the global variable _training_epoch value to True at the start of training each epoch.""" - global _training_epoch - _training_epoch = True - - -def on_fit_epoch_end(trainer): - """Logs training metrics and model info, and advances to next step on the end of each fit epoch.""" - global _training_epoch - if live and _training_epoch: - all_metrics = {**trainer.label_loss_items(trainer.tloss, prefix="train"), **trainer.metrics, **trainer.lr} - for metric, value in all_metrics.items(): - live.log_metric(metric, value) - - if trainer.epoch == 0: - from ultralytics.utils.torch_utils import model_info_for_loggers - - for metric, value in model_info_for_loggers(trainer).items(): - live.log_metric(metric, value, plot=False) - - _log_plots(trainer.plots, "train") - _log_plots(trainer.validator.plots, "val") - - live.next_step() - _training_epoch = False - - -def on_train_end(trainer): - """Logs the best metrics, plots, and confusion matrix at the end of training if DVCLive is active.""" - if live: - # At the end log the best metrics. It runs validator on the best model internally. - all_metrics = {**trainer.label_loss_items(trainer.tloss, prefix="train"), **trainer.metrics, **trainer.lr} - for metric, value in all_metrics.items(): - live.log_metric(metric, value, plot=False) - - _log_plots(trainer.plots, "val") - _log_plots(trainer.validator.plots, "val") - _log_confusion_matrix(trainer.validator) - - if trainer.best.exists(): - live.log_artifact(trainer.best, copy=True, type="model") - - live.end() - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_pretrain_routine_end": on_pretrain_routine_end, - "on_train_start": on_train_start, - "on_train_epoch_start": on_train_epoch_start, - "on_fit_epoch_end": on_fit_epoch_end, - "on_train_end": on_train_end, - } - if dvclive - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/hub.py b/ultralytics-main/ultralytics/utils/callbacks/hub.py deleted file mode 100644 index cdb42b9..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/hub.py +++ /dev/null @@ -1,108 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import json -from time import time - -from ultralytics.hub.utils import HUB_WEB_ROOT, PREFIX, events -from ultralytics.utils import LOGGER, SETTINGS - - -def on_pretrain_routine_end(trainer): - """Logs info before starting timer for upload rate limit.""" - session = getattr(trainer, "hub_session", None) - if session: - # Start timer for upload rate limit - session.timers = { - "metrics": time(), - "ckpt": time(), - } # start timer on session.rate_limit - - -def on_fit_epoch_end(trainer): - """Uploads training progress metrics at the end of each epoch.""" - session = getattr(trainer, "hub_session", None) - if session: - # Upload metrics after val end - all_plots = { - **trainer.label_loss_items(trainer.tloss, prefix="train"), - **trainer.metrics, - } - if trainer.epoch == 0: - from ultralytics.utils.torch_utils import model_info_for_loggers - - all_plots = {**all_plots, **model_info_for_loggers(trainer)} - - session.metrics_queue[trainer.epoch] = json.dumps(all_plots) - - # If any metrics fail to upload, add them to the queue to attempt uploading again. - if session.metrics_upload_failed_queue: - session.metrics_queue.update(session.metrics_upload_failed_queue) - - if time() - session.timers["metrics"] > session.rate_limits["metrics"]: - session.upload_metrics() - session.timers["metrics"] = time() # reset timer - session.metrics_queue = {} # reset queue - - -def on_model_save(trainer): - """Saves checkpoints to Ultralytics HUB with rate limiting.""" - session = getattr(trainer, "hub_session", None) - if session: - # Upload checkpoints with rate limiting - is_best = trainer.best_fitness == trainer.fitness - if time() - session.timers["ckpt"] > session.rate_limits["ckpt"]: - LOGGER.info(f"{PREFIX}Uploading checkpoint {HUB_WEB_ROOT}/models/{session.model.id}") - session.upload_model(trainer.epoch, trainer.last, is_best) - session.timers["ckpt"] = time() # reset timer - - -def on_train_end(trainer): - """Upload final model and metrics to Ultralytics HUB at the end of training.""" - session = getattr(trainer, "hub_session", None) - if session: - # Upload final model and metrics with exponential standoff - LOGGER.info(f"{PREFIX}Syncing final model...") - session.upload_model( - trainer.epoch, - trainer.best, - map=trainer.metrics.get("metrics/mAP50-95(B)", 0), - final=True, - ) - session.alive = False # stop heartbeats - LOGGER.info(f"{PREFIX}Done ✅\n" f"{PREFIX}View model at {session.model_url} 🚀") - - -def on_train_start(trainer): - """Run events on train start.""" - events(trainer.args) - - -def on_val_start(validator): - """Runs events on validation start.""" - events(validator.args) - - -def on_predict_start(predictor): - """Run events on predict start.""" - events(predictor.args) - - -def on_export_start(exporter): - """Run events on export start.""" - events(exporter.args) - - -callbacks = ( - { - "on_pretrain_routine_end": on_pretrain_routine_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_model_save": on_model_save, - "on_train_end": on_train_end, - "on_train_start": on_train_start, - "on_val_start": on_val_start, - "on_predict_start": on_predict_start, - "on_export_start": on_export_start, - } - if SETTINGS["hub"] is True - else {} -) # verify enabled diff --git a/ultralytics-main/ultralytics/utils/callbacks/mlflow.py b/ultralytics-main/ultralytics/utils/callbacks/mlflow.py deleted file mode 100644 index e554620..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/mlflow.py +++ /dev/null @@ -1,133 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -""" -MLflow Logging for Ultralytics YOLO. - -This module enables MLflow logging for Ultralytics YOLO. It logs metrics, parameters, and model artifacts. -For setting up, a tracking URI should be specified. The logging can be customized using environment variables. - -Commands: - 1. To set a project name: - `export MLFLOW_EXPERIMENT_NAME=` or use the project= argument - - 2. To set a run name: - `export MLFLOW_RUN=` or use the name= argument - - 3. To start a local MLflow server: - mlflow server --backend-store-uri runs/mlflow - It will by default start a local server at http://127.0.0.1:5000. - To specify a different URI, set the MLFLOW_TRACKING_URI environment variable. - - 4. To kill all running MLflow server instances: - ps aux | grep 'mlflow' | grep -v 'grep' | awk '{print $2}' | xargs kill -9 -""" - -from ultralytics.utils import LOGGER, RUNS_DIR, SETTINGS, TESTS_RUNNING, colorstr - -try: - import os - - assert not TESTS_RUNNING or "test_mlflow" in os.environ.get("PYTEST_CURRENT_TEST", "") # do not log pytest - assert SETTINGS["mlflow"] is True # verify integration is enabled - import mlflow - - assert hasattr(mlflow, "__version__") # verify package is not directory - from pathlib import Path - - PREFIX = colorstr("MLflow: ") - SANITIZE = lambda x: {k.replace("(", "").replace(")", ""): float(v) for k, v in x.items()} - -except (ImportError, AssertionError): - mlflow = None - - -def on_pretrain_routine_end(trainer): - """ - Log training parameters to MLflow at the end of the pretraining routine. - - This function sets up MLflow logging based on environment variables and trainer arguments. It sets the tracking URI, - experiment name, and run name, then starts the MLflow run if not already active. It finally logs the parameters - from the trainer. - - Args: - trainer (ultralytics.engine.trainer.BaseTrainer): The training object with arguments and parameters to log. - - Global: - mlflow: The imported mlflow module to use for logging. - - Environment Variables: - MLFLOW_TRACKING_URI: The URI for MLflow tracking. If not set, defaults to 'runs/mlflow'. - MLFLOW_EXPERIMENT_NAME: The name of the MLflow experiment. If not set, defaults to trainer.args.project. - MLFLOW_RUN: The name of the MLflow run. If not set, defaults to trainer.args.name. - MLFLOW_KEEP_RUN_ACTIVE: Boolean indicating whether to keep the MLflow run active after the end of the training phase. - """ - global mlflow - - uri = os.environ.get("MLFLOW_TRACKING_URI") or str(RUNS_DIR / "mlflow") - LOGGER.debug(f"{PREFIX} tracking uri: {uri}") - mlflow.set_tracking_uri(uri) - - # Set experiment and run names - experiment_name = os.environ.get("MLFLOW_EXPERIMENT_NAME") or trainer.args.project or "/Shared/YOLOv8" - run_name = os.environ.get("MLFLOW_RUN") or trainer.args.name - mlflow.set_experiment(experiment_name) - - mlflow.autolog() - try: - active_run = mlflow.active_run() or mlflow.start_run(run_name=run_name) - LOGGER.info(f"{PREFIX}logging run_id({active_run.info.run_id}) to {uri}") - if Path(uri).is_dir(): - LOGGER.info(f"{PREFIX}view at http://127.0.0.1:5000 with 'mlflow server --backend-store-uri {uri}'") - LOGGER.info(f"{PREFIX}disable with 'yolo settings mlflow=False'") - mlflow.log_params(dict(trainer.args)) - except Exception as e: - LOGGER.warning(f"{PREFIX}WARNING ⚠️ Failed to initialize: {e}\n" f"{PREFIX}WARNING ⚠️ Not tracking this run") - - -def on_train_epoch_end(trainer): - """Log training metrics at the end of each train epoch to MLflow.""" - if mlflow: - mlflow.log_metrics( - metrics={ - **SANITIZE(trainer.lr), - **SANITIZE(trainer.label_loss_items(trainer.tloss, prefix="train")), - }, - step=trainer.epoch, - ) - - -def on_fit_epoch_end(trainer): - """Log training metrics at the end of each fit epoch to MLflow.""" - if mlflow: - mlflow.log_metrics(metrics=SANITIZE(trainer.metrics), step=trainer.epoch) - - -def on_train_end(trainer): - """Log model artifacts at the end of the training.""" - if mlflow: - mlflow.log_artifact(str(trainer.best.parent)) # log save_dir/weights directory with best.pt and last.pt - for f in trainer.save_dir.glob("*"): # log all other files in save_dir - if f.suffix in {".png", ".jpg", ".csv", ".pt", ".yaml"}: - mlflow.log_artifact(str(f)) - keep_run_active = os.environ.get("MLFLOW_KEEP_RUN_ACTIVE", "False").lower() in ("true") - if keep_run_active: - LOGGER.info(f"{PREFIX}mlflow run still alive, remember to close it using mlflow.end_run()") - else: - mlflow.end_run() - LOGGER.debug(f"{PREFIX}mlflow run ended") - - LOGGER.info( - f"{PREFIX}results logged to {mlflow.get_tracking_uri()}\n" - f"{PREFIX}disable with 'yolo settings mlflow=False'" - ) - - -callbacks = ( - { - "on_pretrain_routine_end": on_pretrain_routine_end, - "on_train_epoch_end": on_train_epoch_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_train_end": on_train_end, - } - if mlflow - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/neptune.py b/ultralytics-main/ultralytics/utils/callbacks/neptune.py deleted file mode 100644 index 6be8a82..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/neptune.py +++ /dev/null @@ -1,112 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING - -try: - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["neptune"] is True # verify integration is enabled - import neptune - from neptune.types import File - - assert hasattr(neptune, "__version__") - - run = None # NeptuneAI experiment logger instance - -except (ImportError, AssertionError): - neptune = None - - -def _log_scalars(scalars, step=0): - """Log scalars to the NeptuneAI experiment logger.""" - if run: - for k, v in scalars.items(): - run[k].append(value=v, step=step) - - -def _log_images(imgs_dict, group=""): - """Log scalars to the NeptuneAI experiment logger.""" - if run: - for k, v in imgs_dict.items(): - run[f"{group}/{k}"].upload(File(v)) - - -def _log_plot(title, plot_path): - """ - Log plots to the NeptuneAI experiment logger. - - Args: - title (str): Title of the plot. - plot_path (PosixPath | str): Path to the saved image file. - """ - import matplotlib.image as mpimg - import matplotlib.pyplot as plt - - img = mpimg.imread(plot_path) - fig = plt.figure() - ax = fig.add_axes([0, 0, 1, 1], frameon=False, aspect="auto", xticks=[], yticks=[]) # no ticks - ax.imshow(img) - run[f"Plots/{title}"].upload(fig) - - -def on_pretrain_routine_start(trainer): - """Callback function called before the training routine starts.""" - try: - global run - run = neptune.init_run(project=trainer.args.project or "YOLOv8", name=trainer.args.name, tags=["YOLOv8"]) - run["Configuration/Hyperparameters"] = {k: "" if v is None else v for k, v in vars(trainer.args).items()} - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ NeptuneAI installed but not initialized correctly, not logging this run. {e}") - - -def on_train_epoch_end(trainer): - """Callback function called at end of each training epoch.""" - _log_scalars(trainer.label_loss_items(trainer.tloss, prefix="train"), trainer.epoch + 1) - _log_scalars(trainer.lr, trainer.epoch + 1) - if trainer.epoch == 1: - _log_images({f.stem: str(f) for f in trainer.save_dir.glob("train_batch*.jpg")}, "Mosaic") - - -def on_fit_epoch_end(trainer): - """Callback function called at end of each fit (train+val) epoch.""" - if run and trainer.epoch == 0: - from ultralytics.utils.torch_utils import model_info_for_loggers - - run["Configuration/Model"] = model_info_for_loggers(trainer) - _log_scalars(trainer.metrics, trainer.epoch + 1) - - -def on_val_end(validator): - """Callback function called at end of each validation.""" - if run: - # Log val_labels and val_pred - _log_images({f.stem: str(f) for f in validator.save_dir.glob("val*.jpg")}, "Validation") - - -def on_train_end(trainer): - """Callback function called at end of training.""" - if run: - # Log final results, CM matrix + PR plots - files = [ - "results.png", - "confusion_matrix.png", - "confusion_matrix_normalized.png", - *(f"{x}_curve.png" for x in ("F1", "PR", "P", "R")), - ] - files = [(trainer.save_dir / f) for f in files if (trainer.save_dir / f).exists()] # filter - for f in files: - _log_plot(title=f.stem, plot_path=f) - # Log the final model - run[f"weights/{trainer.args.name or trainer.args.task}/{trainer.best.name}"].upload(File(str(trainer.best))) - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_train_epoch_end": on_train_epoch_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_val_end": on_val_end, - "on_train_end": on_train_end, - } - if neptune - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/raytune.py b/ultralytics-main/ultralytics/utils/callbacks/raytune.py deleted file mode 100644 index f269455..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/raytune.py +++ /dev/null @@ -1,29 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import SETTINGS - -try: - assert SETTINGS["raytune"] is True # verify integration is enabled - import ray - from ray import tune - from ray.air import session - -except (ImportError, AssertionError): - tune = None - - -def on_fit_epoch_end(trainer): - """Sends training metrics to Ray Tune at end of each epoch.""" - if ray.tune.is_session_enabled(): - metrics = trainer.metrics - metrics["epoch"] = trainer.epoch - session.report(metrics) - - -callbacks = ( - { - "on_fit_epoch_end": on_fit_epoch_end, - } - if tune - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/tensorboard.py b/ultralytics-main/ultralytics/utils/callbacks/tensorboard.py deleted file mode 100644 index 59024ee..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/tensorboard.py +++ /dev/null @@ -1,106 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -import contextlib - -from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING, colorstr - -try: - # WARNING: do not move SummaryWriter import due to protobuf bug https://github.com/ultralytics/ultralytics/pull/4674 - from torch.utils.tensorboard import SummaryWriter - - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["tensorboard"] is True # verify integration is enabled - WRITER = None # TensorBoard SummaryWriter instance - PREFIX = colorstr("TensorBoard: ") - - # Imports below only required if TensorBoard enabled - import warnings - from copy import deepcopy - from ultralytics.utils.torch_utils import de_parallel, torch - -except (ImportError, AssertionError, TypeError, AttributeError): - # TypeError for handling 'Descriptors cannot not be created directly.' protobuf errors in Windows - # AttributeError: module 'tensorflow' has no attribute 'io' if 'tensorflow' not installed - SummaryWriter = None - - -def _log_scalars(scalars, step=0): - """Logs scalar values to TensorBoard.""" - if WRITER: - for k, v in scalars.items(): - WRITER.add_scalar(k, v, step) - - -def _log_tensorboard_graph(trainer): - """Log model graph to TensorBoard.""" - - # Input image - imgsz = trainer.args.imgsz - imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz - p = next(trainer.model.parameters()) # for device, type - im = torch.zeros((1, 3, *imgsz), device=p.device, dtype=p.dtype) # input image (must be zeros, not empty) - - with warnings.catch_warnings(): - warnings.simplefilter("ignore", category=UserWarning) # suppress jit trace warning - warnings.simplefilter("ignore", category=torch.jit.TracerWarning) # suppress jit trace warning - - # Try simple method first (YOLO) - with contextlib.suppress(Exception): - trainer.model.eval() # place in .eval() mode to avoid BatchNorm statistics changes - WRITER.add_graph(torch.jit.trace(de_parallel(trainer.model), im, strict=False), []) - LOGGER.info(f"{PREFIX}model graph visualization added ✅") - return - - # Fallback to TorchScript export steps (RTDETR) - try: - model = deepcopy(de_parallel(trainer.model)) - model.eval() - model = model.fuse(verbose=False) - for m in model.modules(): - if hasattr(m, "export"): # Detect, RTDETRDecoder (Segment and Pose use Detect base class) - m.export = True - m.format = "torchscript" - model(im) # dry run - WRITER.add_graph(torch.jit.trace(model, im, strict=False), []) - LOGGER.info(f"{PREFIX}model graph visualization added ✅") - except Exception as e: - LOGGER.warning(f"{PREFIX}WARNING ⚠️ TensorBoard graph visualization failure {e}") - - -def on_pretrain_routine_start(trainer): - """Initialize TensorBoard logging with SummaryWriter.""" - if SummaryWriter: - try: - global WRITER - WRITER = SummaryWriter(str(trainer.save_dir)) - LOGGER.info(f"{PREFIX}Start with 'tensorboard --logdir {trainer.save_dir}', view at http://localhost:6006/") - except Exception as e: - LOGGER.warning(f"{PREFIX}WARNING ⚠️ TensorBoard not initialized correctly, not logging this run. {e}") - - -def on_train_start(trainer): - """Log TensorBoard graph.""" - if WRITER: - _log_tensorboard_graph(trainer) - - -def on_train_epoch_end(trainer): - """Logs scalar statistics at the end of a training epoch.""" - _log_scalars(trainer.label_loss_items(trainer.tloss, prefix="train"), trainer.epoch + 1) - _log_scalars(trainer.lr, trainer.epoch + 1) - - -def on_fit_epoch_end(trainer): - """Logs epoch metrics at end of training epoch.""" - _log_scalars(trainer.metrics, trainer.epoch + 1) - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_train_start": on_train_start, - "on_fit_epoch_end": on_fit_epoch_end, - "on_train_epoch_end": on_train_epoch_end, - } - if SummaryWriter - else {} -) diff --git a/ultralytics-main/ultralytics/utils/callbacks/wb.py b/ultralytics-main/ultralytics/utils/callbacks/wb.py deleted file mode 100644 index 25a1b64..0000000 --- a/ultralytics-main/ultralytics/utils/callbacks/wb.py +++ /dev/null @@ -1,163 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import SETTINGS, TESTS_RUNNING -from ultralytics.utils.torch_utils import model_info_for_loggers - -try: - assert not TESTS_RUNNING # do not log pytest - assert SETTINGS["wandb"] is True # verify integration is enabled - import wandb as wb - - assert hasattr(wb, "__version__") # verify package is not directory - - import numpy as np - import pandas as pd - - _processed_plots = {} - -except (ImportError, AssertionError): - wb = None - - -def _custom_table(x, y, classes, title="Precision Recall Curve", x_title="Recall", y_title="Precision"): - """ - Create and log a custom metric visualization to wandb.plot.pr_curve. - - This function crafts a custom metric visualization that mimics the behavior of wandb's default precision-recall - curve while allowing for enhanced customization. The visual metric is useful for monitoring model performance across - different classes. - - Args: - x (List): Values for the x-axis; expected to have length N. - y (List): Corresponding values for the y-axis; also expected to have length N. - classes (List): Labels identifying the class of each point; length N. - title (str, optional): Title for the plot; defaults to 'Precision Recall Curve'. - x_title (str, optional): Label for the x-axis; defaults to 'Recall'. - y_title (str, optional): Label for the y-axis; defaults to 'Precision'. - - Returns: - (wandb.Object): A wandb object suitable for logging, showcasing the crafted metric visualization. - """ - df = pd.DataFrame({"class": classes, "y": y, "x": x}).round(3) - fields = {"x": "x", "y": "y", "class": "class"} - string_fields = {"title": title, "x-axis-title": x_title, "y-axis-title": y_title} - return wb.plot_table( - "wandb/area-under-curve/v0", wb.Table(dataframe=df), fields=fields, string_fields=string_fields - ) - - -def _plot_curve( - x, - y, - names=None, - id="precision-recall", - title="Precision Recall Curve", - x_title="Recall", - y_title="Precision", - num_x=100, - only_mean=False, -): - """ - Log a metric curve visualization. - - This function generates a metric curve based on input data and logs the visualization to wandb. - The curve can represent aggregated data (mean) or individual class data, depending on the 'only_mean' flag. - - Args: - x (np.ndarray): Data points for the x-axis with length N. - y (np.ndarray): Corresponding data points for the y-axis with shape CxN, where C is the number of classes. - names (list, optional): Names of the classes corresponding to the y-axis data; length C. Defaults to []. - id (str, optional): Unique identifier for the logged data in wandb. Defaults to 'precision-recall'. - title (str, optional): Title for the visualization plot. Defaults to 'Precision Recall Curve'. - x_title (str, optional): Label for the x-axis. Defaults to 'Recall'. - y_title (str, optional): Label for the y-axis. Defaults to 'Precision'. - num_x (int, optional): Number of interpolated data points for visualization. Defaults to 100. - only_mean (bool, optional): Flag to indicate if only the mean curve should be plotted. Defaults to True. - - Note: - The function leverages the '_custom_table' function to generate the actual visualization. - """ - # Create new x - if names is None: - names = [] - x_new = np.linspace(x[0], x[-1], num_x).round(5) - - # Create arrays for logging - x_log = x_new.tolist() - y_log = np.interp(x_new, x, np.mean(y, axis=0)).round(3).tolist() - - if only_mean: - table = wb.Table(data=list(zip(x_log, y_log)), columns=[x_title, y_title]) - wb.run.log({title: wb.plot.line(table, x_title, y_title, title=title)}) - else: - classes = ["mean"] * len(x_log) - for i, yi in enumerate(y): - x_log.extend(x_new) # add new x - y_log.extend(np.interp(x_new, x, yi)) # interpolate y to new x - classes.extend([names[i]] * len(x_new)) # add class names - wb.log({id: _custom_table(x_log, y_log, classes, title, x_title, y_title)}, commit=False) - - -def _log_plots(plots, step): - """Logs plots from the input dictionary if they haven't been logged already at the specified step.""" - for name, params in plots.items(): - timestamp = params["timestamp"] - if _processed_plots.get(name) != timestamp: - wb.run.log({name.stem: wb.Image(str(name))}, step=step) - _processed_plots[name] = timestamp - - -def on_pretrain_routine_start(trainer): - """Initiate and start project if module is present.""" - wb.run or wb.init(project=trainer.args.project or "YOLOv8", name=trainer.args.name, config=vars(trainer.args)) - - -def on_fit_epoch_end(trainer): - """Logs training metrics and model information at the end of an epoch.""" - wb.run.log(trainer.metrics, step=trainer.epoch + 1) - _log_plots(trainer.plots, step=trainer.epoch + 1) - _log_plots(trainer.validator.plots, step=trainer.epoch + 1) - if trainer.epoch == 0: - wb.run.log(model_info_for_loggers(trainer), step=trainer.epoch + 1) - - -def on_train_epoch_end(trainer): - """Log metrics and save images at the end of each training epoch.""" - wb.run.log(trainer.label_loss_items(trainer.tloss, prefix="train"), step=trainer.epoch + 1) - wb.run.log(trainer.lr, step=trainer.epoch + 1) - if trainer.epoch == 1: - _log_plots(trainer.plots, step=trainer.epoch + 1) - - -def on_train_end(trainer): - """Save the best model as an artifact at end of training.""" - _log_plots(trainer.validator.plots, step=trainer.epoch + 1) - _log_plots(trainer.plots, step=trainer.epoch + 1) - art = wb.Artifact(type="model", name=f"run_{wb.run.id}_model") - if trainer.best.exists(): - art.add_file(trainer.best) - wb.run.log_artifact(art, aliases=["best"]) - for curve_name, curve_values in zip(trainer.validator.metrics.curves, trainer.validator.metrics.curves_results): - x, y, x_title, y_title = curve_values - _plot_curve( - x, - y, - names=list(trainer.validator.metrics.names.values()), - id=f"curves/{curve_name}", - title=curve_name, - x_title=x_title, - y_title=y_title, - ) - wb.run.finish() # required or run continues on dashboard - - -callbacks = ( - { - "on_pretrain_routine_start": on_pretrain_routine_start, - "on_train_epoch_end": on_train_epoch_end, - "on_fit_epoch_end": on_fit_epoch_end, - "on_train_end": on_train_end, - } - if wb - else {} -) diff --git a/ultralytics-main/ultralytics/utils/checks.py b/ultralytics-main/ultralytics/utils/checks.py deleted file mode 100644 index 106fa4e..0000000 --- a/ultralytics-main/ultralytics/utils/checks.py +++ /dev/null @@ -1,729 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import glob -import inspect -import math -import os -import platform -import re -import shutil -import subprocess -import time -from importlib import metadata -from pathlib import Path -from typing import Optional - -import cv2 -import numpy as np -import requests -import torch -from matplotlib import font_manager - -from ultralytics.utils import ( - ASSETS, - AUTOINSTALL, - LINUX, - LOGGER, - ONLINE, - ROOT, - USER_CONFIG_DIR, - SimpleNamespace, - ThreadingLocked, - TryExcept, - clean_url, - colorstr, - downloads, - emojis, - is_colab, - is_docker, - is_github_action_running, - is_jupyter, - is_kaggle, - is_online, - is_pip_package, - url2file, -) - -PYTHON_VERSION = platform.python_version() - - -def parse_requirements(file_path=ROOT.parent / "requirements.txt", package=""): - """ - Parse a requirements.txt file, ignoring lines that start with '#' and any text after '#'. - - Args: - file_path (Path): Path to the requirements.txt file. - package (str, optional): Python package to use instead of requirements.txt file, i.e. package='ultralytics'. - - Returns: - (List[Dict[str, str]]): List of parsed requirements as dictionaries with `name` and `specifier` keys. - - Example: - ```python - from ultralytics.utils.checks import parse_requirements - - parse_requirements(package='ultralytics') - ``` - """ - - if package: - requires = [x for x in metadata.distribution(package).requires if "extra == " not in x] - else: - requires = Path(file_path).read_text().splitlines() - - requirements = [] - for line in requires: - line = line.strip() - if line and not line.startswith("#"): - line = line.split("#")[0].strip() # ignore inline comments - match = re.match(r"([a-zA-Z0-9-_]+)\s*([<>!=~]+.*)?", line) - if match: - requirements.append(SimpleNamespace(name=match[1], specifier=match[2].strip() if match[2] else "")) - - return requirements - - -def parse_version(version="0.0.0") -> tuple: - """ - Convert a version string to a tuple of integers, ignoring any extra non-numeric string attached to the version. This - function replaces deprecated 'pkg_resources.parse_version(v)'. - - Args: - version (str): Version string, i.e. '2.0.1+cpu' - - Returns: - (tuple): Tuple of integers representing the numeric part of the version and the extra string, i.e. (2, 0, 1) - """ - try: - return tuple(map(int, re.findall(r"\d+", version)[:3])) # '2.0.1+cpu' -> (2, 0, 1) - except Exception as e: - LOGGER.warning(f"WARNING ⚠️ failure for parse_version({version}), returning (0, 0, 0): {e}") - return 0, 0, 0 - - -def is_ascii(s) -> bool: - """ - Check if a string is composed of only ASCII characters. - - Args: - s (str): String to be checked. - - Returns: - (bool): True if the string is composed only of ASCII characters, False otherwise. - """ - # Convert list, tuple, None, etc. to string - s = str(s) - - # Check if the string is composed of only ASCII characters - return all(ord(c) < 128 for c in s) - - -def check_imgsz(imgsz, stride=32, min_dim=1, max_dim=2, floor=0): - """ - Verify image size is a multiple of the given stride in each dimension. If the image size is not a multiple of the - stride, update it to the nearest multiple of the stride that is greater than or equal to the given floor value. - - Args: - imgsz (int | cList[int]): Image size. - stride (int): Stride value. - min_dim (int): Minimum number of dimensions. - max_dim (int): Maximum number of dimensions. - floor (int): Minimum allowed value for image size. - - Returns: - (List[int]): Updated image size. - """ - # Convert stride to integer if it is a tensor - stride = int(stride.max() if isinstance(stride, torch.Tensor) else stride) - - # Convert image size to list if it is an integer - if isinstance(imgsz, int): - imgsz = [imgsz] - elif isinstance(imgsz, (list, tuple)): - imgsz = list(imgsz) - else: - raise TypeError( - f"'imgsz={imgsz}' is of invalid type {type(imgsz).__name__}. " - f"Valid imgsz types are int i.e. 'imgsz=640' or list i.e. 'imgsz=[640,640]'" - ) - - # Apply max_dim - if len(imgsz) > max_dim: - msg = ( - "'train' and 'val' imgsz must be an integer, while 'predict' and 'export' imgsz may be a [h, w] list " - "or an integer, i.e. 'yolo export imgsz=640,480' or 'yolo export imgsz=640'" - ) - if max_dim != 1: - raise ValueError(f"imgsz={imgsz} is not a valid image size. {msg}") - LOGGER.warning(f"WARNING ⚠️ updating to 'imgsz={max(imgsz)}'. {msg}") - imgsz = [max(imgsz)] - # Make image size a multiple of the stride - sz = [max(math.ceil(x / stride) * stride, floor) for x in imgsz] - - # Print warning message if image size was updated - if sz != imgsz: - LOGGER.warning(f"WARNING ⚠️ imgsz={imgsz} must be multiple of max stride {stride}, updating to {sz}") - - # Add missing dimensions if necessary - sz = [sz[0], sz[0]] if min_dim == 2 and len(sz) == 1 else sz[0] if min_dim == 1 and len(sz) == 1 else sz - - return sz - - -def check_version( - current: str = "0.0.0", - required: str = "0.0.0", - name: str = "version", - hard: bool = False, - verbose: bool = False, - msg: str = "", -) -> bool: - """ - Check current version against the required version or range. - - Args: - current (str): Current version or package name to get version from. - required (str): Required version or range (in pip-style format). - name (str, optional): Name to be used in warning message. - hard (bool, optional): If True, raise an AssertionError if the requirement is not met. - verbose (bool, optional): If True, print warning message if requirement is not met. - msg (str, optional): Extra message to display if verbose. - - Returns: - (bool): True if requirement is met, False otherwise. - - Example: - ```python - # Check if current version is exactly 22.04 - check_version(current='22.04', required='==22.04') - - # Check if current version is greater than or equal to 22.04 - check_version(current='22.10', required='22.04') # assumes '>=' inequality if none passed - - # Check if current version is less than or equal to 22.04 - check_version(current='22.04', required='<=22.04') - - # Check if current version is between 20.04 (inclusive) and 22.04 (exclusive) - check_version(current='21.10', required='>20.04,<22.04') - ``` - """ - if not current: # if current is '' or None - LOGGER.warning(f"WARNING ⚠️ invalid check_version({current}, {required}) requested, please check values.") - return True - elif not current[0].isdigit(): # current is package name rather than version string, i.e. current='ultralytics' - try: - name = current # assigned package name to 'name' arg - current = metadata.version(current) # get version string from package name - except metadata.PackageNotFoundError as e: - if hard: - raise ModuleNotFoundError(emojis(f"WARNING ⚠️ {current} package is required but not installed")) from e - else: - return False - - if not required: # if required is '' or None - return True - - op = "" - version = "" - result = True - c = parse_version(current) # '1.2.3' -> (1, 2, 3) - for r in required.strip(",").split(","): - op, version = re.match(r"([^0-9]*)([\d.]+)", r).groups() # split '>=22.04' -> ('>=', '22.04') - v = parse_version(version) # '1.2.3' -> (1, 2, 3) - if op == "==" and c != v: - result = False - elif op == "!=" and c == v: - result = False - elif op in (">=", "") and not (c >= v): # if no constraint passed assume '>=required' - result = False - elif op == "<=" and not (c <= v): - result = False - elif op == ">" and not (c > v): - result = False - elif op == "<" and not (c < v): - result = False - if not result: - warning = f"WARNING ⚠️ {name}{op}{version} is required, but {name}=={current} is currently installed {msg}" - if hard: - raise ModuleNotFoundError(emojis(warning)) # assert version requirements met - if verbose: - LOGGER.warning(warning) - return result - - -def check_latest_pypi_version(package_name="ultralytics"): - """ - Returns the latest version of a PyPI package without downloading or installing it. - - Parameters: - package_name (str): The name of the package to find the latest version for. - - Returns: - (str): The latest version of the package. - """ - with contextlib.suppress(Exception): - requests.packages.urllib3.disable_warnings() # Disable the InsecureRequestWarning - response = requests.get(f"https://pypi.org/pypi/{package_name}/json", timeout=3) - if response.status_code == 200: - return response.json()["info"]["version"] - - -def check_pip_update_available(): - """ - Checks if a new version of the ultralytics package is available on PyPI. - - Returns: - (bool): True if an update is available, False otherwise. - """ - if ONLINE and is_pip_package(): - with contextlib.suppress(Exception): - from ultralytics import __version__ - - latest = check_latest_pypi_version() - if check_version(__version__, f"<{latest}"): # check if current version is < latest version - LOGGER.info( - f"New https://pypi.org/project/ultralytics/{latest} available 😃 " - f"Update with 'pip install -U ultralytics'" - ) - return True - return False - - -@ThreadingLocked() -def check_font(font="Arial.ttf"): - """ - Find font locally or download to user's configuration directory if it does not already exist. - - Args: - font (str): Path or name of font. - - Returns: - file (Path): Resolved font file path. - """ - name = Path(font).name - - # Check USER_CONFIG_DIR - file = USER_CONFIG_DIR / name - if file.exists(): - return file - - # Check system fonts - matches = [s for s in font_manager.findSystemFonts() if font in s] - if any(matches): - return matches[0] - - # Download to USER_CONFIG_DIR if missing - url = f"https://ultralytics.com/assets/{name}" - if downloads.is_url(url): - downloads.safe_download(url=url, file=file) - return file - - -def check_python(minimum: str = "3.8.0") -> bool: - """ - Check current python version against the required minimum version. - - Args: - minimum (str): Required minimum version of python. - - Returns: - (bool): Whether the installed Python version meets the minimum constraints. - """ - return check_version(PYTHON_VERSION, minimum, name="Python ", hard=True) - - -@TryExcept() -def check_requirements(requirements=ROOT.parent / "requirements.txt", exclude=(), install=True, cmds=""): - """ - Check if installed dependencies meet YOLOv8 requirements and attempt to auto-update if needed. - - Args: - requirements (Union[Path, str, List[str]]): Path to a requirements.txt file, a single package requirement as a - string, or a list of package requirements as strings. - exclude (Tuple[str]): Tuple of package names to exclude from checking. - install (bool): If True, attempt to auto-update packages that don't meet requirements. - cmds (str): Additional commands to pass to the pip install command when auto-updating. - - Example: - ```python - from ultralytics.utils.checks import check_requirements - - # Check a requirements.txt file - check_requirements('path/to/requirements.txt') - - # Check a single package - check_requirements('ultralytics>=8.0.0') - - # Check multiple packages - check_requirements(['numpy', 'ultralytics>=8.0.0']) - ``` - """ - - prefix = colorstr("red", "bold", "requirements:") - check_python() # check python version - check_torchvision() # check torch-torchvision compatibility - if isinstance(requirements, Path): # requirements.txt file - file = requirements.resolve() - assert file.exists(), f"{prefix} {file} not found, check failed." - requirements = [f"{x.name}{x.specifier}" for x in parse_requirements(file) if x.name not in exclude] - elif isinstance(requirements, str): - requirements = [requirements] - - pkgs = [] - for r in requirements: - r_stripped = r.split("/")[-1].replace(".git", "") # replace git+https://org/repo.git -> 'repo' - match = re.match(r"([a-zA-Z0-9-_]+)([<>!=~]+.*)?", r_stripped) - name, required = match[1], match[2].strip() if match[2] else "" - try: - assert check_version(metadata.version(name), required) # exception if requirements not met - except (AssertionError, metadata.PackageNotFoundError): - pkgs.append(r) - - s = " ".join(f'"{x}"' for x in pkgs) # console string - if s: - if install and AUTOINSTALL: # check environment variable - n = len(pkgs) # number of packages updates - LOGGER.info(f"{prefix} Ultralytics requirement{'s' * (n > 1)} {pkgs} not found, attempting AutoUpdate...") - try: - t = time.time() - assert is_online(), "AutoUpdate skipped (offline)" - LOGGER.info(subprocess.check_output(f"pip install --no-cache {s} {cmds}", shell=True).decode()) - dt = time.time() - t - LOGGER.info( - f"{prefix} AutoUpdate success ✅ {dt:.1f}s, installed {n} package{'s' * (n > 1)}: {pkgs}\n" - f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n" - ) - except Exception as e: - LOGGER.warning(f"{prefix} ❌ {e}") - return False - else: - return False - - return True - - -def check_torchvision(): - """ - Checks the installed versions of PyTorch and Torchvision to ensure they're compatible. - - This function checks the installed versions of PyTorch and Torchvision, and warns if they're incompatible according - to the provided compatibility table based on: - https://github.com/pytorch/vision#installation. - - The compatibility table is a dictionary where the keys are PyTorch versions and the values are lists of compatible - Torchvision versions. - """ - - import torchvision - - # Compatibility table - compatibility_table = {"2.0": ["0.15"], "1.13": ["0.14"], "1.12": ["0.13"]} - - # Extract only the major and minor versions - v_torch = ".".join(torch.__version__.split("+")[0].split(".")[:2]) - v_torchvision = ".".join(torchvision.__version__.split("+")[0].split(".")[:2]) - - if v_torch in compatibility_table: - compatible_versions = compatibility_table[v_torch] - if all(v_torchvision != v for v in compatible_versions): - print( - f"WARNING ⚠️ torchvision=={v_torchvision} is incompatible with torch=={v_torch}.\n" - f"Run 'pip install torchvision=={compatible_versions[0]}' to fix torchvision or " - "'pip install -U torch torchvision' to update both.\n" - "For a full compatibility table see https://github.com/pytorch/vision#installation" - ) - - -def check_suffix(file="yolov8n.pt", suffix=".pt", msg=""): - """Check file(s) for acceptable suffix.""" - if file and suffix: - if isinstance(suffix, str): - suffix = (suffix,) - for f in file if isinstance(file, (list, tuple)) else [file]: - s = Path(f).suffix.lower().strip() # file suffix - if len(s): - assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}, not {s}" - - -def check_yolov5u_filename(file: str, verbose: bool = True): - """Replace legacy YOLOv5 filenames with updated YOLOv5u filenames.""" - if "yolov3" in file or "yolov5" in file: - if "u.yaml" in file: - file = file.replace("u.yaml", ".yaml") # i.e. yolov5nu.yaml -> yolov5n.yaml - elif ".pt" in file and "u" not in file: - original_file = file - file = re.sub(r"(.*yolov5([nsmlx]))\.pt", "\\1u.pt", file) # i.e. yolov5n.pt -> yolov5nu.pt - file = re.sub(r"(.*yolov5([nsmlx])6)\.pt", "\\1u.pt", file) # i.e. yolov5n6.pt -> yolov5n6u.pt - file = re.sub(r"(.*yolov3(|-tiny|-spp))\.pt", "\\1u.pt", file) # i.e. yolov3-spp.pt -> yolov3-sppu.pt - if file != original_file and verbose: - LOGGER.info( - f"PRO TIP 💡 Replace 'model={original_file}' with new 'model={file}'.\nYOLOv5 'u' models are " - f"trained with https://github.com/ultralytics/ultralytics and feature improved performance vs " - f"standard YOLOv5 models trained with https://github.com/ultralytics/yolov5.\n" - ) - return file - - -def check_model_file_from_stem(model="yolov8n"): - """Return a model filename from a valid model stem.""" - if model and not Path(model).suffix and Path(model).stem in downloads.GITHUB_ASSETS_STEMS: - return Path(model).with_suffix(".pt") # add suffix, i.e. yolov8n -> yolov8n.pt - else: - return model - - -def check_file(file, suffix="", download=True, hard=True): - """Search/download file (if necessary) and return path.""" - check_suffix(file, suffix) # optional - file = str(file).strip() # convert to string and strip spaces - file = check_yolov5u_filename(file) # yolov5n -> yolov5nu - if ( - not file - or ("://" not in file and Path(file).exists()) # '://' check required in Windows Python<3.10 - or file.lower().startswith("grpc://") - ): # file exists or gRPC Triton images - return file - elif download and file.lower().startswith(("https://", "http://", "rtsp://", "rtmp://", "tcp://")): # download - url = file # warning: Pathlib turns :// -> :/ - file = url2file(file) # '%2F' to '/', split https://url.com/file.txt?auth - if Path(file).exists(): - LOGGER.info(f"Found {clean_url(url)} locally at {file}") # file already exists - else: - downloads.safe_download(url=url, file=file, unzip=False) - return file - else: # search - files = glob.glob(str(ROOT / "**" / file), recursive=True) or glob.glob(str(ROOT.parent / file)) # find file - if not files and hard: - raise FileNotFoundError(f"'{file}' does not exist") - elif len(files) > 1 and hard: - raise FileNotFoundError(f"Multiple files match '{file}', specify exact path: {files}") - return files[0] if len(files) else [] # return file - - -def check_yaml(file, suffix=(".yaml", ".yml"), hard=True): - """Search/download YAML file (if necessary) and return path, checking suffix.""" - return check_file(file, suffix, hard=hard) - - -def check_is_path_safe(basedir, path): - """ - Check if the resolved path is under the intended directory to prevent path traversal. - - Args: - basedir (Path | str): The intended directory. - path (Path | str): The path to check. - - Returns: - (bool): True if the path is safe, False otherwise. - """ - base_dir_resolved = Path(basedir).resolve() - path_resolved = Path(path).resolve() - - return path_resolved.is_file() and path_resolved.parts[: len(base_dir_resolved.parts)] == base_dir_resolved.parts - - -def check_imshow(warn=False): - """Check if environment supports image displays.""" - try: - if LINUX: - assert "DISPLAY" in os.environ and not is_docker() and not is_colab() and not is_kaggle() - cv2.imshow("test", np.zeros((8, 8, 3), dtype=np.uint8)) # show a small 8-pixel image - cv2.waitKey(1) - cv2.destroyAllWindows() - cv2.waitKey(1) - return True - except Exception as e: - if warn: - LOGGER.warning(f"WARNING ⚠️ Environment does not support cv2.imshow() or PIL Image.show()\n{e}") - return False - - -def check_yolo(verbose=True, device=""): - """Return a human-readable YOLO software and hardware summary.""" - import psutil - - from ultralytics.utils.torch_utils import select_device - - if is_jupyter(): - if check_requirements("wandb", install=False): - os.system("pip uninstall -y wandb") # uninstall wandb: unwanted account creation prompt with infinite hang - if is_colab(): - shutil.rmtree("sample_data", ignore_errors=True) # remove colab /sample_data directory - - if verbose: - # System info - gib = 1 << 30 # bytes per GiB - ram = psutil.virtual_memory().total - total, used, free = shutil.disk_usage("/") - s = f"({os.cpu_count()} CPUs, {ram / gib:.1f} GB RAM, {(total - free) / gib:.1f}/{total / gib:.1f} GB disk)" - with contextlib.suppress(Exception): # clear display if ipython is installed - from IPython import display - - display.clear_output() - else: - s = "" - - select_device(device=device, newline=False) - LOGGER.info(f"Setup complete ✅ {s}") - - -def collect_system_info(): - """Collect and print relevant system information including OS, Python, RAM, CPU, and CUDA.""" - - import psutil - - from ultralytics.utils import ENVIRONMENT, is_git_dir - from ultralytics.utils.torch_utils import get_cpu_info - - ram_info = psutil.virtual_memory().total / (1024**3) # Convert bytes to GB - check_yolo() - LOGGER.info( - f"\n{'OS':<20}{platform.platform()}\n" - f"{'Environment':<20}{ENVIRONMENT}\n" - f"{'Python':<20}{PYTHON_VERSION}\n" - f"{'Install':<20}{'git' if is_git_dir() else 'pip' if is_pip_package() else 'other'}\n" - f"{'RAM':<20}{ram_info:.2f} GB\n" - f"{'CPU':<20}{get_cpu_info()}\n" - f"{'CUDA':<20}{torch.version.cuda if torch and torch.cuda.is_available() else None}\n" - ) - - for r in parse_requirements(package="ultralytics"): - try: - current = metadata.version(r.name) - is_met = "✅ " if check_version(current, str(r.specifier), hard=True) else "❌ " - except metadata.PackageNotFoundError: - current = "(not installed)" - is_met = "❌ " - LOGGER.info(f"{r.name:<20}{is_met}{current}{r.specifier}") - - if is_github_action_running(): - LOGGER.info( - f"\nRUNNER_OS: {os.getenv('RUNNER_OS')}\n" - f"GITHUB_EVENT_NAME: {os.getenv('GITHUB_EVENT_NAME')}\n" - f"GITHUB_WORKFLOW: {os.getenv('GITHUB_WORKFLOW')}\n" - f"GITHUB_ACTOR: {os.getenv('GITHUB_ACTOR')}\n" - f"GITHUB_REPOSITORY: {os.getenv('GITHUB_REPOSITORY')}\n" - f"GITHUB_REPOSITORY_OWNER: {os.getenv('GITHUB_REPOSITORY_OWNER')}\n" - ) - - -def check_amp(model): - """ - This function checks the PyTorch Automatic Mixed Precision (AMP) functionality of a YOLOv8 model. If the checks - fail, it means there are anomalies with AMP on the system that may cause NaN losses or zero-mAP results, so AMP will - be disabled during training. - - Args: - model (nn.Module): A YOLOv8 model instance. - - Example: - ```python - from ultralytics import YOLO - from ultralytics.utils.checks import check_amp - - model = YOLO('yolov8n.pt').model.cuda() - check_amp(model) - ``` - - Returns: - (bool): Returns True if the AMP functionality works correctly with YOLOv8 model, else False. - """ - device = next(model.parameters()).device # get model device - if device.type in ("cpu", "mps"): - return False # AMP only used on CUDA devices - - def amp_allclose(m, im): - """All close FP32 vs AMP results.""" - a = m(im, device=device, verbose=False)[0].boxes.data # FP32 inference - with torch.cuda.amp.autocast(True): - b = m(im, device=device, verbose=False)[0].boxes.data # AMP inference - del m - return a.shape == b.shape and torch.allclose(a, b.float(), atol=0.5) # close to 0.5 absolute tolerance - - im = ASSETS / "bus.jpg" # image to check - prefix = colorstr("AMP: ") - LOGGER.info(f"{prefix}running Automatic Mixed Precision (AMP) checks with YOLOv8n...") - warning_msg = "Setting 'amp=True'. If you experience zero-mAP or NaN losses you can disable AMP with amp=False." - try: - from ultralytics import YOLO - - assert amp_allclose(YOLO("yolov8n.pt"), im) - LOGGER.info(f"{prefix}checks passed ✅") - except ConnectionError: - LOGGER.warning(f"{prefix}checks skipped ⚠️, offline and unable to download YOLOv8n. {warning_msg}") - except (AttributeError, ModuleNotFoundError): - LOGGER.warning( - f"{prefix}checks skipped ⚠️. " - f"Unable to load YOLOv8n due to possible Ultralytics package modifications. {warning_msg}" - ) - except AssertionError: - LOGGER.warning( - f"{prefix}checks failed ❌. Anomalies were detected with AMP on your system that may lead to " - f"NaN losses or zero-mAP results, so AMP will be disabled during training." - ) - return False - return True - - -def git_describe(path=ROOT): # path must be a directory - """Return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe.""" - with contextlib.suppress(Exception): - return subprocess.check_output(f"git -C {path} describe --tags --long --always", shell=True).decode()[:-1] - return "" - - -def print_args(args: Optional[dict] = None, show_file=True, show_func=False): - """Print function arguments (optional args dict).""" - - def strip_auth(v): - """Clean longer Ultralytics HUB URLs by stripping potential authentication information.""" - return clean_url(v) if (isinstance(v, str) and v.startswith("http") and len(v) > 100) else v - - x = inspect.currentframe().f_back # previous frame - file, _, func, _, _ = inspect.getframeinfo(x) - if args is None: # get args automatically - args, _, _, frm = inspect.getargvalues(x) - args = {k: v for k, v in frm.items() if k in args} - try: - file = Path(file).resolve().relative_to(ROOT).with_suffix("") - except ValueError: - file = Path(file).stem - s = (f"{file}: " if show_file else "") + (f"{func}: " if show_func else "") - LOGGER.info(colorstr(s) + ", ".join(f"{k}={strip_auth(v)}" for k, v in args.items())) - - -def cuda_device_count() -> int: - """ - Get the number of NVIDIA GPUs available in the environment. - - Returns: - (int): The number of NVIDIA GPUs available. - """ - try: - # Run the nvidia-smi command and capture its output - output = subprocess.check_output( - ["nvidia-smi", "--query-gpu=count", "--format=csv,noheader,nounits"], encoding="utf-8" - ) - - # Take the first line and strip any leading/trailing white space - first_line = output.strip().split("\n")[0] - - return int(first_line) - except (subprocess.CalledProcessError, FileNotFoundError, ValueError): - # If the command fails, nvidia-smi is not found, or output is not an integer, assume no GPUs are available - return 0 - - -def cuda_is_available() -> bool: - """ - Check if CUDA is available in the environment. - - Returns: - (bool): True if one or more NVIDIA GPUs are available, False otherwise. - """ - return cuda_device_count() > 0 - - -# Define constants -IS_PYTHON_3_12 = check_version(PYTHON_VERSION, "==3.12", name="Python ", hard=False) diff --git a/ultralytics-main/ultralytics/utils/dist.py b/ultralytics-main/ultralytics/utils/dist.py deleted file mode 100644 index b669e52..0000000 --- a/ultralytics-main/ultralytics/utils/dist.py +++ /dev/null @@ -1,71 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import os -import shutil -import socket -import sys -import tempfile - -from . import USER_CONFIG_DIR -from .torch_utils import TORCH_1_9 - - -def find_free_network_port() -> int: - """ - Finds a free port on localhost. - - It is useful in single-node training when we don't want to connect to a real main node but have to set the - `MASTER_PORT` environment variable. - """ - with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: - s.bind(("127.0.0.1", 0)) - return s.getsockname()[1] # port - - -def generate_ddp_file(trainer): - """Generates a DDP file and returns its file name.""" - module, name = f"{trainer.__class__.__module__}.{trainer.__class__.__name__}".rsplit(".", 1) - - content = f""" -# Ultralytics Multi-GPU training temp file (should be automatically deleted after use) -overrides = {vars(trainer.args)} - -if __name__ == "__main__": - from {module} import {name} - from ultralytics.utils import DEFAULT_CFG_DICT - - cfg = DEFAULT_CFG_DICT.copy() - cfg.update(save_dir='') # handle the extra key 'save_dir' - trainer = {name}(cfg=cfg, overrides=overrides) - results = trainer.train() -""" - (USER_CONFIG_DIR / "DDP").mkdir(exist_ok=True) - with tempfile.NamedTemporaryFile( - prefix="_temp_", - suffix=f"{id(trainer)}.py", - mode="w+", - encoding="utf-8", - dir=USER_CONFIG_DIR / "DDP", - delete=False, - ) as file: - file.write(content) - return file.name - - -def generate_ddp_command(world_size, trainer): - """Generates and returns command for distributed training.""" - import __main__ # noqa local import to avoid https://github.com/Lightning-AI/lightning/issues/15218 - - if not trainer.resume: - shutil.rmtree(trainer.save_dir) # remove the save_dir - file = generate_ddp_file(trainer) - dist_cmd = "torch.distributed.run" if TORCH_1_9 else "torch.distributed.launch" - port = find_free_network_port() - cmd = [sys.executable, "-m", dist_cmd, "--nproc_per_node", f"{world_size}", "--master_port", f"{port}", file] - return cmd, file - - -def ddp_cleanup(trainer, file): - """Delete temp file if created.""" - if f"{id(trainer)}.py" in file: # if temp_file suffix in file - os.remove(file) diff --git a/ultralytics-main/ultralytics/utils/downloads.py b/ultralytics-main/ultralytics/utils/downloads.py deleted file mode 100644 index c9c33a8..0000000 --- a/ultralytics-main/ultralytics/utils/downloads.py +++ /dev/null @@ -1,500 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import re -import shutil -import subprocess -from itertools import repeat -from multiprocessing.pool import ThreadPool -from pathlib import Path -from urllib import parse, request - -import requests -import torch - -from ultralytics.utils import LOGGER, TQDM, checks, clean_url, emojis, is_online, url2file - -# Define Ultralytics GitHub assets maintained at https://github.com/ultralytics/assets -GITHUB_ASSETS_REPO = "ultralytics/assets" -GITHUB_ASSETS_NAMES = ( - [f"yolov8{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb")] - + [f"yolov5{k}{resolution}u.pt" for k in "nsmlx" for resolution in ("", "6")] - + [f"yolov3{k}u.pt" for k in ("", "-spp", "-tiny")] - + [f"yolov8{k}-world.pt" for k in "smlx"] - + [f"yolov8{k}-worldv2.pt" for k in "smlx"] - + [f"yolov9{k}.pt" for k in "ce"] - + [f"yolo_nas_{k}.pt" for k in "sml"] - + [f"sam_{k}.pt" for k in "bl"] - + [f"FastSAM-{k}.pt" for k in "sx"] - + [f"rtdetr-{k}.pt" for k in "lx"] - + ["mobile_sam.pt"] - + ["calibration_image_sample_data_20x128x128x3_float32.npy.zip"] -) -GITHUB_ASSETS_STEMS = [Path(k).stem for k in GITHUB_ASSETS_NAMES] - - -def is_url(url, check=True): - """ - Validates if the given string is a URL and optionally checks if the URL exists online. - - Args: - url (str): The string to be validated as a URL. - check (bool, optional): If True, performs an additional check to see if the URL exists online. - Defaults to True. - - Returns: - (bool): Returns True for a valid URL. If 'check' is True, also returns True if the URL exists online. - Returns False otherwise. - - Example: - ```python - valid = is_url("https://www.example.com") - ``` - """ - with contextlib.suppress(Exception): - url = str(url) - result = parse.urlparse(url) - assert all([result.scheme, result.netloc]) # check if is url - if check: - with request.urlopen(url) as response: - return response.getcode() == 200 # check if exists online - return True - return False - - -def delete_dsstore(path, files_to_delete=(".DS_Store", "__MACOSX")): - """ - Deletes all ".DS_store" files under a specified directory. - - Args: - path (str, optional): The directory path where the ".DS_store" files should be deleted. - files_to_delete (tuple): The files to be deleted. - - Example: - ```python - from ultralytics.utils.downloads import delete_dsstore - - delete_dsstore('path/to/dir') - ``` - - Note: - ".DS_store" files are created by the Apple operating system and contain metadata about folders and files. They - are hidden system files and can cause issues when transferring files between different operating systems. - """ - for file in files_to_delete: - matches = list(Path(path).rglob(file)) - LOGGER.info(f"Deleting {file} files: {matches}") - for f in matches: - f.unlink() - - -def zip_directory(directory, compress=True, exclude=(".DS_Store", "__MACOSX"), progress=True): - """ - Zips the contents of a directory, excluding files containing strings in the exclude list. The resulting zip file is - named after the directory and placed alongside it. - - Args: - directory (str | Path): The path to the directory to be zipped. - compress (bool): Whether to compress the files while zipping. Default is True. - exclude (tuple, optional): A tuple of filename strings to be excluded. Defaults to ('.DS_Store', '__MACOSX'). - progress (bool, optional): Whether to display a progress bar. Defaults to True. - - Returns: - (Path): The path to the resulting zip file. - - Example: - ```python - from ultralytics.utils.downloads import zip_directory - - file = zip_directory('path/to/dir') - ``` - """ - from zipfile import ZIP_DEFLATED, ZIP_STORED, ZipFile - - delete_dsstore(directory) - directory = Path(directory) - if not directory.is_dir(): - raise FileNotFoundError(f"Directory '{directory}' does not exist.") - - # Unzip with progress bar - files_to_zip = [f for f in directory.rglob("*") if f.is_file() and all(x not in f.name for x in exclude)] - zip_file = directory.with_suffix(".zip") - compression = ZIP_DEFLATED if compress else ZIP_STORED - with ZipFile(zip_file, "w", compression) as f: - for file in TQDM(files_to_zip, desc=f"Zipping {directory} to {zip_file}...", unit="file", disable=not progress): - f.write(file, file.relative_to(directory)) - - return zip_file # return path to zip file - - -def unzip_file(file, path=None, exclude=(".DS_Store", "__MACOSX"), exist_ok=False, progress=True): - """ - Unzips a *.zip file to the specified path, excluding files containing strings in the exclude list. - - If the zipfile does not contain a single top-level directory, the function will create a new - directory with the same name as the zipfile (without the extension) to extract its contents. - If a path is not provided, the function will use the parent directory of the zipfile as the default path. - - Args: - file (str): The path to the zipfile to be extracted. - path (str, optional): The path to extract the zipfile to. Defaults to None. - exclude (tuple, optional): A tuple of filename strings to be excluded. Defaults to ('.DS_Store', '__MACOSX'). - exist_ok (bool, optional): Whether to overwrite existing contents if they exist. Defaults to False. - progress (bool, optional): Whether to display a progress bar. Defaults to True. - - Raises: - BadZipFile: If the provided file does not exist or is not a valid zipfile. - - Returns: - (Path): The path to the directory where the zipfile was extracted. - - Example: - ```python - from ultralytics.utils.downloads import unzip_file - - dir = unzip_file('path/to/file.zip') - ``` - """ - from zipfile import BadZipFile, ZipFile, is_zipfile - - if not (Path(file).exists() and is_zipfile(file)): - raise BadZipFile(f"File '{file}' does not exist or is a bad zip file.") - if path is None: - path = Path(file).parent # default path - - # Unzip the file contents - with ZipFile(file) as zipObj: - files = [f for f in zipObj.namelist() if all(x not in f for x in exclude)] - top_level_dirs = {Path(f).parts[0] for f in files} - - if len(top_level_dirs) > 1 or (len(files) > 1 and not files[0].endswith("/")): - # Zip has multiple files at top level - path = extract_path = Path(path) / Path(file).stem # i.e. ../datasets/coco8 - else: - # Zip has 1 top-level directory - extract_path = path # i.e. ../datasets - path = Path(path) / list(top_level_dirs)[0] # i.e. ../datasets/coco8 - - # Check if destination directory already exists and contains files - if path.exists() and any(path.iterdir()) and not exist_ok: - # If it exists and is not empty, return the path without unzipping - LOGGER.warning(f"WARNING ⚠️ Skipping {file} unzip as destination directory {path} is not empty.") - return path - - for f in TQDM(files, desc=f"Unzipping {file} to {Path(path).resolve()}...", unit="file", disable=not progress): - # Ensure the file is within the extract_path to avoid path traversal security vulnerability - if ".." in Path(f).parts: - LOGGER.warning(f"Potentially insecure file path: {f}, skipping extraction.") - continue - zipObj.extract(f, extract_path) - - return path # return unzip dir - - -def check_disk_space(url="https://ultralytics.com/assets/coco128.zip", path=Path.cwd(), sf=1.5, hard=True): - """ - Check if there is sufficient disk space to download and store a file. - - Args: - url (str, optional): The URL to the file. Defaults to 'https://ultralytics.com/assets/coco128.zip'. - path (str | Path, optional): The path or drive to check the available free space on. - sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 2.0. - hard (bool, optional): Whether to throw an error or not on insufficient disk space. Defaults to True. - - Returns: - (bool): True if there is sufficient disk space, False otherwise. - """ - try: - r = requests.head(url) # response - assert r.status_code < 400, f"URL error for {url}: {r.status_code} {r.reason}" # check response - except Exception: - return True # requests issue, default to True - - # Check file size - gib = 1 << 30 # bytes per GiB - data = int(r.headers.get("Content-Length", 0)) / gib # file size (GB) - total, used, free = (x / gib for x in shutil.disk_usage(path)) # bytes - - if data * sf < free: - return True # sufficient space - - # Insufficient space - text = ( - f"WARNING ⚠️ Insufficient free disk space {free:.1f} GB < {data * sf:.3f} GB required, " - f"Please free {data * sf - free:.1f} GB additional disk space and try again." - ) - if hard: - raise MemoryError(text) - LOGGER.warning(text) - return False - - -def get_google_drive_file_info(link): - """ - Retrieves the direct download link and filename for a shareable Google Drive file link. - - Args: - link (str): The shareable link of the Google Drive file. - - Returns: - (str): Direct download URL for the Google Drive file. - (str): Original filename of the Google Drive file. If filename extraction fails, returns None. - - Example: - ```python - from ultralytics.utils.downloads import get_google_drive_file_info - - link = "https://drive.google.com/file/d/1cqT-cJgANNrhIHCrEufUYhQ4RqiWG_lJ/view?usp=drive_link" - url, filename = get_google_drive_file_info(link) - ``` - """ - file_id = link.split("/d/")[1].split("/view")[0] - drive_url = f"https://drive.google.com/uc?export=download&id={file_id}" - filename = None - - # Start session - with requests.Session() as session: - response = session.get(drive_url, stream=True) - if "quota exceeded" in str(response.content.lower()): - raise ConnectionError( - emojis( - f"❌ Google Drive file download quota exceeded. " - f"Please try again later or download this file manually at {link}." - ) - ) - for k, v in response.cookies.items(): - if k.startswith("download_warning"): - drive_url += f"&confirm={v}" # v is token - cd = response.headers.get("content-disposition") - if cd: - filename = re.findall('filename="(.+)"', cd)[0] - return drive_url, filename - - -def safe_download( - url, - file=None, - dir=None, - unzip=True, - delete=False, - curl=False, - retry=3, - min_bytes=1e0, - exist_ok=False, - progress=True, -): - """ - Downloads files from a URL, with options for retrying, unzipping, and deleting the downloaded file. - - Args: - url (str): The URL of the file to be downloaded. - file (str, optional): The filename of the downloaded file. - If not provided, the file will be saved with the same name as the URL. - dir (str, optional): The directory to save the downloaded file. - If not provided, the file will be saved in the current working directory. - unzip (bool, optional): Whether to unzip the downloaded file. Default: True. - delete (bool, optional): Whether to delete the downloaded file after unzipping. Default: False. - curl (bool, optional): Whether to use curl command line tool for downloading. Default: False. - retry (int, optional): The number of times to retry the download in case of failure. Default: 3. - min_bytes (float, optional): The minimum number of bytes that the downloaded file should have, to be considered - a successful download. Default: 1E0. - exist_ok (bool, optional): Whether to overwrite existing contents during unzipping. Defaults to False. - progress (bool, optional): Whether to display a progress bar during the download. Default: True. - - Example: - ```python - from ultralytics.utils.downloads import safe_download - - link = "https://ultralytics.com/assets/bus.jpg" - path = safe_download(link) - ``` - """ - gdrive = url.startswith("https://drive.google.com/") # check if the URL is a Google Drive link - if gdrive: - url, file = get_google_drive_file_info(url) - - f = Path(dir or ".") / (file or url2file(url)) # URL converted to filename - if "://" not in str(url) and Path(url).is_file(): # URL exists ('://' check required in Windows Python<3.10) - f = Path(url) # filename - elif not f.is_file(): # URL and file do not exist - desc = f"Downloading {url if gdrive else clean_url(url)} to '{f}'" - LOGGER.info(f"{desc}...") - f.parent.mkdir(parents=True, exist_ok=True) # make directory if missing - check_disk_space(url, path=f.parent) - for i in range(retry + 1): - try: - if curl or i > 0: # curl download with retry, continue - s = "sS" * (not progress) # silent - r = subprocess.run(["curl", "-#", f"-{s}L", url, "-o", f, "--retry", "3", "-C", "-"]).returncode - assert r == 0, f"Curl return value {r}" - else: # urllib download - method = "torch" - if method == "torch": - torch.hub.download_url_to_file(url, f, progress=progress) - else: - with request.urlopen(url) as response, TQDM( - total=int(response.getheader("Content-Length", 0)), - desc=desc, - disable=not progress, - unit="B", - unit_scale=True, - unit_divisor=1024, - ) as pbar: - with open(f, "wb") as f_opened: - for data in response: - f_opened.write(data) - pbar.update(len(data)) - - if f.exists(): - if f.stat().st_size > min_bytes: - break # success - f.unlink() # remove partial downloads - except Exception as e: - if i == 0 and not is_online(): - raise ConnectionError(emojis(f"❌ Download failure for {url}. Environment is not online.")) from e - elif i >= retry: - raise ConnectionError(emojis(f"❌ Download failure for {url}. Retry limit reached.")) from e - LOGGER.warning(f"⚠️ Download failure, retrying {i + 1}/{retry} {url}...") - - if unzip and f.exists() and f.suffix in ("", ".zip", ".tar", ".gz"): - from zipfile import is_zipfile - - unzip_dir = (dir or f.parent).resolve() # unzip to dir if provided else unzip in place - if is_zipfile(f): - unzip_dir = unzip_file(file=f, path=unzip_dir, exist_ok=exist_ok, progress=progress) # unzip - elif f.suffix in (".tar", ".gz"): - LOGGER.info(f"Unzipping {f} to {unzip_dir}...") - subprocess.run(["tar", "xf" if f.suffix == ".tar" else "xfz", f, "--directory", unzip_dir], check=True) - if delete: - f.unlink() # remove zip - return unzip_dir - - -def get_github_assets(repo="ultralytics/assets", version="latest", retry=False): - """ - Retrieve the specified version's tag and assets from a GitHub repository. If the version is not specified, the - function fetches the latest release assets. - - Args: - repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'. - version (str, optional): The release version to fetch assets from. Defaults to 'latest'. - retry (bool, optional): Flag to retry the request in case of a failure. Defaults to False. - - Returns: - (tuple): A tuple containing the release tag and a list of asset names. - - Example: - ```python - tag, assets = get_github_assets(repo='ultralytics/assets', version='latest') - ``` - """ - - if version != "latest": - version = f"tags/{version}" # i.e. tags/v6.2 - url = f"https://api.github.com/repos/{repo}/releases/{version}" - r = requests.get(url) # github api - if r.status_code != 200 and r.reason != "rate limit exceeded" and retry: # failed and not 403 rate limit exceeded - r = requests.get(url) # try again - if r.status_code != 200: - LOGGER.warning(f"⚠️ GitHub assets check failure for {url}: {r.status_code} {r.reason}") - return "", [] - data = r.json() - return data["tag_name"], [x["name"] for x in data["assets"]] # tag, assets i.e. ['yolov8n.pt', 'yolov8s.pt', ...] - - -def attempt_download_asset(file, repo="ultralytics/assets", release="v8.1.0", **kwargs): - """ - Attempt to download a file from GitHub release assets if it is not found locally. The function checks for the file - locally first, then tries to download it from the specified GitHub repository release. - - Args: - file (str | Path): The filename or file path to be downloaded. - repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'. - release (str, optional): The specific release version to be downloaded. Defaults to 'v8.1.0'. - **kwargs (any): Additional keyword arguments for the download process. - - Returns: - (str): The path to the downloaded file. - - Example: - ```python - file_path = attempt_download_asset('yolov5s.pt', repo='ultralytics/assets', release='latest') - ``` - """ - from ultralytics.utils import SETTINGS # scoped for circular import - - # YOLOv3/5u updates - file = str(file) - file = checks.check_yolov5u_filename(file) - file = Path(file.strip().replace("'", "")) - if file.exists(): - return str(file) - elif (SETTINGS["weights_dir"] / file).exists(): - return str(SETTINGS["weights_dir"] / file) - else: - # URL specified - name = Path(parse.unquote(str(file))).name # decode '%2F' to '/' etc. - download_url = f"https://github.com/{repo}/releases/download" - if str(file).startswith(("http:/", "https:/")): # download - url = str(file).replace(":/", "://") # Pathlib turns :// -> :/ - file = url2file(name) # parse authentication https://url.com/file.txt?auth... - if Path(file).is_file(): - LOGGER.info(f"Found {clean_url(url)} locally at {file}") # file already exists - else: - safe_download(url=url, file=file, min_bytes=1e5, **kwargs) - - elif repo == GITHUB_ASSETS_REPO and name in GITHUB_ASSETS_NAMES: - safe_download(url=f"{download_url}/{release}/{name}", file=file, min_bytes=1e5, **kwargs) - - else: - tag, assets = get_github_assets(repo, release) - if not assets: - tag, assets = get_github_assets(repo) # latest release - if name in assets: - safe_download(url=f"{download_url}/{tag}/{name}", file=file, min_bytes=1e5, **kwargs) - - return str(file) - - -def download(url, dir=Path.cwd(), unzip=True, delete=False, curl=False, threads=1, retry=3, exist_ok=False): - """ - Downloads files from specified URLs to a given directory. Supports concurrent downloads if multiple threads are - specified. - - Args: - url (str | list): The URL or list of URLs of the files to be downloaded. - dir (Path, optional): The directory where the files will be saved. Defaults to the current working directory. - unzip (bool, optional): Flag to unzip the files after downloading. Defaults to True. - delete (bool, optional): Flag to delete the zip files after extraction. Defaults to False. - curl (bool, optional): Flag to use curl for downloading. Defaults to False. - threads (int, optional): Number of threads to use for concurrent downloads. Defaults to 1. - retry (int, optional): Number of retries in case of download failure. Defaults to 3. - exist_ok (bool, optional): Whether to overwrite existing contents during unzipping. Defaults to False. - - Example: - ```python - download('https://ultralytics.com/assets/example.zip', dir='path/to/dir', unzip=True) - ``` - """ - dir = Path(dir) - dir.mkdir(parents=True, exist_ok=True) # make directory - if threads > 1: - with ThreadPool(threads) as pool: - pool.map( - lambda x: safe_download( - url=x[0], - dir=x[1], - unzip=unzip, - delete=delete, - curl=curl, - retry=retry, - exist_ok=exist_ok, - progress=threads <= 1, - ), - zip(url, repeat(dir)), - ) - pool.close() - pool.join() - else: - for u in [url] if isinstance(url, (str, Path)) else url: - safe_download(url=u, dir=dir, unzip=unzip, delete=delete, curl=curl, retry=retry, exist_ok=exist_ok) diff --git a/ultralytics-main/ultralytics/utils/errors.py b/ultralytics-main/ultralytics/utils/errors.py deleted file mode 100644 index 86aee1d..0000000 --- a/ultralytics-main/ultralytics/utils/errors.py +++ /dev/null @@ -1,22 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from ultralytics.utils import emojis - - -class HUBModelError(Exception): - """ - Custom exception class for handling errors related to model fetching in Ultralytics YOLO. - - This exception is raised when a requested model is not found or cannot be retrieved. - The message is also processed to include emojis for better user experience. - - Attributes: - message (str): The error message displayed when the exception is raised. - - Note: - The message is automatically processed through the 'emojis' function from the 'ultralytics.utils' package. - """ - - def __init__(self, message="Model not found. Please check model URL and try again."): - """Create an exception for when a model is not found.""" - super().__init__(emojis(message)) diff --git a/ultralytics-main/ultralytics/utils/files.py b/ultralytics-main/ultralytics/utils/files.py deleted file mode 100644 index 719caca..0000000 --- a/ultralytics-main/ultralytics/utils/files.py +++ /dev/null @@ -1,188 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import glob -import os -import shutil -import tempfile -from contextlib import contextmanager -from datetime import datetime -from pathlib import Path - - -class WorkingDirectory(contextlib.ContextDecorator): - """Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager.""" - - def __init__(self, new_dir): - """Sets the working directory to 'new_dir' upon instantiation.""" - self.dir = new_dir # new dir - self.cwd = Path.cwd().resolve() # current dir - - def __enter__(self): - """Changes the current directory to the specified directory.""" - os.chdir(self.dir) - - def __exit__(self, exc_type, exc_val, exc_tb): # noqa - """Restore the current working directory on context exit.""" - os.chdir(self.cwd) - - -@contextmanager -def spaces_in_path(path): - """ - Context manager to handle paths with spaces in their names. If a path contains spaces, it replaces them with - underscores, copies the file/directory to the new path, executes the context code block, then copies the - file/directory back to its original location. - - Args: - path (str | Path): The original path. - - Yields: - (Path): Temporary path with spaces replaced by underscores if spaces were present, otherwise the original path. - - Example: - ```python - with ultralytics.utils.files import spaces_in_path - - with spaces_in_path('/path/with spaces') as new_path: - # Your code here - ``` - """ - - # If path has spaces, replace them with underscores - if " " in str(path): - string = isinstance(path, str) # input type - path = Path(path) - - # Create a temporary directory and construct the new path - with tempfile.TemporaryDirectory() as tmp_dir: - tmp_path = Path(tmp_dir) / path.name.replace(" ", "_") - - # Copy file/directory - if path.is_dir(): - # tmp_path.mkdir(parents=True, exist_ok=True) - shutil.copytree(path, tmp_path) - elif path.is_file(): - tmp_path.parent.mkdir(parents=True, exist_ok=True) - shutil.copy2(path, tmp_path) - - try: - # Yield the temporary path - yield str(tmp_path) if string else tmp_path - - finally: - # Copy file/directory back - if tmp_path.is_dir(): - shutil.copytree(tmp_path, path, dirs_exist_ok=True) - elif tmp_path.is_file(): - shutil.copy2(tmp_path, path) # Copy back the file - - else: - # If there are no spaces, just yield the original path - yield path - - -def increment_path(path, exist_ok=False, sep="", mkdir=False): - """ - Increments a file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. - - If the path exists and exist_ok is not set to True, the path will be incremented by appending a number and sep to - the end of the path. If the path is a file, the file extension will be preserved. If the path is a directory, the - number will be appended directly to the end of the path. If mkdir is set to True, the path will be created as a - directory if it does not already exist. - - Args: - path (str, pathlib.Path): Path to increment. - exist_ok (bool, optional): If True, the path will not be incremented and returned as-is. Defaults to False. - sep (str, optional): Separator to use between the path and the incrementation number. Defaults to ''. - mkdir (bool, optional): Create a directory if it does not exist. Defaults to False. - - Returns: - (pathlib.Path): Incremented path. - """ - path = Path(path) # os-agnostic - if path.exists() and not exist_ok: - path, suffix = (path.with_suffix(""), path.suffix) if path.is_file() else (path, "") - - # Method 1 - for n in range(2, 9999): - p = f"{path}{sep}{n}{suffix}" # increment path - if not os.path.exists(p): - break - path = Path(p) - - if mkdir: - path.mkdir(parents=True, exist_ok=True) # make directory - - return path - - -def file_age(path=__file__): - """Return days since last file update.""" - dt = datetime.now() - datetime.fromtimestamp(Path(path).stat().st_mtime) # delta - return dt.days # + dt.seconds / 86400 # fractional days - - -def file_date(path=__file__): - """Return human-readable file modification date, i.e. '2021-3-26'.""" - t = datetime.fromtimestamp(Path(path).stat().st_mtime) - return f"{t.year}-{t.month}-{t.day}" - - -def file_size(path): - """Return file/dir size (MB).""" - if isinstance(path, (str, Path)): - mb = 1 << 20 # bytes to MiB (1024 ** 2) - path = Path(path) - if path.is_file(): - return path.stat().st_size / mb - elif path.is_dir(): - return sum(f.stat().st_size for f in path.glob("**/*") if f.is_file()) / mb - return 0.0 - - -def get_latest_run(search_dir="."): - """Return path to most recent 'last.pt' in /runs (i.e. to --resume from).""" - last_list = glob.glob(f"{search_dir}/**/last*.pt", recursive=True) - return max(last_list, key=os.path.getctime) if last_list else "" - - -def update_models(model_names=("yolov8n.pt",), source_dir=Path("."), update_names=False): - """ - Updates and re-saves specified YOLO models in an 'updated_models' subdirectory. - - Args: - model_names (tuple, optional): Model filenames to update, defaults to ("yolov8n.pt"). - source_dir (Path, optional): Directory containing models and target subdirectory, defaults to current directory. - update_names (bool, optional): Update model names from a data YAML. - - Example: - ```python - from ultralytics.utils.files import update_models - - model_names = (f"rtdetr-{size}.pt" for size in "lx") - update_models(model_names) - ``` - """ - from ultralytics import YOLO - from ultralytics.nn.autobackend import default_class_names - - target_dir = source_dir / "updated_models" - target_dir.mkdir(parents=True, exist_ok=True) # Ensure target directory exists - - for model_name in model_names: - model_path = source_dir / model_name - print(f"Loading model from {model_path}") - - # Load model - model = YOLO(model_path) - model.half() - if update_names: # update model names from a dataset YAML - model.model.names = default_class_names("coco8.yaml") - - # Define new save path - save_path = target_dir / model_name - - # Save model using model.save() - print(f"Re-saving {model_name} model to {save_path}") - model.save(save_path, use_dill=False) diff --git a/ultralytics-main/ultralytics/utils/instance.py b/ultralytics-main/ultralytics/utils/instance.py deleted file mode 100644 index 4e9ef2c..0000000 --- a/ultralytics-main/ultralytics/utils/instance.py +++ /dev/null @@ -1,407 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from collections import abc -from itertools import repeat -from numbers import Number -from typing import List - -import numpy as np - -from .ops import ltwh2xywh, ltwh2xyxy, xywh2ltwh, xywh2xyxy, xyxy2ltwh, xyxy2xywh - - -def _ntuple(n): - """From PyTorch internals.""" - - def parse(x): - """Parse bounding boxes format between XYWH and LTWH.""" - return x if isinstance(x, abc.Iterable) else tuple(repeat(x, n)) - - return parse - - -to_2tuple = _ntuple(2) -to_4tuple = _ntuple(4) - -# `xyxy` means left top and right bottom -# `xywh` means center x, center y and width, height(YOLO format) -# `ltwh` means left top and width, height(COCO format) -_formats = ["xyxy", "xywh", "ltwh"] - -__all__ = ("Bboxes",) # tuple or list - - -class Bboxes: - """ - A class for handling bounding boxes. - - The class supports various bounding box formats like 'xyxy', 'xywh', and 'ltwh'. - Bounding box data should be provided in numpy arrays. - - Attributes: - bboxes (numpy.ndarray): The bounding boxes stored in a 2D numpy array. - format (str): The format of the bounding boxes ('xyxy', 'xywh', or 'ltwh'). - - Note: - This class does not handle normalization or denormalization of bounding boxes. - """ - - def __init__(self, bboxes, format="xyxy") -> None: - """Initializes the Bboxes class with bounding box data in a specified format.""" - assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}" - bboxes = bboxes[None, :] if bboxes.ndim == 1 else bboxes - assert bboxes.ndim == 2 - assert bboxes.shape[1] == 4 - self.bboxes = bboxes - self.format = format - # self.normalized = normalized - - def convert(self, format): - """Converts bounding box format from one type to another.""" - assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}" - if self.format == format: - return - elif self.format == "xyxy": - func = xyxy2xywh if format == "xywh" else xyxy2ltwh - elif self.format == "xywh": - func = xywh2xyxy if format == "xyxy" else xywh2ltwh - else: - func = ltwh2xyxy if format == "xyxy" else ltwh2xywh - self.bboxes = func(self.bboxes) - self.format = format - - def areas(self): - """Return box areas.""" - self.convert("xyxy") - return (self.bboxes[:, 2] - self.bboxes[:, 0]) * (self.bboxes[:, 3] - self.bboxes[:, 1]) - - # def denormalize(self, w, h): - # if not self.normalized: - # return - # assert (self.bboxes <= 1.0).all() - # self.bboxes[:, 0::2] *= w - # self.bboxes[:, 1::2] *= h - # self.normalized = False - # - # def normalize(self, w, h): - # if self.normalized: - # return - # assert (self.bboxes > 1.0).any() - # self.bboxes[:, 0::2] /= w - # self.bboxes[:, 1::2] /= h - # self.normalized = True - - def mul(self, scale): - """ - Args: - scale (tuple | list | int): the scale for four coords. - """ - if isinstance(scale, Number): - scale = to_4tuple(scale) - assert isinstance(scale, (tuple, list)) - assert len(scale) == 4 - self.bboxes[:, 0] *= scale[0] - self.bboxes[:, 1] *= scale[1] - self.bboxes[:, 2] *= scale[2] - self.bboxes[:, 3] *= scale[3] - - def add(self, offset): - """ - Args: - offset (tuple | list | int): the offset for four coords. - """ - if isinstance(offset, Number): - offset = to_4tuple(offset) - assert isinstance(offset, (tuple, list)) - assert len(offset) == 4 - self.bboxes[:, 0] += offset[0] - self.bboxes[:, 1] += offset[1] - self.bboxes[:, 2] += offset[2] - self.bboxes[:, 3] += offset[3] - - def __len__(self): - """Return the number of boxes.""" - return len(self.bboxes) - - @classmethod - def concatenate(cls, boxes_list: List["Bboxes"], axis=0) -> "Bboxes": - """ - Concatenate a list of Bboxes objects into a single Bboxes object. - - Args: - boxes_list (List[Bboxes]): A list of Bboxes objects to concatenate. - axis (int, optional): The axis along which to concatenate the bounding boxes. - Defaults to 0. - - Returns: - Bboxes: A new Bboxes object containing the concatenated bounding boxes. - - Note: - The input should be a list or tuple of Bboxes objects. - """ - assert isinstance(boxes_list, (list, tuple)) - if not boxes_list: - return cls(np.empty(0)) - assert all(isinstance(box, Bboxes) for box in boxes_list) - - if len(boxes_list) == 1: - return boxes_list[0] - return cls(np.concatenate([b.bboxes for b in boxes_list], axis=axis)) - - def __getitem__(self, index) -> "Bboxes": - """ - Retrieve a specific bounding box or a set of bounding boxes using indexing. - - Args: - index (int, slice, or np.ndarray): The index, slice, or boolean array to select - the desired bounding boxes. - - Returns: - Bboxes: A new Bboxes object containing the selected bounding boxes. - - Raises: - AssertionError: If the indexed bounding boxes do not form a 2-dimensional matrix. - - Note: - When using boolean indexing, make sure to provide a boolean array with the same - length as the number of bounding boxes. - """ - if isinstance(index, int): - return Bboxes(self.bboxes[index].view(1, -1)) - b = self.bboxes[index] - assert b.ndim == 2, f"Indexing on Bboxes with {index} failed to return a matrix!" - return Bboxes(b) - - -class Instances: - """ - Container for bounding boxes, segments, and keypoints of detected objects in an image. - - Attributes: - _bboxes (Bboxes): Internal object for handling bounding box operations. - keypoints (ndarray): keypoints(x, y, visible) with shape [N, 17, 3]. Default is None. - normalized (bool): Flag indicating whether the bounding box coordinates are normalized. - segments (ndarray): Segments array with shape [N, 1000, 2] after resampling. - - Args: - bboxes (ndarray): An array of bounding boxes with shape [N, 4]. - segments (list | ndarray, optional): A list or array of object segments. Default is None. - keypoints (ndarray, optional): An array of keypoints with shape [N, 17, 3]. Default is None. - bbox_format (str, optional): The format of bounding boxes ('xywh' or 'xyxy'). Default is 'xywh'. - normalized (bool, optional): Whether the bounding box coordinates are normalized. Default is True. - - Examples: - ```python - # Create an Instances object - instances = Instances( - bboxes=np.array([[10, 10, 30, 30], [20, 20, 40, 40]]), - segments=[np.array([[5, 5], [10, 10]]), np.array([[15, 15], [20, 20]])], - keypoints=np.array([[[5, 5, 1], [10, 10, 1]], [[15, 15, 1], [20, 20, 1]]]) - ) - ``` - - Note: - The bounding box format is either 'xywh' or 'xyxy', and is determined by the `bbox_format` argument. - This class does not perform input validation, and it assumes the inputs are well-formed. - """ - - def __init__(self, bboxes, segments=None, keypoints=None, bbox_format="xywh", normalized=True) -> None: - """ - Args: - bboxes (ndarray): bboxes with shape [N, 4]. - segments (list | ndarray): segments. - keypoints (ndarray): keypoints(x, y, visible) with shape [N, 17, 3]. - """ - self._bboxes = Bboxes(bboxes=bboxes, format=bbox_format) - self.keypoints = keypoints - self.normalized = normalized - self.segments = segments - - def convert_bbox(self, format): - """Convert bounding box format.""" - self._bboxes.convert(format=format) - - @property - def bbox_areas(self): - """Calculate the area of bounding boxes.""" - return self._bboxes.areas() - - def scale(self, scale_w, scale_h, bbox_only=False): - """This might be similar with denormalize func but without normalized sign.""" - self._bboxes.mul(scale=(scale_w, scale_h, scale_w, scale_h)) - if bbox_only: - return - self.segments[..., 0] *= scale_w - self.segments[..., 1] *= scale_h - if self.keypoints is not None: - self.keypoints[..., 0] *= scale_w - self.keypoints[..., 1] *= scale_h - - def denormalize(self, w, h): - """Denormalizes boxes, segments, and keypoints from normalized coordinates.""" - if not self.normalized: - return - self._bboxes.mul(scale=(w, h, w, h)) - self.segments[..., 0] *= w - self.segments[..., 1] *= h - if self.keypoints is not None: - self.keypoints[..., 0] *= w - self.keypoints[..., 1] *= h - self.normalized = False - - def normalize(self, w, h): - """Normalize bounding boxes, segments, and keypoints to image dimensions.""" - if self.normalized: - return - self._bboxes.mul(scale=(1 / w, 1 / h, 1 / w, 1 / h)) - self.segments[..., 0] /= w - self.segments[..., 1] /= h - if self.keypoints is not None: - self.keypoints[..., 0] /= w - self.keypoints[..., 1] /= h - self.normalized = True - - def add_padding(self, padw, padh): - """Handle rect and mosaic situation.""" - assert not self.normalized, "you should add padding with absolute coordinates." - self._bboxes.add(offset=(padw, padh, padw, padh)) - self.segments[..., 0] += padw - self.segments[..., 1] += padh - if self.keypoints is not None: - self.keypoints[..., 0] += padw - self.keypoints[..., 1] += padh - - def __getitem__(self, index) -> "Instances": - """ - Retrieve a specific instance or a set of instances using indexing. - - Args: - index (int, slice, or np.ndarray): The index, slice, or boolean array to select - the desired instances. - - Returns: - Instances: A new Instances object containing the selected bounding boxes, - segments, and keypoints if present. - - Note: - When using boolean indexing, make sure to provide a boolean array with the same - length as the number of instances. - """ - segments = self.segments[index] if len(self.segments) else self.segments - keypoints = self.keypoints[index] if self.keypoints is not None else None - bboxes = self.bboxes[index] - bbox_format = self._bboxes.format - return Instances( - bboxes=bboxes, - segments=segments, - keypoints=keypoints, - bbox_format=bbox_format, - normalized=self.normalized, - ) - - def flipud(self, h): - """Flips the coordinates of bounding boxes, segments, and keypoints vertically.""" - if self._bboxes.format == "xyxy": - y1 = self.bboxes[:, 1].copy() - y2 = self.bboxes[:, 3].copy() - self.bboxes[:, 1] = h - y2 - self.bboxes[:, 3] = h - y1 - else: - self.bboxes[:, 1] = h - self.bboxes[:, 1] - self.segments[..., 1] = h - self.segments[..., 1] - if self.keypoints is not None: - self.keypoints[..., 1] = h - self.keypoints[..., 1] - - def fliplr(self, w): - """Reverses the order of the bounding boxes and segments horizontally.""" - if self._bboxes.format == "xyxy": - x1 = self.bboxes[:, 0].copy() - x2 = self.bboxes[:, 2].copy() - self.bboxes[:, 0] = w - x2 - self.bboxes[:, 2] = w - x1 - else: - self.bboxes[:, 0] = w - self.bboxes[:, 0] - self.segments[..., 0] = w - self.segments[..., 0] - if self.keypoints is not None: - self.keypoints[..., 0] = w - self.keypoints[..., 0] - - def clip(self, w, h): - """Clips bounding boxes, segments, and keypoints values to stay within image boundaries.""" - ori_format = self._bboxes.format - self.convert_bbox(format="xyxy") - self.bboxes[:, [0, 2]] = self.bboxes[:, [0, 2]].clip(0, w) - self.bboxes[:, [1, 3]] = self.bboxes[:, [1, 3]].clip(0, h) - if ori_format != "xyxy": - self.convert_bbox(format=ori_format) - self.segments[..., 0] = self.segments[..., 0].clip(0, w) - self.segments[..., 1] = self.segments[..., 1].clip(0, h) - if self.keypoints is not None: - self.keypoints[..., 0] = self.keypoints[..., 0].clip(0, w) - self.keypoints[..., 1] = self.keypoints[..., 1].clip(0, h) - - def remove_zero_area_boxes(self): - """ - Remove zero-area boxes, i.e. after clipping some boxes may have zero width or height. - - This removes them. - """ - good = self.bbox_areas > 0 - if not all(good): - self._bboxes = self._bboxes[good] - if len(self.segments): - self.segments = self.segments[good] - if self.keypoints is not None: - self.keypoints = self.keypoints[good] - return good - - def update(self, bboxes, segments=None, keypoints=None): - """Updates instance variables.""" - self._bboxes = Bboxes(bboxes, format=self._bboxes.format) - if segments is not None: - self.segments = segments - if keypoints is not None: - self.keypoints = keypoints - - def __len__(self): - """Return the length of the instance list.""" - return len(self.bboxes) - - @classmethod - def concatenate(cls, instances_list: List["Instances"], axis=0) -> "Instances": - """ - Concatenates a list of Instances objects into a single Instances object. - - Args: - instances_list (List[Instances]): A list of Instances objects to concatenate. - axis (int, optional): The axis along which the arrays will be concatenated. Defaults to 0. - - Returns: - Instances: A new Instances object containing the concatenated bounding boxes, - segments, and keypoints if present. - - Note: - The `Instances` objects in the list should have the same properties, such as - the format of the bounding boxes, whether keypoints are present, and if the - coordinates are normalized. - """ - assert isinstance(instances_list, (list, tuple)) - if not instances_list: - return cls(np.empty(0)) - assert all(isinstance(instance, Instances) for instance in instances_list) - - if len(instances_list) == 1: - return instances_list[0] - - use_keypoint = instances_list[0].keypoints is not None - bbox_format = instances_list[0]._bboxes.format - normalized = instances_list[0].normalized - - cat_boxes = np.concatenate([ins.bboxes for ins in instances_list], axis=axis) - cat_segments = np.concatenate([b.segments for b in instances_list], axis=axis) - cat_keypoints = np.concatenate([b.keypoints for b in instances_list], axis=axis) if use_keypoint else None - return cls(cat_boxes, cat_segments, cat_keypoints, bbox_format, normalized) - - @property - def bboxes(self): - """Return bounding boxes.""" - return self._bboxes.bboxes diff --git a/ultralytics-main/ultralytics/utils/loss.py b/ultralytics-main/ultralytics/utils/loss.py deleted file mode 100644 index 360a292..0000000 --- a/ultralytics-main/ultralytics/utils/loss.py +++ /dev/null @@ -1,715 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch -import torch.nn as nn -import torch.nn.functional as F - -from ultralytics.utils.metrics import OKS_SIGMA -from ultralytics.utils.ops import crop_mask, xywh2xyxy, xyxy2xywh -from ultralytics.utils.tal import RotatedTaskAlignedAssigner, TaskAlignedAssigner, dist2bbox, dist2rbox, make_anchors -from .metrics import bbox_iou, probiou -from .tal import bbox2dist - - -class VarifocalLoss(nn.Module): - """ - Varifocal loss by Zhang et al. - - https://arxiv.org/abs/2008.13367. - """ - - def __init__(self): - """Initialize the VarifocalLoss class.""" - super().__init__() - - @staticmethod - def forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0): - """Computes varfocal loss.""" - weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label - with torch.cuda.amp.autocast(enabled=False): - loss = ( - (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction="none") * weight) - .mean(1) - .sum() - ) - return loss - - -class FocalLoss(nn.Module): - """Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5).""" - - def __init__(self): - """Initializer for FocalLoss class with no parameters.""" - super().__init__() - - @staticmethod - def forward(pred, label, gamma=1.5, alpha=0.25): - """Calculates and updates confusion matrix for object detection/classification tasks.""" - loss = F.binary_cross_entropy_with_logits(pred, label, reduction="none") - # p_t = torch.exp(-loss) - # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability - - # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py - pred_prob = pred.sigmoid() # prob from logits - p_t = label * pred_prob + (1 - label) * (1 - pred_prob) - modulating_factor = (1.0 - p_t) ** gamma - loss *= modulating_factor - if alpha > 0: - alpha_factor = label * alpha + (1 - label) * (1 - alpha) - loss *= alpha_factor - return loss.mean(1).sum() - - -class BboxLoss(nn.Module): - """Criterion class for computing training losses during training.""" - - def __init__(self, reg_max, use_dfl=False): - """Initialize the BboxLoss module with regularization maximum and DFL settings.""" - super().__init__() - self.reg_max = reg_max - self.use_dfl = use_dfl - - def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask): - """IoU loss.""" - weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1) - iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True) - loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum - - # DFL loss - if self.use_dfl: - target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max) - loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight - loss_dfl = loss_dfl.sum() / target_scores_sum - else: - loss_dfl = torch.tensor(0.0).to(pred_dist.device) - - return loss_iou, loss_dfl - - @staticmethod - def _df_loss(pred_dist, target): - """ - Return sum of left and right DFL losses. - - Distribution Focal Loss (DFL) proposed in Generalized Focal Loss - https://ieeexplore.ieee.org/document/9792391 - """ - tl = target.long() # target left - tr = tl + 1 # target right - wl = tr - target # weight left - wr = 1 - wl # weight right - return ( - F.cross_entropy(pred_dist, tl.view(-1), reduction="none").view(tl.shape) * wl - + F.cross_entropy(pred_dist, tr.view(-1), reduction="none").view(tl.shape) * wr - ).mean(-1, keepdim=True) - - -class RotatedBboxLoss(BboxLoss): - """Criterion class for computing training losses during training.""" - - def __init__(self, reg_max, use_dfl=False): - """Initialize the BboxLoss module with regularization maximum and DFL settings.""" - super().__init__(reg_max, use_dfl) - - def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask): - """IoU loss.""" - weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1) - iou = probiou(pred_bboxes[fg_mask], target_bboxes[fg_mask]) - loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum - - # DFL loss - if self.use_dfl: - target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max) - loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight - loss_dfl = loss_dfl.sum() / target_scores_sum - else: - loss_dfl = torch.tensor(0.0).to(pred_dist.device) - - return loss_iou, loss_dfl - - -class KeypointLoss(nn.Module): - """Criterion class for computing training losses.""" - - def __init__(self, sigmas) -> None: - """Initialize the KeypointLoss class.""" - super().__init__() - self.sigmas = sigmas - - def forward(self, pred_kpts, gt_kpts, kpt_mask, area): - """Calculates keypoint loss factor and Euclidean distance loss for predicted and actual keypoints.""" - d = (pred_kpts[..., 0] - gt_kpts[..., 0]).pow(2) + (pred_kpts[..., 1] - gt_kpts[..., 1]).pow(2) - kpt_loss_factor = kpt_mask.shape[1] / (torch.sum(kpt_mask != 0, dim=1) + 1e-9) - # e = d / (2 * (area * self.sigmas) ** 2 + 1e-9) # from formula - e = d / ((2 * self.sigmas).pow(2) * (area + 1e-9) * 2) # from cocoeval - return (kpt_loss_factor.view(-1, 1) * ((1 - torch.exp(-e)) * kpt_mask)).mean() - - -class v8DetectionLoss: - """Criterion class for computing training losses.""" - - def __init__(self, model): # model must be de-paralleled - """Initializes v8DetectionLoss with the model, defining model-related properties and BCE loss function.""" - device = next(model.parameters()).device # get model device - h = model.args # hyperparameters - - m = model.model[-1] # Detect() module - self.bce = nn.BCEWithLogitsLoss(reduction="none") - self.hyp = h - self.stride = m.stride # model strides - self.nc = m.nc # number of classes - self.no = m.no - self.reg_max = m.reg_max - self.device = device - - self.use_dfl = m.reg_max > 1 - - self.assigner = TaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0) - self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device) - self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device) - - def preprocess(self, targets, batch_size, scale_tensor): - """Preprocesses the target counts and matches with the input batch size to output a tensor.""" - if targets.shape[0] == 0: - out = torch.zeros(batch_size, 0, 5, device=self.device) - else: - i = targets[:, 0] # image index - _, counts = i.unique(return_counts=True) - counts = counts.to(dtype=torch.int32) - out = torch.zeros(batch_size, counts.max(), 5, device=self.device) - for j in range(batch_size): - matches = i == j - n = matches.sum() - if n: - out[j, :n] = targets[matches, 1:] - out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor)) - return out - - def bbox_decode(self, anchor_points, pred_dist): - """Decode predicted object bounding box coordinates from anchor points and distribution.""" - if self.use_dfl: - b, a, c = pred_dist.shape # batch, anchors, channels - pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype)) - # pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype)) - # pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2) - return dist2bbox(pred_dist, anchor_points, xywh=False) - - def __call__(self, preds, batch): - """Calculate the sum of the loss for box, cls and dfl multiplied by batch size.""" - loss = torch.zeros(3, device=self.device) # box, cls, dfl - feats = preds[1] if isinstance(preds, tuple) else preds - pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( - (self.reg_max * 4, self.nc), 1 - ) - - pred_scores = pred_scores.permute(0, 2, 1).contiguous() - pred_distri = pred_distri.permute(0, 2, 1).contiguous() - - dtype = pred_scores.dtype - batch_size = pred_scores.shape[0] - imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) - anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) - - # Targets - targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1) - targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) - gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy - mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) - - # Pboxes - pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) - - _, target_bboxes, target_scores, fg_mask, _ = self.assigner( - pred_scores.detach().sigmoid(), - (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype), - anchor_points * stride_tensor, - gt_labels, - gt_bboxes, - mask_gt, - ) - - target_scores_sum = max(target_scores.sum(), 1) - - # Cls loss - # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way - loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE - - # Bbox loss - if fg_mask.sum(): - target_bboxes /= stride_tensor - loss[0], loss[2] = self.bbox_loss( - pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask - ) - - loss[0] *= self.hyp.box # box gain - loss[1] *= self.hyp.cls # cls gain - loss[2] *= self.hyp.dfl # dfl gain - - return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) - - -class v8SegmentationLoss(v8DetectionLoss): - """Criterion class for computing training losses.""" - - def __init__(self, model): # model must be de-paralleled - """Initializes the v8SegmentationLoss class, taking a de-paralleled model as argument.""" - super().__init__(model) - self.overlap = model.args.overlap_mask - - def __call__(self, preds, batch): - """Calculate and return the loss for the YOLO model.""" - loss = torch.zeros(4, device=self.device) # box, cls, dfl - feats, pred_masks, proto = preds if len(preds) == 3 else preds[1] - batch_size, _, mask_h, mask_w = proto.shape # batch size, number of masks, mask height, mask width - pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( - (self.reg_max * 4, self.nc), 1 - ) - - # B, grids, .. - pred_scores = pred_scores.permute(0, 2, 1).contiguous() - pred_distri = pred_distri.permute(0, 2, 1).contiguous() - pred_masks = pred_masks.permute(0, 2, 1).contiguous() - - dtype = pred_scores.dtype - imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) - anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) - - # Targets - try: - batch_idx = batch["batch_idx"].view(-1, 1) - targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1) - targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) - gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy - mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) - except RuntimeError as e: - raise TypeError( - "ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.\n" - "This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, " - "i.e. 'yolo train model=yolov8n-seg.pt data=coco8.yaml'.\nVerify your dataset is a " - "correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' " - "as an example.\nSee https://docs.ultralytics.com/datasets/segment/ for help." - ) from e - - # Pboxes - pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) - - _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner( - pred_scores.detach().sigmoid(), - (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype), - anchor_points * stride_tensor, - gt_labels, - gt_bboxes, - mask_gt, - ) - - target_scores_sum = max(target_scores.sum(), 1) - - # Cls loss - # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way - loss[2] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE - - if fg_mask.sum(): - # Bbox loss - loss[0], loss[3] = self.bbox_loss( - pred_distri, - pred_bboxes, - anchor_points, - target_bboxes / stride_tensor, - target_scores, - target_scores_sum, - fg_mask, - ) - # Masks loss - masks = batch["masks"].to(self.device).float() - if tuple(masks.shape[-2:]) != (mask_h, mask_w): # downsample - masks = F.interpolate(masks[None], (mask_h, mask_w), mode="nearest")[0] - - loss[1] = self.calculate_segmentation_loss( - fg_mask, masks, target_gt_idx, target_bboxes, batch_idx, proto, pred_masks, imgsz, self.overlap - ) - - # WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove - else: - loss[1] += (proto * 0).sum() + (pred_masks * 0).sum() # inf sums may lead to nan loss - - loss[0] *= self.hyp.box # box gain - loss[1] *= self.hyp.box # seg gain - loss[2] *= self.hyp.cls # cls gain - loss[3] *= self.hyp.dfl # dfl gain - - return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) - - @staticmethod - def single_mask_loss( - gt_mask: torch.Tensor, pred: torch.Tensor, proto: torch.Tensor, xyxy: torch.Tensor, area: torch.Tensor - ) -> torch.Tensor: - """ - Compute the instance segmentation loss for a single image. - - Args: - gt_mask (torch.Tensor): Ground truth mask of shape (n, H, W), where n is the number of objects. - pred (torch.Tensor): Predicted mask coefficients of shape (n, 32). - proto (torch.Tensor): Prototype masks of shape (32, H, W). - xyxy (torch.Tensor): Ground truth bounding boxes in xyxy format, normalized to [0, 1], of shape (n, 4). - area (torch.Tensor): Area of each ground truth bounding box of shape (n,). - - Returns: - (torch.Tensor): The calculated mask loss for a single image. - - Notes: - The function uses the equation pred_mask = torch.einsum('in,nhw->ihw', pred, proto) to produce the - predicted masks from the prototype masks and predicted mask coefficients. - """ - pred_mask = torch.einsum("in,nhw->ihw", pred, proto) # (n, 32) @ (32, 80, 80) -> (n, 80, 80) - loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction="none") - return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).sum() - - def calculate_segmentation_loss( - self, - fg_mask: torch.Tensor, - masks: torch.Tensor, - target_gt_idx: torch.Tensor, - target_bboxes: torch.Tensor, - batch_idx: torch.Tensor, - proto: torch.Tensor, - pred_masks: torch.Tensor, - imgsz: torch.Tensor, - overlap: bool, - ) -> torch.Tensor: - """ - Calculate the loss for instance segmentation. - - Args: - fg_mask (torch.Tensor): A binary tensor of shape (BS, N_anchors) indicating which anchors are positive. - masks (torch.Tensor): Ground truth masks of shape (BS, H, W) if `overlap` is False, otherwise (BS, ?, H, W). - target_gt_idx (torch.Tensor): Indexes of ground truth objects for each anchor of shape (BS, N_anchors). - target_bboxes (torch.Tensor): Ground truth bounding boxes for each anchor of shape (BS, N_anchors, 4). - batch_idx (torch.Tensor): Batch indices of shape (N_labels_in_batch, 1). - proto (torch.Tensor): Prototype masks of shape (BS, 32, H, W). - pred_masks (torch.Tensor): Predicted masks for each anchor of shape (BS, N_anchors, 32). - imgsz (torch.Tensor): Size of the input image as a tensor of shape (2), i.e., (H, W). - overlap (bool): Whether the masks in `masks` tensor overlap. - - Returns: - (torch.Tensor): The calculated loss for instance segmentation. - - Notes: - The batch loss can be computed for improved speed at higher memory usage. - For example, pred_mask can be computed as follows: - pred_mask = torch.einsum('in,nhw->ihw', pred, proto) # (i, 32) @ (32, 160, 160) -> (i, 160, 160) - """ - _, _, mask_h, mask_w = proto.shape - loss = 0 - - # Normalize to 0-1 - target_bboxes_normalized = target_bboxes / imgsz[[1, 0, 1, 0]] - - # Areas of target bboxes - marea = xyxy2xywh(target_bboxes_normalized)[..., 2:].prod(2) - - # Normalize to mask size - mxyxy = target_bboxes_normalized * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=proto.device) - - for i, single_i in enumerate(zip(fg_mask, target_gt_idx, pred_masks, proto, mxyxy, marea, masks)): - fg_mask_i, target_gt_idx_i, pred_masks_i, proto_i, mxyxy_i, marea_i, masks_i = single_i - if fg_mask_i.any(): - mask_idx = target_gt_idx_i[fg_mask_i] - if overlap: - gt_mask = masks_i == (mask_idx + 1).view(-1, 1, 1) - gt_mask = gt_mask.float() - else: - gt_mask = masks[batch_idx.view(-1) == i][mask_idx] - - loss += self.single_mask_loss( - gt_mask, pred_masks_i[fg_mask_i], proto_i, mxyxy_i[fg_mask_i], marea_i[fg_mask_i] - ) - - # WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove - else: - loss += (proto * 0).sum() + (pred_masks * 0).sum() # inf sums may lead to nan loss - - return loss / fg_mask.sum() - - -class v8PoseLoss(v8DetectionLoss): - """Criterion class for computing training losses.""" - - def __init__(self, model): # model must be de-paralleled - """Initializes v8PoseLoss with model, sets keypoint variables and declares a keypoint loss instance.""" - super().__init__(model) - self.kpt_shape = model.model[-1].kpt_shape - self.bce_pose = nn.BCEWithLogitsLoss() - is_pose = self.kpt_shape == [17, 3] - nkpt = self.kpt_shape[0] # number of keypoints - sigmas = torch.from_numpy(OKS_SIGMA).to(self.device) if is_pose else torch.ones(nkpt, device=self.device) / nkpt - self.keypoint_loss = KeypointLoss(sigmas=sigmas) - - def __call__(self, preds, batch): - """Calculate the total loss and detach it.""" - loss = torch.zeros(5, device=self.device) # box, cls, dfl, kpt_location, kpt_visibility - feats, pred_kpts = preds if isinstance(preds[0], list) else preds[1] - pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( - (self.reg_max * 4, self.nc), 1 - ) - - # B, grids, .. - pred_scores = pred_scores.permute(0, 2, 1).contiguous() - pred_distri = pred_distri.permute(0, 2, 1).contiguous() - pred_kpts = pred_kpts.permute(0, 2, 1).contiguous() - - dtype = pred_scores.dtype - imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) - anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) - - # Targets - batch_size = pred_scores.shape[0] - batch_idx = batch["batch_idx"].view(-1, 1) - targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1) - targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) - gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy - mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) - - # Pboxes - pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4) - pred_kpts = self.kpts_decode(anchor_points, pred_kpts.view(batch_size, -1, *self.kpt_shape)) # (b, h*w, 17, 3) - - _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner( - pred_scores.detach().sigmoid(), - (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype), - anchor_points * stride_tensor, - gt_labels, - gt_bboxes, - mask_gt, - ) - - target_scores_sum = max(target_scores.sum(), 1) - - # Cls loss - # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way - loss[3] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE - - # Bbox loss - if fg_mask.sum(): - target_bboxes /= stride_tensor - loss[0], loss[4] = self.bbox_loss( - pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask - ) - keypoints = batch["keypoints"].to(self.device).float().clone() - keypoints[..., 0] *= imgsz[1] - keypoints[..., 1] *= imgsz[0] - - loss[1], loss[2] = self.calculate_keypoints_loss( - fg_mask, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts - ) - - loss[0] *= self.hyp.box # box gain - loss[1] *= self.hyp.pose # pose gain - loss[2] *= self.hyp.kobj # kobj gain - loss[3] *= self.hyp.cls # cls gain - loss[4] *= self.hyp.dfl # dfl gain - - return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) - - @staticmethod - def kpts_decode(anchor_points, pred_kpts): - """Decodes predicted keypoints to image coordinates.""" - y = pred_kpts.clone() - y[..., :2] *= 2.0 - y[..., 0] += anchor_points[:, [0]] - 0.5 - y[..., 1] += anchor_points[:, [1]] - 0.5 - return y - - def calculate_keypoints_loss( - self, masks, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts - ): - """ - Calculate the keypoints loss for the model. - - This function calculates the keypoints loss and keypoints object loss for a given batch. The keypoints loss is - based on the difference between the predicted keypoints and ground truth keypoints. The keypoints object loss is - a binary classification loss that classifies whether a keypoint is present or not. - - Args: - masks (torch.Tensor): Binary mask tensor indicating object presence, shape (BS, N_anchors). - target_gt_idx (torch.Tensor): Index tensor mapping anchors to ground truth objects, shape (BS, N_anchors). - keypoints (torch.Tensor): Ground truth keypoints, shape (N_kpts_in_batch, N_kpts_per_object, kpts_dim). - batch_idx (torch.Tensor): Batch index tensor for keypoints, shape (N_kpts_in_batch, 1). - stride_tensor (torch.Tensor): Stride tensor for anchors, shape (N_anchors, 1). - target_bboxes (torch.Tensor): Ground truth boxes in (x1, y1, x2, y2) format, shape (BS, N_anchors, 4). - pred_kpts (torch.Tensor): Predicted keypoints, shape (BS, N_anchors, N_kpts_per_object, kpts_dim). - - Returns: - (tuple): Returns a tuple containing: - - kpts_loss (torch.Tensor): The keypoints loss. - - kpts_obj_loss (torch.Tensor): The keypoints object loss. - """ - batch_idx = batch_idx.flatten() - batch_size = len(masks) - - # Find the maximum number of keypoints in a single image - max_kpts = torch.unique(batch_idx, return_counts=True)[1].max() - - # Create a tensor to hold batched keypoints - batched_keypoints = torch.zeros( - (batch_size, max_kpts, keypoints.shape[1], keypoints.shape[2]), device=keypoints.device - ) - - # TODO: any idea how to vectorize this? - # Fill batched_keypoints with keypoints based on batch_idx - for i in range(batch_size): - keypoints_i = keypoints[batch_idx == i] - batched_keypoints[i, : keypoints_i.shape[0]] = keypoints_i - - # Expand dimensions of target_gt_idx to match the shape of batched_keypoints - target_gt_idx_expanded = target_gt_idx.unsqueeze(-1).unsqueeze(-1) - - # Use target_gt_idx_expanded to select keypoints from batched_keypoints - selected_keypoints = batched_keypoints.gather( - 1, target_gt_idx_expanded.expand(-1, -1, keypoints.shape[1], keypoints.shape[2]) - ) - - # Divide coordinates by stride - selected_keypoints /= stride_tensor.view(1, -1, 1, 1) - - kpts_loss = 0 - kpts_obj_loss = 0 - - if masks.any(): - gt_kpt = selected_keypoints[masks] - area = xyxy2xywh(target_bboxes[masks])[:, 2:].prod(1, keepdim=True) - pred_kpt = pred_kpts[masks] - kpt_mask = gt_kpt[..., 2] != 0 if gt_kpt.shape[-1] == 3 else torch.full_like(gt_kpt[..., 0], True) - kpts_loss = self.keypoint_loss(pred_kpt, gt_kpt, kpt_mask, area) # pose loss - - if pred_kpt.shape[-1] == 3: - kpts_obj_loss = self.bce_pose(pred_kpt[..., 2], kpt_mask.float()) # keypoint obj loss - - return kpts_loss, kpts_obj_loss - - -class v8ClassificationLoss: - """Criterion class for computing training losses.""" - - def __call__(self, preds, batch): - """Compute the classification loss between predictions and true labels.""" - loss = torch.nn.functional.cross_entropy(preds, batch["cls"], reduction="mean") - loss_items = loss.detach() - return loss, loss_items - - -class v8OBBLoss(v8DetectionLoss): - def __init__(self, model): - """ - Initializes v8OBBLoss with model, assigner, and rotated bbox loss. - - Note model must be de-paralleled. - """ - super().__init__(model) - self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0) - self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device) - - def preprocess(self, targets, batch_size, scale_tensor): - """Preprocesses the target counts and matches with the input batch size to output a tensor.""" - if targets.shape[0] == 0: - out = torch.zeros(batch_size, 0, 6, device=self.device) - else: - i = targets[:, 0] # image index - _, counts = i.unique(return_counts=True) - counts = counts.to(dtype=torch.int32) - out = torch.zeros(batch_size, counts.max(), 6, device=self.device) - for j in range(batch_size): - matches = i == j - n = matches.sum() - if n: - bboxes = targets[matches, 2:] - bboxes[..., :4].mul_(scale_tensor) - out[j, :n] = torch.cat([targets[matches, 1:2], bboxes], dim=-1) - return out - - def __call__(self, preds, batch): - """Calculate and return the loss for the YOLO model.""" - loss = torch.zeros(3, device=self.device) # box, cls, dfl - feats, pred_angle = preds if isinstance(preds[0], list) else preds[1] - batch_size = pred_angle.shape[0] # batch size, number of masks, mask height, mask width - pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( - (self.reg_max * 4, self.nc), 1 - ) - - # b, grids, .. - pred_scores = pred_scores.permute(0, 2, 1).contiguous() - pred_distri = pred_distri.permute(0, 2, 1).contiguous() - pred_angle = pred_angle.permute(0, 2, 1).contiguous() - - dtype = pred_scores.dtype - imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w) - anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5) - - # targets - try: - batch_idx = batch["batch_idx"].view(-1, 1) - targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"].view(-1, 5)), 1) - rw, rh = targets[:, 4] * imgsz[0].item(), targets[:, 5] * imgsz[1].item() - targets = targets[(rw >= 2) & (rh >= 2)] # filter rboxes of tiny size to stabilize training - targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]]) - gt_labels, gt_bboxes = targets.split((1, 5), 2) # cls, xywhr - mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0) - except RuntimeError as e: - raise TypeError( - "ERROR ❌ OBB dataset incorrectly formatted or not a OBB dataset.\n" - "This error can occur when incorrectly training a 'OBB' model on a 'detect' dataset, " - "i.e. 'yolo train model=yolov8n-obb.pt data=dota8.yaml'.\nVerify your dataset is a " - "correctly formatted 'OBB' dataset using 'data=dota8.yaml' " - "as an example.\nSee https://docs.ultralytics.com/datasets/obb/ for help." - ) from e - - # Pboxes - pred_bboxes = self.bbox_decode(anchor_points, pred_distri, pred_angle) # xyxy, (b, h*w, 4) - - bboxes_for_assigner = pred_bboxes.clone().detach() - # Only the first four elements need to be scaled - bboxes_for_assigner[..., :4] *= stride_tensor - _, target_bboxes, target_scores, fg_mask, _ = self.assigner( - pred_scores.detach().sigmoid(), - bboxes_for_assigner.type(gt_bboxes.dtype), - anchor_points * stride_tensor, - gt_labels, - gt_bboxes, - mask_gt, - ) - - target_scores_sum = max(target_scores.sum(), 1) - - # Cls loss - # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way - loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE - - # Bbox loss - if fg_mask.sum(): - target_bboxes[..., :4] /= stride_tensor - loss[0], loss[2] = self.bbox_loss( - pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask - ) - else: - loss[0] += (pred_angle * 0).sum() - - loss[0] *= self.hyp.box # box gain - loss[1] *= self.hyp.cls # cls gain - loss[2] *= self.hyp.dfl # dfl gain - - return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl) - - def bbox_decode(self, anchor_points, pred_dist, pred_angle): - """ - Decode predicted object bounding box coordinates from anchor points and distribution. - - Args: - anchor_points (torch.Tensor): Anchor points, (h*w, 2). - pred_dist (torch.Tensor): Predicted rotated distance, (bs, h*w, 4). - pred_angle (torch.Tensor): Predicted angle, (bs, h*w, 1). - - Returns: - (torch.Tensor): Predicted rotated bounding boxes with angles, (bs, h*w, 5). - """ - if self.use_dfl: - b, a, c = pred_dist.shape # batch, anchors, channels - pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype)) - return torch.cat((dist2rbox(pred_dist, pred_angle, anchor_points), pred_angle), dim=-1) diff --git a/ultralytics-main/ultralytics/utils/metrics.py b/ultralytics-main/ultralytics/utils/metrics.py deleted file mode 100644 index 235db56..0000000 --- a/ultralytics-main/ultralytics/utils/metrics.py +++ /dev/null @@ -1,1289 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Model validation metrics.""" - -import math -import warnings -from pathlib import Path - -import matplotlib.pyplot as plt -import numpy as np -import torch - -from ultralytics.utils import LOGGER, SimpleClass, TryExcept, plt_settings - -OKS_SIGMA = ( - np.array([0.26, 0.25, 0.25, 0.35, 0.35, 0.79, 0.79, 0.72, 0.72, 0.62, 0.62, 1.07, 1.07, 0.87, 0.87, 0.89, 0.89]) - / 10.0 -) - - -def bbox_ioa(box1, box2, iou=False, eps=1e-7): - """ - Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format. - - Args: - box1 (np.ndarray): A numpy array of shape (n, 4) representing n bounding boxes. - box2 (np.ndarray): A numpy array of shape (m, 4) representing m bounding boxes. - iou (bool): Calculate the standard IoU if True else return inter_area/box2_area. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (np.ndarray): A numpy array of shape (n, m) representing the intersection over box2 area. - """ - - # Get the coordinates of bounding boxes - b1_x1, b1_y1, b1_x2, b1_y2 = box1.T - b2_x1, b2_y1, b2_x2, b2_y2 = box2.T - - # Intersection area - inter_area = (np.minimum(b1_x2[:, None], b2_x2) - np.maximum(b1_x1[:, None], b2_x1)).clip(0) * ( - np.minimum(b1_y2[:, None], b2_y2) - np.maximum(b1_y1[:, None], b2_y1) - ).clip(0) - - # Box2 area - area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) - if iou: - box1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1) - area = area + box1_area[:, None] - inter_area - - # Intersection over box2 area - return inter_area / (area + eps) - - -def box_iou(box1, box2, eps=1e-7): - """ - Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. - Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py - - Args: - box1 (torch.Tensor): A tensor of shape (N, 4) representing N bounding boxes. - box2 (torch.Tensor): A tensor of shape (M, 4) representing M bounding boxes. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): An NxM tensor containing the pairwise IoU values for every element in box1 and box2. - """ - - # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) - (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2) - inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp_(0).prod(2) - - # IoU = inter / (area1 + area2 - inter) - return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps) - - -def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): - """ - Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4). - - Args: - box1 (torch.Tensor): A tensor representing a single bounding box with shape (1, 4). - box2 (torch.Tensor): A tensor representing n bounding boxes with shape (n, 4). - xywh (bool, optional): If True, input boxes are in (x, y, w, h) format. If False, input boxes are in - (x1, y1, x2, y2) format. Defaults to True. - GIoU (bool, optional): If True, calculate Generalized IoU. Defaults to False. - DIoU (bool, optional): If True, calculate Distance IoU. Defaults to False. - CIoU (bool, optional): If True, calculate Complete IoU. Defaults to False. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): IoU, GIoU, DIoU, or CIoU values depending on the specified flags. - """ - - # Get the coordinates of bounding boxes - if xywh: # transform from xywh to xyxy - (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1) - w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2 - b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_ - b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_ - else: # x1, y1, x2, y2 = box1 - b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1) - b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1) - w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps - w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps - - # Intersection area - inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp_(0) * ( - b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1) - ).clamp_(0) - - # Union Area - union = w1 * h1 + w2 * h2 - inter + eps - - # IoU - iou = inter / union - if CIoU or DIoU or GIoU: - cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1) # convex (smallest enclosing box) width - ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1) # convex height - if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 - c2 = cw.pow(2) + ch.pow(2) + eps # convex diagonal squared - rho2 = ( - (b2_x1 + b2_x2 - b1_x1 - b1_x2).pow(2) + (b2_y1 + b2_y2 - b1_y1 - b1_y2).pow(2) - ) / 4 # center dist**2 - if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 - v = (4 / math.pi**2) * ((w2 / h2).atan() - (w1 / h1).atan()).pow(2) - with torch.no_grad(): - alpha = v / (v - iou + (1 + eps)) - return iou - (rho2 / c2 + v * alpha) # CIoU - return iou - rho2 / c2 # DIoU - c_area = cw * ch + eps # convex area - return iou - (c_area - union) / c_area # GIoU https://arxiv.org/pdf/1902.09630.pdf - return iou # IoU - - -def mask_iou(mask1, mask2, eps=1e-7): - """ - Calculate masks IoU. - - Args: - mask1 (torch.Tensor): A tensor of shape (N, n) where N is the number of ground truth objects and n is the - product of image width and height. - mask2 (torch.Tensor): A tensor of shape (M, n) where M is the number of predicted objects and n is the - product of image width and height. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): A tensor of shape (N, M) representing masks IoU. - """ - intersection = torch.matmul(mask1, mask2.T).clamp_(0) - union = (mask1.sum(1)[:, None] + mask2.sum(1)[None]) - intersection # (area1 + area2) - intersection - return intersection / (union + eps) - - -def kpt_iou(kpt1, kpt2, area, sigma, eps=1e-7): - """ - Calculate Object Keypoint Similarity (OKS). - - Args: - kpt1 (torch.Tensor): A tensor of shape (N, 17, 3) representing ground truth keypoints. - kpt2 (torch.Tensor): A tensor of shape (M, 17, 3) representing predicted keypoints. - area (torch.Tensor): A tensor of shape (N,) representing areas from ground truth. - sigma (list): A list containing 17 values representing keypoint scales. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): A tensor of shape (N, M) representing keypoint similarities. - """ - d = (kpt1[:, None, :, 0] - kpt2[..., 0]).pow(2) + (kpt1[:, None, :, 1] - kpt2[..., 1]).pow(2) # (N, M, 17) - sigma = torch.tensor(sigma, device=kpt1.device, dtype=kpt1.dtype) # (17, ) - kpt_mask = kpt1[..., 2] != 0 # (N, 17) - e = d / (2 * sigma).pow(2) / (area[:, None, None] + eps) / 2 # from cocoeval - # e = d / ((area[None, :, None] + eps) * sigma) ** 2 / 2 # from formula - return ((-e).exp() * kpt_mask[:, None]).sum(-1) / (kpt_mask.sum(-1)[:, None] + eps) - - -def _get_covariance_matrix(boxes): - """ - Generating covariance matrix from obbs. - - Args: - boxes (torch.Tensor): A tensor of shape (N, 5) representing rotated bounding boxes, with xywhr format. - - Returns: - (torch.Tensor): Covariance metrixs corresponding to original rotated bounding boxes. - """ - # Gaussian bounding boxes, ignore the center points (the first two columns) because they are not needed here. - gbbs = torch.cat((boxes[:, 2:4].pow(2) / 12, boxes[:, 4:]), dim=-1) - a, b, c = gbbs.split(1, dim=-1) - cos = c.cos() - sin = c.sin() - cos2 = cos.pow(2) - sin2 = sin.pow(2) - return a * cos2 + b * sin2, a * sin2 + b * cos2, (a - b) * cos * sin - - -def probiou(obb1, obb2, CIoU=False, eps=1e-7): - """ - Calculate the prob IoU between oriented bounding boxes, https://arxiv.org/pdf/2106.06072v1.pdf. - - Args: - obb1 (torch.Tensor): A tensor of shape (N, 5) representing ground truth obbs, with xywhr format. - obb2 (torch.Tensor): A tensor of shape (N, 5) representing predicted obbs, with xywhr format. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): A tensor of shape (N, ) representing obb similarities. - """ - x1, y1 = obb1[..., :2].split(1, dim=-1) - x2, y2 = obb2[..., :2].split(1, dim=-1) - a1, b1, c1 = _get_covariance_matrix(obb1) - a2, b2, c2 = _get_covariance_matrix(obb2) - - t1 = ( - ((a1 + a2) * (y1 - y2).pow(2) + (b1 + b2) * (x1 - x2).pow(2)) / ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2) + eps) - ) * 0.25 - t2 = (((c1 + c2) * (x2 - x1) * (y1 - y2)) / ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2) + eps)) * 0.5 - t3 = ( - ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2)) - / (4 * ((a1 * b1 - c1.pow(2)).clamp_(0) * (a2 * b2 - c2.pow(2)).clamp_(0)).sqrt() + eps) - + eps - ).log() * 0.5 - bd = (t1 + t2 + t3).clamp(eps, 100.0) - hd = (1.0 - (-bd).exp() + eps).sqrt() - iou = 1 - hd - if CIoU: # only include the wh aspect ratio part - w1, h1 = obb1[..., 2:4].split(1, dim=-1) - w2, h2 = obb2[..., 2:4].split(1, dim=-1) - v = (4 / math.pi**2) * ((w2 / h2).atan() - (w1 / h1).atan()).pow(2) - with torch.no_grad(): - alpha = v / (v - iou + (1 + eps)) - return iou - v * alpha # CIoU - return iou - - -def batch_probiou(obb1, obb2, eps=1e-7): - """ - Calculate the prob IoU between oriented bounding boxes, https://arxiv.org/pdf/2106.06072v1.pdf. - - Args: - obb1 (torch.Tensor | np.ndarray): A tensor of shape (N, 5) representing ground truth obbs, with xywhr format. - obb2 (torch.Tensor | np.ndarray): A tensor of shape (M, 5) representing predicted obbs, with xywhr format. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. - - Returns: - (torch.Tensor): A tensor of shape (N, M) representing obb similarities. - """ - obb1 = torch.from_numpy(obb1) if isinstance(obb1, np.ndarray) else obb1 - obb2 = torch.from_numpy(obb2) if isinstance(obb2, np.ndarray) else obb2 - - x1, y1 = obb1[..., :2].split(1, dim=-1) - x2, y2 = (x.squeeze(-1)[None] for x in obb2[..., :2].split(1, dim=-1)) - a1, b1, c1 = _get_covariance_matrix(obb1) - a2, b2, c2 = (x.squeeze(-1)[None] for x in _get_covariance_matrix(obb2)) - - t1 = ( - ((a1 + a2) * (y1 - y2).pow(2) + (b1 + b2) * (x1 - x2).pow(2)) / ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2) + eps) - ) * 0.25 - t2 = (((c1 + c2) * (x2 - x1) * (y1 - y2)) / ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2) + eps)) * 0.5 - t3 = ( - ((a1 + a2) * (b1 + b2) - (c1 + c2).pow(2)) - / (4 * ((a1 * b1 - c1.pow(2)).clamp_(0) * (a2 * b2 - c2.pow(2)).clamp_(0)).sqrt() + eps) - + eps - ).log() * 0.5 - bd = (t1 + t2 + t3).clamp(eps, 100.0) - hd = (1.0 - (-bd).exp() + eps).sqrt() - return 1 - hd - - -def smooth_BCE(eps=0.1): - """ - Computes smoothed positive and negative Binary Cross-Entropy targets. - - This function calculates positive and negative label smoothing BCE targets based on a given epsilon value. - For implementation details, refer to https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441. - - Args: - eps (float, optional): The epsilon value for label smoothing. Defaults to 0.1. - - Returns: - (tuple): A tuple containing the positive and negative label smoothing BCE targets. - """ - return 1.0 - 0.5 * eps, 0.5 * eps - - -class ConfusionMatrix: - """ - A class for calculating and updating a confusion matrix for object detection and classification tasks. - - Attributes: - task (str): The type of task, either 'detect' or 'classify'. - matrix (np.ndarray): The confusion matrix, with dimensions depending on the task. - nc (int): The number of classes. - conf (float): The confidence threshold for detections. - iou_thres (float): The Intersection over Union threshold. - """ - - def __init__(self, nc, conf=0.25, iou_thres=0.45, task="detect"): - """Initialize attributes for the YOLO model.""" - self.task = task - self.matrix = np.zeros((nc + 1, nc + 1)) if self.task == "detect" else np.zeros((nc, nc)) - self.nc = nc # number of classes - self.conf = 0.25 if conf in (None, 0.001) else conf # apply 0.25 if default val conf is passed - self.iou_thres = iou_thres - - def process_cls_preds(self, preds, targets): - """ - Update confusion matrix for classification task. - - Args: - preds (Array[N, min(nc,5)]): Predicted class labels. - targets (Array[N, 1]): Ground truth class labels. - """ - preds, targets = torch.cat(preds)[:, 0], torch.cat(targets) - for p, t in zip(preds.cpu().numpy(), targets.cpu().numpy()): - self.matrix[p][t] += 1 - - def process_batch(self, detections, gt_bboxes, gt_cls): - """ - Update confusion matrix for object detection task. - - Args: - detections (Array[N, 6] | Array[N, 7]): Detected bounding boxes and their associated information. - Each row should contain (x1, y1, x2, y2, conf, class) - or with an additional element `angle` when it's obb. - gt_bboxes (Array[M, 4]| Array[N, 5]): Ground truth bounding boxes with xyxy/xyxyr format. - gt_cls (Array[M]): The class labels. - """ - if gt_cls.shape[0] == 0: # Check if labels is empty - if detections is not None: - detections = detections[detections[:, 4] > self.conf] - detection_classes = detections[:, 5].int() - for dc in detection_classes: - self.matrix[dc, self.nc] += 1 # false positives - return - if detections is None: - gt_classes = gt_cls.int() - for gc in gt_classes: - self.matrix[self.nc, gc] += 1 # background FN - return - - detections = detections[detections[:, 4] > self.conf] - gt_classes = gt_cls.int() - detection_classes = detections[:, 5].int() - is_obb = detections.shape[1] == 7 and gt_bboxes.shape[1] == 5 # with additional `angle` dimension - iou = ( - batch_probiou(gt_bboxes, torch.cat([detections[:, :4], detections[:, -1:]], dim=-1)) - if is_obb - else box_iou(gt_bboxes, detections[:, :4]) - ) - - x = torch.where(iou > self.iou_thres) - if x[0].shape[0]: - matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() - if x[0].shape[0] > 1: - matches = matches[matches[:, 2].argsort()[::-1]] - matches = matches[np.unique(matches[:, 1], return_index=True)[1]] - matches = matches[matches[:, 2].argsort()[::-1]] - matches = matches[np.unique(matches[:, 0], return_index=True)[1]] - else: - matches = np.zeros((0, 3)) - - n = matches.shape[0] > 0 - m0, m1, _ = matches.transpose().astype(int) - for i, gc in enumerate(gt_classes): - j = m0 == i - if n and sum(j) == 1: - self.matrix[detection_classes[m1[j]], gc] += 1 # correct - else: - self.matrix[self.nc, gc] += 1 # true background - - if n: - for i, dc in enumerate(detection_classes): - if not any(m1 == i): - self.matrix[dc, self.nc] += 1 # predicted background - - def matrix(self): - """Returns the confusion matrix.""" - return self.matrix - - def tp_fp(self): - """Returns true positives and false positives.""" - tp = self.matrix.diagonal() # true positives - fp = self.matrix.sum(1) - tp # false positives - # fn = self.matrix.sum(0) - tp # false negatives (missed detections) - return (tp[:-1], fp[:-1]) if self.task == "detect" else (tp, fp) # remove background class if task=detect - - @TryExcept("WARNING ⚠️ ConfusionMatrix plot failure") - @plt_settings() - def plot(self, normalize=True, save_dir="", names=(), on_plot=None): - """ - Plot the confusion matrix using seaborn and save it to a file. - - Args: - normalize (bool): Whether to normalize the confusion matrix. - save_dir (str): Directory where the plot will be saved. - names (tuple): Names of classes, used as labels on the plot. - on_plot (func): An optional callback to pass plots path and data when they are rendered. - """ - import seaborn as sn - - array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1e-9) if normalize else 1) # normalize columns - array[array < 0.005] = np.nan # don't annotate (would appear as 0.00) - - fig, ax = plt.subplots(1, 1, figsize=(12, 9), tight_layout=True) - nc, nn = self.nc, len(names) # number of classes, names - sn.set(font_scale=1.0 if nc < 50 else 0.8) # for label size - labels = (0 < nn < 99) and (nn == nc) # apply names to ticklabels - ticklabels = (list(names) + ["background"]) if labels else "auto" - with warnings.catch_warnings(): - warnings.simplefilter("ignore") # suppress empty matrix RuntimeWarning: All-NaN slice encountered - sn.heatmap( - array, - ax=ax, - annot=nc < 30, - annot_kws={"size": 8}, - cmap="Blues", - fmt=".2f" if normalize else ".0f", - square=True, - vmin=0.0, - xticklabels=ticklabels, - yticklabels=ticklabels, - ).set_facecolor((1, 1, 1)) - title = "Confusion Matrix" + " Normalized" * normalize - ax.set_xlabel("True") - ax.set_ylabel("Predicted") - ax.set_title(title) - plot_fname = Path(save_dir) / f'{title.lower().replace(" ", "_")}.png' - fig.savefig(plot_fname, dpi=250) - plt.close(fig) - if on_plot: - on_plot(plot_fname) - - def print(self): - """Print the confusion matrix to the console.""" - for i in range(self.nc + 1): - LOGGER.info(" ".join(map(str, self.matrix[i]))) - - -def smooth(y, f=0.05): - """Box filter of fraction f.""" - nf = round(len(y) * f * 2) // 2 + 1 # number of filter elements (must be odd) - p = np.ones(nf // 2) # ones padding - yp = np.concatenate((p * y[0], y, p * y[-1]), 0) # y padded - return np.convolve(yp, np.ones(nf) / nf, mode="valid") # y-smoothed - - -@plt_settings() -def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names=(), on_plot=None): - """Plots a precision-recall curve.""" - fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) - py = np.stack(py, axis=1) - - if 0 < len(names) < 21: # display per-class legend if < 21 classes - for i, y in enumerate(py.T): - ax.plot(px, y, linewidth=1, label=f"{names[i]} {ap[i, 0]:.3f}") # plot(recall, precision) - else: - ax.plot(px, py, linewidth=1, color="grey") # plot(recall, precision) - - ax.plot(px, py.mean(1), linewidth=3, color="blue", label="all classes %.3f mAP@0.5" % ap[:, 0].mean()) - ax.set_xlabel("Recall") - ax.set_ylabel("Precision") - ax.set_xlim(0, 1) - ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") - ax.set_title("Precision-Recall Curve") - fig.savefig(save_dir, dpi=250) - plt.close(fig) - if on_plot: - on_plot(save_dir) - - -@plt_settings() -def plot_mc_curve(px, py, save_dir=Path("mc_curve.png"), names=(), xlabel="Confidence", ylabel="Metric", on_plot=None): - """Plots a metric-confidence curve.""" - fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) - - if 0 < len(names) < 21: # display per-class legend if < 21 classes - for i, y in enumerate(py): - ax.plot(px, y, linewidth=1, label=f"{names[i]}") # plot(confidence, metric) - else: - ax.plot(px, py.T, linewidth=1, color="grey") # plot(confidence, metric) - - y = smooth(py.mean(0), 0.05) - ax.plot(px, y, linewidth=3, color="blue", label=f"all classes {y.max():.2f} at {px[y.argmax()]:.3f}") - ax.set_xlabel(xlabel) - ax.set_ylabel(ylabel) - ax.set_xlim(0, 1) - ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") - ax.set_title(f"{ylabel}-Confidence Curve") - fig.savefig(save_dir, dpi=250) - plt.close(fig) - if on_plot: - on_plot(save_dir) - - -def compute_ap(recall, precision): - """ - Compute the average precision (AP) given the recall and precision curves. - - Args: - recall (list): The recall curve. - precision (list): The precision curve. - - Returns: - (float): Average precision. - (np.ndarray): Precision envelope curve. - (np.ndarray): Modified recall curve with sentinel values added at the beginning and end. - """ - - # Append sentinel values to beginning and end - mrec = np.concatenate(([0.0], recall, [1.0])) - mpre = np.concatenate(([1.0], precision, [0.0])) - - # Compute the precision envelope - mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) - - # Integrate area under curve - method = "interp" # methods: 'continuous', 'interp' - if method == "interp": - x = np.linspace(0, 1, 101) # 101-point interp (COCO) - ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate - else: # 'continuous' - i = np.where(mrec[1:] != mrec[:-1])[0] # points where x-axis (recall) changes - ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve - - return ap, mpre, mrec - - -def ap_per_class( - tp, conf, pred_cls, target_cls, plot=False, on_plot=None, save_dir=Path(), names=(), eps=1e-16, prefix="" -): - """ - Computes the average precision per class for object detection evaluation. - - Args: - tp (np.ndarray): Binary array indicating whether the detection is correct (True) or not (False). - conf (np.ndarray): Array of confidence scores of the detections. - pred_cls (np.ndarray): Array of predicted classes of the detections. - target_cls (np.ndarray): Array of true classes of the detections. - plot (bool, optional): Whether to plot PR curves or not. Defaults to False. - on_plot (func, optional): A callback to pass plots path and data when they are rendered. Defaults to None. - save_dir (Path, optional): Directory to save the PR curves. Defaults to an empty path. - names (tuple, optional): Tuple of class names to plot PR curves. Defaults to an empty tuple. - eps (float, optional): A small value to avoid division by zero. Defaults to 1e-16. - prefix (str, optional): A prefix string for saving the plot files. Defaults to an empty string. - - Returns: - (tuple): A tuple of six arrays and one array of unique classes, where: - tp (np.ndarray): True positive counts at threshold given by max F1 metric for each class.Shape: (nc,). - fp (np.ndarray): False positive counts at threshold given by max F1 metric for each class. Shape: (nc,). - p (np.ndarray): Precision values at threshold given by max F1 metric for each class. Shape: (nc,). - r (np.ndarray): Recall values at threshold given by max F1 metric for each class. Shape: (nc,). - f1 (np.ndarray): F1-score values at threshold given by max F1 metric for each class. Shape: (nc,). - ap (np.ndarray): Average precision for each class at different IoU thresholds. Shape: (nc, 10). - unique_classes (np.ndarray): An array of unique classes that have data. Shape: (nc,). - p_curve (np.ndarray): Precision curves for each class. Shape: (nc, 1000). - r_curve (np.ndarray): Recall curves for each class. Shape: (nc, 1000). - f1_curve (np.ndarray): F1-score curves for each class. Shape: (nc, 1000). - x (np.ndarray): X-axis values for the curves. Shape: (1000,). - prec_values: Precision values at mAP@0.5 for each class. Shape: (nc, 1000). - """ - - # Sort by objectness - i = np.argsort(-conf) - tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] - - # Find unique classes - unique_classes, nt = np.unique(target_cls, return_counts=True) - nc = unique_classes.shape[0] # number of classes, number of detections - - # Create Precision-Recall curve and compute AP for each class - x, prec_values = np.linspace(0, 1, 1000), [] - - # Average precision, precision and recall curves - ap, p_curve, r_curve = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000)) - for ci, c in enumerate(unique_classes): - i = pred_cls == c - n_l = nt[ci] # number of labels - n_p = i.sum() # number of predictions - if n_p == 0 or n_l == 0: - continue - - # Accumulate FPs and TPs - fpc = (1 - tp[i]).cumsum(0) - tpc = tp[i].cumsum(0) - - # Recall - recall = tpc / (n_l + eps) # recall curve - r_curve[ci] = np.interp(-x, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases - - # Precision - precision = tpc / (tpc + fpc) # precision curve - p_curve[ci] = np.interp(-x, -conf[i], precision[:, 0], left=1) # p at pr_score - - # AP from recall-precision curve - for j in range(tp.shape[1]): - ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j]) - if plot and j == 0: - prec_values.append(np.interp(x, mrec, mpre)) # precision at mAP@0.5 - - prec_values = np.array(prec_values) # (nc, 1000) - - # Compute F1 (harmonic mean of precision and recall) - f1_curve = 2 * p_curve * r_curve / (p_curve + r_curve + eps) - names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data - names = dict(enumerate(names)) # to dict - if plot: - plot_pr_curve(x, prec_values, ap, save_dir / f"{prefix}PR_curve.png", names, on_plot=on_plot) - plot_mc_curve(x, f1_curve, save_dir / f"{prefix}F1_curve.png", names, ylabel="F1", on_plot=on_plot) - plot_mc_curve(x, p_curve, save_dir / f"{prefix}P_curve.png", names, ylabel="Precision", on_plot=on_plot) - plot_mc_curve(x, r_curve, save_dir / f"{prefix}R_curve.png", names, ylabel="Recall", on_plot=on_plot) - - i = smooth(f1_curve.mean(0), 0.1).argmax() # max F1 index - p, r, f1 = p_curve[:, i], r_curve[:, i], f1_curve[:, i] # max-F1 precision, recall, F1 values - tp = (r * nt).round() # true positives - fp = (tp / (p + eps) - tp).round() # false positives - return tp, fp, p, r, f1, ap, unique_classes.astype(int), p_curve, r_curve, f1_curve, x, prec_values - - -class Metric(SimpleClass): - """ - Class for computing evaluation metrics for YOLOv8 model. - - Attributes: - p (list): Precision for each class. Shape: (nc,). - r (list): Recall for each class. Shape: (nc,). - f1 (list): F1 score for each class. Shape: (nc,). - all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10). - ap_class_index (list): Index of class for each AP score. Shape: (nc,). - nc (int): Number of classes. - - Methods: - ap50(): AP at IoU threshold of 0.5 for all classes. Returns: List of AP scores. Shape: (nc,) or []. - ap(): AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: List of AP scores. Shape: (nc,) or []. - mp(): Mean precision of all classes. Returns: Float. - mr(): Mean recall of all classes. Returns: Float. - map50(): Mean AP at IoU threshold of 0.5 for all classes. Returns: Float. - map75(): Mean AP at IoU threshold of 0.75 for all classes. Returns: Float. - map(): Mean AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: Float. - mean_results(): Mean of results, returns mp, mr, map50, map. - class_result(i): Class-aware result, returns p[i], r[i], ap50[i], ap[i]. - maps(): mAP of each class. Returns: Array of mAP scores, shape: (nc,). - fitness(): Model fitness as a weighted combination of metrics. Returns: Float. - update(results): Update metric attributes with new evaluation results. - """ - - def __init__(self) -> None: - """Initializes a Metric instance for computing evaluation metrics for the YOLOv8 model.""" - self.p = [] # (nc, ) - self.r = [] # (nc, ) - self.f1 = [] # (nc, ) - self.all_ap = [] # (nc, 10) - self.ap_class_index = [] # (nc, ) - self.nc = 0 - - @property - def ap50(self): - """ - Returns the Average Precision (AP) at an IoU threshold of 0.5 for all classes. - - Returns: - (np.ndarray, list): Array of shape (nc,) with AP50 values per class, or an empty list if not available. - """ - return self.all_ap[:, 0] if len(self.all_ap) else [] - - @property - def ap(self): - """ - Returns the Average Precision (AP) at an IoU threshold of 0.5-0.95 for all classes. - - Returns: - (np.ndarray, list): Array of shape (nc,) with AP50-95 values per class, or an empty list if not available. - """ - return self.all_ap.mean(1) if len(self.all_ap) else [] - - @property - def mp(self): - """ - Returns the Mean Precision of all classes. - - Returns: - (float): The mean precision of all classes. - """ - return self.p.mean() if len(self.p) else 0.0 - - @property - def mr(self): - """ - Returns the Mean Recall of all classes. - - Returns: - (float): The mean recall of all classes. - """ - return self.r.mean() if len(self.r) else 0.0 - - @property - def map50(self): - """ - Returns the mean Average Precision (mAP) at an IoU threshold of 0.5. - - Returns: - (float): The mAP at an IoU threshold of 0.5. - """ - return self.all_ap[:, 0].mean() if len(self.all_ap) else 0.0 - - @property - def map75(self): - """ - Returns the mean Average Precision (mAP) at an IoU threshold of 0.75. - - Returns: - (float): The mAP at an IoU threshold of 0.75. - """ - return self.all_ap[:, 5].mean() if len(self.all_ap) else 0.0 - - @property - def map(self): - """ - Returns the mean Average Precision (mAP) over IoU thresholds of 0.5 - 0.95 in steps of 0.05. - - Returns: - (float): The mAP over IoU thresholds of 0.5 - 0.95 in steps of 0.05. - """ - return self.all_ap.mean() if len(self.all_ap) else 0.0 - - def mean_results(self): - """Mean of results, return mp, mr, map50, map.""" - return [self.mp, self.mr, self.map50, self.map] - - def class_result(self, i): - """Class-aware result, return p[i], r[i], ap50[i], ap[i].""" - return self.p[i], self.r[i], self.ap50[i], self.ap[i] - - @property - def maps(self): - """MAP of each class.""" - maps = np.zeros(self.nc) + self.map - for i, c in enumerate(self.ap_class_index): - maps[c] = self.ap[i] - return maps - - def fitness(self): - """Model fitness as a weighted combination of metrics.""" - w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] - return (np.array(self.mean_results()) * w).sum() - - def update(self, results): - """ - Updates the evaluation metrics of the model with a new set of results. - - Args: - results (tuple): A tuple containing the following evaluation metrics: - - p (list): Precision for each class. Shape: (nc,). - - r (list): Recall for each class. Shape: (nc,). - - f1 (list): F1 score for each class. Shape: (nc,). - - all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10). - - ap_class_index (list): Index of class for each AP score. Shape: (nc,). - - Side Effects: - Updates the class attributes `self.p`, `self.r`, `self.f1`, `self.all_ap`, and `self.ap_class_index` based - on the values provided in the `results` tuple. - """ - ( - self.p, - self.r, - self.f1, - self.all_ap, - self.ap_class_index, - self.p_curve, - self.r_curve, - self.f1_curve, - self.px, - self.prec_values, - ) = results - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [] - - @property - def curves_results(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [ - [self.px, self.prec_values, "Recall", "Precision"], - [self.px, self.f1_curve, "Confidence", "F1"], - [self.px, self.p_curve, "Confidence", "Precision"], - [self.px, self.r_curve, "Confidence", "Recall"], - ] - - -class DetMetrics(SimpleClass): - """ - This class is a utility class for computing detection metrics such as precision, recall, and mean average precision - (mAP) of an object detection model. - - Args: - save_dir (Path): A path to the directory where the output plots will be saved. Defaults to current directory. - plot (bool): A flag that indicates whether to plot precision-recall curves for each class. Defaults to False. - on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. - names (tuple of str): A tuple of strings that represents the names of the classes. Defaults to an empty tuple. - - Attributes: - save_dir (Path): A path to the directory where the output plots will be saved. - plot (bool): A flag that indicates whether to plot the precision-recall curves for each class. - on_plot (func): An optional callback to pass plots path and data when they are rendered. - names (tuple of str): A tuple of strings that represents the names of the classes. - box (Metric): An instance of the Metric class for storing the results of the detection metrics. - speed (dict): A dictionary for storing the execution time of different parts of the detection process. - - Methods: - process(tp, conf, pred_cls, target_cls): Updates the metric results with the latest batch of predictions. - keys: Returns a list of keys for accessing the computed detection metrics. - mean_results: Returns a list of mean values for the computed detection metrics. - class_result(i): Returns a list of values for the computed detection metrics for a specific class. - maps: Returns a dictionary of mean average precision (mAP) values for different IoU thresholds. - fitness: Computes the fitness score based on the computed detection metrics. - ap_class_index: Returns a list of class indices sorted by their average precision (AP) values. - results_dict: Returns a dictionary that maps detection metric keys to their computed values. - curves: TODO - curves_results: TODO - """ - - def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None: - """Initialize a DetMetrics instance with a save directory, plot flag, callback function, and class names.""" - self.save_dir = save_dir - self.plot = plot - self.on_plot = on_plot - self.names = names - self.box = Metric() - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - self.task = "detect" - - def process(self, tp, conf, pred_cls, target_cls): - """Process predicted results for object detection and update metrics.""" - results = ap_per_class( - tp, - conf, - pred_cls, - target_cls, - plot=self.plot, - save_dir=self.save_dir, - names=self.names, - on_plot=self.on_plot, - )[2:] - self.box.nc = len(self.names) - self.box.update(results) - - @property - def keys(self): - """Returns a list of keys for accessing specific metrics.""" - return ["metrics/precision(B)", "metrics/recall(B)", "metrics/mAP50(B)", "metrics/mAP50-95(B)"] - - def mean_results(self): - """Calculate mean of detected objects & return precision, recall, mAP50, and mAP50-95.""" - return self.box.mean_results() - - def class_result(self, i): - """Return the result of evaluating the performance of an object detection model on a specific class.""" - return self.box.class_result(i) - - @property - def maps(self): - """Returns mean Average Precision (mAP) scores per class.""" - return self.box.maps - - @property - def fitness(self): - """Returns the fitness of box object.""" - return self.box.fitness() - - @property - def ap_class_index(self): - """Returns the average precision index per class.""" - return self.box.ap_class_index - - @property - def results_dict(self): - """Returns dictionary of computed performance metrics and statistics.""" - return dict(zip(self.keys + ["fitness"], self.mean_results() + [self.fitness])) - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return ["Precision-Recall(B)", "F1-Confidence(B)", "Precision-Confidence(B)", "Recall-Confidence(B)"] - - @property - def curves_results(self): - """Returns dictionary of computed performance metrics and statistics.""" - return self.box.curves_results - - -class SegmentMetrics(SimpleClass): - """ - Calculates and aggregates detection and segmentation metrics over a given set of classes. - - Args: - save_dir (Path): Path to the directory where the output plots should be saved. Default is the current directory. - plot (bool): Whether to save the detection and segmentation plots. Default is False. - on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. - names (list): List of class names. Default is an empty list. - - Attributes: - save_dir (Path): Path to the directory where the output plots should be saved. - plot (bool): Whether to save the detection and segmentation plots. - on_plot (func): An optional callback to pass plots path and data when they are rendered. - names (list): List of class names. - box (Metric): An instance of the Metric class to calculate box detection metrics. - seg (Metric): An instance of the Metric class to calculate mask segmentation metrics. - speed (dict): Dictionary to store the time taken in different phases of inference. - - Methods: - process(tp_m, tp_b, conf, pred_cls, target_cls): Processes metrics over the given set of predictions. - mean_results(): Returns the mean of the detection and segmentation metrics over all the classes. - class_result(i): Returns the detection and segmentation metrics of class `i`. - maps: Returns the mean Average Precision (mAP) scores for IoU thresholds ranging from 0.50 to 0.95. - fitness: Returns the fitness scores, which are a single weighted combination of metrics. - ap_class_index: Returns the list of indices of classes used to compute Average Precision (AP). - results_dict: Returns the dictionary containing all the detection and segmentation metrics and fitness score. - """ - - def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None: - """Initialize a SegmentMetrics instance with a save directory, plot flag, callback function, and class names.""" - self.save_dir = save_dir - self.plot = plot - self.on_plot = on_plot - self.names = names - self.box = Metric() - self.seg = Metric() - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - self.task = "segment" - - def process(self, tp, tp_m, conf, pred_cls, target_cls): - """ - Processes the detection and segmentation metrics over the given set of predictions. - - Args: - tp (list): List of True Positive boxes. - tp_m (list): List of True Positive masks. - conf (list): List of confidence scores. - pred_cls (list): List of predicted classes. - target_cls (list): List of target classes. - """ - - results_mask = ap_per_class( - tp_m, - conf, - pred_cls, - target_cls, - plot=self.plot, - on_plot=self.on_plot, - save_dir=self.save_dir, - names=self.names, - prefix="Mask", - )[2:] - self.seg.nc = len(self.names) - self.seg.update(results_mask) - results_box = ap_per_class( - tp, - conf, - pred_cls, - target_cls, - plot=self.plot, - on_plot=self.on_plot, - save_dir=self.save_dir, - names=self.names, - prefix="Box", - )[2:] - self.box.nc = len(self.names) - self.box.update(results_box) - - @property - def keys(self): - """Returns a list of keys for accessing metrics.""" - return [ - "metrics/precision(B)", - "metrics/recall(B)", - "metrics/mAP50(B)", - "metrics/mAP50-95(B)", - "metrics/precision(M)", - "metrics/recall(M)", - "metrics/mAP50(M)", - "metrics/mAP50-95(M)", - ] - - def mean_results(self): - """Return the mean metrics for bounding box and segmentation results.""" - return self.box.mean_results() + self.seg.mean_results() - - def class_result(self, i): - """Returns classification results for a specified class index.""" - return self.box.class_result(i) + self.seg.class_result(i) - - @property - def maps(self): - """Returns mAP scores for object detection and semantic segmentation models.""" - return self.box.maps + self.seg.maps - - @property - def fitness(self): - """Get the fitness score for both segmentation and bounding box models.""" - return self.seg.fitness() + self.box.fitness() - - @property - def ap_class_index(self): - """Boxes and masks have the same ap_class_index.""" - return self.box.ap_class_index - - @property - def results_dict(self): - """Returns results of object detection model for evaluation.""" - return dict(zip(self.keys + ["fitness"], self.mean_results() + [self.fitness])) - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [ - "Precision-Recall(B)", - "F1-Confidence(B)", - "Precision-Confidence(B)", - "Recall-Confidence(B)", - "Precision-Recall(M)", - "F1-Confidence(M)", - "Precision-Confidence(M)", - "Recall-Confidence(M)", - ] - - @property - def curves_results(self): - """Returns dictionary of computed performance metrics and statistics.""" - return self.box.curves_results + self.seg.curves_results - - -class PoseMetrics(SegmentMetrics): - """ - Calculates and aggregates detection and pose metrics over a given set of classes. - - Args: - save_dir (Path): Path to the directory where the output plots should be saved. Default is the current directory. - plot (bool): Whether to save the detection and segmentation plots. Default is False. - on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. - names (list): List of class names. Default is an empty list. - - Attributes: - save_dir (Path): Path to the directory where the output plots should be saved. - plot (bool): Whether to save the detection and segmentation plots. - on_plot (func): An optional callback to pass plots path and data when they are rendered. - names (list): List of class names. - box (Metric): An instance of the Metric class to calculate box detection metrics. - pose (Metric): An instance of the Metric class to calculate mask segmentation metrics. - speed (dict): Dictionary to store the time taken in different phases of inference. - - Methods: - process(tp_m, tp_b, conf, pred_cls, target_cls): Processes metrics over the given set of predictions. - mean_results(): Returns the mean of the detection and segmentation metrics over all the classes. - class_result(i): Returns the detection and segmentation metrics of class `i`. - maps: Returns the mean Average Precision (mAP) scores for IoU thresholds ranging from 0.50 to 0.95. - fitness: Returns the fitness scores, which are a single weighted combination of metrics. - ap_class_index: Returns the list of indices of classes used to compute Average Precision (AP). - results_dict: Returns the dictionary containing all the detection and segmentation metrics and fitness score. - """ - - def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None: - """Initialize the PoseMetrics class with directory path, class names, and plotting options.""" - super().__init__(save_dir, plot, names) - self.save_dir = save_dir - self.plot = plot - self.on_plot = on_plot - self.names = names - self.box = Metric() - self.pose = Metric() - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - self.task = "pose" - - def process(self, tp, tp_p, conf, pred_cls, target_cls): - """ - Processes the detection and pose metrics over the given set of predictions. - - Args: - tp (list): List of True Positive boxes. - tp_p (list): List of True Positive keypoints. - conf (list): List of confidence scores. - pred_cls (list): List of predicted classes. - target_cls (list): List of target classes. - """ - - results_pose = ap_per_class( - tp_p, - conf, - pred_cls, - target_cls, - plot=self.plot, - on_plot=self.on_plot, - save_dir=self.save_dir, - names=self.names, - prefix="Pose", - )[2:] - self.pose.nc = len(self.names) - self.pose.update(results_pose) - results_box = ap_per_class( - tp, - conf, - pred_cls, - target_cls, - plot=self.plot, - on_plot=self.on_plot, - save_dir=self.save_dir, - names=self.names, - prefix="Box", - )[2:] - self.box.nc = len(self.names) - self.box.update(results_box) - - @property - def keys(self): - """Returns list of evaluation metric keys.""" - return [ - "metrics/precision(B)", - "metrics/recall(B)", - "metrics/mAP50(B)", - "metrics/mAP50-95(B)", - "metrics/precision(P)", - "metrics/recall(P)", - "metrics/mAP50(P)", - "metrics/mAP50-95(P)", - ] - - def mean_results(self): - """Return the mean results of box and pose.""" - return self.box.mean_results() + self.pose.mean_results() - - def class_result(self, i): - """Return the class-wise detection results for a specific class i.""" - return self.box.class_result(i) + self.pose.class_result(i) - - @property - def maps(self): - """Returns the mean average precision (mAP) per class for both box and pose detections.""" - return self.box.maps + self.pose.maps - - @property - def fitness(self): - """Computes classification metrics and speed using the `targets` and `pred` inputs.""" - return self.pose.fitness() + self.box.fitness() - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [ - "Precision-Recall(B)", - "F1-Confidence(B)", - "Precision-Confidence(B)", - "Recall-Confidence(B)", - "Precision-Recall(P)", - "F1-Confidence(P)", - "Precision-Confidence(P)", - "Recall-Confidence(P)", - ] - - @property - def curves_results(self): - """Returns dictionary of computed performance metrics and statistics.""" - return self.box.curves_results + self.pose.curves_results - - -class ClassifyMetrics(SimpleClass): - """ - Class for computing classification metrics including top-1 and top-5 accuracy. - - Attributes: - top1 (float): The top-1 accuracy. - top5 (float): The top-5 accuracy. - speed (Dict[str, float]): A dictionary containing the time taken for each step in the pipeline. - - Properties: - fitness (float): The fitness of the model, which is equal to top-5 accuracy. - results_dict (Dict[str, Union[float, str]]): A dictionary containing the classification metrics and fitness. - keys (List[str]): A list of keys for the results_dict. - - Methods: - process(targets, pred): Processes the targets and predictions to compute classification metrics. - """ - - def __init__(self) -> None: - """Initialize a ClassifyMetrics instance.""" - self.top1 = 0 - self.top5 = 0 - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - self.task = "classify" - - def process(self, targets, pred): - """Target classes and predicted classes.""" - pred, targets = torch.cat(pred), torch.cat(targets) - correct = (targets[:, None] == pred).float() - acc = torch.stack((correct[:, 0], correct.max(1).values), dim=1) # (top1, top5) accuracy - self.top1, self.top5 = acc.mean(0).tolist() - - @property - def fitness(self): - """Returns mean of top-1 and top-5 accuracies as fitness score.""" - return (self.top1 + self.top5) / 2 - - @property - def results_dict(self): - """Returns a dictionary with model's performance metrics and fitness score.""" - return dict(zip(self.keys + ["fitness"], [self.top1, self.top5, self.fitness])) - - @property - def keys(self): - """Returns a list of keys for the results_dict property.""" - return ["metrics/accuracy_top1", "metrics/accuracy_top5"] - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [] - - @property - def curves_results(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [] - - -class OBBMetrics(SimpleClass): - def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None: - self.save_dir = save_dir - self.plot = plot - self.on_plot = on_plot - self.names = names - self.box = Metric() - self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0} - - def process(self, tp, conf, pred_cls, target_cls): - """Process predicted results for object detection and update metrics.""" - results = ap_per_class( - tp, - conf, - pred_cls, - target_cls, - plot=self.plot, - save_dir=self.save_dir, - names=self.names, - on_plot=self.on_plot, - )[2:] - self.box.nc = len(self.names) - self.box.update(results) - - @property - def keys(self): - """Returns a list of keys for accessing specific metrics.""" - return ["metrics/precision(B)", "metrics/recall(B)", "metrics/mAP50(B)", "metrics/mAP50-95(B)"] - - def mean_results(self): - """Calculate mean of detected objects & return precision, recall, mAP50, and mAP50-95.""" - return self.box.mean_results() - - def class_result(self, i): - """Return the result of evaluating the performance of an object detection model on a specific class.""" - return self.box.class_result(i) - - @property - def maps(self): - """Returns mean Average Precision (mAP) scores per class.""" - return self.box.maps - - @property - def fitness(self): - """Returns the fitness of box object.""" - return self.box.fitness() - - @property - def ap_class_index(self): - """Returns the average precision index per class.""" - return self.box.ap_class_index - - @property - def results_dict(self): - """Returns dictionary of computed performance metrics and statistics.""" - return dict(zip(self.keys + ["fitness"], self.mean_results() + [self.fitness])) - - @property - def curves(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [] - - @property - def curves_results(self): - """Returns a list of curves for accessing specific metrics curves.""" - return [] diff --git a/ultralytics-main/ultralytics/utils/ops.py b/ultralytics-main/ultralytics/utils/ops.py deleted file mode 100644 index 439f944..0000000 --- a/ultralytics-main/ultralytics/utils/ops.py +++ /dev/null @@ -1,849 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import math -import re -import time - -import cv2 -import numpy as np -import torch -import torch.nn.functional as F -import torchvision - -from ultralytics.utils import LOGGER -from ultralytics.utils.metrics import batch_probiou - - -class Profile(contextlib.ContextDecorator): - """ - YOLOv8 Profile class. Use as a decorator with @Profile() or as a context manager with 'with Profile():'. - - Example: - ```python - from ultralytics.utils.ops import Profile - - with Profile(device=device) as dt: - pass # slow operation here - - print(dt) # prints "Elapsed time is 9.5367431640625e-07 s" - ``` - """ - - def __init__(self, t=0.0, device: torch.device = None): - """ - Initialize the Profile class. - - Args: - t (float): Initial time. Defaults to 0.0. - device (torch.device): Devices used for model inference. Defaults to None (cpu). - """ - self.t = t - self.device = device - self.cuda = bool(device and str(device).startswith("cuda")) - - def __enter__(self): - """Start timing.""" - self.start = self.time() - return self - - def __exit__(self, type, value, traceback): # noqa - """Stop timing.""" - self.dt = self.time() - self.start # delta-time - self.t += self.dt # accumulate dt - - def __str__(self): - """Returns a human-readable string representing the accumulated elapsed time in the profiler.""" - return f"Elapsed time is {self.t} s" - - def time(self): - """Get current time.""" - if self.cuda: - torch.cuda.synchronize(self.device) - return time.time() - - -def segment2box(segment, width=640, height=640): - """ - Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy). - - Args: - segment (torch.Tensor): the segment label - width (int): the width of the image. Defaults to 640 - height (int): The height of the image. Defaults to 640 - - Returns: - (np.ndarray): the minimum and maximum x and y values of the segment. - """ - x, y = segment.T # segment xy - inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height) - x = x[inside] - y = y[inside] - return ( - np.array([x.min(), y.min(), x.max(), y.max()], dtype=segment.dtype) - if any(x) - else np.zeros(4, dtype=segment.dtype) - ) # xyxy - - -def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True, xywh=False): - """ - Rescales bounding boxes (in the format of xyxy by default) from the shape of the image they were originally - specified in (img1_shape) to the shape of a different image (img0_shape). - - Args: - img1_shape (tuple): The shape of the image that the bounding boxes are for, in the format of (height, width). - boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2) - img0_shape (tuple): the shape of the target image, in the format of (height, width). - ratio_pad (tuple): a tuple of (ratio, pad) for scaling the boxes. If not provided, the ratio and pad will be - calculated based on the size difference between the two images. - padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular - rescaling. - xywh (bool): The box format is xywh or not, default=False. - - Returns: - boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2) - """ - if ratio_pad is None: # calculate from img0_shape - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new - pad = ( - round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1), - round((img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1), - ) # wh padding - else: - gain = ratio_pad[0][0] - pad = ratio_pad[1] - - if padding: - boxes[..., 0] -= pad[0] # x padding - boxes[..., 1] -= pad[1] # y padding - if not xywh: - boxes[..., 2] -= pad[0] # x padding - boxes[..., 3] -= pad[1] # y padding - boxes[..., :4] /= gain - return clip_boxes(boxes, img0_shape) - - -def make_divisible(x, divisor): - """ - Returns the nearest number that is divisible by the given divisor. - - Args: - x (int): The number to make divisible. - divisor (int | torch.Tensor): The divisor. - - Returns: - (int): The nearest number divisible by the divisor. - """ - if isinstance(divisor, torch.Tensor): - divisor = int(divisor.max()) # to int - return math.ceil(x / divisor) * divisor - - -def nms_rotated(boxes, scores, threshold=0.45): - """ - NMS for obbs, powered by probiou and fast-nms. - - Args: - boxes (torch.Tensor): (N, 5), xywhr. - scores (torch.Tensor): (N, ). - threshold (float): IoU threshold. - - Returns: - """ - if len(boxes) == 0: - return np.empty((0,), dtype=np.int8) - sorted_idx = torch.argsort(scores, descending=True) - boxes = boxes[sorted_idx] - ious = batch_probiou(boxes, boxes).triu_(diagonal=1) - pick = torch.nonzero(ious.max(dim=0)[0] < threshold).squeeze_(-1) - return sorted_idx[pick] - - -def non_max_suppression( - prediction, - conf_thres=0.25, - iou_thres=0.45, - classes=None, - agnostic=False, - multi_label=False, - labels=(), - max_det=300, - nc=0, # number of classes (optional) - max_time_img=0.05, - max_nms=30000, - max_wh=7680, - in_place=True, - rotated=False, -): - """ - Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box. - - Args: - prediction (torch.Tensor): A tensor of shape (batch_size, num_classes + 4 + num_masks, num_boxes) - containing the predicted boxes, classes, and masks. The tensor should be in the format - output by a model, such as YOLO. - conf_thres (float): The confidence threshold below which boxes will be filtered out. - Valid values are between 0.0 and 1.0. - iou_thres (float): The IoU threshold below which boxes will be filtered out during NMS. - Valid values are between 0.0 and 1.0. - classes (List[int]): A list of class indices to consider. If None, all classes will be considered. - agnostic (bool): If True, the model is agnostic to the number of classes, and all - classes will be considered as one. - multi_label (bool): If True, each box may have multiple labels. - labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner - list contains the apriori labels for a given image. The list should be in the format - output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2). - max_det (int): The maximum number of boxes to keep after NMS. - nc (int, optional): The number of classes output by the model. Any indices after this will be considered masks. - max_time_img (float): The maximum time (seconds) for processing one image. - max_nms (int): The maximum number of boxes into torchvision.ops.nms(). - max_wh (int): The maximum box width and height in pixels. - in_place (bool): If True, the input prediction tensor will be modified in place. - - Returns: - (List[torch.Tensor]): A list of length batch_size, where each element is a tensor of - shape (num_boxes, 6 + num_masks) containing the kept boxes, with columns - (x1, y1, x2, y2, confidence, class, mask1, mask2, ...). - """ - - # Checks - assert 0 <= conf_thres <= 1, f"Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0" - assert 0 <= iou_thres <= 1, f"Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0" - if isinstance(prediction, (list, tuple)): # YOLOv8 model in validation model, output = (inference_out, loss_out) - prediction = prediction[0] # select only inference output - - bs = prediction.shape[0] # batch size - nc = nc or (prediction.shape[1] - 4) # number of classes - nm = prediction.shape[1] - nc - 4 - mi = 4 + nc # mask start index - xc = prediction[:, 4:mi].amax(1) > conf_thres # candidates - - # Settings - # min_wh = 2 # (pixels) minimum box width and height - time_limit = 2.0 + max_time_img * bs # seconds to quit after - multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img) - - prediction = prediction.transpose(-1, -2) # shape(1,84,6300) to shape(1,6300,84) - if not rotated: - if in_place: - prediction[..., :4] = xywh2xyxy(prediction[..., :4]) # xywh to xyxy - else: - prediction = torch.cat((xywh2xyxy(prediction[..., :4]), prediction[..., 4:]), dim=-1) # xywh to xyxy - - t = time.time() - output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs - for xi, x in enumerate(prediction): # image index, image inference - # Apply constraints - # x[((x[:, 2:4] < min_wh) | (x[:, 2:4] > max_wh)).any(1), 4] = 0 # width-height - x = x[xc[xi]] # confidence - - # Cat apriori labels if autolabelling - if labels and len(labels[xi]) and not rotated: - lb = labels[xi] - v = torch.zeros((len(lb), nc + nm + 4), device=x.device) - v[:, :4] = xywh2xyxy(lb[:, 1:5]) # box - v[range(len(lb)), lb[:, 0].long() + 4] = 1.0 # cls - x = torch.cat((x, v), 0) - - # If none remain process next image - if not x.shape[0]: - continue - - # Detections matrix nx6 (xyxy, conf, cls) - box, cls, mask = x.split((4, nc, nm), 1) - - if multi_label: - i, j = torch.where(cls > conf_thres) - x = torch.cat((box[i], x[i, 4 + j, None], j[:, None].float(), mask[i]), 1) - else: # best class only - conf, j = cls.max(1, keepdim=True) - x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres] - - # Filter by class - if classes is not None: - x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] - - # Check shape - n = x.shape[0] # number of boxes - if not n: # no boxes - continue - if n > max_nms: # excess boxes - x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence and remove excess boxes - - # Batched NMS - c = x[:, 5:6] * (0 if agnostic else max_wh) # classes - scores = x[:, 4] # scores - if rotated: - boxes = torch.cat((x[:, :2] + c, x[:, 2:4], x[:, -1:]), dim=-1) # xywhr - i = nms_rotated(boxes, scores, iou_thres) - else: - boxes = x[:, :4] + c # boxes (offset by class) - i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS - i = i[:max_det] # limit detections - - # # Experimental - # merge = False # use merge-NMS - # if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean) - # # Update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) - # from .metrics import box_iou - # iou = box_iou(boxes[i], boxes) > iou_thres # IoU matrix - # weights = iou * scores[None] # box weights - # x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes - # redundant = True # require redundant detections - # if redundant: - # i = i[iou.sum(1) > 1] # require redundancy - - output[xi] = x[i] - if (time.time() - t) > time_limit: - LOGGER.warning(f"WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded") - break # time limit exceeded - - return output - - -def clip_boxes(boxes, shape): - """ - Takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape. - - Args: - boxes (torch.Tensor): the bounding boxes to clip - shape (tuple): the shape of the image - - Returns: - (torch.Tensor | numpy.ndarray): Clipped boxes - """ - if isinstance(boxes, torch.Tensor): # faster individually (WARNING: inplace .clamp_() Apple MPS bug) - boxes[..., 0] = boxes[..., 0].clamp(0, shape[1]) # x1 - boxes[..., 1] = boxes[..., 1].clamp(0, shape[0]) # y1 - boxes[..., 2] = boxes[..., 2].clamp(0, shape[1]) # x2 - boxes[..., 3] = boxes[..., 3].clamp(0, shape[0]) # y2 - else: # np.array (faster grouped) - boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1]) # x1, x2 - boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0]) # y1, y2 - return boxes - - -def clip_coords(coords, shape): - """ - Clip line coordinates to the image boundaries. - - Args: - coords (torch.Tensor | numpy.ndarray): A list of line coordinates. - shape (tuple): A tuple of integers representing the size of the image in the format (height, width). - - Returns: - (torch.Tensor | numpy.ndarray): Clipped coordinates - """ - if isinstance(coords, torch.Tensor): # faster individually (WARNING: inplace .clamp_() Apple MPS bug) - coords[..., 0] = coords[..., 0].clamp(0, shape[1]) # x - coords[..., 1] = coords[..., 1].clamp(0, shape[0]) # y - else: # np.array (faster grouped) - coords[..., 0] = coords[..., 0].clip(0, shape[1]) # x - coords[..., 1] = coords[..., 1].clip(0, shape[0]) # y - return coords - - -def scale_image(masks, im0_shape, ratio_pad=None): - """ - Takes a mask, and resizes it to the original image size. - - Args: - masks (np.ndarray): resized and padded masks/images, [h, w, num]/[h, w, 3]. - im0_shape (tuple): the original image shape - ratio_pad (tuple): the ratio of the padding to the original image. - - Returns: - masks (torch.Tensor): The masks that are being returned. - """ - # Rescale coordinates (xyxy) from im1_shape to im0_shape - im1_shape = masks.shape - if im1_shape[:2] == im0_shape[:2]: - return masks - if ratio_pad is None: # calculate from im0_shape - gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new - pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding - else: - # gain = ratio_pad[0][0] - pad = ratio_pad[1] - top, left = int(pad[1]), int(pad[0]) # y, x - bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0]) - - if len(masks.shape) < 2: - raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}') - masks = masks[top:bottom, left:right] - masks = cv2.resize(masks, (im0_shape[1], im0_shape[0])) - if len(masks.shape) == 2: - masks = masks[:, :, None] - - return masks - - -def xyxy2xywh(x): - """ - Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format where (x1, y1) is the - top-left corner and (x2, y2) is the bottom-right corner. - - Args: - x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format. - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height) format. - """ - assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy - y[..., 0] = (x[..., 0] + x[..., 2]) / 2 # x center - y[..., 1] = (x[..., 1] + x[..., 3]) / 2 # y center - y[..., 2] = x[..., 2] - x[..., 0] # width - y[..., 3] = x[..., 3] - x[..., 1] # height - return y - - -def xywh2xyxy(x): - """ - Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the - top-left corner and (x2, y2) is the bottom-right corner. - - Args: - x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x, y, width, height) format. - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in (x1, y1, x2, y2) format. - """ - assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy - dw = x[..., 2] / 2 # half-width - dh = x[..., 3] / 2 # half-height - y[..., 0] = x[..., 0] - dw # top left x - y[..., 1] = x[..., 1] - dh # top left y - y[..., 2] = x[..., 0] + dw # bottom right x - y[..., 3] = x[..., 1] + dh # bottom right y - return y - - -def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): - """ - Convert normalized bounding box coordinates to pixel coordinates. - - Args: - x (np.ndarray | torch.Tensor): The bounding box coordinates. - w (int): Width of the image. Defaults to 640 - h (int): Height of the image. Defaults to 640 - padw (int): Padding width. Defaults to 0 - padh (int): Padding height. Defaults to 0 - Returns: - y (np.ndarray | torch.Tensor): The coordinates of the bounding box in the format [x1, y1, x2, y2] where - x1,y1 is the top-left corner, x2,y2 is the bottom-right corner of the bounding box. - """ - assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy - y[..., 0] = w * (x[..., 0] - x[..., 2] / 2) + padw # top left x - y[..., 1] = h * (x[..., 1] - x[..., 3] / 2) + padh # top left y - y[..., 2] = w * (x[..., 0] + x[..., 2] / 2) + padw # bottom right x - y[..., 3] = h * (x[..., 1] + x[..., 3] / 2) + padh # bottom right y - return y - - -def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0): - """ - Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height, normalized) format. x, y, - width and height are normalized to image dimensions. - - Args: - x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format. - w (int): The width of the image. Defaults to 640 - h (int): The height of the image. Defaults to 640 - clip (bool): If True, the boxes will be clipped to the image boundaries. Defaults to False - eps (float): The minimum value of the box's width and height. Defaults to 0.0 - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height, normalized) format - """ - if clip: - x = clip_boxes(x, (h - eps, w - eps)) - assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy - y[..., 0] = ((x[..., 0] + x[..., 2]) / 2) / w # x center - y[..., 1] = ((x[..., 1] + x[..., 3]) / 2) / h # y center - y[..., 2] = (x[..., 2] - x[..., 0]) / w # width - y[..., 3] = (x[..., 3] - x[..., 1]) / h # height - return y - - -def xywh2ltwh(x): - """ - Convert the bounding box format from [x, y, w, h] to [x1, y1, w, h], where x1, y1 are the top-left coordinates. - - Args: - x (np.ndarray | torch.Tensor): The input tensor with the bounding box coordinates in the xywh format - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format - """ - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[..., 0] = x[..., 0] - x[..., 2] / 2 # top left x - y[..., 1] = x[..., 1] - x[..., 3] / 2 # top left y - return y - - -def xyxy2ltwh(x): - """ - Convert nx4 bounding boxes from [x1, y1, x2, y2] to [x1, y1, w, h], where xy1=top-left, xy2=bottom-right. - - Args: - x (np.ndarray | torch.Tensor): The input tensor with the bounding boxes coordinates in the xyxy format - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format. - """ - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[..., 2] = x[..., 2] - x[..., 0] # width - y[..., 3] = x[..., 3] - x[..., 1] # height - return y - - -def ltwh2xywh(x): - """ - Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center. - - Args: - x (torch.Tensor): the input tensor - - Returns: - y (np.ndarray | torch.Tensor): The bounding box coordinates in the xywh format. - """ - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[..., 0] = x[..., 0] + x[..., 2] / 2 # center x - y[..., 1] = x[..., 1] + x[..., 3] / 2 # center y - return y - - -def xyxyxyxy2xywhr(corners): - """ - Convert batched Oriented Bounding Boxes (OBB) from [xy1, xy2, xy3, xy4] to [xywh, rotation]. Rotation values are - expected in degrees from 0 to 90. - - Args: - corners (numpy.ndarray | torch.Tensor): Input corners of shape (n, 8). - - Returns: - (numpy.ndarray | torch.Tensor): Converted data in [cx, cy, w, h, rotation] format of shape (n, 5). - """ - is_torch = isinstance(corners, torch.Tensor) - points = corners.cpu().numpy() if is_torch else corners - points = points.reshape(len(corners), -1, 2) - rboxes = [] - for pts in points: - # NOTE: Use cv2.minAreaRect to get accurate xywhr, - # especially some objects are cut off by augmentations in dataloader. - (x, y), (w, h), angle = cv2.minAreaRect(pts) - rboxes.append([x, y, w, h, angle / 180 * np.pi]) - return ( - torch.tensor(rboxes, device=corners.device, dtype=corners.dtype) - if is_torch - else np.asarray(rboxes, dtype=points.dtype) - ) # rboxes - - -def xywhr2xyxyxyxy(rboxes): - """ - Convert batched Oriented Bounding Boxes (OBB) from [xywh, rotation] to [xy1, xy2, xy3, xy4]. Rotation values should - be in degrees from 0 to 90. - - Args: - rboxes (numpy.ndarray | torch.Tensor): Boxes in [cx, cy, w, h, rotation] format of shape (n, 5) or (b, n, 5). - - Returns: - (numpy.ndarray | torch.Tensor): Converted corner points of shape (n, 4, 2) or (b, n, 4, 2). - """ - is_numpy = isinstance(rboxes, np.ndarray) - cos, sin = (np.cos, np.sin) if is_numpy else (torch.cos, torch.sin) - - ctr = rboxes[..., :2] - w, h, angle = (rboxes[..., i : i + 1] for i in range(2, 5)) - cos_value, sin_value = cos(angle), sin(angle) - vec1 = [w / 2 * cos_value, w / 2 * sin_value] - vec2 = [-h / 2 * sin_value, h / 2 * cos_value] - vec1 = np.concatenate(vec1, axis=-1) if is_numpy else torch.cat(vec1, dim=-1) - vec2 = np.concatenate(vec2, axis=-1) if is_numpy else torch.cat(vec2, dim=-1) - pt1 = ctr + vec1 + vec2 - pt2 = ctr + vec1 - vec2 - pt3 = ctr - vec1 - vec2 - pt4 = ctr - vec1 + vec2 - return np.stack([pt1, pt2, pt3, pt4], axis=-2) if is_numpy else torch.stack([pt1, pt2, pt3, pt4], dim=-2) - - -def ltwh2xyxy(x): - """ - It converts the bounding box from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right. - - Args: - x (np.ndarray | torch.Tensor): the input image - - Returns: - y (np.ndarray | torch.Tensor): the xyxy coordinates of the bounding boxes. - """ - y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) - y[..., 2] = x[..., 2] + x[..., 0] # width - y[..., 3] = x[..., 3] + x[..., 1] # height - return y - - -def segments2boxes(segments): - """ - It converts segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh) - - Args: - segments (list): list of segments, each segment is a list of points, each point is a list of x, y coordinates - - Returns: - (np.ndarray): the xywh coordinates of the bounding boxes. - """ - boxes = [] - for s in segments: - x, y = s.T # segment xy - boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy - return xyxy2xywh(np.array(boxes)) # cls, xywh - - -def resample_segments(segments, n=1000): - """ - Inputs a list of segments (n,2) and returns a list of segments (n,2) up-sampled to n points each. - - Args: - segments (list): a list of (n,2) arrays, where n is the number of points in the segment. - n (int): number of points to resample the segment to. Defaults to 1000 - - Returns: - segments (list): the resampled segments. - """ - for i, s in enumerate(segments): - s = np.concatenate((s, s[0:1, :]), axis=0) - x = np.linspace(0, len(s) - 1, n) - xp = np.arange(len(s)) - segments[i] = ( - np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)], dtype=np.float32).reshape(2, -1).T - ) # segment xy - return segments - - -def crop_mask(masks, boxes): - """ - It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box. - - Args: - masks (torch.Tensor): [n, h, w] tensor of masks - boxes (torch.Tensor): [n, 4] tensor of bbox coordinates in relative point form - - Returns: - (torch.Tensor): The masks are being cropped to the bounding box. - """ - _, h, w = masks.shape - x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1) # x1 shape(n,1,1) - r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :] # rows shape(1,1,w) - c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None] # cols shape(1,h,1) - - return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2)) - - -def process_mask_upsample(protos, masks_in, bboxes, shape): - """ - Takes the output of the mask head, and applies the mask to the bounding boxes. This produces masks of higher quality - but is slower. - - Args: - protos (torch.Tensor): [mask_dim, mask_h, mask_w] - masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms - bboxes (torch.Tensor): [n, 4], n is number of masks after nms - shape (tuple): the size of the input image (h,w) - - Returns: - (torch.Tensor): The upsampled masks. - """ - c, mh, mw = protos.shape # CHW - masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) - masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0] # CHW - masks = crop_mask(masks, bboxes) # CHW - return masks.gt_(0.5) - - -def process_mask(protos, masks_in, bboxes, shape, upsample=False): - """ - Apply masks to bounding boxes using the output of the mask head. - - Args: - protos (torch.Tensor): A tensor of shape [mask_dim, mask_h, mask_w]. - masks_in (torch.Tensor): A tensor of shape [n, mask_dim], where n is the number of masks after NMS. - bboxes (torch.Tensor): A tensor of shape [n, 4], where n is the number of masks after NMS. - shape (tuple): A tuple of integers representing the size of the input image in the format (h, w). - upsample (bool): A flag to indicate whether to upsample the mask to the original image size. Default is False. - - Returns: - (torch.Tensor): A binary mask tensor of shape [n, h, w], where n is the number of masks after NMS, and h and w - are the height and width of the input image. The mask is applied to the bounding boxes. - """ - - c, mh, mw = protos.shape # CHW - ih, iw = shape - masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW - width_ratio = mw / iw - height_ratio = mh / ih - - downsampled_bboxes = bboxes.clone() - downsampled_bboxes[:, 0] *= width_ratio - downsampled_bboxes[:, 2] *= width_ratio - downsampled_bboxes[:, 3] *= height_ratio - downsampled_bboxes[:, 1] *= height_ratio - - masks = crop_mask(masks, downsampled_bboxes) # CHW - if upsample: - masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0] # CHW - return masks.gt_(0.5) - - -def process_mask_native(protos, masks_in, bboxes, shape): - """ - It takes the output of the mask head, and crops it after upsampling to the bounding boxes. - - Args: - protos (torch.Tensor): [mask_dim, mask_h, mask_w] - masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms - bboxes (torch.Tensor): [n, 4], n is number of masks after nms - shape (tuple): the size of the input image (h,w) - - Returns: - masks (torch.Tensor): The returned masks with dimensions [h, w, n] - """ - c, mh, mw = protos.shape # CHW - masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) - masks = scale_masks(masks[None], shape)[0] # CHW - masks = crop_mask(masks, bboxes) # CHW - return masks.gt_(0.5) - - -def scale_masks(masks, shape, padding=True): - """ - Rescale segment masks to shape. - - Args: - masks (torch.Tensor): (N, C, H, W). - shape (tuple): Height and width. - padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular - rescaling. - """ - mh, mw = masks.shape[2:] - gain = min(mh / shape[0], mw / shape[1]) # gain = old / new - pad = [mw - shape[1] * gain, mh - shape[0] * gain] # wh padding - if padding: - pad[0] /= 2 - pad[1] /= 2 - top, left = (int(pad[1]), int(pad[0])) if padding else (0, 0) # y, x - bottom, right = (int(mh - pad[1]), int(mw - pad[0])) - masks = masks[..., top:bottom, left:right] - - masks = F.interpolate(masks, shape, mode="bilinear", align_corners=False) # NCHW - return masks - - -def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize=False, padding=True): - """ - Rescale segment coordinates (xy) from img1_shape to img0_shape. - - Args: - img1_shape (tuple): The shape of the image that the coords are from. - coords (torch.Tensor): the coords to be scaled of shape n,2. - img0_shape (tuple): the shape of the image that the segmentation is being applied to. - ratio_pad (tuple): the ratio of the image size to the padded image size. - normalize (bool): If True, the coordinates will be normalized to the range [0, 1]. Defaults to False. - padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular - rescaling. - - Returns: - coords (torch.Tensor): The scaled coordinates. - """ - if ratio_pad is None: # calculate from img0_shape - gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new - pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding - else: - gain = ratio_pad[0][0] - pad = ratio_pad[1] - - if padding: - coords[..., 0] -= pad[0] # x padding - coords[..., 1] -= pad[1] # y padding - coords[..., 0] /= gain - coords[..., 1] /= gain - coords = clip_coords(coords, img0_shape) - if normalize: - coords[..., 0] /= img0_shape[1] # width - coords[..., 1] /= img0_shape[0] # height - return coords - - -def regularize_rboxes(rboxes): - """ - Regularize rotated boxes in range [0, pi/2]. - - Args: - rboxes (torch.Tensor): (N, 5), xywhr. - - Returns: - (torch.Tensor): The regularized boxes. - """ - x, y, w, h, t = rboxes.unbind(dim=-1) - # Swap edge and angle if h >= w - w_ = torch.where(w > h, w, h) - h_ = torch.where(w > h, h, w) - t = torch.where(w > h, t, t + math.pi / 2) % math.pi - return torch.stack([x, y, w_, h_, t], dim=-1) # regularized boxes - - -def masks2segments(masks, strategy="largest"): - """ - It takes a list of masks(n,h,w) and returns a list of segments(n,xy) - - Args: - masks (torch.Tensor): the output of the model, which is a tensor of shape (batch_size, 160, 160) - strategy (str): 'concat' or 'largest'. Defaults to largest - - Returns: - segments (List): list of segment masks - """ - segments = [] - for x in masks.int().cpu().numpy().astype("uint8"): - c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0] - if c: - if strategy == "concat": # concatenate all segments - c = np.concatenate([x.reshape(-1, 2) for x in c]) - elif strategy == "largest": # select largest segment - c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2) - else: - c = np.zeros((0, 2)) # no segments found - segments.append(c.astype("float32")) - return segments - - -def convert_torch2numpy_batch(batch: torch.Tensor) -> np.ndarray: - """ - Convert a batch of FP32 torch tensors (0.0-1.0) to a NumPy uint8 array (0-255), changing from BCHW to BHWC layout. - - Args: - batch (torch.Tensor): Input tensor batch of shape (Batch, Channels, Height, Width) and dtype torch.float32. - - Returns: - (np.ndarray): Output NumPy array batch of shape (Batch, Height, Width, Channels) and dtype uint8. - """ - return (batch.permute(0, 2, 3, 1).contiguous() * 255).clamp(0, 255).to(torch.uint8).cpu().numpy() - - -def clean_str(s): - """ - Cleans a string by replacing special characters with underscore _ - - Args: - s (str): a string needing special characters replaced - - Returns: - (str): a string with special characters replaced by an underscore _ - """ - return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s) diff --git a/ultralytics-main/ultralytics/utils/patches.py b/ultralytics-main/ultralytics/utils/patches.py deleted file mode 100644 index d438407..0000000 --- a/ultralytics-main/ultralytics/utils/patches.py +++ /dev/null @@ -1,88 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -"""Monkey patches to update/extend functionality of existing functions.""" - -import time -from pathlib import Path - -import cv2 -import numpy as np -import torch - -# OpenCV Multilanguage-friendly functions ------------------------------------------------------------------------------ -_imshow = cv2.imshow # copy to avoid recursion errors - - -def imread(filename: str, flags: int = cv2.IMREAD_COLOR): - """ - Read an image from a file. - - Args: - filename (str): Path to the file to read. - flags (int, optional): Flag that can take values of cv2.IMREAD_*. Defaults to cv2.IMREAD_COLOR. - - Returns: - (np.ndarray): The read image. - """ - return cv2.imdecode(np.fromfile(filename, np.uint8), flags) - - -def imwrite(filename: str, img: np.ndarray, params=None): - """ - Write an image to a file. - - Args: - filename (str): Path to the file to write. - img (np.ndarray): Image to write. - params (list of ints, optional): Additional parameters. See OpenCV documentation. - - Returns: - (bool): True if the file was written, False otherwise. - """ - try: - cv2.imencode(Path(filename).suffix, img, params)[1].tofile(filename) - return True - except Exception: - return False - - -def imshow(winname: str, mat: np.ndarray): - """ - Displays an image in the specified window. - - Args: - winname (str): Name of the window. - mat (np.ndarray): Image to be shown. - """ - _imshow(winname.encode("unicode_escape").decode(), mat) - - -# PyTorch functions ---------------------------------------------------------------------------------------------------- -_torch_save = torch.save # copy to avoid recursion errors - - -def torch_save(*args, use_dill=True, **kwargs): - """ - Optionally use dill to serialize lambda functions where pickle does not, adding robustness with 3 retries and - exponential standoff in case of save failure. - - Args: - *args (tuple): Positional arguments to pass to torch.save. - use_dill (bool): Whether to try using dill for serialization if available. Defaults to True. - **kwargs (any): Keyword arguments to pass to torch.save. - """ - try: - assert use_dill - import dill as pickle - except (AssertionError, ImportError): - import pickle - - if "pickle_module" not in kwargs: - kwargs["pickle_module"] = pickle - - for i in range(4): # 3 retries - try: - return _torch_save(*args, **kwargs) - except RuntimeError as e: # unable to save, possibly waiting for device to flush or antivirus scan - if i == 3: - raise e - time.sleep((2**i) / 2) # exponential standoff: 0.5s, 1.0s, 2.0s diff --git a/ultralytics-main/ultralytics/utils/plotting.py b/ultralytics-main/ultralytics/utils/plotting.py deleted file mode 100644 index a86d457..0000000 --- a/ultralytics-main/ultralytics/utils/plotting.py +++ /dev/null @@ -1,1048 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import contextlib -import math -import warnings -from pathlib import Path - -import cv2 -import matplotlib.pyplot as plt -import numpy as np -import torch -from PIL import Image, ImageDraw, ImageFont -from PIL import __version__ as pil_version - -from ultralytics.utils import LOGGER, TryExcept, ops, plt_settings, threaded -from .checks import check_font, check_version, is_ascii -from .files import increment_path - - -class Colors: - """ - Ultralytics default color palette https://ultralytics.com/. - - This class provides methods to work with the Ultralytics color palette, including converting hex color codes to - RGB values. - - Attributes: - palette (list of tuple): List of RGB color values. - n (int): The number of colors in the palette. - pose_palette (np.ndarray): A specific color palette array with dtype np.uint8. - """ - - def __init__(self): - """Initialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values().""" - hexs = ( - "FF3838", - "FF9D97", - "FF701F", - "FFB21D", - "CFD231", - "48F90A", - "92CC17", - "3DDB86", - "1A9334", - "00D4BB", - "2C99A8", - "00C2FF", - "344593", - "6473FF", - "0018EC", - "8438FF", - "520085", - "CB38FF", - "FF95C8", - "FF37C7", - ) - self.palette = [self.hex2rgb(f"#{c}") for c in hexs] - self.n = len(self.palette) - self.pose_palette = np.array( - [ - [255, 128, 0], - [255, 153, 51], - [255, 178, 102], - [230, 230, 0], - [255, 153, 255], - [153, 204, 255], - [255, 102, 255], - [255, 51, 255], - [102, 178, 255], - [51, 153, 255], - [255, 153, 153], - [255, 102, 102], - [255, 51, 51], - [153, 255, 153], - [102, 255, 102], - [51, 255, 51], - [0, 255, 0], - [0, 0, 255], - [255, 0, 0], - [255, 255, 255], - ], - dtype=np.uint8, - ) - - def __call__(self, i, bgr=False): - """Converts hex color codes to RGB values.""" - c = self.palette[int(i) % self.n] - return (c[2], c[1], c[0]) if bgr else c - - @staticmethod - def hex2rgb(h): - """Converts hex color codes to RGB values (i.e. default PIL order).""" - return tuple(int(h[1 + i : 1 + i + 2], 16) for i in (0, 2, 4)) - - -colors = Colors() # create instance for 'from utils.plots import colors' - - -class Annotator: - """ - Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations. - - Attributes: - im (Image.Image or numpy array): The image to annotate. - pil (bool): Whether to use PIL or cv2 for drawing annotations. - font (ImageFont.truetype or ImageFont.load_default): Font used for text annotations. - lw (float): Line width for drawing. - skeleton (List[List[int]]): Skeleton structure for keypoints. - limb_color (List[int]): Color palette for limbs. - kpt_color (List[int]): Color palette for keypoints. - """ - - def __init__(self, im, line_width=None, font_size=None, font="Arial.ttf", pil=False, example="abc"): - """Initialize the Annotator class with image and line width along with color palette for keypoints and limbs.""" - non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic - input_is_pil = isinstance(im, Image.Image) - self.pil = pil or non_ascii or input_is_pil - self.lw = line_width or max(round(sum(im.size if input_is_pil else im.shape) / 2 * 0.003), 2) - if self.pil: # use PIL - self.im = im if input_is_pil else Image.fromarray(im) - self.draw = ImageDraw.Draw(self.im) - try: - font = check_font("Arial.Unicode.ttf" if non_ascii else font) - size = font_size or max(round(sum(self.im.size) / 2 * 0.035), 12) - self.font = ImageFont.truetype(str(font), size) - except Exception: - self.font = ImageFont.load_default() - # Deprecation fix for w, h = getsize(string) -> _, _, w, h = getbox(string) - if check_version(pil_version, "9.2.0"): - self.font.getsize = lambda x: self.font.getbbox(x)[2:4] # text width, height - else: # use cv2 - assert im.data.contiguous, "Image not contiguous. Apply np.ascontiguousarray(im) to Annotator input images." - self.im = im if im.flags.writeable else im.copy() - self.tf = max(self.lw - 1, 1) # font thickness - self.sf = self.lw / 3 # font scale - # Pose - self.skeleton = [ - [16, 14], - [14, 12], - [17, 15], - [15, 13], - [12, 13], - [6, 12], - [7, 13], - [6, 7], - [6, 8], - [7, 9], - [8, 10], - [9, 11], - [2, 3], - [1, 2], - [1, 3], - [2, 4], - [3, 5], - [4, 6], - [5, 7], - ] - - self.limb_color = colors.pose_palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]] - self.kpt_color = colors.pose_palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]] - - def box_label(self, box, label="", color=(128, 128, 128), txt_color=(255, 255, 255), rotated=False): - """Add one xyxy box to image with label.""" - if isinstance(box, torch.Tensor): - box = box.tolist() - if self.pil or not is_ascii(label): - if rotated: - p1 = box[0] - # NOTE: PIL-version polygon needs tuple type. - self.draw.polygon([tuple(b) for b in box], width=self.lw, outline=color) - else: - p1 = (box[0], box[1]) - self.draw.rectangle(box, width=self.lw, outline=color) # box - if label: - w, h = self.font.getsize(label) # text width, height - outside = p1[1] - h >= 0 # label fits outside box - self.draw.rectangle( - (p1[0], p1[1] - h if outside else p1[1], p1[0] + w + 1, p1[1] + 1 if outside else p1[1] + h + 1), - fill=color, - ) - # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 - self.draw.text((p1[0], p1[1] - h if outside else p1[1]), label, fill=txt_color, font=self.font) - else: # cv2 - if rotated: - p1 = [int(b) for b in box[0]] - # NOTE: cv2-version polylines needs np.asarray type. - cv2.polylines(self.im, [np.asarray(box, dtype=int)], True, color, self.lw) - else: - p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) - cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) - - if label: - w, h = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0] # text width, height - outside = p1[1] - h >= 3 - p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 - cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled - cv2.putText( - self.im, - label, - (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), - 0, - self.sf, - txt_color, - thickness=self.tf, - lineType=cv2.LINE_AA, - ) - - def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False): - """ - Plot masks on image. - - Args: - masks (tensor): Predicted masks on cuda, shape: [n, h, w] - colors (List[List[Int]]): Colors for predicted masks, [[r, g, b] * n] - im_gpu (tensor): Image is in cuda, shape: [3, h, w], range: [0, 1] - alpha (float): Mask transparency: 0.0 fully transparent, 1.0 opaque - retina_masks (bool): Whether to use high resolution masks or not. Defaults to False. - """ - if self.pil: - # Convert to numpy first - self.im = np.asarray(self.im).copy() - if len(masks) == 0: - self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255 - if im_gpu.device != masks.device: - im_gpu = im_gpu.to(masks.device) - colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0 # shape(n,3) - colors = colors[:, None, None] # shape(n,1,1,3) - masks = masks.unsqueeze(3) # shape(n,h,w,1) - masks_color = masks * (colors * alpha) # shape(n,h,w,3) - - inv_alpha_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1) - mcs = masks_color.max(dim=0).values # shape(n,h,w,3) - - im_gpu = im_gpu.flip(dims=[0]) # flip channel - im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3) - im_gpu = im_gpu * inv_alpha_masks[-1] + mcs - im_mask = im_gpu * 255 - im_mask_np = im_mask.byte().cpu().numpy() - self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape) - if self.pil: - # Convert im back to PIL and update draw - self.fromarray(self.im) - - def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True): - """ - Plot keypoints on the image. - - Args: - kpts (tensor): Predicted keypoints with shape [17, 3]. Each keypoint has (x, y, confidence). - shape (tuple): Image shape as a tuple (h, w), where h is the height and w is the width. - radius (int, optional): Radius of the drawn keypoints. Default is 5. - kpt_line (bool, optional): If True, the function will draw lines connecting keypoints - for human pose. Default is True. - - Note: - `kpt_line=True` currently only supports human pose plotting. - """ - if self.pil: - # Convert to numpy first - self.im = np.asarray(self.im).copy() - nkpt, ndim = kpts.shape - is_pose = nkpt == 17 and ndim in {2, 3} - kpt_line &= is_pose # `kpt_line=True` for now only supports human pose plotting - for i, k in enumerate(kpts): - color_k = [int(x) for x in self.kpt_color[i]] if is_pose else colors(i) - x_coord, y_coord = k[0], k[1] - if x_coord % shape[1] != 0 and y_coord % shape[0] != 0: - if len(k) == 3: - conf = k[2] - if conf < 0.5: - continue - cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, color_k, -1, lineType=cv2.LINE_AA) - - if kpt_line: - ndim = kpts.shape[-1] - for i, sk in enumerate(self.skeleton): - pos1 = (int(kpts[(sk[0] - 1), 0]), int(kpts[(sk[0] - 1), 1])) - pos2 = (int(kpts[(sk[1] - 1), 0]), int(kpts[(sk[1] - 1), 1])) - if ndim == 3: - conf1 = kpts[(sk[0] - 1), 2] - conf2 = kpts[(sk[1] - 1), 2] - if conf1 < 0.5 or conf2 < 0.5: - continue - if pos1[0] % shape[1] == 0 or pos1[1] % shape[0] == 0 or pos1[0] < 0 or pos1[1] < 0: - continue - if pos2[0] % shape[1] == 0 or pos2[1] % shape[0] == 0 or pos2[0] < 0 or pos2[1] < 0: - continue - cv2.line(self.im, pos1, pos2, [int(x) for x in self.limb_color[i]], thickness=2, lineType=cv2.LINE_AA) - if self.pil: - # Convert im back to PIL and update draw - self.fromarray(self.im) - - def rectangle(self, xy, fill=None, outline=None, width=1): - """Add rectangle to image (PIL-only).""" - self.draw.rectangle(xy, fill, outline, width) - - def text(self, xy, text, txt_color=(255, 255, 255), anchor="top", box_style=False): - """Adds text to an image using PIL or cv2.""" - if anchor == "bottom": # start y from font bottom - w, h = self.font.getsize(text) # text width, height - xy[1] += 1 - h - if self.pil: - if box_style: - w, h = self.font.getsize(text) - self.draw.rectangle((xy[0], xy[1], xy[0] + w + 1, xy[1] + h + 1), fill=txt_color) - # Using `txt_color` for background and draw fg with white color - txt_color = (255, 255, 255) - if "\n" in text: - lines = text.split("\n") - _, h = self.font.getsize(text) - for line in lines: - self.draw.text(xy, line, fill=txt_color, font=self.font) - xy[1] += h - else: - self.draw.text(xy, text, fill=txt_color, font=self.font) - else: - if box_style: - w, h = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0] # text width, height - outside = xy[1] - h >= 3 - p2 = xy[0] + w, xy[1] - h - 3 if outside else xy[1] + h + 3 - cv2.rectangle(self.im, xy, p2, txt_color, -1, cv2.LINE_AA) # filled - # Using `txt_color` for background and draw fg with white color - txt_color = (255, 255, 255) - cv2.putText(self.im, text, xy, 0, self.sf, txt_color, thickness=self.tf, lineType=cv2.LINE_AA) - - def fromarray(self, im): - """Update self.im from a numpy array.""" - self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) - self.draw = ImageDraw.Draw(self.im) - - def result(self): - """Return annotated image as array.""" - return np.asarray(self.im) - - def show(self, title=None): - """Show the annotated image.""" - Image.fromarray(np.asarray(self.im)[..., ::-1]).show(title) - - def save(self, filename="image.jpg"): - """Save the annotated image to 'filename'.""" - cv2.imwrite(filename, np.asarray(self.im)) - - def draw_region(self, reg_pts=None, color=(0, 255, 0), thickness=5): - """ - Draw region line. - - Args: - reg_pts (list): Region Points (for line 2 points, for region 4 points) - color (tuple): Region Color value - thickness (int): Region area thickness value - """ - cv2.polylines(self.im, [np.array(reg_pts, dtype=np.int32)], isClosed=True, color=color, thickness=thickness) - - def draw_centroid_and_tracks(self, track, color=(255, 0, 255), track_thickness=2): - """ - Draw centroid point and track trails. - - Args: - track (list): object tracking points for trails display - color (tuple): tracks line color - track_thickness (int): track line thickness value - """ - points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines(self.im, [points], isClosed=False, color=color, thickness=track_thickness) - cv2.circle(self.im, (int(track[-1][0]), int(track[-1][1])), track_thickness * 2, color, -1) - - def count_labels(self, counts=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0)): - """ - Plot counts for object counter. - - Args: - counts (int): objects counts value - count_txt_size (int): text size for counts display - color (tuple): background color of counts display - txt_color (tuple): text color of counts display - """ - self.tf = count_txt_size - tl = self.tf or round(0.002 * (self.im.shape[0] + self.im.shape[1]) / 2) + 1 - tf = max(tl - 1, 1) - - # Get text size for in_count and out_count - t_size_in = cv2.getTextSize(str(counts), 0, fontScale=tl / 2, thickness=tf)[0] - - # Calculate positions for counts label - text_width = t_size_in[0] - text_x = (self.im.shape[1] - text_width) // 2 # Center x-coordinate - text_y = t_size_in[1] - - # Create a rounded rectangle for in_count - cv2.rectangle( - self.im, (text_x - 5, text_y - 5), (text_x + text_width + 7, text_y + t_size_in[1] + 7), color, -1 - ) - cv2.putText( - self.im, str(counts), (text_x, text_y + t_size_in[1]), 0, tl / 2, txt_color, self.tf, lineType=cv2.LINE_AA - ) - - @staticmethod - def estimate_pose_angle(a, b, c): - """ - Calculate the pose angle for object. - - Args: - a (float) : The value of pose point a - b (float): The value of pose point b - c (float): The value o pose point c - - Returns: - angle (degree): Degree value of angle between three points - """ - a, b, c = np.array(a), np.array(b), np.array(c) - radians = np.arctan2(c[1] - b[1], c[0] - b[0]) - np.arctan2(a[1] - b[1], a[0] - b[0]) - angle = np.abs(radians * 180.0 / np.pi) - if angle > 180.0: - angle = 360 - angle - return angle - - def draw_specific_points(self, keypoints, indices=[2, 5, 7], shape=(640, 640), radius=2): - """ - Draw specific keypoints for gym steps counting. - - Args: - keypoints (list): list of keypoints data to be plotted - indices (list): keypoints ids list to be plotted - shape (tuple): imgsz for model inference - radius (int): Keypoint radius value - """ - for i, k in enumerate(keypoints): - if i in indices: - x_coord, y_coord = k[0], k[1] - if x_coord % shape[1] != 0 and y_coord % shape[0] != 0: - if len(k) == 3: - conf = k[2] - if conf < 0.5: - continue - cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, (0, 255, 0), -1, lineType=cv2.LINE_AA) - return self.im - - def plot_angle_and_count_and_stage(self, angle_text, count_text, stage_text, center_kpt, line_thickness=2): - """ - Plot the pose angle, count value and step stage. - - Args: - angle_text (str): angle value for workout monitoring - count_text (str): counts value for workout monitoring - stage_text (str): stage decision for workout monitoring - center_kpt (int): centroid pose index for workout monitoring - line_thickness (int): thickness for text display - """ - angle_text, count_text, stage_text = (f" {angle_text:.2f}", f"Steps : {count_text}", f" {stage_text}") - font_scale = 0.6 + (line_thickness / 10.0) - - # Draw angle - (angle_text_width, angle_text_height), _ = cv2.getTextSize(angle_text, 0, font_scale, line_thickness) - angle_text_position = (int(center_kpt[0]), int(center_kpt[1])) - angle_background_position = (angle_text_position[0], angle_text_position[1] - angle_text_height - 5) - angle_background_size = (angle_text_width + 2 * 5, angle_text_height + 2 * 5 + (line_thickness * 2)) - cv2.rectangle( - self.im, - angle_background_position, - ( - angle_background_position[0] + angle_background_size[0], - angle_background_position[1] + angle_background_size[1], - ), - (255, 255, 255), - -1, - ) - cv2.putText(self.im, angle_text, angle_text_position, 0, font_scale, (0, 0, 0), line_thickness) - - # Draw Counts - (count_text_width, count_text_height), _ = cv2.getTextSize(count_text, 0, font_scale, line_thickness) - count_text_position = (angle_text_position[0], angle_text_position[1] + angle_text_height + 20) - count_background_position = ( - angle_background_position[0], - angle_background_position[1] + angle_background_size[1] + 5, - ) - count_background_size = (count_text_width + 10, count_text_height + 10 + (line_thickness * 2)) - - cv2.rectangle( - self.im, - count_background_position, - ( - count_background_position[0] + count_background_size[0], - count_background_position[1] + count_background_size[1], - ), - (255, 255, 255), - -1, - ) - cv2.putText(self.im, count_text, count_text_position, 0, font_scale, (0, 0, 0), line_thickness) - - # Draw Stage - (stage_text_width, stage_text_height), _ = cv2.getTextSize(stage_text, 0, font_scale, line_thickness) - stage_text_position = (int(center_kpt[0]), int(center_kpt[1]) + angle_text_height + count_text_height + 40) - stage_background_position = (stage_text_position[0], stage_text_position[1] - stage_text_height - 5) - stage_background_size = (stage_text_width + 10, stage_text_height + 10) - - cv2.rectangle( - self.im, - stage_background_position, - ( - stage_background_position[0] + stage_background_size[0], - stage_background_position[1] + stage_background_size[1], - ), - (255, 255, 255), - -1, - ) - cv2.putText(self.im, stage_text, stage_text_position, 0, font_scale, (0, 0, 0), line_thickness) - - def seg_bbox(self, mask, mask_color=(255, 0, 255), det_label=None, track_label=None): - """ - Function for drawing segmented object in bounding box shape. - - Args: - mask (list): masks data list for instance segmentation area plotting - mask_color (tuple): mask foreground color - det_label (str): Detection label text - track_label (str): Tracking label text - """ - cv2.polylines(self.im, [np.int32([mask])], isClosed=True, color=mask_color, thickness=2) - - label = f"Track ID: {track_label}" if track_label else det_label - text_size, _ = cv2.getTextSize(label, 0, 0.7, 1) - - cv2.rectangle( - self.im, - (int(mask[0][0]) - text_size[0] // 2 - 10, int(mask[0][1]) - text_size[1] - 10), - (int(mask[0][0]) + text_size[0] // 2 + 5, int(mask[0][1] + 5)), - mask_color, - -1, - ) - - cv2.putText( - self.im, label, (int(mask[0][0]) - text_size[0] // 2, int(mask[0][1]) - 5), 0, 0.7, (255, 255, 255), 2 - ) - - def plot_distance_and_line(self, distance_m, distance_mm, centroids, line_color, centroid_color): - """ - Plot the distance and line on frame. - - Args: - distance_m (float): Distance between two bbox centroids in meters. - distance_mm (float): Distance between two bbox centroids in millimeters. - centroids (list): Bounding box centroids data. - line_color (RGB): Distance line color. - centroid_color (RGB): Bounding box centroid color. - """ - (text_width_m, text_height_m), _ = cv2.getTextSize( - f"Distance M: {distance_m:.2f}m", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2 - ) - cv2.rectangle(self.im, (15, 25), (15 + text_width_m + 10, 25 + text_height_m + 20), (255, 255, 255), -1) - cv2.putText( - self.im, - f"Distance M: {distance_m:.2f}m", - (20, 50), - cv2.FONT_HERSHEY_SIMPLEX, - 0.8, - (0, 0, 0), - 2, - cv2.LINE_AA, - ) - - (text_width_mm, text_height_mm), _ = cv2.getTextSize( - f"Distance MM: {distance_mm:.2f}mm", cv2.FONT_HERSHEY_SIMPLEX, 0.8, 2 - ) - cv2.rectangle(self.im, (15, 75), (15 + text_width_mm + 10, 75 + text_height_mm + 20), (255, 255, 255), -1) - cv2.putText( - self.im, - f"Distance MM: {distance_mm:.2f}mm", - (20, 100), - cv2.FONT_HERSHEY_SIMPLEX, - 0.8, - (0, 0, 0), - 2, - cv2.LINE_AA, - ) - - cv2.line(self.im, centroids[0], centroids[1], line_color, 3) - cv2.circle(self.im, centroids[0], 6, centroid_color, -1) - cv2.circle(self.im, centroids[1], 6, centroid_color, -1) - - def visioneye(self, box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255), thickness=2, pins_radius=10): - """ - Function for pinpoint human-vision eye mapping and plotting. - - Args: - box (list): Bounding box coordinates - center_point (tuple): center point for vision eye view - color (tuple): object centroid and line color value - pin_color (tuple): visioneye point color value - thickness (int): int value for line thickness - pins_radius (int): visioneye point radius value - """ - center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2) - cv2.circle(self.im, center_point, pins_radius, pin_color, -1) - cv2.circle(self.im, center_bbox, pins_radius, color, -1) - cv2.line(self.im, center_point, center_bbox, color, thickness) - - -@TryExcept() # known issue https://github.com/ultralytics/yolov5/issues/5395 -@plt_settings() -def plot_labels(boxes, cls, names=(), save_dir=Path(""), on_plot=None): - """Plot training labels including class histograms and box statistics.""" - import pandas as pd - import seaborn as sn - - # Filter matplotlib>=3.7.2 warning and Seaborn use_inf and is_categorical FutureWarnings - warnings.filterwarnings("ignore", category=UserWarning, message="The figure layout has changed to tight") - warnings.filterwarnings("ignore", category=FutureWarning) - - # Plot dataset labels - LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ") - nc = int(cls.max() + 1) # number of classes - boxes = boxes[:1000000] # limit to 1M boxes - x = pd.DataFrame(boxes, columns=["x", "y", "width", "height"]) - - # Seaborn correlogram - sn.pairplot(x, corner=True, diag_kind="auto", kind="hist", diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9)) - plt.savefig(save_dir / "labels_correlogram.jpg", dpi=200) - plt.close() - - # Matplotlib labels - ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() - y = ax[0].hist(cls, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) - for i in range(nc): - y[2].patches[i].set_color([x / 255 for x in colors(i)]) - ax[0].set_ylabel("instances") - if 0 < len(names) < 30: - ax[0].set_xticks(range(len(names))) - ax[0].set_xticklabels(list(names.values()), rotation=90, fontsize=10) - else: - ax[0].set_xlabel("classes") - sn.histplot(x, x="x", y="y", ax=ax[2], bins=50, pmax=0.9) - sn.histplot(x, x="width", y="height", ax=ax[3], bins=50, pmax=0.9) - - # Rectangles - boxes[:, 0:2] = 0.5 # center - boxes = ops.xywh2xyxy(boxes) * 1000 - img = Image.fromarray(np.ones((1000, 1000, 3), dtype=np.uint8) * 255) - for cls, box in zip(cls[:500], boxes[:500]): - ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot - ax[1].imshow(img) - ax[1].axis("off") - - for a in [0, 1, 2, 3]: - for s in ["top", "right", "left", "bottom"]: - ax[a].spines[s].set_visible(False) - - fname = save_dir / "labels.jpg" - plt.savefig(fname, dpi=200) - plt.close() - if on_plot: - on_plot(fname) - - -def save_one_box(xyxy, im, file=Path("im.jpg"), gain=1.02, pad=10, square=False, BGR=False, save=True): - """ - Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop. - - This function takes a bounding box and an image, and then saves a cropped portion of the image according - to the bounding box. Optionally, the crop can be squared, and the function allows for gain and padding - adjustments to the bounding box. - - Args: - xyxy (torch.Tensor or list): A tensor or list representing the bounding box in xyxy format. - im (numpy.ndarray): The input image. - file (Path, optional): The path where the cropped image will be saved. Defaults to 'im.jpg'. - gain (float, optional): A multiplicative factor to increase the size of the bounding box. Defaults to 1.02. - pad (int, optional): The number of pixels to add to the width and height of the bounding box. Defaults to 10. - square (bool, optional): If True, the bounding box will be transformed into a square. Defaults to False. - BGR (bool, optional): If True, the image will be saved in BGR format, otherwise in RGB. Defaults to False. - save (bool, optional): If True, the cropped image will be saved to disk. Defaults to True. - - Returns: - (numpy.ndarray): The cropped image. - - Example: - ```python - from ultralytics.utils.plotting import save_one_box - - xyxy = [50, 50, 150, 150] - im = cv2.imread('image.jpg') - cropped_im = save_one_box(xyxy, im, file='cropped.jpg', square=True) - ``` - """ - - if not isinstance(xyxy, torch.Tensor): # may be list - xyxy = torch.stack(xyxy) - b = ops.xyxy2xywh(xyxy.view(-1, 4)) # boxes - if square: - b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square - b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad - xyxy = ops.xywh2xyxy(b).long() - xyxy = ops.clip_boxes(xyxy, im.shape) - crop = im[int(xyxy[0, 1]) : int(xyxy[0, 3]), int(xyxy[0, 0]) : int(xyxy[0, 2]), :: (1 if BGR else -1)] - if save: - file.parent.mkdir(parents=True, exist_ok=True) # make directory - f = str(increment_path(file).with_suffix(".jpg")) - # cv2.imwrite(f, crop) # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue - Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0) # save RGB - return crop - - -@threaded -def plot_images( - images, - batch_idx, - cls, - bboxes=np.zeros(0, dtype=np.float32), - confs=None, - masks=np.zeros(0, dtype=np.uint8), - kpts=np.zeros((0, 51), dtype=np.float32), - paths=None, - fname="images.jpg", - names=None, - on_plot=None, - max_subplots=16, - save=True, - conf_thres=0.25, -): - """Plot image grid with labels.""" - if isinstance(images, torch.Tensor): - images = images.cpu().float().numpy() - if isinstance(cls, torch.Tensor): - cls = cls.cpu().numpy() - if isinstance(bboxes, torch.Tensor): - bboxes = bboxes.cpu().numpy() - if isinstance(masks, torch.Tensor): - masks = masks.cpu().numpy().astype(int) - if isinstance(kpts, torch.Tensor): - kpts = kpts.cpu().numpy() - if isinstance(batch_idx, torch.Tensor): - batch_idx = batch_idx.cpu().numpy() - - max_size = 1920 # max image size - bs, _, h, w = images.shape # batch size, _, height, width - bs = min(bs, max_subplots) # limit plot images - ns = np.ceil(bs**0.5) # number of subplots (square) - if np.max(images[0]) <= 1: - images *= 255 # de-normalise (optional) - - # Build Image - mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init - for i in range(bs): - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - mosaic[y : y + h, x : x + w, :] = images[i].transpose(1, 2, 0) - - # Resize (optional) - scale = max_size / ns / max(h, w) - if scale < 1: - h = math.ceil(scale * h) - w = math.ceil(scale * w) - mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) - - # Annotate - fs = int((h + w) * ns * 0.01) # font size - annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) - for i in range(bs): - x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin - annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders - if paths: - annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames - if len(cls) > 0: - idx = batch_idx == i - classes = cls[idx].astype("int") - labels = confs is None - - if len(bboxes): - boxes = bboxes[idx] - conf = confs[idx] if confs is not None else None # check for confidence presence (label vs pred) - is_obb = boxes.shape[-1] == 5 # xywhr - boxes = ops.xywhr2xyxyxyxy(boxes) if is_obb else ops.xywh2xyxy(boxes) - if len(boxes): - if boxes[:, :4].max() <= 1.1: # if normalized with tolerance 0.1 - boxes[..., 0::2] *= w # scale to pixels - boxes[..., 1::2] *= h - elif scale < 1: # absolute coords need scale if image scales - boxes[..., :4] *= scale - boxes[..., 0::2] += x - boxes[..., 1::2] += y - for j, box in enumerate(boxes.astype(np.int64).tolist()): - c = classes[j] - color = colors(c) - c = names.get(c, c) if names else c - if labels or conf[j] > conf_thres: - label = f"{c}" if labels else f"{c} {conf[j]:.1f}" - annotator.box_label(box, label, color=color, rotated=is_obb) - - elif len(classes): - for c in classes: - color = colors(c) - c = names.get(c, c) if names else c - annotator.text((x, y), f"{c}", txt_color=color, box_style=True) - - # Plot keypoints - if len(kpts): - kpts_ = kpts[idx].copy() - if len(kpts_): - if kpts_[..., 0].max() <= 1.01 or kpts_[..., 1].max() <= 1.01: # if normalized with tolerance .01 - kpts_[..., 0] *= w # scale to pixels - kpts_[..., 1] *= h - elif scale < 1: # absolute coords need scale if image scales - kpts_ *= scale - kpts_[..., 0] += x - kpts_[..., 1] += y - for j in range(len(kpts_)): - if labels or conf[j] > conf_thres: - annotator.kpts(kpts_[j]) - - # Plot masks - if len(masks): - if idx.shape[0] == masks.shape[0]: # overlap_masks=False - image_masks = masks[idx] - else: # overlap_masks=True - image_masks = masks[[i]] # (1, 640, 640) - nl = idx.sum() - index = np.arange(nl).reshape((nl, 1, 1)) + 1 - image_masks = np.repeat(image_masks, nl, axis=0) - image_masks = np.where(image_masks == index, 1.0, 0.0) - - im = np.asarray(annotator.im).copy() - for j in range(len(image_masks)): - if labels or conf[j] > conf_thres: - color = colors(classes[j]) - mh, mw = image_masks[j].shape - if mh != h or mw != w: - mask = image_masks[j].astype(np.uint8) - mask = cv2.resize(mask, (w, h)) - mask = mask.astype(bool) - else: - mask = image_masks[j].astype(bool) - with contextlib.suppress(Exception): - im[y : y + h, x : x + w, :][mask] = ( - im[y : y + h, x : x + w, :][mask] * 0.4 + np.array(color) * 0.6 - ) - annotator.fromarray(im) - if not save: - return np.asarray(annotator.im) - annotator.im.save(fname) # save - if on_plot: - on_plot(fname) - - -@plt_settings() -def plot_results(file="path/to/results.csv", dir="", segment=False, pose=False, classify=False, on_plot=None): - """ - Plot training results from a results CSV file. The function supports various types of data including segmentation, - pose estimation, and classification. Plots are saved as 'results.png' in the directory where the CSV is located. - - Args: - file (str, optional): Path to the CSV file containing the training results. Defaults to 'path/to/results.csv'. - dir (str, optional): Directory where the CSV file is located if 'file' is not provided. Defaults to ''. - segment (bool, optional): Flag to indicate if the data is for segmentation. Defaults to False. - pose (bool, optional): Flag to indicate if the data is for pose estimation. Defaults to False. - classify (bool, optional): Flag to indicate if the data is for classification. Defaults to False. - on_plot (callable, optional): Callback function to be executed after plotting. Takes filename as an argument. - Defaults to None. - - Example: - ```python - from ultralytics.utils.plotting import plot_results - - plot_results('path/to/results.csv', segment=True) - ``` - """ - import pandas as pd - from scipy.ndimage import gaussian_filter1d - - save_dir = Path(file).parent if file else Path(dir) - if classify: - fig, ax = plt.subplots(2, 2, figsize=(6, 6), tight_layout=True) - index = [1, 4, 2, 3] - elif segment: - fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True) - index = [1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12] - elif pose: - fig, ax = plt.subplots(2, 9, figsize=(21, 6), tight_layout=True) - index = [1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 18, 8, 9, 12, 13] - else: - fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True) - index = [1, 2, 3, 4, 5, 8, 9, 10, 6, 7] - ax = ax.ravel() - files = list(save_dir.glob("results*.csv")) - assert len(files), f"No results.csv files found in {save_dir.resolve()}, nothing to plot." - for f in files: - try: - data = pd.read_csv(f) - s = [x.strip() for x in data.columns] - x = data.values[:, 0] - for i, j in enumerate(index): - y = data.values[:, j].astype("float") - # y[y == 0] = np.nan # don't show zero values - ax[i].plot(x, y, marker=".", label=f.stem, linewidth=2, markersize=8) # actual results - ax[i].plot(x, gaussian_filter1d(y, sigma=3), ":", label="smooth", linewidth=2) # smoothing line - ax[i].set_title(s[j], fontsize=12) - # if j in [8, 9, 10]: # share train and val loss y axes - # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) - except Exception as e: - LOGGER.warning(f"WARNING: Plotting error for {f}: {e}") - ax[1].legend() - fname = save_dir / "results.png" - fig.savefig(fname, dpi=200) - plt.close() - if on_plot: - on_plot(fname) - - -def plt_color_scatter(v, f, bins=20, cmap="viridis", alpha=0.8, edgecolors="none"): - """ - Plots a scatter plot with points colored based on a 2D histogram. - - Args: - v (array-like): Values for the x-axis. - f (array-like): Values for the y-axis. - bins (int, optional): Number of bins for the histogram. Defaults to 20. - cmap (str, optional): Colormap for the scatter plot. Defaults to 'viridis'. - alpha (float, optional): Alpha for the scatter plot. Defaults to 0.8. - edgecolors (str, optional): Edge colors for the scatter plot. Defaults to 'none'. - - Examples: - >>> v = np.random.rand(100) - >>> f = np.random.rand(100) - >>> plt_color_scatter(v, f) - """ - - # Calculate 2D histogram and corresponding colors - hist, xedges, yedges = np.histogram2d(v, f, bins=bins) - colors = [ - hist[ - min(np.digitize(v[i], xedges, right=True) - 1, hist.shape[0] - 1), - min(np.digitize(f[i], yedges, right=True) - 1, hist.shape[1] - 1), - ] - for i in range(len(v)) - ] - - # Scatter plot - plt.scatter(v, f, c=colors, cmap=cmap, alpha=alpha, edgecolors=edgecolors) - - -def plot_tune_results(csv_file="tune_results.csv"): - """ - Plot the evolution results stored in an 'tune_results.csv' file. The function generates a scatter plot for each key - in the CSV, color-coded based on fitness scores. The best-performing configurations are highlighted on the plots. - - Args: - csv_file (str, optional): Path to the CSV file containing the tuning results. Defaults to 'tune_results.csv'. - - Examples: - >>> plot_tune_results('path/to/tune_results.csv') - """ - - import pandas as pd - from scipy.ndimage import gaussian_filter1d - - # Scatter plots for each hyperparameter - csv_file = Path(csv_file) - data = pd.read_csv(csv_file) - num_metrics_columns = 1 - keys = [x.strip() for x in data.columns][num_metrics_columns:] - x = data.values - fitness = x[:, 0] # fitness - j = np.argmax(fitness) # max fitness index - n = math.ceil(len(keys) ** 0.5) # columns and rows in plot - plt.figure(figsize=(10, 10), tight_layout=True) - for i, k in enumerate(keys): - v = x[:, i + num_metrics_columns] - mu = v[j] # best single result - plt.subplot(n, n, i + 1) - plt_color_scatter(v, fitness, cmap="viridis", alpha=0.8, edgecolors="none") - plt.plot(mu, fitness.max(), "k+", markersize=15) - plt.title(f"{k} = {mu:.3g}", fontdict={"size": 9}) # limit to 40 characters - plt.tick_params(axis="both", labelsize=8) # Set axis label size to 8 - if i % n != 0: - plt.yticks([]) - - file = csv_file.with_name("tune_scatter_plots.png") # filename - plt.savefig(file, dpi=200) - plt.close() - LOGGER.info(f"Saved {file}") - - # Fitness vs iteration - x = range(1, len(fitness) + 1) - plt.figure(figsize=(10, 6), tight_layout=True) - plt.plot(x, fitness, marker="o", linestyle="none", label="fitness") - plt.plot(x, gaussian_filter1d(fitness, sigma=3), ":", label="smoothed", linewidth=2) # smoothing line - plt.title("Fitness vs Iteration") - plt.xlabel("Iteration") - plt.ylabel("Fitness") - plt.grid(True) - plt.legend() - - file = csv_file.with_name("tune_fitness.png") # filename - plt.savefig(file, dpi=200) - plt.close() - LOGGER.info(f"Saved {file}") - - -def output_to_target(output, max_det=300): - """Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting.""" - targets = [] - for i, o in enumerate(output): - box, conf, cls = o[:max_det, :6].cpu().split((4, 1, 1), 1) - j = torch.full((conf.shape[0], 1), i) - targets.append(torch.cat((j, cls, ops.xyxy2xywh(box), conf), 1)) - targets = torch.cat(targets, 0).numpy() - return targets[:, 0], targets[:, 1], targets[:, 2:-1], targets[:, -1] - - -def output_to_rotated_target(output, max_det=300): - """Convert model output to target format [batch_id, class_id, x, y, w, h, conf] for plotting.""" - targets = [] - for i, o in enumerate(output): - box, conf, cls, angle = o[:max_det].cpu().split((4, 1, 1, 1), 1) - j = torch.full((conf.shape[0], 1), i) - targets.append(torch.cat((j, cls, box, angle, conf), 1)) - targets = torch.cat(targets, 0).numpy() - return targets[:, 0], targets[:, 1], targets[:, 2:-1], targets[:, -1] - - -def feature_visualization(x, module_type, stage, n=32, save_dir=Path("runs/detect/exp")): - """ - Visualize feature maps of a given model module during inference. - - Args: - x (torch.Tensor): Features to be visualized. - module_type (str): Module type. - stage (int): Module stage within the model. - n (int, optional): Maximum number of feature maps to plot. Defaults to 32. - save_dir (Path, optional): Directory to save results. Defaults to Path('runs/detect/exp'). - """ - for m in ["Detect", "Pose", "Segment"]: - if m in module_type: - return - _, channels, height, width = x.shape # batch, channels, height, width - if height > 1 and width > 1: - f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename - - blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels - n = min(n, channels) # number of plots - _, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols - ax = ax.ravel() - plt.subplots_adjust(wspace=0.05, hspace=0.05) - for i in range(n): - ax[i].imshow(blocks[i].squeeze()) # cmap='gray' - ax[i].axis("off") - - LOGGER.info(f"Saving {f}... ({n}/{channels})") - plt.savefig(f, dpi=300, bbox_inches="tight") - plt.close() - np.save(str(f.with_suffix(".npy")), x[0].cpu().numpy()) # npy save diff --git a/ultralytics-main/ultralytics/utils/tal.py b/ultralytics-main/ultralytics/utils/tal.py deleted file mode 100644 index 9cee050..0000000 --- a/ultralytics-main/ultralytics/utils/tal.py +++ /dev/null @@ -1,344 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import torch -import torch.nn as nn - -from .checks import check_version -from .metrics import bbox_iou, probiou -from .ops import xywhr2xyxyxyxy - -TORCH_1_10 = check_version(torch.__version__, "1.10.0") - - -class TaskAlignedAssigner(nn.Module): - """ - A task-aligned assigner for object detection. - - This class assigns ground-truth (gt) objects to anchors based on the task-aligned metric, which combines both - classification and localization information. - - Attributes: - topk (int): The number of top candidates to consider. - num_classes (int): The number of object classes. - alpha (float): The alpha parameter for the classification component of the task-aligned metric. - beta (float): The beta parameter for the localization component of the task-aligned metric. - eps (float): A small value to prevent division by zero. - """ - - def __init__(self, topk=13, num_classes=80, alpha=1.0, beta=6.0, eps=1e-9): - """Initialize a TaskAlignedAssigner object with customizable hyperparameters.""" - super().__init__() - self.topk = topk - self.num_classes = num_classes - self.bg_idx = num_classes - self.alpha = alpha - self.beta = beta - self.eps = eps - - @torch.no_grad() - def forward(self, pd_scores, pd_bboxes, anc_points, gt_labels, gt_bboxes, mask_gt): - """ - Compute the task-aligned assignment. Reference code is available at - https://github.com/Nioolek/PPYOLOE_pytorch/blob/master/ppyoloe/assigner/tal_assigner.py. - - Args: - pd_scores (Tensor): shape(bs, num_total_anchors, num_classes) - pd_bboxes (Tensor): shape(bs, num_total_anchors, 4) - anc_points (Tensor): shape(num_total_anchors, 2) - gt_labels (Tensor): shape(bs, n_max_boxes, 1) - gt_bboxes (Tensor): shape(bs, n_max_boxes, 4) - mask_gt (Tensor): shape(bs, n_max_boxes, 1) - - Returns: - target_labels (Tensor): shape(bs, num_total_anchors) - target_bboxes (Tensor): shape(bs, num_total_anchors, 4) - target_scores (Tensor): shape(bs, num_total_anchors, num_classes) - fg_mask (Tensor): shape(bs, num_total_anchors) - target_gt_idx (Tensor): shape(bs, num_total_anchors) - """ - self.bs = pd_scores.shape[0] - self.n_max_boxes = gt_bboxes.shape[1] - - if self.n_max_boxes == 0: - device = gt_bboxes.device - return ( - torch.full_like(pd_scores[..., 0], self.bg_idx).to(device), - torch.zeros_like(pd_bboxes).to(device), - torch.zeros_like(pd_scores).to(device), - torch.zeros_like(pd_scores[..., 0]).to(device), - torch.zeros_like(pd_scores[..., 0]).to(device), - ) - - mask_pos, align_metric, overlaps = self.get_pos_mask( - pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points, mask_gt - ) - - target_gt_idx, fg_mask, mask_pos = self.select_highest_overlaps(mask_pos, overlaps, self.n_max_boxes) - - # Assigned target - target_labels, target_bboxes, target_scores = self.get_targets(gt_labels, gt_bboxes, target_gt_idx, fg_mask) - - # Normalize - align_metric *= mask_pos - pos_align_metrics = align_metric.amax(dim=-1, keepdim=True) # b, max_num_obj - pos_overlaps = (overlaps * mask_pos).amax(dim=-1, keepdim=True) # b, max_num_obj - norm_align_metric = (align_metric * pos_overlaps / (pos_align_metrics + self.eps)).amax(-2).unsqueeze(-1) - target_scores = target_scores * norm_align_metric - - return target_labels, target_bboxes, target_scores, fg_mask.bool(), target_gt_idx - - def get_pos_mask(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points, mask_gt): - """Get in_gts mask, (b, max_num_obj, h*w).""" - mask_in_gts = self.select_candidates_in_gts(anc_points, gt_bboxes) - # Get anchor_align metric, (b, max_num_obj, h*w) - align_metric, overlaps = self.get_box_metrics(pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_in_gts * mask_gt) - # Get topk_metric mask, (b, max_num_obj, h*w) - mask_topk = self.select_topk_candidates(align_metric, topk_mask=mask_gt.expand(-1, -1, self.topk).bool()) - # Merge all mask to a final mask, (b, max_num_obj, h*w) - mask_pos = mask_topk * mask_in_gts * mask_gt - - return mask_pos, align_metric, overlaps - - def get_box_metrics(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_gt): - """Compute alignment metric given predicted and ground truth bounding boxes.""" - na = pd_bboxes.shape[-2] - mask_gt = mask_gt.bool() # b, max_num_obj, h*w - overlaps = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_bboxes.dtype, device=pd_bboxes.device) - bbox_scores = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_scores.dtype, device=pd_scores.device) - - ind = torch.zeros([2, self.bs, self.n_max_boxes], dtype=torch.long) # 2, b, max_num_obj - ind[0] = torch.arange(end=self.bs).view(-1, 1).expand(-1, self.n_max_boxes) # b, max_num_obj - ind[1] = gt_labels.squeeze(-1) # b, max_num_obj - # Get the scores of each grid for each gt cls - bbox_scores[mask_gt] = pd_scores[ind[0], :, ind[1]][mask_gt] # b, max_num_obj, h*w - - # (b, max_num_obj, 1, 4), (b, 1, h*w, 4) - pd_boxes = pd_bboxes.unsqueeze(1).expand(-1, self.n_max_boxes, -1, -1)[mask_gt] - gt_boxes = gt_bboxes.unsqueeze(2).expand(-1, -1, na, -1)[mask_gt] - overlaps[mask_gt] = self.iou_calculation(gt_boxes, pd_boxes) - - align_metric = bbox_scores.pow(self.alpha) * overlaps.pow(self.beta) - return align_metric, overlaps - - def iou_calculation(self, gt_bboxes, pd_bboxes): - """IoU calculation for horizontal bounding boxes.""" - return bbox_iou(gt_bboxes, pd_bboxes, xywh=False, CIoU=True).squeeze(-1).clamp_(0) - - def select_topk_candidates(self, metrics, largest=True, topk_mask=None): - """ - Select the top-k candidates based on the given metrics. - - Args: - metrics (Tensor): A tensor of shape (b, max_num_obj, h*w), where b is the batch size, - max_num_obj is the maximum number of objects, and h*w represents the - total number of anchor points. - largest (bool): If True, select the largest values; otherwise, select the smallest values. - topk_mask (Tensor): An optional boolean tensor of shape (b, max_num_obj, topk), where - topk is the number of top candidates to consider. If not provided, - the top-k values are automatically computed based on the given metrics. - - Returns: - (Tensor): A tensor of shape (b, max_num_obj, h*w) containing the selected top-k candidates. - """ - - # (b, max_num_obj, topk) - topk_metrics, topk_idxs = torch.topk(metrics, self.topk, dim=-1, largest=largest) - if topk_mask is None: - topk_mask = (topk_metrics.max(-1, keepdim=True)[0] > self.eps).expand_as(topk_idxs) - # (b, max_num_obj, topk) - topk_idxs.masked_fill_(~topk_mask, 0) - - # (b, max_num_obj, topk, h*w) -> (b, max_num_obj, h*w) - count_tensor = torch.zeros(metrics.shape, dtype=torch.int8, device=topk_idxs.device) - ones = torch.ones_like(topk_idxs[:, :, :1], dtype=torch.int8, device=topk_idxs.device) - for k in range(self.topk): - # Expand topk_idxs for each value of k and add 1 at the specified positions - count_tensor.scatter_add_(-1, topk_idxs[:, :, k : k + 1], ones) - # count_tensor.scatter_add_(-1, topk_idxs, torch.ones_like(topk_idxs, dtype=torch.int8, device=topk_idxs.device)) - # Filter invalid bboxes - count_tensor.masked_fill_(count_tensor > 1, 0) - - return count_tensor.to(metrics.dtype) - - def get_targets(self, gt_labels, gt_bboxes, target_gt_idx, fg_mask): - """ - Compute target labels, target bounding boxes, and target scores for the positive anchor points. - - Args: - gt_labels (Tensor): Ground truth labels of shape (b, max_num_obj, 1), where b is the - batch size and max_num_obj is the maximum number of objects. - gt_bboxes (Tensor): Ground truth bounding boxes of shape (b, max_num_obj, 4). - target_gt_idx (Tensor): Indices of the assigned ground truth objects for positive - anchor points, with shape (b, h*w), where h*w is the total - number of anchor points. - fg_mask (Tensor): A boolean tensor of shape (b, h*w) indicating the positive - (foreground) anchor points. - - Returns: - (Tuple[Tensor, Tensor, Tensor]): A tuple containing the following tensors: - - target_labels (Tensor): Shape (b, h*w), containing the target labels for - positive anchor points. - - target_bboxes (Tensor): Shape (b, h*w, 4), containing the target bounding boxes - for positive anchor points. - - target_scores (Tensor): Shape (b, h*w, num_classes), containing the target scores - for positive anchor points, where num_classes is the number - of object classes. - """ - - # Assigned target labels, (b, 1) - batch_ind = torch.arange(end=self.bs, dtype=torch.int64, device=gt_labels.device)[..., None] - target_gt_idx = target_gt_idx + batch_ind * self.n_max_boxes # (b, h*w) - target_labels = gt_labels.long().flatten()[target_gt_idx] # (b, h*w) - - # Assigned target boxes, (b, max_num_obj, 4) -> (b, h*w, 4) - target_bboxes = gt_bboxes.view(-1, gt_bboxes.shape[-1])[target_gt_idx] - - # Assigned target scores - target_labels.clamp_(0) - - # 10x faster than F.one_hot() - target_scores = torch.zeros( - (target_labels.shape[0], target_labels.shape[1], self.num_classes), - dtype=torch.int64, - device=target_labels.device, - ) # (b, h*w, 80) - target_scores.scatter_(2, target_labels.unsqueeze(-1), 1) - - fg_scores_mask = fg_mask[:, :, None].repeat(1, 1, self.num_classes) # (b, h*w, 80) - target_scores = torch.where(fg_scores_mask > 0, target_scores, 0) - - return target_labels, target_bboxes, target_scores - - @staticmethod - def select_candidates_in_gts(xy_centers, gt_bboxes, eps=1e-9): - """ - Select the positive anchor center in gt. - - Args: - xy_centers (Tensor): shape(h*w, 2) - gt_bboxes (Tensor): shape(b, n_boxes, 4) - - Returns: - (Tensor): shape(b, n_boxes, h*w) - """ - n_anchors = xy_centers.shape[0] - bs, n_boxes, _ = gt_bboxes.shape - lt, rb = gt_bboxes.view(-1, 1, 4).chunk(2, 2) # left-top, right-bottom - bbox_deltas = torch.cat((xy_centers[None] - lt, rb - xy_centers[None]), dim=2).view(bs, n_boxes, n_anchors, -1) - # return (bbox_deltas.min(3)[0] > eps).to(gt_bboxes.dtype) - return bbox_deltas.amin(3).gt_(eps) - - @staticmethod - def select_highest_overlaps(mask_pos, overlaps, n_max_boxes): - """ - If an anchor box is assigned to multiple gts, the one with the highest IoU will be selected. - - Args: - mask_pos (Tensor): shape(b, n_max_boxes, h*w) - overlaps (Tensor): shape(b, n_max_boxes, h*w) - - Returns: - target_gt_idx (Tensor): shape(b, h*w) - fg_mask (Tensor): shape(b, h*w) - mask_pos (Tensor): shape(b, n_max_boxes, h*w) - """ - # (b, n_max_boxes, h*w) -> (b, h*w) - fg_mask = mask_pos.sum(-2) - if fg_mask.max() > 1: # one anchor is assigned to multiple gt_bboxes - mask_multi_gts = (fg_mask.unsqueeze(1) > 1).expand(-1, n_max_boxes, -1) # (b, n_max_boxes, h*w) - max_overlaps_idx = overlaps.argmax(1) # (b, h*w) - - is_max_overlaps = torch.zeros(mask_pos.shape, dtype=mask_pos.dtype, device=mask_pos.device) - is_max_overlaps.scatter_(1, max_overlaps_idx.unsqueeze(1), 1) - - mask_pos = torch.where(mask_multi_gts, is_max_overlaps, mask_pos).float() # (b, n_max_boxes, h*w) - fg_mask = mask_pos.sum(-2) - # Find each grid serve which gt(index) - target_gt_idx = mask_pos.argmax(-2) # (b, h*w) - return target_gt_idx, fg_mask, mask_pos - - -class RotatedTaskAlignedAssigner(TaskAlignedAssigner): - def iou_calculation(self, gt_bboxes, pd_bboxes): - """IoU calculation for rotated bounding boxes.""" - return probiou(gt_bboxes, pd_bboxes).squeeze(-1).clamp_(0) - - @staticmethod - def select_candidates_in_gts(xy_centers, gt_bboxes): - """ - Select the positive anchor center in gt for rotated bounding boxes. - - Args: - xy_centers (Tensor): shape(h*w, 2) - gt_bboxes (Tensor): shape(b, n_boxes, 5) - - Returns: - (Tensor): shape(b, n_boxes, h*w) - """ - # (b, n_boxes, 5) --> (b, n_boxes, 4, 2) - corners = xywhr2xyxyxyxy(gt_bboxes) - # (b, n_boxes, 1, 2) - a, b, _, d = corners.split(1, dim=-2) - ab = b - a - ad = d - a - - # (b, n_boxes, h*w, 2) - ap = xy_centers - a - norm_ab = (ab * ab).sum(dim=-1) - norm_ad = (ad * ad).sum(dim=-1) - ap_dot_ab = (ap * ab).sum(dim=-1) - ap_dot_ad = (ap * ad).sum(dim=-1) - return (ap_dot_ab >= 0) & (ap_dot_ab <= norm_ab) & (ap_dot_ad >= 0) & (ap_dot_ad <= norm_ad) # is_in_box - - -def make_anchors(feats, strides, grid_cell_offset=0.5): - """Generate anchors from features.""" - anchor_points, stride_tensor = [], [] - assert feats is not None - dtype, device = feats[0].dtype, feats[0].device - for i, stride in enumerate(strides): - _, _, h, w = feats[i].shape - sx = torch.arange(end=w, device=device, dtype=dtype) + grid_cell_offset # shift x - sy = torch.arange(end=h, device=device, dtype=dtype) + grid_cell_offset # shift y - sy, sx = torch.meshgrid(sy, sx, indexing="ij") if TORCH_1_10 else torch.meshgrid(sy, sx) - anchor_points.append(torch.stack((sx, sy), -1).view(-1, 2)) - stride_tensor.append(torch.full((h * w, 1), stride, dtype=dtype, device=device)) - return torch.cat(anchor_points), torch.cat(stride_tensor) - - -def dist2bbox(distance, anchor_points, xywh=True, dim=-1): - """Transform distance(ltrb) to box(xywh or xyxy).""" - lt, rb = distance.chunk(2, dim) - x1y1 = anchor_points - lt - x2y2 = anchor_points + rb - if xywh: - c_xy = (x1y1 + x2y2) / 2 - wh = x2y2 - x1y1 - return torch.cat((c_xy, wh), dim) # xywh bbox - return torch.cat((x1y1, x2y2), dim) # xyxy bbox - - -def bbox2dist(anchor_points, bbox, reg_max): - """Transform bbox(xyxy) to dist(ltrb).""" - x1y1, x2y2 = bbox.chunk(2, -1) - return torch.cat((anchor_points - x1y1, x2y2 - anchor_points), -1).clamp_(0, reg_max - 0.01) # dist (lt, rb) - - -def dist2rbox(pred_dist, pred_angle, anchor_points, dim=-1): - """ - Decode predicted object bounding box coordinates from anchor points and distribution. - - Args: - pred_dist (torch.Tensor): Predicted rotated distance, (bs, h*w, 4). - pred_angle (torch.Tensor): Predicted angle, (bs, h*w, 1). - anchor_points (torch.Tensor): Anchor points, (h*w, 2). - Returns: - (torch.Tensor): Predicted rotated bounding boxes, (bs, h*w, 4). - """ - lt, rb = pred_dist.split(2, dim=dim) - cos, sin = torch.cos(pred_angle), torch.sin(pred_angle) - # (bs, h*w, 1) - xf, yf = ((rb - lt) / 2).split(1, dim=dim) - x, y = xf * cos - yf * sin, xf * sin + yf * cos - xy = torch.cat([x, y], dim=dim) + anchor_points - return torch.cat([xy, lt + rb], dim=dim) diff --git a/ultralytics-main/ultralytics/utils/torch_utils.py b/ultralytics-main/ultralytics/utils/torch_utils.py deleted file mode 100644 index ea0cdf1..0000000 --- a/ultralytics-main/ultralytics/utils/torch_utils.py +++ /dev/null @@ -1,608 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import math -import os -import random -import time -from contextlib import contextmanager -from copy import deepcopy -from pathlib import Path -from typing import Union - -import numpy as np -import torch -import torch.distributed as dist -import torch.nn as nn -import torch.nn.functional as F -import torchvision - -from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, __version__ -from ultralytics.utils.checks import PYTHON_VERSION, check_version - -try: - import thop -except ImportError: - thop = None - -TORCH_1_9 = check_version(torch.__version__, "1.9.0") -TORCH_1_13 = check_version(torch.__version__, "1.13.0") -TORCH_2_0 = check_version(torch.__version__, "2.0.0") -TORCHVISION_0_10 = check_version(torchvision.__version__, "0.10.0") -TORCHVISION_0_11 = check_version(torchvision.__version__, "0.11.0") -TORCHVISION_0_13 = check_version(torchvision.__version__, "0.13.0") - - -@contextmanager -def torch_distributed_zero_first(local_rank: int): - """Decorator to make all processes in distributed training wait for each local_master to do something.""" - initialized = torch.distributed.is_available() and torch.distributed.is_initialized() - if initialized and local_rank not in (-1, 0): - dist.barrier(device_ids=[local_rank]) - yield - if initialized and local_rank == 0: - dist.barrier(device_ids=[0]) - - -def smart_inference_mode(): - """Applies torch.inference_mode() decorator if torch>=1.9.0 else torch.no_grad() decorator.""" - - def decorate(fn): - """Applies appropriate torch decorator for inference mode based on torch version.""" - if TORCH_1_9 and torch.is_inference_mode_enabled(): - return fn # already in inference_mode, act as a pass-through - else: - return (torch.inference_mode if TORCH_1_9 else torch.no_grad)()(fn) - - return decorate - - -def get_cpu_info(): - """Return a string with system CPU information, i.e. 'Apple M2'.""" - import cpuinfo # pip install py-cpuinfo - - k = "brand_raw", "hardware_raw", "arch_string_raw" # info keys sorted by preference (not all keys always available) - info = cpuinfo.get_cpu_info() # info dict - string = info.get(k[0] if k[0] in info else k[1] if k[1] in info else k[2], "unknown") - return string.replace("(R)", "").replace("CPU ", "").replace("@ ", "") - - -def select_device(device="", batch=0, newline=False, verbose=True): - """ - Selects the appropriate PyTorch device based on the provided arguments. - - The function takes a string specifying the device or a torch.device object and returns a torch.device object - representing the selected device. The function also validates the number of available devices and raises an - exception if the requested device(s) are not available. - - Args: - device (str | torch.device, optional): Device string or torch.device object. - Options are 'None', 'cpu', or 'cuda', or '0' or '0,1,2,3'. Defaults to an empty string, which auto-selects - the first available GPU, or CPU if no GPU is available. - batch (int, optional): Batch size being used in your model. Defaults to 0. - newline (bool, optional): If True, adds a newline at the end of the log string. Defaults to False. - verbose (bool, optional): If True, logs the device information. Defaults to True. - - Returns: - (torch.device): Selected device. - - Raises: - ValueError: If the specified device is not available or if the batch size is not a multiple of the number of - devices when using multiple GPUs. - - Examples: - >>> select_device('cuda:0') - device(type='cuda', index=0) - - >>> select_device('cpu') - device(type='cpu') - - Note: - Sets the 'CUDA_VISIBLE_DEVICES' environment variable for specifying which GPUs to use. - """ - - if isinstance(device, torch.device): - return device - - s = f"Ultralytics YOLOv{__version__} 🚀 Python-{PYTHON_VERSION} torch-{torch.__version__} " - device = str(device).lower() - for remove in "cuda:", "none", "(", ")", "[", "]", "'", " ": - device = device.replace(remove, "") # to string, 'cuda:0' -> '0' and '(0, 1)' -> '0,1' - cpu = device == "cpu" - mps = device in ("mps", "mps:0") # Apple Metal Performance Shaders (MPS) - if cpu or mps: - os.environ["CUDA_VISIBLE_DEVICES"] = "-1" # force torch.cuda.is_available() = False - elif device: # non-cpu device requested - if device == "cuda": - device = "0" - visible = os.environ.get("CUDA_VISIBLE_DEVICES", None) - os.environ["CUDA_VISIBLE_DEVICES"] = device # set environment variable - must be before assert is_available() - if not (torch.cuda.is_available() and torch.cuda.device_count() >= len(device.split(","))): - LOGGER.info(s) - install = ( - "See https://pytorch.org/get-started/locally/ for up-to-date torch install instructions if no " - "CUDA devices are seen by torch.\n" - if torch.cuda.device_count() == 0 - else "" - ) - raise ValueError( - f"Invalid CUDA 'device={device}' requested." - f" Use 'device=cpu' or pass valid CUDA device(s) if available," - f" i.e. 'device=0' or 'device=0,1,2,3' for Multi-GPU.\n" - f"\ntorch.cuda.is_available(): {torch.cuda.is_available()}" - f"\ntorch.cuda.device_count(): {torch.cuda.device_count()}" - f"\nos.environ['CUDA_VISIBLE_DEVICES']: {visible}\n" - f"{install}" - ) - - if not cpu and not mps and torch.cuda.is_available(): # prefer GPU if available - devices = device.split(",") if device else "0" # range(torch.cuda.device_count()) # i.e. 0,1,6,7 - n = len(devices) # device count - if n > 1 and batch > 0 and batch % n != 0: # check batch_size is divisible by device_count - raise ValueError( - f"'batch={batch}' must be a multiple of GPU count {n}. Try 'batch={batch // n * n}' or " - f"'batch={batch // n * n + n}', the nearest batch sizes evenly divisible by {n}." - ) - space = " " * (len(s) + 1) - for i, d in enumerate(devices): - p = torch.cuda.get_device_properties(i) - s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / (1 << 20):.0f}MiB)\n" # bytes to MB - arg = "cuda:0" - elif mps and TORCH_2_0 and torch.backends.mps.is_available(): - # Prefer MPS if available - s += f"MPS ({get_cpu_info()})\n" - arg = "mps" - else: # revert to CPU - s += f"CPU ({get_cpu_info()})\n" - arg = "cpu" - - if verbose: - LOGGER.info(s if newline else s.rstrip()) - return torch.device(arg) - - -def time_sync(): - """PyTorch-accurate time.""" - if torch.cuda.is_available(): - torch.cuda.synchronize() - return time.time() - - -def fuse_conv_and_bn(conv, bn): - """Fuse Conv2d() and BatchNorm2d() layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/.""" - fusedconv = ( - nn.Conv2d( - conv.in_channels, - conv.out_channels, - kernel_size=conv.kernel_size, - stride=conv.stride, - padding=conv.padding, - dilation=conv.dilation, - groups=conv.groups, - bias=True, - ) - .requires_grad_(False) - .to(conv.weight.device) - ) - - # Prepare filters - w_conv = conv.weight.clone().view(conv.out_channels, -1) - w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) - fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape)) - - # Prepare spatial bias - b_conv = torch.zeros(conv.weight.shape[0], device=conv.weight.device) if conv.bias is None else conv.bias - b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) - fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) - - return fusedconv - - -def fuse_deconv_and_bn(deconv, bn): - """Fuse ConvTranspose2d() and BatchNorm2d() layers.""" - fuseddconv = ( - nn.ConvTranspose2d( - deconv.in_channels, - deconv.out_channels, - kernel_size=deconv.kernel_size, - stride=deconv.stride, - padding=deconv.padding, - output_padding=deconv.output_padding, - dilation=deconv.dilation, - groups=deconv.groups, - bias=True, - ) - .requires_grad_(False) - .to(deconv.weight.device) - ) - - # Prepare filters - w_deconv = deconv.weight.clone().view(deconv.out_channels, -1) - w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) - fuseddconv.weight.copy_(torch.mm(w_bn, w_deconv).view(fuseddconv.weight.shape)) - - # Prepare spatial bias - b_conv = torch.zeros(deconv.weight.shape[1], device=deconv.weight.device) if deconv.bias is None else deconv.bias - b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) - fuseddconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) - - return fuseddconv - - -def model_info(model, detailed=False, verbose=True, imgsz=640): - """ - Model information. - - imgsz may be int or list, i.e. imgsz=640 or imgsz=[640, 320]. - """ - if not verbose: - return - n_p = get_num_params(model) # number of parameters - n_g = get_num_gradients(model) # number of gradients - n_l = len(list(model.modules())) # number of layers - if detailed: - LOGGER.info( - f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}" - ) - for i, (name, p) in enumerate(model.named_parameters()): - name = name.replace("module_list.", "") - LOGGER.info( - "%5g %40s %9s %12g %20s %10.3g %10.3g %10s" - % (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std(), p.dtype) - ) - - flops = get_flops(model, imgsz) - fused = " (fused)" if getattr(model, "is_fused", lambda: False)() else "" - fs = f", {flops:.1f} GFLOPs" if flops else "" - yaml_file = getattr(model, "yaml_file", "") or getattr(model, "yaml", {}).get("yaml_file", "") - model_name = Path(yaml_file).stem.replace("yolo", "YOLO") or "Model" - LOGGER.info(f"{model_name} summary{fused}: {n_l} layers, {n_p} parameters, {n_g} gradients{fs}") - return n_l, n_p, n_g, flops - - -def get_num_params(model): - """Return the total number of parameters in a YOLO model.""" - return sum(x.numel() for x in model.parameters()) - - -def get_num_gradients(model): - """Return the total number of parameters with gradients in a YOLO model.""" - return sum(x.numel() for x in model.parameters() if x.requires_grad) - - -def model_info_for_loggers(trainer): - """ - Return model info dict with useful model information. - - Example: - YOLOv8n info for loggers - ```python - results = {'model/parameters': 3151904, - 'model/GFLOPs': 8.746, - 'model/speed_ONNX(ms)': 41.244, - 'model/speed_TensorRT(ms)': 3.211, - 'model/speed_PyTorch(ms)': 18.755} - ``` - """ - if trainer.args.profile: # profile ONNX and TensorRT times - from ultralytics.utils.benchmarks import ProfileModels - - results = ProfileModels([trainer.last], device=trainer.device).profile()[0] - results.pop("model/name") - else: # only return PyTorch times from most recent validation - results = { - "model/parameters": get_num_params(trainer.model), - "model/GFLOPs": round(get_flops(trainer.model), 3), - } - results["model/speed_PyTorch(ms)"] = round(trainer.validator.speed["inference"], 3) - return results - - -def get_flops(model, imgsz=640): - """Return a YOLO model's FLOPs.""" - if not thop: - return 0.0 # if not installed return 0.0 GFLOPs - - try: - model = de_parallel(model) - p = next(model.parameters()) - if not isinstance(imgsz, list): - imgsz = [imgsz, imgsz] # expand if int/float - try: - # Use stride size for input tensor - stride = max(int(model.stride.max()), 32) if hasattr(model, "stride") else 32 # max stride - im = torch.empty((1, p.shape[1], stride, stride), device=p.device) # input image in BCHW format - flops = thop.profile(deepcopy(model), inputs=[im], verbose=False)[0] / 1e9 * 2 # stride GFLOPs - return flops * imgsz[0] / stride * imgsz[1] / stride # imgsz GFLOPs - except Exception: - # Use actual image size for input tensor (i.e. required for RTDETR models) - im = torch.empty((1, p.shape[1], *imgsz), device=p.device) # input image in BCHW format - return thop.profile(deepcopy(model), inputs=[im], verbose=False)[0] / 1e9 * 2 # imgsz GFLOPs - except Exception: - return 0.0 - - -def get_flops_with_torch_profiler(model, imgsz=640): - """Compute model FLOPs (thop alternative).""" - if TORCH_2_0: - model = de_parallel(model) - p = next(model.parameters()) - stride = (max(int(model.stride.max()), 32) if hasattr(model, "stride") else 32) * 2 # max stride - im = torch.zeros((1, p.shape[1], stride, stride), device=p.device) # input image in BCHW format - with torch.profiler.profile(with_flops=True) as prof: - model(im) - flops = sum(x.flops for x in prof.key_averages()) / 1e9 - imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz] # expand if int/float - flops = flops * imgsz[0] / stride * imgsz[1] / stride # 640x640 GFLOPs - return flops - return 0 - - -def initialize_weights(model): - """Initialize model weights to random values.""" - for m in model.modules(): - t = type(m) - if t is nn.Conv2d: - pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') - elif t is nn.BatchNorm2d: - m.eps = 1e-3 - m.momentum = 0.03 - elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]: - m.inplace = True - - -def scale_img(img, ratio=1.0, same_shape=False, gs=32): - """Scales and pads an image tensor of shape img(bs,3,y,x) based on given ratio and grid size gs, optionally - retaining the original shape. - """ - if ratio == 1.0: - return img - h, w = img.shape[2:] - s = (int(h * ratio), int(w * ratio)) # new size - img = F.interpolate(img, size=s, mode="bilinear", align_corners=False) # resize - if not same_shape: # pad/crop img - h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w)) - return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean - - -def make_divisible(x, divisor): - """Returns nearest x divisible by divisor.""" - if isinstance(divisor, torch.Tensor): - divisor = int(divisor.max()) # to int - return math.ceil(x / divisor) * divisor - - -def copy_attr(a, b, include=(), exclude=()): - """Copies attributes from object 'b' to object 'a', with options to include/exclude certain attributes.""" - for k, v in b.__dict__.items(): - if (len(include) and k not in include) or k.startswith("_") or k in exclude: - continue - else: - setattr(a, k, v) - - -def get_latest_opset(): - """Return second-most (for maturity) recently supported ONNX opset by this version of torch.""" - return max(int(k[14:]) for k in vars(torch.onnx) if "symbolic_opset" in k) - 1 # opset - - -def intersect_dicts(da, db, exclude=()): - """Returns a dictionary of intersecting keys with matching shapes, excluding 'exclude' keys, using da values.""" - return {k: v for k, v in da.items() if k in db and all(x not in k for x in exclude) and v.shape == db[k].shape} - - -def is_parallel(model): - """Returns True if model is of type DP or DDP.""" - return isinstance(model, (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)) - - -def de_parallel(model): - """De-parallelize a model: returns single-GPU model if model is of type DP or DDP.""" - return model.module if is_parallel(model) else model - - -def one_cycle(y1=0.0, y2=1.0, steps=100): - """Returns a lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf.""" - return lambda x: max((1 - math.cos(x * math.pi / steps)) / 2, 0) * (y2 - y1) + y1 - - -def init_seeds(seed=0, deterministic=False): - """Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html.""" - random.seed(seed) - np.random.seed(seed) - torch.manual_seed(seed) - torch.cuda.manual_seed(seed) - torch.cuda.manual_seed_all(seed) # for Multi-GPU, exception safe - # torch.backends.cudnn.benchmark = True # AutoBatch problem https://github.com/ultralytics/yolov5/issues/9287 - if deterministic: - if TORCH_2_0: - torch.use_deterministic_algorithms(True, warn_only=True) # warn if deterministic is not possible - torch.backends.cudnn.deterministic = True - os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8" - os.environ["PYTHONHASHSEED"] = str(seed) - else: - LOGGER.warning("WARNING ⚠️ Upgrade to torch>=2.0.0 for deterministic training.") - else: - torch.use_deterministic_algorithms(False) - torch.backends.cudnn.deterministic = False - - -class ModelEMA: - """Updated Exponential Moving Average (EMA) from https://github.com/rwightman/pytorch-image-models - Keeps a moving average of everything in the model state_dict (parameters and buffers) - For EMA details see https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage - To disable EMA set the `enabled` attribute to `False`. - """ - - def __init__(self, model, decay=0.9999, tau=2000, updates=0): - """Create EMA.""" - self.ema = deepcopy(de_parallel(model)).eval() # FP32 EMA - self.updates = updates # number of EMA updates - self.decay = lambda x: decay * (1 - math.exp(-x / tau)) # decay exponential ramp (to help early epochs) - for p in self.ema.parameters(): - p.requires_grad_(False) - self.enabled = True - - def update(self, model): - """Update EMA parameters.""" - if self.enabled: - self.updates += 1 - d = self.decay(self.updates) - - msd = de_parallel(model).state_dict() # model state_dict - for k, v in self.ema.state_dict().items(): - if v.dtype.is_floating_point: # true for FP16 and FP32 - v *= d - v += (1 - d) * msd[k].detach() - # assert v.dtype == msd[k].dtype == torch.float32, f'{k}: EMA {v.dtype}, model {msd[k].dtype}' - - def update_attr(self, model, include=(), exclude=("process_group", "reducer")): - """Updates attributes and saves stripped model with optimizer removed.""" - if self.enabled: - copy_attr(self.ema, model, include, exclude) - - -def strip_optimizer(f: Union[str, Path] = "best.pt", s: str = "") -> None: - """ - Strip optimizer from 'f' to finalize training, optionally save as 's'. - - Args: - f (str): file path to model to strip the optimizer from. Default is 'best.pt'. - s (str): file path to save the model with stripped optimizer to. If not provided, 'f' will be overwritten. - - Returns: - None - - Example: - ```python - from pathlib import Path - from ultralytics.utils.torch_utils import strip_optimizer - - for f in Path('path/to/weights').rglob('*.pt'): - strip_optimizer(f) - ``` - """ - x = torch.load(f, map_location=torch.device("cpu")) - if "model" not in x: - LOGGER.info(f"Skipping {f}, not a valid Ultralytics model.") - return - - if hasattr(x["model"], "args"): - x["model"].args = dict(x["model"].args) # convert from IterableSimpleNamespace to dict - args = {**DEFAULT_CFG_DICT, **x["train_args"]} if "train_args" in x else None # combine args - if x.get("ema"): - x["model"] = x["ema"] # replace model with ema - for k in "optimizer", "best_fitness", "ema", "updates": # keys - x[k] = None - x["epoch"] = -1 - x["model"].half() # to FP16 - for p in x["model"].parameters(): - p.requires_grad = False - x["train_args"] = {k: v for k, v in args.items() if k in DEFAULT_CFG_KEYS} # strip non-default keys - # x['model'].args = x['train_args'] - torch.save(x, s or f) - mb = os.path.getsize(s or f) / 1e6 # file size - LOGGER.info(f"Optimizer stripped from {f},{f' saved as {s},' if s else ''} {mb:.1f}MB") - - -def profile(input, ops, n=10, device=None): - """ - Ultralytics speed, memory and FLOPs profiler. - - Example: - ```python - from ultralytics.utils.torch_utils import profile - - input = torch.randn(16, 3, 640, 640) - m1 = lambda x: x * torch.sigmoid(x) - m2 = nn.SiLU() - profile(input, [m1, m2], n=100) # profile over 100 iterations - ``` - """ - results = [] - if not isinstance(device, torch.device): - device = select_device(device) - LOGGER.info( - f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}" - f"{'input':>24s}{'output':>24s}" - ) - - for x in input if isinstance(input, list) else [input]: - x = x.to(device) - x.requires_grad = True - for m in ops if isinstance(ops, list) else [ops]: - m = m.to(device) if hasattr(m, "to") else m # device - m = m.half() if hasattr(m, "half") and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m - tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward - try: - flops = thop.profile(m, inputs=[x], verbose=False)[0] / 1e9 * 2 if thop else 0 # GFLOPs - except Exception: - flops = 0 - - try: - for _ in range(n): - t[0] = time_sync() - y = m(x) - t[1] = time_sync() - try: - (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward() - t[2] = time_sync() - except Exception: # no backward method - # print(e) # for debug - t[2] = float("nan") - tf += (t[1] - t[0]) * 1000 / n # ms per op forward - tb += (t[2] - t[1]) * 1000 / n # ms per op backward - mem = torch.cuda.memory_reserved() / 1e9 if torch.cuda.is_available() else 0 # (GB) - s_in, s_out = (tuple(x.shape) if isinstance(x, torch.Tensor) else "list" for x in (x, y)) # shapes - p = sum(x.numel() for x in m.parameters()) if isinstance(m, nn.Module) else 0 # parameters - LOGGER.info(f"{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}") - results.append([p, flops, mem, tf, tb, s_in, s_out]) - except Exception as e: - LOGGER.info(e) - results.append(None) - torch.cuda.empty_cache() - return results - - -class EarlyStopping: - """Early stopping class that stops training when a specified number of epochs have passed without improvement.""" - - def __init__(self, patience=50): - """ - Initialize early stopping object. - - Args: - patience (int, optional): Number of epochs to wait after fitness stops improving before stopping. - """ - self.best_fitness = 0.0 # i.e. mAP - self.best_epoch = 0 - self.patience = patience or float("inf") # epochs to wait after fitness stops improving to stop - self.possible_stop = False # possible stop may occur next epoch - - def __call__(self, epoch, fitness): - """ - Check whether to stop training. - - Args: - epoch (int): Current epoch of training - fitness (float): Fitness value of current epoch - - Returns: - (bool): True if training should stop, False otherwise - """ - if fitness is None: # check if fitness=None (happens when val=False) - return False - - if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training - self.best_epoch = epoch - self.best_fitness = fitness - delta = epoch - self.best_epoch # epochs without improvement - self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch - stop = delta >= self.patience # stop training if patience exceeded - if stop: - LOGGER.info( - f"Stopping training early as no improvement observed in last {self.patience} epochs. " - f"Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n" - f"To update EarlyStopping(patience={self.patience}) pass a new patience value, " - f"i.e. `patience=300` or use `patience=0` to disable EarlyStopping." - ) - return stop diff --git a/ultralytics-main/ultralytics/utils/triton.py b/ultralytics-main/ultralytics/utils/triton.py deleted file mode 100644 index 3f873a6..0000000 --- a/ultralytics-main/ultralytics/utils/triton.py +++ /dev/null @@ -1,92 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -from typing import List -from urllib.parse import urlsplit - -import numpy as np - - -class TritonRemoteModel: - """ - Client for interacting with a remote Triton Inference Server model. - - Attributes: - endpoint (str): The name of the model on the Triton server. - url (str): The URL of the Triton server. - triton_client: The Triton client (either HTTP or gRPC). - InferInput: The input class for the Triton client. - InferRequestedOutput: The output request class for the Triton client. - input_formats (List[str]): The data types of the model inputs. - np_input_formats (List[type]): The numpy data types of the model inputs. - input_names (List[str]): The names of the model inputs. - output_names (List[str]): The names of the model outputs. - """ - - def __init__(self, url: str, endpoint: str = "", scheme: str = ""): - """ - Initialize the TritonRemoteModel. - - Arguments may be provided individually or parsed from a collective 'url' argument of the form - ://// - - Args: - url (str): The URL of the Triton server. - endpoint (str): The name of the model on the Triton server. - scheme (str): The communication scheme ('http' or 'grpc'). - """ - if not endpoint and not scheme: # Parse all args from URL string - splits = urlsplit(url) - endpoint = splits.path.strip("/").split("/")[0] - scheme = splits.scheme - url = splits.netloc - - self.endpoint = endpoint - self.url = url - - # Choose the Triton client based on the communication scheme - if scheme == "http": - import tritonclient.http as client # noqa - - self.triton_client = client.InferenceServerClient(url=self.url, verbose=False, ssl=False) - config = self.triton_client.get_model_config(endpoint) - else: - import tritonclient.grpc as client # noqa - - self.triton_client = client.InferenceServerClient(url=self.url, verbose=False, ssl=False) - config = self.triton_client.get_model_config(endpoint, as_json=True)["config"] - - # Sort output names alphabetically, i.e. 'output0', 'output1', etc. - config["output"] = sorted(config["output"], key=lambda x: x.get("name")) - - # Define model attributes - type_map = {"TYPE_FP32": np.float32, "TYPE_FP16": np.float16, "TYPE_UINT8": np.uint8} - self.InferRequestedOutput = client.InferRequestedOutput - self.InferInput = client.InferInput - self.input_formats = [x["data_type"] for x in config["input"]] - self.np_input_formats = [type_map[x] for x in self.input_formats] - self.input_names = [x["name"] for x in config["input"]] - self.output_names = [x["name"] for x in config["output"]] - - def __call__(self, *inputs: np.ndarray) -> List[np.ndarray]: - """ - Call the model with the given inputs. - - Args: - *inputs (List[np.ndarray]): Input data to the model. - - Returns: - (List[np.ndarray]): Model outputs. - """ - infer_inputs = [] - input_format = inputs[0].dtype - for i, x in enumerate(inputs): - if x.dtype != self.np_input_formats[i]: - x = x.astype(self.np_input_formats[i]) - infer_input = self.InferInput(self.input_names[i], [*x.shape], self.input_formats[i].replace("TYPE_", "")) - infer_input.set_data_from_numpy(x) - infer_inputs.append(infer_input) - - infer_outputs = [self.InferRequestedOutput(output_name) for output_name in self.output_names] - outputs = self.triton_client.infer(model_name=self.endpoint, inputs=infer_inputs, outputs=infer_outputs) - - return [outputs.as_numpy(output_name).astype(input_format) for output_name in self.output_names] diff --git a/ultralytics-main/ultralytics/utils/tuner.py b/ultralytics-main/ultralytics/utils/tuner.py deleted file mode 100644 index 20e3b75..0000000 --- a/ultralytics-main/ultralytics/utils/tuner.py +++ /dev/null @@ -1,146 +0,0 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license - -import subprocess - -from ultralytics.cfg import TASK2DATA, TASK2METRIC, get_save_dir -from ultralytics.utils import DEFAULT_CFG, DEFAULT_CFG_DICT, LOGGER, NUM_THREADS - - -def run_ray_tune( - model, space: dict = None, grace_period: int = 10, gpu_per_trial: int = None, max_samples: int = 10, **train_args -): - """ - Runs hyperparameter tuning using Ray Tune. - - Args: - model (YOLO): Model to run the tuner on. - space (dict, optional): The hyperparameter search space. Defaults to None. - grace_period (int, optional): The grace period in epochs of the ASHA scheduler. Defaults to 10. - gpu_per_trial (int, optional): The number of GPUs to allocate per trial. Defaults to None. - max_samples (int, optional): The maximum number of trials to run. Defaults to 10. - train_args (dict, optional): Additional arguments to pass to the `train()` method. Defaults to {}. - - Returns: - (dict): A dictionary containing the results of the hyperparameter search. - - Example: - ```python - from ultralytics import YOLO - - # Load a YOLOv8n model - model = YOLO('yolov8n.pt') - - # Start tuning hyperparameters for YOLOv8n training on the COCO8 dataset - result_grid = model.tune(data='coco8.yaml', use_ray=True) - ``` - """ - - LOGGER.info("💡 Learn about RayTune at https://docs.ultralytics.com/integrations/ray-tune") - if train_args is None: - train_args = {} - - try: - subprocess.run("pip install ray[tune]".split(), check=True) - - import ray - from ray import tune - from ray.air import RunConfig - from ray.air.integrations.wandb import WandbLoggerCallback - from ray.tune.schedulers import ASHAScheduler - except ImportError: - raise ModuleNotFoundError('Tuning hyperparameters requires Ray Tune. Install with: pip install "ray[tune]"') - - try: - import wandb - - assert hasattr(wandb, "__version__") - except (ImportError, AssertionError): - wandb = False - - default_space = { - # 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']), - "lr0": tune.uniform(1e-5, 1e-1), - "lrf": tune.uniform(0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf) - "momentum": tune.uniform(0.6, 0.98), # SGD momentum/Adam beta1 - "weight_decay": tune.uniform(0.0, 0.001), # optimizer weight decay 5e-4 - "warmup_epochs": tune.uniform(0.0, 5.0), # warmup epochs (fractions ok) - "warmup_momentum": tune.uniform(0.0, 0.95), # warmup initial momentum - "box": tune.uniform(0.02, 0.2), # box loss gain - "cls": tune.uniform(0.2, 4.0), # cls loss gain (scale with pixels) - "hsv_h": tune.uniform(0.0, 0.1), # image HSV-Hue augmentation (fraction) - "hsv_s": tune.uniform(0.0, 0.9), # image HSV-Saturation augmentation (fraction) - "hsv_v": tune.uniform(0.0, 0.9), # image HSV-Value augmentation (fraction) - "degrees": tune.uniform(0.0, 45.0), # image rotation (+/- deg) - "translate": tune.uniform(0.0, 0.9), # image translation (+/- fraction) - "scale": tune.uniform(0.0, 0.9), # image scale (+/- gain) - "shear": tune.uniform(0.0, 10.0), # image shear (+/- deg) - "perspective": tune.uniform(0.0, 0.001), # image perspective (+/- fraction), range 0-0.001 - "flipud": tune.uniform(0.0, 1.0), # image flip up-down (probability) - "fliplr": tune.uniform(0.0, 1.0), # image flip left-right (probability) - "mosaic": tune.uniform(0.0, 1.0), # image mixup (probability) - "mixup": tune.uniform(0.0, 1.0), # image mixup (probability) - "copy_paste": tune.uniform(0.0, 1.0), # segment copy-paste (probability) - } - - # Put the model in ray store - task = model.task - model_in_store = ray.put(model) - - def _tune(config): - """ - Trains the YOLO model with the specified hyperparameters and additional arguments. - - Args: - config (dict): A dictionary of hyperparameters to use for training. - - Returns: - None - """ - model_to_train = ray.get(model_in_store) # get the model from ray store for tuning - model_to_train.reset_callbacks() - config.update(train_args) - results = model_to_train.train(**config) - return results.results_dict - - # Get search space - if not space: - space = default_space - LOGGER.warning("WARNING ⚠️ search space not provided, using default search space.") - - # Get dataset - data = train_args.get("data", TASK2DATA[task]) - space["data"] = data - if "data" not in train_args: - LOGGER.warning(f'WARNING ⚠️ data not provided, using default "data={data}".') - - # Define the trainable function with allocated resources - trainable_with_resources = tune.with_resources(_tune, {"cpu": NUM_THREADS, "gpu": gpu_per_trial or 0}) - - # Define the ASHA scheduler for hyperparameter search - asha_scheduler = ASHAScheduler( - time_attr="epoch", - metric=TASK2METRIC[task], - mode="max", - max_t=train_args.get("epochs") or DEFAULT_CFG_DICT["epochs"] or 100, - grace_period=grace_period, - reduction_factor=3, - ) - - # Define the callbacks for the hyperparameter search - tuner_callbacks = [WandbLoggerCallback(project="YOLOv8-tune")] if wandb else [] - - # Create the Ray Tune hyperparameter search tuner - tune_dir = get_save_dir(DEFAULT_CFG, name="tune").resolve() # must be absolute dir - tune_dir.mkdir(parents=True, exist_ok=True) - tuner = tune.Tuner( - trainable_with_resources, - param_space=space, - tune_config=tune.TuneConfig(scheduler=asha_scheduler, num_samples=max_samples), - run_config=RunConfig(callbacks=tuner_callbacks, storage_path=tune_dir), - ) - - # Run the hyperparameter search - tuner.fit() - - # Return the results of the hyperparameter search - return tuner.get_results() diff --git a/ultralytics-main/ultralytics/zidane.jpg b/ultralytics-main/ultralytics/zidane.jpg deleted file mode 100644 index 92d72ea..0000000 Binary files a/ultralytics-main/ultralytics/zidane.jpg and /dev/null differ diff --git a/ultralytics-main/yolov8-stereo.py b/ultralytics-main/yolov8-stereo.py deleted file mode 100644 index ffee4b3..0000000 --- a/ultralytics-main/yolov8-stereo.py +++ /dev/null @@ -1,69 +0,0 @@ -import cv2 -import torch -import argparse -from ultralytics import YOLO -from stereo import stereoconfig_040_2 -from stereo.stereo import stereo_40 -from stereo.stereo import stereo_threading, MyThread -from stereo.dianyuntu_yolo import preprocess, undistortion, getRectifyTransform, draw_line, rectifyImage, \ - stereoMatchSGBM - -def main(): - cap = cv2.VideoCapture('ultralytics/assets/a2.mp4') - model = YOLO('yolov8n.pt') - cv2.namedWindow('00', cv2.WINDOW_NORMAL) - cv2.resizeWindow('00', 1280, 360) # 设置宽高 - out_video = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc(*'XVID'), 30, (2560, 720)) - while True: - ret, im0 = cap.read() - if not ret: - print("Video frame is empty or video processing has been successfully completed.") - break - # img = cv2.cvtColor(image_net, cv2.COLOR_BGRA2BGR) - im0 = cv2.resize(im0, (2560, 720)) - config = stereoconfig_040_2.stereoCamera() - map1x, map1y, map2x, map2y, Q = getRectifyTransform(720, 1280, config) - thread = MyThread(stereo_threading, args=(config, im0, map1x, map1y, map2x, map2y, Q)) - thread.start() - results = model.track(im0, save=False, conf=0.5) - annotated_frame = results[0].plot() - boxes = results[0].boxes.xywh.cpu() - for i, box in enumerate(boxes): - # for box, class_idx in zip(boxes, classes): - x_center, y_center, width, height = box.tolist() - x1 = x_center - width / 2 - y1 = y_center - height / 2 - x2 = x_center + width / 2 - y2 = y_center + height / 2 - print('x2',x2) - if (0 < x2 < 1280): - thread.join() - points_3d = thread.get_result() - # gol.set_value('points_3d', points_3d) - a = points_3d[int(y_center), int(x_center), 0] / 1000 - b = points_3d[int(y_center), int(x_center), 1] / 1000 - c = points_3d[int(y_center), int(x_center), 2] / 1000 - distance = ((a ** 2 + b ** 2 + c ** 2) ** 0.5) - if (distance != 0): - text_dis_avg = "dis:%0.2fm" % distance - cv2.putText(annotated_frame, text_dis_avg, (int(x2 + 5), int(y1 + 30)), cv2.FONT_ITALIC, 1.2, - (0, 255, 255), 3) - cv2.imshow('00', annotated_frame) - out_video.write(annotated_frame) - key = cv2.waitKey(1) - if key == 'q': - break - out_video.release() - cap.release() - cv2.destroyAllWindows() - -if __name__ == '__main__': - parser = argparse.ArgumentParser() - parser.add_argument('--weights', type=str, default='yolov8n.pt', help='model.pt path(s)') - parser.add_argument('--svo', type=str, default=None, help='optional svo file') - parser.add_argument('--img_size', type=int, default=416, help='inference size (pixels)') - parser.add_argument('--conf_thres', type=float, default=0.4, help='object confidence threshold') - opt = parser.parse_args() - - with torch.no_grad(): - main() \ No newline at end of file diff --git a/yolov5_Monocular_social_ranging/.dockerignore b/yolov5_Monocular_social_ranging/.dockerignore new file mode 100644 index 0000000..af51ccc --- /dev/null +++ b/yolov5_Monocular_social_ranging/.dockerignore @@ -0,0 +1,222 @@ +# Repo-specific DockerIgnore ------------------------------------------------------------------------------------------- +#.git +.cache +.idea +runs +output +coco +storage.googleapis.com + +data/samples/* +**/results*.csv +*.jpg + +# Neural Network weights ----------------------------------------------------------------------------------------------- +**/*.pt +**/*.pth +**/*.onnx +**/*.engine +**/*.mlmodel +**/*.torchscript +**/*.torchscript.pt +**/*.tflite +**/*.h5 +**/*.pb +*_saved_model/ +*_web_model/ +*_openvino_model/ + +# Below Copied From .gitignore ----------------------------------------------------------------------------------------- +# Below Copied From .gitignore ----------------------------------------------------------------------------------------- + + +# GitHub Python GitIgnore ---------------------------------------------------------------------------------------------- +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +env/ +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +*.egg-info/ +wandb/ +.installed.cfg +*.egg + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +.hypothesis/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# pyenv +.python-version + +# celery beat schedule file +celerybeat-schedule + +# SageMath parsed files +*.sage.py + +# dotenv +.env + +# virtualenv +.venv* +venv*/ +ENV*/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ + + +# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore ----------------------------------------------- + +# General +.DS_Store +.AppleDouble +.LSOverride + +# Icon must end with two \r +Icon +Icon? + +# Thumbnails +._* + +# Files that might appear in the root of a volume +.DocumentRevisions-V100 +.fseventsd +.Spotlight-V100 +.TemporaryItems +.Trashes +.VolumeIcon.icns +.com.apple.timemachine.donotpresent + +# Directories potentially created on remote AFP share +.AppleDB +.AppleDesktop +Network Trash Folder +Temporary Items +.apdisk + + +# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore +# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm +# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 + +# User-specific stuff: +.idea/* +.idea/**/workspace.xml +.idea/**/tasks.xml +.idea/dictionaries +.html # Bokeh Plots +.pg # TensorFlow Frozen Graphs +.avi # videos + +# Sensitive or high-churn files: +.idea/**/dataSources/ +.idea/**/dataSources.ids +.idea/**/dataSources.local.xml +.idea/**/sqlDataSources.xml +.idea/**/dynamic.xml +.idea/**/uiDesigner.xml + +# Gradle: +.idea/**/gradle.xml +.idea/**/libraries + +# CMake +cmake-build-debug/ +cmake-build-release/ + +# Mongo Explorer plugin: +.idea/**/mongoSettings.xml + +## File-based project format: +*.iws + +## Plugin-specific files: + +# IntelliJ +out/ + +# mpeltonen/sbt-idea plugin +.idea_modules/ + +# JIRA plugin +atlassian-ide-plugin.xml + +# Cursive Clojure plugin +.idea/replstate.xml + +# Crashlytics plugin (for Android Studio and IntelliJ) +com_crashlytics_export_strings.xml +crashlytics.properties +crashlytics-build.properties +fabric.properties diff --git a/yolov5_Monocular_social_ranging/.gitattributes b/yolov5_Monocular_social_ranging/.gitattributes new file mode 100644 index 0000000..dad4239 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.gitattributes @@ -0,0 +1,2 @@ +# this drop notebooks from GitHub language stats +*.ipynb linguist-vendored diff --git a/yolov5_Monocular_social_ranging/.github/FUNDING.yml b/yolov5_Monocular_social_ranging/.github/FUNDING.yml new file mode 100644 index 0000000..3da386f --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/FUNDING.yml @@ -0,0 +1,5 @@ +# These are supported funding model platforms + +github: glenn-jocher +patreon: ultralytics +open_collective: ultralytics diff --git a/ultralytics-main/.github/ISSUE_TEMPLATE/bug-report.yml b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/bug-report.yml similarity index 54% rename from ultralytics-main/.github/ISSUE_TEMPLATE/bug-report.yml rename to yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/bug-report.yml index 203250b..fcb6413 100644 --- a/ultralytics-main/.github/ISSUE_TEMPLATE/bug-report.yml +++ b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/bug-report.yml @@ -1,38 +1,37 @@ name: 🐛 Bug Report # title: " " -description: Problems with YOLOv8 +description: Problems with YOLOv5 labels: [bug, triage] body: - type: markdown attributes: value: | - Thank you for submitting a YOLOv8 🐛 Bug Report! + Thank you for submitting a YOLOv5 🐛 Bug Report! - type: checkboxes attributes: label: Search before asking description: > - Please search the Ultralytics [Docs](https://docs.ultralytics.com) and [issues](https://github.com/ultralytics/ultralytics/issues) to see if a similar bug report already exists. + Please search the [issues](https://github.com/ultralytics/yolov5/issues) to see if a similar bug report already exists. options: - label: > - I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report. + I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and found no similar bug report. required: true - type: dropdown attributes: - label: YOLOv8 Component + label: YOLOv5 Component description: | - Please select the part of YOLOv8 where you found the bug. + Please select the part of YOLOv5 where you found the bug. multiple: true options: - - "Install" - - "Train" - - "Val" - - "Predict" + - "Training" + - "Validation" + - "Detection" - "Export" + - "PyTorch Hub" - "Multi-GPU" - - "Augmentation" - - "Hyperparameter Tuning" + - "Evolution" - "Integrations" - "Other" validations: @@ -52,19 +51,9 @@ body: label: Environment description: Please specify the software and hardware you used to produce the bug. placeholder: | - Paste output of `yolo checks` or `ultralytics.checks()` command, i.e.: - ``` - Ultralytics YOLOv8.0.181 🚀 Python-3.11.2 torch-2.0.1 CPU (Apple M2) - Setup complete ✅ (8 CPUs, 16.0 GB RAM, 266.5/460.4 GB disk) - - OS macOS-13.5.2 - Environment Jupyter - Python 3.11.2 - Install git - RAM 16.00 GB - CPU Apple M2 - CUDA None - ``` + - YOLO: YOLOv5 🚀 v6.0-67-g60e42e1 torch 1.9.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB) + - OS: Ubuntu 20.04 + - Python: 3.9.0 validations: required: false @@ -73,7 +62,7 @@ body: label: Minimal Reproducible Example description: > When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to **reproduce** the problem. - This is referred to by community members as creating a [minimal reproducible example](https://docs.ultralytics.com/help/minimum_reproducible_example/). + This is referred to by community members as creating a [minimal reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). placeholder: | ``` # Code to reproduce your issue here @@ -90,7 +79,7 @@ body: attributes: label: Are you willing to submit a PR? description: > - (Optional) We encourage you to submit a [Pull Request](https://github.com/ultralytics/ultralytics/pulls) (PR) to help improve YOLOv8 for everyone, especially if you have a good understanding of how to implement a fix or feature. - See the YOLOv8 [Contributing Guide](https://docs.ultralytics.com/help/contributing) to get started. + (Optional) We encourage you to submit a [Pull Request](https://github.com/ultralytics/yolov5/pulls) (PR) to help improve YOLOv5 for everyone, especially if you have a good understanding of how to implement a fix or feature. + See the YOLOv5 [Contributing Guide](https://github.com/ultralytics/yolov5/blob/master/CONTRIBUTING.md) to get started. options: - label: Yes I'd like to help by submitting a PR! diff --git a/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/config.yml b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/config.yml new file mode 100644 index 0000000..f388d7b --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/config.yml @@ -0,0 +1,8 @@ +blank_issues_enabled: true +contact_links: + - name: Slack + url: https://join.slack.com/t/ultralytics/shared_invite/zt-w29ei8bp-jczz7QYUmDtgo6r6KcMIAg + about: Ask on Ultralytics Slack Forum + - name: Stack Overflow + url: https://stackoverflow.com/search?q=YOLOv5 + about: Ask on Stack Overflow with 'YOLOv5' tag diff --git a/ultralytics-main/.github/ISSUE_TEMPLATE/feature-request.yml b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/feature-request.yml similarity index 58% rename from ultralytics-main/.github/ISSUE_TEMPLATE/feature-request.yml rename to yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/feature-request.yml index 76fc7b1..68ef985 100644 --- a/ultralytics-main/.github/ISSUE_TEMPLATE/feature-request.yml +++ b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/feature-request.yml @@ -1,21 +1,21 @@ name: 🚀 Feature Request -description: Suggest a YOLOv8 idea +description: Suggest a YOLOv5 idea # title: " " labels: [enhancement] body: - type: markdown attributes: value: | - Thank you for submitting a YOLOv8 🚀 Feature Request! + Thank you for submitting a YOLOv5 🚀 Feature Request! - type: checkboxes attributes: label: Search before asking description: > - Please search the Ultralytics [Docs](https://docs.ultralytics.com) and [issues](https://github.com/ultralytics/ultralytics/issues) to see if a similar feature request already exists. + Please search the [issues](https://github.com/ultralytics/yolov5/issues) to see if a similar feature request already exists. options: - label: > - I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests. + I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and found no similar feature requests. required: true - type: textarea @@ -23,7 +23,7 @@ body: label: Description description: A short description of your feature. placeholder: | - What new feature would you like to see in YOLOv8? + What new feature would you like to see in YOLOv5? validations: required: true @@ -44,7 +44,7 @@ body: attributes: label: Are you willing to submit a PR? description: > - (Optional) We encourage you to submit a [Pull Request](https://github.com/ultralytics/ultralytics/pulls) (PR) to help improve YOLOv8 for everyone, especially if you have a good understanding of how to implement a fix or feature. - See the YOLOv8 [Contributing Guide](https://docs.ultralytics.com/help/contributing) to get started. + (Optional) We encourage you to submit a [Pull Request](https://github.com/ultralytics/yolov5/pulls) (PR) to help improve YOLOv5 for everyone, especially if you have a good understanding of how to implement a fix or feature. + See the YOLOv5 [Contributing Guide](https://github.com/ultralytics/yolov5/blob/master/CONTRIBUTING.md) to get started. options: - label: Yes I'd like to help by submitting a PR! diff --git a/ultralytics-main/.github/ISSUE_TEMPLATE/question.yml b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/question.yml similarity index 55% rename from ultralytics-main/.github/ISSUE_TEMPLATE/question.yml rename to yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/question.yml index 090bc5d..8e0993c 100644 --- a/ultralytics-main/.github/ISSUE_TEMPLATE/question.yml +++ b/yolov5_Monocular_social_ranging/.github/ISSUE_TEMPLATE/question.yml @@ -1,21 +1,21 @@ name: ❓ Question -description: Ask a YOLOv8 question +description: Ask a YOLOv5 question # title: " " labels: [question] body: - type: markdown attributes: value: | - Thank you for asking a YOLOv8 ❓ Question! + Thank you for asking a YOLOv5 ❓ Question! - type: checkboxes attributes: label: Search before asking description: > - Please search the Ultralytics [Docs](https://docs.ultralytics.com), [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) to see if a similar question already exists. + Please search the [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) to see if a similar question already exists. options: - label: > - I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. + I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. required: true - type: textarea diff --git a/yolov5_Monocular_social_ranging/.github/PULL_REQUEST_TEMPLATE.md b/yolov5_Monocular_social_ranging/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..7a3e1b7 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,7 @@ +Thank you for submitting a YOLOv5 🚀 Pull Request! We want to make contributing to YOLOv5 as easy and transparent as possible. A few tips to get you started: + +- Search existing YOLOv5 [PRs](https://github.com/ultralytics/yolov5/pull) to see if a similar PR already exists. +- Link this PR to a YOLOv5 [issue](https://github.com/ultralytics/yolov5/issues) to help us understand what bug fix or feature is being implemented. +- Provide before and after profiling/inference/training results to help us quantify the improvement your PR provides (if applicable). + +Please see our ✅ [Contributing Guide](https://github.com/ultralytics/yolov5/blob/master/CONTRIBUTING.md) for more details. diff --git a/ultralytics-main/.github/dependabot.yml b/yolov5_Monocular_social_ranging/.github/dependabot.yml similarity index 65% rename from ultralytics-main/.github/dependabot.yml rename to yolov5_Monocular_social_ranging/.github/dependabot.yml index 2d4ae31..c1b3d5d 100644 --- a/ultralytics-main/.github/dependabot.yml +++ b/yolov5_Monocular_social_ranging/.github/dependabot.yml @@ -1,7 +1,3 @@ -# Ultralytics YOLO 🚀, AGPL-3.0 license -# Dependabot for package version updates -# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates - version: 2 updates: - package-ecosystem: pip @@ -16,7 +12,7 @@ updates: - dependencies - package-ecosystem: github-actions - directory: "/.github/workflows" + directory: "/" schedule: interval: weekly time: "04:00" diff --git a/yolov5_Monocular_social_ranging/.github/workflows/ci-testing.yml b/yolov5_Monocular_social_ranging/.github/workflows/ci-testing.yml new file mode 100644 index 0000000..5cf1613 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/workflows/ci-testing.yml @@ -0,0 +1,93 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +name: CI CPU testing + +on: # https://help.github.com/en/actions/reference/events-that-trigger-workflows + push: + branches: [ master ] + pull_request: + # The branches below must be a subset of the branches above + branches: [ master ] + schedule: + - cron: '0 0 * * *' # Runs at 00:00 UTC every day + +jobs: + cpu-tests: + + runs-on: ${{ matrix.os }} + strategy: + fail-fast: false + matrix: + os: [ ubuntu-latest, macos-latest, windows-latest ] + python-version: [ 3.9 ] + model: [ 'yolov5n' ] # models to test + + # Timeout: https://stackoverflow.com/a/59076067/4521646 + timeout-minutes: 60 + steps: + - uses: actions/checkout@v2 + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ matrix.python-version }} + + # Note: This uses an internal pip API and may not always work + # https://github.com/actions/cache/blob/master/examples.md#multiple-oss-in-a-workflow + - name: Get pip cache + id: pip-cache + run: | + python -c "from pip._internal.locations import USER_CACHE_DIR; print('::set-output name=dir::' + USER_CACHE_DIR)" + + - name: Cache pip + uses: actions/cache@v2.1.7 + with: + path: ${{ steps.pip-cache.outputs.dir }} + key: ${{ runner.os }}-${{ matrix.python-version }}-pip-${{ hashFiles('requirements.txt') }} + restore-keys: | + ${{ runner.os }}-${{ matrix.python-version }}-pip- + + # Known Keras 2.7.0 issue: https://github.com/ultralytics/yolov5/pull/5486 + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install -qr requirements.txt -f https://download.pytorch.org/whl/cpu/torch_stable.html + pip install -q onnx tensorflow-cpu keras==2.6.0 # wandb # extras + python --version + pip --version + pip list + shell: bash + + # - name: W&B login + # run: wandb login 345011b3fb26dc8337fd9b20e53857c1d403f2aa + + # - name: Download data + # run: | + # curl -L -o tmp.zip https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip + # unzip -q tmp.zip -d ../datasets + + - name: Tests workflow + run: | + # export PYTHONPATH="$PWD" # to run '$ python *.py' files in subdirectories + d=cpu # device + weights=runs/train/exp/weights/best.pt + + # Train + python train.py --img 64 --batch 32 --weights ${{ matrix.model }}.pt --cfg ${{ matrix.model }}.yaml --epochs 1 --device $d + # Val + python val.py --img 64 --batch 32 --weights ${{ matrix.model }}.pt --device $d + python val.py --img 64 --batch 32 --weights $weights --device $d + # Detect + python detect.py --weights ${{ matrix.model }}.pt --device $d + python detect.py --weights $weights --device $d + python hubconf.py # hub + # Export + python models/yolo.py --cfg ${{ matrix.model }}.yaml # build PyTorch model + python models/tf.py --weights ${{ matrix.model }}.pt # build TensorFlow model + python export.py --weights ${{ matrix.model }}.pt --img 64 --include torchscript onnx # export + # Python + python - <=3.7.0**](https://www.python.org/) with all [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) installed including [**PyTorch>=1.7**](https://pytorch.org/get-started/locally/). To get started: + ```bash + git clone https://github.com/ultralytics/yolov5 # clone + cd yolov5 + pip install -r requirements.txt # install + ``` + + ## Environments + + YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): + + - **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle + - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) + - **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) + - **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls + + + ## Status + + CI CPU testing + + If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit. diff --git a/yolov5_Monocular_social_ranging/.github/workflows/rebase.yml b/yolov5_Monocular_social_ranging/.github/workflows/rebase.yml new file mode 100644 index 0000000..a4db1ef --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/workflows/rebase.yml @@ -0,0 +1,21 @@ +# https://github.com/marketplace/actions/automatic-rebase + +name: Automatic Rebase +on: + issue_comment: + types: [created] +jobs: + rebase: + name: Rebase + if: github.event.issue.pull_request != '' && contains(github.event.comment.body, '/rebase') + runs-on: ubuntu-latest + steps: + - name: Checkout the latest code + uses: actions/checkout@v2 + with: + token: ${{ secrets.ACTIONS_TOKEN }} + fetch-depth: 0 # otherwise, you will fail to push refs to dest repo + - name: Automatic Rebase + uses: cirrus-actions/rebase@1.5 + env: + GITHUB_TOKEN: ${{ secrets.ACTIONS_TOKEN }} diff --git a/yolov5_Monocular_social_ranging/.github/workflows/stale.yml b/yolov5_Monocular_social_ranging/.github/workflows/stale.yml new file mode 100644 index 0000000..7a83950 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.github/workflows/stale.yml @@ -0,0 +1,38 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +name: Close stale issues +on: + schedule: + - cron: '0 0 * * *' # Runs at 00:00 UTC every day + +jobs: + stale: + runs-on: ubuntu-latest + steps: + - uses: actions/stale@v4 + with: + repo-token: ${{ secrets.GITHUB_TOKEN }} + stale-issue-message: | + 👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs. + + Access additional [YOLOv5](https://ultralytics.com/yolov5) 🚀 resources: + - **Wiki** – https://github.com/ultralytics/yolov5/wiki + - **Tutorials** – https://github.com/ultralytics/yolov5#tutorials + - **Docs** – https://docs.ultralytics.com + + Access additional [Ultralytics](https://ultralytics.com) ⚡ resources: + - **Ultralytics HUB** – https://ultralytics.com/hub + - **Vision API** – https://ultralytics.com/yolov5 + - **About Us** – https://ultralytics.com/about + - **Join Our Team** – https://ultralytics.com/work + - **Contact Us** – https://ultralytics.com/contact + + Feel free to inform us of any other **issues** you discover or **feature requests** that come to mind in the future. Pull Requests (PRs) are also always welcomed! + + Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐! + + stale-pr-message: 'This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions YOLOv5 🚀 and Vision AI ⭐.' + days-before-stale: 30 + days-before-close: 5 + exempt-issue-labels: 'documentation,tutorial,TODO' + operations-per-run: 100 # The maximum number of operations per run, used to control rate limiting. diff --git a/yolov5_Monocular_social_ranging/.gitignore b/yolov5_Monocular_social_ranging/.gitignore new file mode 100644 index 0000000..69a0084 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.gitignore @@ -0,0 +1,256 @@ +# Repo-specific GitIgnore ---------------------------------------------------------------------------------------------- +*.jpg +*.jpeg +*.png +*.bmp +*.tif +*.tiff +*.heic +*.JPG +*.JPEG +*.PNG +*.BMP +*.TIF +*.TIFF +*.HEIC +*.mp4 +*.mov +*.MOV +*.avi +*.data +*.json +*.cfg +!setup.cfg +!cfg/yolov3*.cfg + +storage.googleapis.com +runs/* +data/* +data/images/* +!data/*.yaml +!data/hyps +!data/scripts +!data/images +!data/images/zidane.jpg +!data/images/bus.jpg +!data/*.sh + +results*.csv + +# Datasets ------------------------------------------------------------------------------------------------------------- +coco/ +coco128/ +VOC/ + +# MATLAB GitIgnore ----------------------------------------------------------------------------------------------------- +*.m~ +*.mat +!targets*.mat + +# Neural Network weights ----------------------------------------------------------------------------------------------- +*.weights +*.pt +*.pb +*.onnx +*.engine +*.mlmodel +*.torchscript +*.tflite +*.h5 +*_saved_model/ +*_web_model/ +*_openvino_model/ +darknet53.conv.74 +yolov3-tiny.conv.15 + +# GitHub Python GitIgnore ---------------------------------------------------------------------------------------------- +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +env/ +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +*.egg-info/ +/wandb/ +.installed.cfg +*.egg + + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +.hypothesis/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# pyenv +.python-version + +# celery beat schedule file +celerybeat-schedule + +# SageMath parsed files +*.sage.py + +# dotenv +.env + +# virtualenv +.venv* +venv*/ +ENV*/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ + + +# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore ----------------------------------------------- + +# General +.DS_Store +.AppleDouble +.LSOverride + +# Icon must end with two \r +Icon +Icon? + +# Thumbnails +._* + +# Files that might appear in the root of a volume +.DocumentRevisions-V100 +.fseventsd +.Spotlight-V100 +.TemporaryItems +.Trashes +.VolumeIcon.icns +.com.apple.timemachine.donotpresent + +# Directories potentially created on remote AFP share +.AppleDB +.AppleDesktop +Network Trash Folder +Temporary Items +.apdisk + + +# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore +# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm +# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 + +# User-specific stuff: +.idea/* +.idea/**/workspace.xml +.idea/**/tasks.xml +.idea/dictionaries +.html # Bokeh Plots +.pg # TensorFlow Frozen Graphs +.avi # videos + +# Sensitive or high-churn files: +.idea/**/dataSources/ +.idea/**/dataSources.ids +.idea/**/dataSources.local.xml +.idea/**/sqlDataSources.xml +.idea/**/dynamic.xml +.idea/**/uiDesigner.xml + +# Gradle: +.idea/**/gradle.xml +.idea/**/libraries + +# CMake +cmake-build-debug/ +cmake-build-release/ + +# Mongo Explorer plugin: +.idea/**/mongoSettings.xml + +## File-based project format: +*.iws + +## Plugin-specific files: + +# IntelliJ +out/ + +# mpeltonen/sbt-idea plugin +.idea_modules/ + +# JIRA plugin +atlassian-ide-plugin.xml + +# Cursive Clojure plugin +.idea/replstate.xml + +# Crashlytics plugin (for Android Studio and IntelliJ) +com_crashlytics_export_strings.xml +crashlytics.properties +crashlytics-build.properties +fabric.properties diff --git a/yolov5_Monocular_social_ranging/.pre-commit-config.yaml b/yolov5_Monocular_social_ranging/.pre-commit-config.yaml new file mode 100644 index 0000000..526a560 --- /dev/null +++ b/yolov5_Monocular_social_ranging/.pre-commit-config.yaml @@ -0,0 +1,66 @@ +# Define hooks for code formations +# Will be applied on any updated commit files if a user has installed and linked commit hook + +default_language_version: + python: python3.8 + +# Define bot property if installed via https://github.com/marketplace/pre-commit-ci +ci: + autofix_prs: true + autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions' + autoupdate_schedule: quarterly + # submodules: true + +repos: + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v4.1.0 + hooks: + - id: end-of-file-fixer + - id: trailing-whitespace + - id: check-case-conflict + - id: check-yaml + - id: check-toml + - id: pretty-format-json + - id: check-docstring-first + + - repo: https://github.com/asottile/pyupgrade + rev: v2.31.0 + hooks: + - id: pyupgrade + args: [--py36-plus] + name: Upgrade code + + - repo: https://github.com/PyCQA/isort + rev: 5.10.1 + hooks: + - id: isort + name: Sort imports + + # TODO + #- repo: https://github.com/pre-commit/mirrors-yapf + # rev: v0.31.0 + # hooks: + # - id: yapf + # name: formatting + + # TODO + #- repo: https://github.com/executablebooks/mdformat + # rev: 0.7.7 + # hooks: + # - id: mdformat + # additional_dependencies: + # - mdformat-gfm + # - mdformat-black + # - mdformat_frontmatter + + # TODO + #- repo: https://github.com/asottile/yesqa + # rev: v1.2.3 + # hooks: + # - id: yesqa + + - repo: https://github.com/PyCQA/flake8 + rev: 4.0.1 + hooks: + - id: flake8 + name: PEP8 diff --git a/ultralytics-main/ultralytics/solutions/d_speed.py b/yolov5_Monocular_social_ranging/0.8.1' similarity index 100% rename from ultralytics-main/ultralytics/solutions/d_speed.py rename to yolov5_Monocular_social_ranging/0.8.1' diff --git a/yolov5_Monocular_social_ranging/CONTRIBUTING.md b/yolov5_Monocular_social_ranging/CONTRIBUTING.md new file mode 100644 index 0000000..ebde03a --- /dev/null +++ b/yolov5_Monocular_social_ranging/CONTRIBUTING.md @@ -0,0 +1,94 @@ +## Contributing to YOLOv5 🚀 + +We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible, whether it's: + +- Reporting a bug +- Discussing the current state of the code +- Submitting a fix +- Proposing a new feature +- Becoming a maintainer + +YOLOv5 works so well due to our combined community effort, and for every small improvement you contribute you will be +helping push the frontiers of what's possible in AI 😃! + +## Submitting a Pull Request (PR) 🛠️ + +Submitting a PR is easy! This example shows how to submit a PR for updating `requirements.txt` in 4 steps: + +### 1. Select File to Update + +Select `requirements.txt` to update by clicking on it in GitHub. +

PR_step1

+ +### 2. Click 'Edit this file' + +Button is in top-right corner. +

PR_step2

+ +### 3. Make Changes + +Change `matplotlib` version from `3.2.2` to `3.3`. +

PR_step3

+ +### 4. Preview Changes and Submit PR + +Click on the **Preview changes** tab to verify your updates. At the bottom of the screen select 'Create a **new branch** +for this commit', assign your branch a descriptive name such as `fix/matplotlib_version` and click the green **Propose +changes** button. All done, your PR is now submitted to YOLOv5 for review and approval 😃! +

PR_step4

+ +### PR recommendations + +To allow your work to be integrated as seamlessly as possible, we advise you to: + +- ✅ Verify your PR is **up-to-date with upstream/master.** If your PR is behind upstream/master an + automatic [GitHub Actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) merge may + be attempted by writing /rebase in a new comment, or by running the following code, replacing 'feature' with the name + of your local branch: + +```bash +git remote add upstream https://github.com/ultralytics/yolov5.git +git fetch upstream +# git checkout feature # <--- replace 'feature' with local branch name +git merge upstream/master +git push -u origin -f +``` + +- ✅ Verify all Continuous Integration (CI) **checks are passing**. +- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase + but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ — Bruce Lee + +## Submitting a Bug Report 🐛 + +If you spot a problem with YOLOv5 please submit a Bug Report! + +For us to start investigating a possible problem we need to be able to reproduce it ourselves first. We've created a few +short guidelines below to help users provide what we need in order to get started. + +When asking a question, people will be better able to provide help if you provide **code** that they can easily +understand and use to **reproduce** the problem. This is referred to by community members as creating +a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). Your code that reproduces +the problem should be: + +* ✅ **Minimal** – Use as little code as possible that still produces the same problem +* ✅ **Complete** – Provide **all** parts someone else needs to reproduce your problem in the question itself +* ✅ **Reproducible** – Test the code you're about to provide to make sure it reproduces the problem + +In addition to the above requirements, for [Ultralytics](https://ultralytics.com/) to provide assistance your code +should be: + +* ✅ **Current** – Verify that your code is up-to-date with current + GitHub [master](https://github.com/ultralytics/yolov5/tree/master), and if necessary `git pull` or `git clone` a new + copy to ensure your problem has not already been resolved by previous commits. +* ✅ **Unmodified** – Your problem must be reproducible without any modifications to the codebase in this + repository. [Ultralytics](https://ultralytics.com/) does not provide support for custom code ⚠️. + +If you believe your problem meets all of the above criteria, please close this issue and raise a new one using the 🐛 ** +Bug Report** [template](https://github.com/ultralytics/yolov5/issues/new/choose) and providing +a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example) to help us better +understand and diagnose your problem. + +## License + +By contributing, you agree that your contributions will be licensed under +the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/) diff --git a/yolov5_Monocular_social_ranging/Dockerfile b/yolov5_Monocular_social_ranging/Dockerfile new file mode 100644 index 0000000..489dd04 --- /dev/null +++ b/yolov5_Monocular_social_ranging/Dockerfile @@ -0,0 +1,64 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch +FROM nvcr.io/nvidia/pytorch:21.10-py3 + +# Install linux packages +RUN apt update && apt install -y zip htop screen libgl1-mesa-glx + +# Install python dependencies +COPY requirements.txt . +RUN python -m pip install --upgrade pip +RUN pip uninstall -y torch torchvision torchtext +RUN pip install --no-cache -r requirements.txt albumentations wandb gsutil notebook \ + torch==1.10.2+cu113 torchvision==0.11.3+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html +# RUN pip install --no-cache -U torch torchvision + +# Create working directory +RUN mkdir -p /usr/src/app +WORKDIR /usr/src/app + +# Copy contents +COPY . /usr/src/app + +# Downloads to user config dir +ADD https://ultralytics.com/assets/Arial.ttf /root/.config/Ultralytics/ + +# Set environment variables +# ENV HOME=/usr/src/app + + +# Usage Examples ------------------------------------------------------------------------------------------------------- + +# Build and Push +# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t + +# Pull and Run +# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t + +# Pull and Run with local directory access +# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t + +# Kill all +# sudo docker kill $(sudo docker ps -q) + +# Kill all image-based +# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest) + +# Bash into running container +# sudo docker exec -it 5a9b5863d93d bash + +# Bash into stopped container +# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash + +# Clean up +# docker system prune -a --volumes + +# Update Ubuntu drivers +# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/ + +# DDP test +# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3 + +# GCP VM from Image +# docker.io/ultralytics/yolov5:latest diff --git a/ultralytics-main/LICENSE b/yolov5_Monocular_social_ranging/LICENSE similarity index 86% rename from ultralytics-main/LICENSE rename to yolov5_Monocular_social_ranging/LICENSE index be3f7b2..92b370f 100644 --- a/ultralytics-main/LICENSE +++ b/yolov5_Monocular_social_ranging/LICENSE @@ -1,21 +1,23 @@ - GNU AFFERO GENERAL PUBLIC LICENSE - Version 3, 19 November 2007 +GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 - Copyright (C) 2007 Free Software Foundation, Inc. + Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble - The GNU Affero General Public License is a free, copyleft license for -software and other kinds of works, specifically designed to ensure -cooperation with the community in the case of network server software. + The GNU General Public License is a free, copyleft license for +software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, -our General Public Licenses are intended to guarantee your freedom to +the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free -software for all its users. +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you @@ -24,34 +26,44 @@ them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things. - Developers that use our General Public Licenses protect your rights -with two steps: (1) assert copyright on the software, and (2) offer -you this License which gives you legal permission to copy, distribute -and/or modify the software. - - A secondary benefit of defending all users' freedom is that -improvements made in alternate versions of the program, if they -receive widespread use, become available for other developers to -incorporate. Many developers of free software are heartened and -encouraged by the resulting cooperation. However, in the case of -software used on network servers, this result may fail to come about. -The GNU General Public License permits making a modified version and -letting the public access it on a server without ever releasing its -source code to the public. - - The GNU Affero General Public License is designed specifically to -ensure that, in such cases, the modified source code becomes available -to the community. It requires the operator of a network server to -provide the source code of the modified version running there to the -users of that server. Therefore, public use of a modified version, on -a publicly accessible server, gives the public access to the source -code of the modified version. - - An older license, called the Affero General Public License and -published by Affero, was designed to accomplish similar goals. This is -a different license, not a version of the Affero GPL, but Affero has -released a new version of the Affero GPL which permits relicensing under -this license. + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. @@ -60,7 +72,7 @@ modification follow. 0. Definitions. - "This License" refers to version 3 of the GNU Affero General Public License. + "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. @@ -537,45 +549,35 @@ to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. - 13. Remote Network Interaction; Use with the GNU General Public License. - - Notwithstanding any other provision of this License, if you modify the -Program, your modified version must prominently offer all users -interacting with it remotely through a computer network (if your version -supports such interaction) an opportunity to receive the Corresponding -Source of your version by providing access to the Corresponding Source -from a network server at no charge, through some standard or customary -means of facilitating copying of software. This Corresponding Source -shall include the Corresponding Source for any work covered by version 3 -of the GNU General Public License that is incorporated pursuant to the -following paragraph. + 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed -under version 3 of the GNU General Public License into a single +under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, -but the work with which it is combined will remain governed by version -3 of the GNU General Public License. +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of -the GNU Affero General Public License from time to time. Such new versions -will be similar in spirit to the present version, but may differ in detail to +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the -Program specifies that a certain numbered version of the GNU Affero General +Program specifies that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the -GNU Affero General Public License, you may choose any version ever published +GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future -versions of the GNU Affero General Public License can be used, that proxy's +versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. @@ -633,29 +635,40 @@ the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software: you can redistribute it and/or modify - it under the terms of the GNU Affero General Public License as published by + it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU Affero General Public License for more details. + GNU General Public License for more details. - You should have received a copy of the GNU Affero General Public License - along with this program. If not, see . + You should have received a copy of the GNU General Public License + along with this program. If not, see . Also add information on how to contact you by electronic and paper mail. - If your software can interact with users remotely through a computer -network, you should also make sure that it provides a way for users to -get its source. For example, if your program is a web application, its -interface could display a "Source" link that leads users to an archive -of the code. There are many ways you could offer source, and different -solutions will be better for different programs; see section 13 for the -specific requirements. + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. -For more information on this, and how to apply and follow the GNU AGPL, see -. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/yolov5_Monocular_social_ranging/README.md b/yolov5_Monocular_social_ranging/README.md new file mode 100644 index 0000000..b03a7c5 --- /dev/null +++ b/yolov5_Monocular_social_ranging/README.md @@ -0,0 +1,304 @@ +
+

+ + +

+
+
+ CI CPU testing + YOLOv5 Citation + Docker Pulls +
+ Open In Colab + Open In Kaggle + Join Forum +
+ +
+

+YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics + open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development. +

+ + + + + +
+ +##
Documentation
+ +See the [YOLOv5 Docs](https://docs.ultralytics.com) for full documentation on training, testing and deployment. + +##
Quick Start Examples
+ +
+Install + +Clone repo and install [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) in a +[**Python>=3.7.0**](https://www.python.org/) environment, including +[**PyTorch>=1.7**](https://pytorch.org/get-started/locally/). + +```bash +git clone https://github.com/ultralytics/yolov5 # clone +cd yolov5 +pip install -r requirements.txt # install +``` + +
+ +
+Inference + +Inference with YOLOv5 and [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36) +. [Models](https://github.com/ultralytics/yolov5/tree/master/models) download automatically from the latest +YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). + +```python +import torch + +# Model +model = torch.hub.load('ultralytics/yolov5', 'yolov5s') # or yolov5m, yolov5l, yolov5x, custom + +# Images +img = 'https://ultralytics.com/images/zidane.jpg' # or file, Path, PIL, OpenCV, numpy, list + +# Inference +results = model(img) + +# Results +results.print() # or .show(), .save(), .crop(), .pandas(), etc. +``` + +
+ + + +
+Inference with detect.py + +`detect.py` runs inference on a variety of sources, downloading [models](https://github.com/ultralytics/yolov5/tree/master/models) automatically from +the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`. + +```bash +python detect.py --source 0 # webcam + img.jpg # image + vid.mp4 # video + path/ # directory + path/*.jpg # glob + 'https://youtu.be/Zgi9g1ksQHc' # YouTube + 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream +``` + +
+ +
+Training + +The commands below reproduce YOLOv5 [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) +results. [Models](https://github.com/ultralytics/yolov5/tree/master/models) +and [datasets](https://github.com/ultralytics/yolov5/tree/master/data) download automatically from the latest +YOLOv5 [release](https://github.com/ultralytics/yolov5/releases). Training times for YOLOv5n/s/m/l/x are +1/2/4/6/8 days on a V100 GPU ([Multi-GPU](https://github.com/ultralytics/yolov5/issues/475) times faster). Use the +largest `--batch-size` possible, or pass `--batch-size -1` for +YOLOv5 [AutoBatch](https://github.com/ultralytics/yolov5/pull/5092). Batch sizes shown for V100-16GB. + +```bash +python train.py --data coco.yaml --cfg yolov5n.yaml --weights '' --batch-size 128 + yolov5s 64 + yolov5m 40 + yolov5l 24 + yolov5x 16 +``` + + + +
+ +
+Tutorials + +* [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)  🚀 RECOMMENDED +* [Tips for Best Training Results](https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results)  ☘️ + RECOMMENDED +* [Weights & Biases Logging](https://github.com/ultralytics/yolov5/issues/1289)  🌟 NEW +* [Roboflow for Datasets, Labeling, and Active Learning](https://github.com/ultralytics/yolov5/issues/4975)  🌟 NEW +* [Multi-GPU Training](https://github.com/ultralytics/yolov5/issues/475) +* [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36)  ⭐ NEW +* [TFLite, ONNX, CoreML, TensorRT Export](https://github.com/ultralytics/yolov5/issues/251) 🚀 +* [Test-Time Augmentation (TTA)](https://github.com/ultralytics/yolov5/issues/303) +* [Model Ensembling](https://github.com/ultralytics/yolov5/issues/318) +* [Model Pruning/Sparsity](https://github.com/ultralytics/yolov5/issues/304) +* [Hyperparameter Evolution](https://github.com/ultralytics/yolov5/issues/607) +* [Transfer Learning with Frozen Layers](https://github.com/ultralytics/yolov5/issues/1314)  ⭐ NEW +* [TensorRT Deployment](https://github.com/wang-xinyu/tensorrtx) + +
+ +##
Environments
+ +Get started in seconds with our verified environments. Click each icon below for details. + + + +##
Integrations
+ + + +|Weights and Biases|Roboflow ⭐ NEW| +|:-:|:-:| +|Automatically track and visualize all your YOLOv5 training runs in the cloud with [Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_readme)|Label and export your custom datasets directly to YOLOv5 for training with [Roboflow](https://roboflow.com/?ref=ultralytics) | + + + + +##
Why YOLOv5
+ +

+
+ YOLOv5-P5 640 Figure (click to expand) + +

+
+
+ Figure Notes (click to expand) + +* **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset over various inference sizes from 256 to 1536. +* **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32. +* **EfficientDet** data from [google/automl](https://github.com/google/automl) at batch size 8. +* **Reproduce** by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt` +
+ +### Pretrained Checkpoints + +[assets]: https://github.com/ultralytics/yolov5/releases + +[TTA]: https://github.com/ultralytics/yolov5/issues/303 + +|Model |size
(pixels) |mAPval
0.5:0.95 |mAPval
0.5 |Speed
CPU b1
(ms) |Speed
V100 b1
(ms) |Speed
V100 b32
(ms) |params
(M) |FLOPs
@640 (B) +|--- |--- |--- |--- |--- |--- |--- |--- |--- +|[YOLOv5n][assets] |640 |28.0 |45.7 |**45** |**6.3**|**0.6**|**1.9**|**4.5** +|[YOLOv5s][assets] |640 |37.4 |56.8 |98 |6.4 |0.9 |7.2 |16.5 +|[YOLOv5m][assets] |640 |45.4 |64.1 |224 |8.2 |1.7 |21.2 |49.0 +|[YOLOv5l][assets] |640 |49.0 |67.3 |430 |10.1 |2.7 |46.5 |109.1 +|[YOLOv5x][assets] |640 |50.7 |68.9 |766 |12.1 |4.8 |86.7 |205.7 +| | | | | | | | | +|[YOLOv5n6][assets] |1280 |36.0 |54.4 |153 |8.1 |2.1 |3.2 |4.6 +|[YOLOv5s6][assets] |1280 |44.8 |63.7 |385 |8.2 |3.6 |16.8 |12.6 +|[YOLOv5m6][assets] |1280 |51.3 |69.3 |887 |11.1 |6.8 |35.7 |50.0 +|[YOLOv5l6][assets] |1280 |53.7 |71.3 |1784 |15.8 |10.5 |76.8 |111.4 +|[YOLOv5x6][assets]
+ [TTA][TTA]|1280
1536 |55.0
**55.8** |72.7
**72.7** |3136
- |26.2
- |19.4
- |140.7
- |209.8
- + +
+ Table Notes (click to expand) + +* All checkpoints are trained to 300 epochs with default settings. Nano and Small models use [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) hyps, all others use [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml). +* **mAPval** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.
Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` +* **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) instance. NMS times (~1 ms/img) not included.
Reproduce by `python val.py --data coco.yaml --img 640 --task speed --batch 1` +* **TTA** [Test Time Augmentation](https://github.com/ultralytics/yolov5/issues/303) includes reflection and scale augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment` + +
+ +##
Contribute
+ +We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible. Please see our [Contributing Guide](CONTRIBUTING.md) to get started, and fill out the [YOLOv5 Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) to send us feedback on your experiences. Thank you to all our contributors! + + + +##
Contact
+ +For YOLOv5 bugs and feature requests please visit [GitHub Issues](https://github.com/ultralytics/yolov5/issues). For business inquiries or +professional support requests please visit [https://ultralytics.com/contact](https://ultralytics.com/contact). + +
+ + diff --git a/yolov5_Monocular_social_ranging/data/Argoverse.yaml b/yolov5_Monocular_social_ranging/data/Argoverse.yaml new file mode 100644 index 0000000..312791b --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/Argoverse.yaml @@ -0,0 +1,67 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI +# Example usage: python train.py --data Argoverse.yaml +# parent +# ├── yolov5 +# └── datasets +# └── Argoverse ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/Argoverse # dataset root dir +train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images +val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images +test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview + +# Classes +nc: 8 # number of classes +names: ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'truck', 'traffic_light', 'stop_sign'] # class names + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + import json + + from tqdm import tqdm + from utils.general import download, Path + + + def argoverse2yolo(set): + labels = {} + a = json.load(open(set, "rb")) + for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."): + img_id = annot['image_id'] + img_name = a['images'][img_id]['name'] + img_label_name = img_name[:-3] + "txt" + + cls = annot['category_id'] # instance class id + x_center, y_center, width, height = annot['bbox'] + x_center = (x_center + width / 2) / 1920.0 # offset and scale + y_center = (y_center + height / 2) / 1200.0 # offset and scale + width /= 1920.0 # scale + height /= 1200.0 # scale + + img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']] + if not img_dir.exists(): + img_dir.mkdir(parents=True, exist_ok=True) + + k = str(img_dir / img_label_name) + if k not in labels: + labels[k] = [] + labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n") + + for k in labels: + with open(k, "w") as f: + f.writelines(labels[k]) + + + # Download + dir = Path('../datasets/Argoverse') # dataset root dir + urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip'] + download(urls, dir=dir, delete=False) + + # Convert + annotations_dir = 'Argoverse-HD/annotations/' + (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images' + for d in "train.json", "val.json": + argoverse2yolo(dir / annotations_dir / d) # convert VisDrone annotations to YOLO labels diff --git a/yolov5_Monocular_social_ranging/data/GlobalWheat2020.yaml b/yolov5_Monocular_social_ranging/data/GlobalWheat2020.yaml new file mode 100644 index 0000000..869dace --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/GlobalWheat2020.yaml @@ -0,0 +1,53 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan +# Example usage: python train.py --data GlobalWheat2020.yaml +# parent +# ├── yolov5 +# └── datasets +# └── GlobalWheat2020 ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/GlobalWheat2020 # dataset root dir +train: # train images (relative to 'path') 3422 images + - images/arvalis_1 + - images/arvalis_2 + - images/arvalis_3 + - images/ethz_1 + - images/rres_1 + - images/inrae_1 + - images/usask_1 +val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1) + - images/ethz_1 +test: # test images (optional) 1276 images + - images/utokyo_1 + - images/utokyo_2 + - images/nau_1 + - images/uq_1 + +# Classes +nc: 1 # number of classes +names: ['wheat_head'] # class names + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + from utils.general import download, Path + + # Download + dir = Path(yaml['path']) # dataset root dir + urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip'] + download(urls, dir=dir) + + # Make Directories + for p in 'annotations', 'images', 'labels': + (dir / p).mkdir(parents=True, exist_ok=True) + + # Move + for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \ + 'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1': + (dir / p).rename(dir / 'images' / p) # move to /images + f = (dir / p).with_suffix('.json') # json file + if f.exists(): + f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations diff --git a/yolov5_Monocular_social_ranging/data/Objects365.yaml b/yolov5_Monocular_social_ranging/data/Objects365.yaml new file mode 100644 index 0000000..4c7cf3f --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/Objects365.yaml @@ -0,0 +1,112 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Objects365 dataset https://www.objects365.org/ by Megvii +# Example usage: python train.py --data Objects365.yaml +# parent +# ├── yolov5 +# └── datasets +# └── Objects365 ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/Objects365 # dataset root dir +train: images/train # train images (relative to 'path') 1742289 images +val: images/val # val images (relative to 'path') 80000 images +test: # test images (optional) + +# Classes +nc: 365 # number of classes +names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup', + 'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book', + 'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag', + 'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV', + 'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle', + 'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird', + 'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck', + 'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning', + 'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife', + 'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock', + 'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish', + 'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan', + 'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard', + 'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign', + 'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat', + 'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard', + 'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry', + 'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks', + 'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors', + 'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape', + 'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck', + 'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette', + 'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket', + 'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine', + 'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine', + 'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon', + 'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse', + 'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball', + 'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin', + 'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts', + 'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit', + 'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD', + 'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder', + 'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips', + 'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab', + 'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal', + 'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart', + 'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French', + 'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell', + 'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil', + 'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis'] + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + from pycocotools.coco import COCO + from tqdm import tqdm + + from utils.general import Path, download, np, xyxy2xywhn + + # Make Directories + dir = Path(yaml['path']) # dataset root dir + for p in 'images', 'labels': + (dir / p).mkdir(parents=True, exist_ok=True) + for q in 'train', 'val': + (dir / p / q).mkdir(parents=True, exist_ok=True) + + # Train, Val Splits + for split, patches in [('train', 50 + 1), ('val', 43 + 1)]: + print(f"Processing {split} in {patches} patches ...") + images, labels = dir / 'images' / split, dir / 'labels' / split + + # Download + url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/" + if split == 'train': + download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False) # annotations json + download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8) + elif split == 'val': + download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json + download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8) + download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8) + + # Move + for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'): + f.rename(images / f.name) # move to /images/{split} + + # Labels + coco = COCO(dir / f'zhiyuan_objv2_{split}.json') + names = [x["name"] for x in coco.loadCats(coco.getCatIds())] + for cid, cat in enumerate(names): + catIds = coco.getCatIds(catNms=[cat]) + imgIds = coco.getImgIds(catIds=catIds) + for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'): + width, height = im["width"], im["height"] + path = Path(im["file_name"]) # image filename + try: + with open(labels / path.with_suffix('.txt').name, 'a') as file: + annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None) + for a in coco.loadAnns(annIds): + x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner) + xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4) + x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped + file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n") + except Exception as e: + print(e) diff --git a/yolov5_Monocular_social_ranging/data/SKU-110K.yaml b/yolov5_Monocular_social_ranging/data/SKU-110K.yaml new file mode 100644 index 0000000..9481b7a --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/SKU-110K.yaml @@ -0,0 +1,52 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail +# Example usage: python train.py --data SKU-110K.yaml +# parent +# ├── yolov5 +# └── datasets +# └── SKU-110K ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/SKU-110K # dataset root dir +train: train.txt # train images (relative to 'path') 8219 images +val: val.txt # val images (relative to 'path') 588 images +test: test.txt # test images (optional) 2936 images + +# Classes +nc: 1 # number of classes +names: ['object'] # class names + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + import shutil + from tqdm import tqdm + from utils.general import np, pd, Path, download, xyxy2xywh + + # Download + dir = Path(yaml['path']) # dataset root dir + parent = Path(dir.parent) # download dir + urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz'] + download(urls, dir=parent, delete=False) + + # Rename directories + if dir.exists(): + shutil.rmtree(dir) + (parent / 'SKU110K_fixed').rename(dir) # rename dir + (dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir + + # Convert labels + names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names + for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv': + x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations + images, unique_images = x[:, 0], np.unique(x[:, 0]) + with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f: + f.writelines(f'./images/{s}\n' for s in unique_images) + for im in tqdm(unique_images, desc=f'Converting {dir / d}'): + cls = 0 # single-class dataset + with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f: + for r in x[images == im]: + w, h = r[6], r[7] # image width, height + xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance + f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label diff --git a/yolov5_Monocular_social_ranging/data/VOC.yaml b/yolov5_Monocular_social_ranging/data/VOC.yaml new file mode 100644 index 0000000..975d564 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/VOC.yaml @@ -0,0 +1,80 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford +# Example usage: python train.py --data VOC.yaml +# parent +# ├── yolov5 +# └── datasets +# └── VOC ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/VOC +train: # train images (relative to 'path') 16551 images + - images/train2012 + - images/train2007 + - images/val2012 + - images/val2007 +val: # val images (relative to 'path') 4952 images + - images/test2007 +test: # test images (optional) + - images/test2007 + +# Classes +nc: 20 # number of classes +names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', + 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] # class names + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + import xml.etree.ElementTree as ET + + from tqdm import tqdm + from utils.general import download, Path + + + def convert_label(path, lb_path, year, image_id): + def convert_box(size, box): + dw, dh = 1. / size[0], 1. / size[1] + x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2] + return x * dw, y * dh, w * dw, h * dh + + in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml') + out_file = open(lb_path, 'w') + tree = ET.parse(in_file) + root = tree.getroot() + size = root.find('size') + w = int(size.find('width').text) + h = int(size.find('height').text) + + for obj in root.iter('object'): + cls = obj.find('name').text + if cls in yaml['names'] and not int(obj.find('difficult').text) == 1: + xmlbox = obj.find('bndbox') + bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')]) + cls_id = yaml['names'].index(cls) # class id + out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n') + + + # Download + dir = Path(yaml['path']) # dataset root dir + url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' + urls = [url + 'VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images + url + 'VOCtest_06-Nov-2007.zip', # 438MB, 4953 images + url + 'VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images + download(urls, dir=dir / 'images', delete=False) + + # Convert + path = dir / f'images/VOCdevkit' + for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'): + imgs_path = dir / 'images' / f'{image_set}{year}' + lbs_path = dir / 'labels' / f'{image_set}{year}' + imgs_path.mkdir(exist_ok=True, parents=True) + lbs_path.mkdir(exist_ok=True, parents=True) + + image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split() + for id in tqdm(image_ids, desc=f'{image_set}{year}'): + f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path + lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path + f.rename(imgs_path / f.name) # move image + convert_label(path, lb_path, year, id) # convert labels to YOLO format diff --git a/yolov5_Monocular_social_ranging/data/VisDrone.yaml b/yolov5_Monocular_social_ranging/data/VisDrone.yaml new file mode 100644 index 0000000..83a5c7d --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/VisDrone.yaml @@ -0,0 +1,61 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University +# Example usage: python train.py --data VisDrone.yaml +# parent +# ├── yolov5 +# └── datasets +# └── VisDrone ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/VisDrone # dataset root dir +train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images +val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images +test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images + +# Classes +nc: 10 # number of classes +names: ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor'] + + +# Download script/URL (optional) --------------------------------------------------------------------------------------- +download: | + from utils.general import download, os, Path + + def visdrone2yolo(dir): + from PIL import Image + from tqdm import tqdm + + def convert_box(size, box): + # Convert VisDrone box to YOLO xywh box + dw = 1. / size[0] + dh = 1. / size[1] + return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh + + (dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory + pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}') + for f in pbar: + img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size + lines = [] + with open(f, 'r') as file: # read annotation.txt + for row in [x.split(',') for x in file.read().strip().splitlines()]: + if row[4] == '0': # VisDrone 'ignored regions' class 0 + continue + cls = int(row[5]) - 1 + box = convert_box(img_size, tuple(map(int, row[:4]))) + lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n") + with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl: + fl.writelines(lines) # write label.txt + + + # Download + dir = Path(yaml['path']) # dataset root dir + urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip'] + download(urls, dir=dir) + + # Convert + for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev': + visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels diff --git a/yolov5_Monocular_social_ranging/data/coco.yaml b/yolov5_Monocular_social_ranging/data/coco.yaml new file mode 100644 index 0000000..3ed7e48 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/coco.yaml @@ -0,0 +1,44 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# COCO 2017 dataset http://cocodataset.org by Microsoft +# Example usage: python train.py --data coco.yaml +# parent +# ├── yolov5 +# └── datasets +# └── coco ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/coco # dataset root dir +train: train2017.txt # train images (relative to 'path') 118287 images +val: val2017.txt # val images (relative to 'path') 5000 images +test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 + +# Classes +nc: 80 # number of classes +names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', + 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', + 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', + 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', + 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', + 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', + 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', + 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', + 'hair drier', 'toothbrush'] # class names + + +# Download script/URL (optional) +download: | + from utils.general import download, Path + + # Download labels + segments = False # segment or box labels + dir = Path(yaml['path']) # dataset root dir + url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' + urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels + download(urls, dir=dir.parent) + + # Download data + urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images + 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images + 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional) + download(urls, dir=dir / 'images', threads=3) diff --git a/yolov5_Monocular_social_ranging/data/coco128.yaml b/yolov5_Monocular_social_ranging/data/coco128.yaml new file mode 100644 index 0000000..d07c704 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/coco128.yaml @@ -0,0 +1,30 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics +# Example usage: python train.py --data coco128.yaml +# parent +# ├── yolov5 +# └── datasets +# └── coco128 ← downloads here + + +# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] +path: ../datasets/coco128 # dataset root dir +train: images/train2017 # train images (relative to 'path') 128 images +val: images/train2017 # val images (relative to 'path') 128 images +test: # test images (optional) + +# Classes +nc: 80 # number of classes +names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', + 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', + 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', + 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', + 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', + 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', + 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', + 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', + 'hair drier', 'toothbrush'] # class names + + +# Download script/URL (optional) +download: https://ultralytics.com/assets/coco128.zip diff --git a/yolov5_Monocular_social_ranging/data/hyps/hyp.Objects365.yaml b/yolov5_Monocular_social_ranging/data/hyps/hyp.Objects365.yaml new file mode 100644 index 0000000..7497174 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/hyps/hyp.Objects365.yaml @@ -0,0 +1,34 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Hyperparameters for Objects365 training +# python train.py --weights yolov5m.pt --data Objects365.yaml --evolve +# See Hyperparameter Evolution tutorial for details https://github.com/ultralytics/yolov5#tutorials + +lr0: 0.00258 +lrf: 0.17 +momentum: 0.779 +weight_decay: 0.00058 +warmup_epochs: 1.33 +warmup_momentum: 0.86 +warmup_bias_lr: 0.0711 +box: 0.0539 +cls: 0.299 +cls_pw: 0.825 +obj: 0.632 +obj_pw: 1.0 +iou_t: 0.2 +anchor_t: 3.44 +anchors: 3.2 +fl_gamma: 0.0 +hsv_h: 0.0188 +hsv_s: 0.704 +hsv_v: 0.36 +degrees: 0.0 +translate: 0.0902 +scale: 0.491 +shear: 0.0 +perspective: 0.0 +flipud: 0.0 +fliplr: 0.5 +mosaic: 1.0 +mixup: 0.0 +copy_paste: 0.0 diff --git a/yolov5_Monocular_social_ranging/data/hyps/hyp.VOC.yaml b/yolov5_Monocular_social_ranging/data/hyps/hyp.VOC.yaml new file mode 100644 index 0000000..aa952c5 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/hyps/hyp.VOC.yaml @@ -0,0 +1,40 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Hyperparameters for VOC training +# python train.py --batch 128 --weights yolov5m6.pt --data VOC.yaml --epochs 50 --img 512 --hyp hyp.scratch-med.yaml --evolve +# See Hyperparameter Evolution tutorial for details https://github.com/ultralytics/yolov5#tutorials + +# YOLOv5 Hyperparameter Evolution Results +# Best generation: 319 +# Last generation: 434 +# metrics/precision, metrics/recall, metrics/mAP_0.5, metrics/mAP_0.5:0.95, val/box_loss, val/obj_loss, val/cls_loss +# 0.86236, 0.86184, 0.91274, 0.72647, 0.0077056, 0.0042449, 0.0013846 + +lr0: 0.0033 +lrf: 0.15184 +momentum: 0.74747 +weight_decay: 0.00025 +warmup_epochs: 3.4278 +warmup_momentum: 0.59032 +warmup_bias_lr: 0.18742 +box: 0.02 +cls: 0.21563 +cls_pw: 0.5 +obj: 0.50843 +obj_pw: 0.6729 +iou_t: 0.2 +anchor_t: 3.4172 +fl_gamma: 0.0 +hsv_h: 0.01032 +hsv_s: 0.5562 +hsv_v: 0.28255 +degrees: 0.0 +translate: 0.04575 +scale: 0.73711 +shear: 0.0 +perspective: 0.0 +flipud: 0.0 +fliplr: 0.5 +mosaic: 0.87158 +mixup: 0.04294 +copy_paste: 0.0 +anchors: 3.3556 diff --git a/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-high.yaml b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-high.yaml new file mode 100644 index 0000000..123cc84 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-high.yaml @@ -0,0 +1,34 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Hyperparameters for high-augmentation COCO training from scratch +# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300 +# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials + +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.3 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 0.7 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.1 # image translation (+/- fraction) +scale: 0.9 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.1 # image mixup (probability) +copy_paste: 0.1 # segment copy-paste (probability) diff --git a/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-low.yaml b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-low.yaml new file mode 100644 index 0000000..b9ef1d5 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-low.yaml @@ -0,0 +1,34 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Hyperparameters for low-augmentation COCO training from scratch +# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear +# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials + +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.01 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.5 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 1.0 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.1 # image translation (+/- fraction) +scale: 0.5 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.0 # image mixup (probability) +copy_paste: 0.0 # segment copy-paste (probability) diff --git a/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-med.yaml b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-med.yaml new file mode 100644 index 0000000..d6867d7 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/hyps/hyp.scratch-med.yaml @@ -0,0 +1,34 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Hyperparameters for medium-augmentation COCO training from scratch +# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300 +# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials + +lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) +lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf) +momentum: 0.937 # SGD momentum/Adam beta1 +weight_decay: 0.0005 # optimizer weight decay 5e-4 +warmup_epochs: 3.0 # warmup epochs (fractions ok) +warmup_momentum: 0.8 # warmup initial momentum +warmup_bias_lr: 0.1 # warmup initial bias lr +box: 0.05 # box loss gain +cls: 0.3 # cls loss gain +cls_pw: 1.0 # cls BCELoss positive_weight +obj: 0.7 # obj loss gain (scale with pixels) +obj_pw: 1.0 # obj BCELoss positive_weight +iou_t: 0.20 # IoU training threshold +anchor_t: 4.0 # anchor-multiple threshold +# anchors: 3 # anchors per output layer (0 to ignore) +fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) +hsv_h: 0.015 # image HSV-Hue augmentation (fraction) +hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) +hsv_v: 0.4 # image HSV-Value augmentation (fraction) +degrees: 0.0 # image rotation (+/- deg) +translate: 0.1 # image translation (+/- fraction) +scale: 0.9 # image scale (+/- gain) +shear: 0.0 # image shear (+/- deg) +perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 +flipud: 0.0 # image flip up-down (probability) +fliplr: 0.5 # image flip left-right (probability) +mosaic: 1.0 # image mosaic (probability) +mixup: 0.1 # image mixup (probability) +copy_paste: 0.0 # segment copy-paste (probability) diff --git a/yolov5_Monocular_social_ranging/data/scripts/download_weights.sh b/yolov5_Monocular_social_ranging/data/scripts/download_weights.sh new file mode 100644 index 0000000..e9fa653 --- /dev/null +++ b/yolov5_Monocular_social_ranging/data/scripts/download_weights.sh @@ -0,0 +1,20 @@ +#!/bin/bash +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Download latest models from https://github.com/ultralytics/yolov5/releases +# Example usage: bash path/to/download_weights.sh +# parent +# └── yolov5 +# ├── yolov5s.pt ← downloads here +# ├── yolov5m.pt +# └── ... + +python - <= cls >= 0, f'incorrect class index {cls}' + + # Write YOLO label + if id not in shapes: + shapes[id] = Image.open(file).size + box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True) + with open((labels / id).with_suffix('.txt'), 'a') as f: + f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt + except Exception as e: + print(f'WARNING: skipping one label for {file}: {e}') + + + # Download manually from https://challenge.xviewdataset.org + dir = Path(yaml['path']) # dataset root dir + # urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels + # 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images + # 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels) + # download(urls, dir=dir, delete=False) + + # Convert labels + convert_labels(dir / 'xView_train.geojson') + + # Move images + images = Path(dir / 'images') + images.mkdir(parents=True, exist_ok=True) + Path(dir / 'train_images').rename(dir / 'images' / 'train') + Path(dir / 'val_images').rename(dir / 'images' / 'val') + + # Split + autosplit(dir / 'images' / 'train') diff --git a/yolov5_Monocular_social_ranging/detect.py b/yolov5_Monocular_social_ranging/detect.py new file mode 100644 index 0000000..2b35ee7 --- /dev/null +++ b/yolov5_Monocular_social_ranging/detect.py @@ -0,0 +1,332 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Run inference on images, videos, directories, streams, etc. + +Usage - sources: + $ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam + img.jpg # image + vid.mp4 # video + path/ # directory + path/*.jpg # glob + 'https://youtu.be/Zgi9g1ksQHc' # YouTube + 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream + +Usage - formats: + $ python path/to/detect.py --weights yolov5s.pt # PyTorch + yolov5s.torchscript # TorchScript + yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn + yolov5s.xml # OpenVINO + yolov5s.engine # TensorRT + yolov5s.mlmodel # CoreML (MacOS-only) + yolov5s_saved_model # TensorFlow SavedModel + yolov5s.pb # TensorFlow GraphDef + yolov5s.tflite # TensorFlow Lite + yolov5s_edgetpu.tflite # TensorFlow Edge TPU +""" + +import argparse +import itertools +import os +import sys +from pathlib import Path + +import cv2 +import torch +import torch.backends.cudnn as cudnn + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[0] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative + +from models.common import DetectMultiBackend +from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams +from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, + increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh) +from utils.plots import Annotator, colors, save_one_box +from utils.torch_utils import select_device, time_sync +from distance import person_distance,car_distance + +def distancing_1(person_coords, car_coords,dis_m1,dis_m, sq, img): + already_red = dict() + centers_people = [] + centers_car = [] + centers = [] + for i in person_coords: + centers_people.append(((int(i[2])+int(i[0]))//2,(int(i[3])+int(i[1]))//2)) + for i_car in car_coords: + centers_car.append(((int(i_car[2])+int(i_car[0]))//2,(int(i_car[3])+int(i_car[1]))//2)) + centers = centers_people +centers_car + for j in centers: + already_red[j] = 2 + x_combs = itertools.product(person_coords, car_coords, repeat=1) + radius = 10 + thickness = 5 + for x in x_combs: + xyxy1, xyxy2 = x[0],x[1] + cntr1 = ((int(xyxy1[2])+int(xyxy1[0]))//2,(int(xyxy1[3])+int(xyxy1[1]))//2) + cntr2 = ((int(xyxy2[2])+int(xyxy2[0]))//2,(int(xyxy2[3])+int(xyxy2[1]))//2) + + dist_x = (cntr2[0] - cntr1[0]) * sq + dist_y = dis_m1 - dis_m + dist = (dist_x ** 2 + dist_y ** 2) ** 0.5 + + color = (0, 255, 255) + cv2.line(img, cntr1, cntr2, color, thickness) + mid = ((int(cntr1[0])+int(cntr2[0]))//2,(int(cntr1[1])+int(cntr2[1]))//2) + cm = round(dist,2) + cv2.putText(img, str(cm)+" m", mid, cv2.FONT_HERSHEY_SIMPLEX , 1, color, 2, cv2.LINE_AA) + already_red[cntr1] = 0 + already_red[cntr2] = 0 + cv2.circle(img, cntr1, radius, color, -1) + cv2.circle(img, cntr2, radius, color, -1) + # Plots one bounding box on image img + tl = round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness + for xy in x: + cntr = ((int(xy[2])+int(xy[0]))//2,(int(xy[3])+int(xy[1]))//2) + if already_red[cntr] == 0: + z1, z2 =(int(xyxy1[0]),int(xyxy1[1])),(int(xyxy1[2]),int(xyxy1[3])) + zz1, zz2 =(int(xyxy2[0]),int(xyxy2[1])),(int(xyxy2[2]),int(xyxy2[3])) + return (img) +@torch.no_grad() +def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) + source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam + data=ROOT / 'data/coco128.yaml', # dataset.yaml path + imgsz=(640, 640), # inference size (height, width) + conf_thres=0.25, # confidence threshold + iou_thres=0.45, # NMS IOU threshold + max_det=1000, # maximum detections per image + device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu + view_img=False, # show results + save_txt=False, # save results to *.txt + save_conf=False, # save confidences in --save-txt labels + save_crop=False, # save cropped prediction boxes + nosave=False, # do not save images/videos + classes=None, # filter by class: --class 0, or --class 0 2 3 + agnostic_nms=False, # class-agnostic NMS + augment=False, # augmented inference + visualize=False, # visualize features + update=False, # update all models + project=ROOT / 'runs/detect', # save results to project/name + name='exp', # save results to project/name + exist_ok=False, # existing project/name ok, do not increment + line_thickness=3, # bounding box thickness (pixels) + hide_labels=False, # hide labels + hide_conf=False, # hide confidences + half=False, # use FP16 half-precision inference + dnn=False, # use OpenCV DNN for ONNX inference + ): + global dis_m, dis_m1, sq + source = str(source) + save_img = not nosave and not source.endswith('.txt') # save inference images + is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) + is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) + webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file) + if is_url and is_file: + source = check_file(source) # download + + # Directories + save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run + (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir + + # Load model + device = select_device(device) + model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data) + stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine + imgsz = check_img_size(imgsz, s=stride) # check image size + + # Half + half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA + if pt or jit: + model.model.half() if half else model.model.float() + + # Dataloader + if webcam: + view_img = check_imshow() + cudnn.benchmark = True # set True to speed up constant image size inference + dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt) + bs = len(dataset) # batch_size + else: + dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt) + bs = 1 # batch_size + vid_path, vid_writer = [None] * bs, [None] * bs + + # Run inference + model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half) # warmup + dt, seen = [0.0, 0.0, 0.0], 0 + for path, im, im0s, vid_cap, s in dataset: + t1 = time_sync() + im = torch.from_numpy(im).to(device) + im = im.half() if half else im.float() # uint8 to fp16/32 + im /= 255 # 0 - 255 to 0.0 - 1.0 + if len(im.shape) == 3: + im = im[None] # expand for batch dim + t2 = time_sync() + dt[0] += t2 - t1 + + # Inference + visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False + pred = model(im, augment=augment, visualize=visualize) + t3 = time_sync() + dt[1] += t3 - t2 + + # NMS + pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) + dt[2] += time_sync() - t3 + + # Second-stage classifier (optional) + # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) + + # Process predictions + person_coords = [] + car_coords = [] + for i, det in enumerate(pred): # per image + seen += 1 + if webcam: # batch_size >= 1 + p, im0, frame = path[i], im0s[i].copy(), dataset.count + s += f'{i}: ' + else: + p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) + + p = Path(p) # to Path + save_path = str(save_dir / p.name) # im.jpg + txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt + s += '%gx%g ' % im.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + imc = im0.copy() if save_crop else im0 # for save_crop + annotator = Annotator(im0, line_width=line_thickness, example=str(names)) + if len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round() + + # Print results + for c in det[:, -1].unique(): + n = (det[:, -1] == c).sum() # detections per class + s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string + + # Write results + for *xyxy, conf, cls in reversed(det): + if save_txt: # Write to file + xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format + with open(txt_path + '.txt', 'a') as f: + f.write(('%g ' * len(line)).rstrip() % line + '\n') + if save_img or save_crop or view_img: # Add bbox to image + x1 = int(xyxy[0]) + y1 = int(xyxy[1]) + x2 = int(xyxy[2]) + y2 = int(xyxy[3]) + h = y2-y1 + if names[int(cls)] == "person": + person_coords.append(xyxy) + c = int(cls) # integer class 整数类 1111111111 + label = None if hide_labels else ( + names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111 + dis_m = person_distance(h) + sq = 170 / h /100 + label += f' {dis_m}m' + txt = '{0}'.format(label) + # annotator.box_label(xyxy, txt, color=(255, 0, 255)) + annotator.box_label(xyxy, txt, color=colors(c, True)) + if names[int(cls)] == "car": + car_coords.append(xyxy) + c = int(cls) # integer class 整数类 1111111111 + label = None if hide_labels else ( + names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111 + dis_m1 = car_distance(h) + label += f' {dis_m1}m' + txt = '{0}'.format(label) + # annotator.box_label(xyxy, txt, color=(255, 0, 255)) + annotator.box_label(xyxy, txt, color=colors(c, True)) + + if save_crop: + save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) + + # Stream results + im0 = annotator.result() + im = distancing_1(person_coords, car_coords, dis_m1, dis_m, sq, im0) + '''if view_img: + cv2.imshow(str(p), im0) + cv2.waitKey(1) # 1 millisecond''' + if view_img: + cv2.namedWindow("Webcam", cv2.WINDOW_NORMAL) + cv2.resizeWindow("Webcam", 1280, 720) + cv2.moveWindow("Webcam", 0, 100) + cv2.imshow("Webcam", im0) + cv2.waitKey(1) + + # Save results (image with detections) + if save_img: + if dataset.mode == 'image': + cv2.imwrite(save_path, im0) + else: # 'video' or 'stream' + if vid_path[i] != save_path: # new video + vid_path[i] = save_path + if isinstance(vid_writer[i], cv2.VideoWriter): + vid_writer[i].release() # release previous video writer + if vid_cap: # video + fps = vid_cap.get(cv2.CAP_PROP_FPS) + w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + else: # stream + fps, w, h = 30, im0.shape[1], im0.shape[0] + save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos + vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) + vid_writer[i].write(im0) + + # Print time (inference-only) + LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)') + + # Print results + t = tuple(x / seen * 1E3 for x in dt) # speeds per image + LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) + if save_txt or save_img: + s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' + LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") + if update: + strip_optimizer(weights) # update model (to fix SourceChangeWarning) + + +def parse_opt(): + parser = argparse.ArgumentParser() + parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)') + parser.add_argument('--source', type=str, default=ROOT / 'data/images/3.mp4', help='file/dir/URL/glob, 0 for webcam') + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path') + parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w') + parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold') + parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold') + parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image') + parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--view-img', action='store_true', help='show results') + parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') + parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') + parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes') + parser.add_argument('--nosave', action='store_true', help='do not save images/videos') + parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3') + parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS') + parser.add_argument('--augment', action='store_true', help='augmented inference') + parser.add_argument('--visualize', action='store_true', help='visualize features') + parser.add_argument('--update', action='store_true', help='update all models') + parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name') + parser.add_argument('--name', default='exp', help='save results to project/name') + parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') + parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)') + parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels') + parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences') + parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference') + parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference') + opt = parser.parse_args() + opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand + print_args(FILE.stem, opt) + return opt + + +def main(opt): + check_requirements(exclude=('tensorboard', 'thop')) + run(**vars(opt)) + + +if __name__ == "__main__": + opt = parse_opt() + main(opt) diff --git a/yolov5_Monocular_social_ranging/distance.py b/yolov5_Monocular_social_ranging/distance.py new file mode 100644 index 0000000..8db9ef1 --- /dev/null +++ b/yolov5_Monocular_social_ranging/distance.py @@ -0,0 +1,18 @@ +foc = 1990.0 # 镜头焦距 +real_hight_person = 66.9 # 行人高度 +real_hight_car = 57.08 # 轿车高度 + +# 自定义函数，单目测距 +def person_distance(h): + dis_inch = (real_hight_person * foc) / (h - 2) + dis_cm = dis_inch * 2.54 + dis_cm = int(dis_cm) + dis_m = dis_cm/100 + return dis_m + +def car_distance(h): + dis_inch = (real_hight_car * foc) / (h - 2) + dis_cm = dis_inch * 2.54 + dis_cm = int(dis_cm) + dis_m = dis_cm/100 + return dis_m \ No newline at end of file diff --git a/yolov5_Monocular_social_ranging/export.py b/yolov5_Monocular_social_ranging/export.py new file mode 100644 index 0000000..15e92a7 --- /dev/null +++ b/yolov5_Monocular_social_ranging/export.py @@ -0,0 +1,559 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit + +Format | `export.py --include` | Model +--- | --- | --- +PyTorch | - | yolov5s.pt +TorchScript | `torchscript` | yolov5s.torchscript +ONNX | `onnx` | yolov5s.onnx +OpenVINO | `openvino` | yolov5s_openvino_model/ +TensorRT | `engine` | yolov5s.engine +CoreML | `coreml` | yolov5s.mlmodel +TensorFlow SavedModel | `saved_model` | yolov5s_saved_model/ +TensorFlow GraphDef | `pb` | yolov5s.pb +TensorFlow Lite | `tflite` | yolov5s.tflite +TensorFlow Edge TPU | `edgetpu` | yolov5s_edgetpu.tflite +TensorFlow.js | `tfjs` | yolov5s_web_model/ + +Requirements: + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU + +Usage: + $ python path/to/export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ... + +Inference: + $ python path/to/detect.py --weights yolov5s.pt # PyTorch + yolov5s.torchscript # TorchScript + yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn + yolov5s.xml # OpenVINO + yolov5s.engine # TensorRT + yolov5s.mlmodel # CoreML (MacOS-only) + yolov5s_saved_model # TensorFlow SavedModel + yolov5s.pb # TensorFlow GraphDef + yolov5s.tflite # TensorFlow Lite + yolov5s_edgetpu.tflite # TensorFlow Edge TPU + +TensorFlow.js: + $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example + $ npm install + $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model + $ npm start +""" + +import argparse +import json +import os +import platform +import subprocess +import sys +import time +import warnings +from pathlib import Path + +import pandas as pd +import torch +import torch.nn as nn +from torch.utils.mobile_optimizer import optimize_for_mobile + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[0] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative + +from models.common import Conv +from models.experimental import attempt_load +from models.yolo import Detect +from utils.activations import SiLU +from utils.datasets import LoadImages +from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_version, colorstr, + file_size, print_args, url2file) +from utils.torch_utils import select_device + + +def export_formats(): + # YOLOv5 export formats + x = [['PyTorch', '-', '.pt'], + ['TorchScript', 'torchscript', '.torchscript'], + ['ONNX', 'onnx', '.onnx'], + ['OpenVINO', 'openvino', '_openvino_model'], + ['TensorRT', 'engine', '.engine'], + ['CoreML', 'coreml', '.mlmodel'], + ['TensorFlow SavedModel', 'saved_model', '_saved_model'], + ['TensorFlow GraphDef', 'pb', '.pb'], + ['TensorFlow Lite', 'tflite', '.tflite'], + ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite'], + ['TensorFlow.js', 'tfjs', '_web_model']] + return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix']) + + +def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')): + # YOLOv5 TorchScript model export + try: + LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...') + f = file.with_suffix('.torchscript') + + ts = torch.jit.trace(model, im, strict=False) + d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names} + extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap() + if optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html + optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files) + else: + ts.save(str(f), _extra_files=extra_files) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'{prefix} export failure: {e}') + + +def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')): + # YOLOv5 ONNX export + try: + check_requirements(('onnx',)) + import onnx + + LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...') + f = file.with_suffix('.onnx') + + torch.onnx.export(model, im, f, verbose=False, opset_version=opset, + training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL, + do_constant_folding=not train, + input_names=['images'], + output_names=['output'], + dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640) + 'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85) + } if dynamic else None) + + # Checks + model_onnx = onnx.load(f) # load onnx model + onnx.checker.check_model(model_onnx) # check onnx model + # LOGGER.info(onnx.helper.printable_graph(model_onnx.graph)) # print + + # Simplify + if simplify: + try: + check_requirements(('onnx-simplifier',)) + import onnxsim + + LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') + model_onnx, check = onnxsim.simplify( + model_onnx, + dynamic_input_shape=dynamic, + input_shapes={'images': list(im.shape)} if dynamic else None) + assert check, 'assert check failed' + onnx.save(model_onnx, f) + except Exception as e: + LOGGER.info(f'{prefix} simplifier failure: {e}') + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'{prefix} export failure: {e}') + + +def export_openvino(model, im, file, prefix=colorstr('OpenVINO:')): + # YOLOv5 OpenVINO export + try: + check_requirements(('openvino-dev',)) # requires openvino-dev: https://pypi.org/project/openvino-dev/ + import openvino.inference_engine as ie + + LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...') + f = str(file).replace('.pt', '_openvino_model' + os.sep) + + cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f}" + subprocess.check_output(cmd, shell=True) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +def export_coreml(model, im, file, prefix=colorstr('CoreML:')): + # YOLOv5 CoreML export + try: + check_requirements(('coremltools',)) + import coremltools as ct + + LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...') + f = file.with_suffix('.mlmodel') + + ts = torch.jit.trace(model, im, strict=False) # TorchScript model + ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])]) + ct_model.save(f) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return ct_model, f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + return None, None + + +def export_engine(model, im, file, train, half, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')): + # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt + try: + check_requirements(('tensorrt',)) + import tensorrt as trt + + if trt.__version__[0] == '7': # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012 + grid = model.model[-1].anchor_grid + model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid] + export_onnx(model, im, file, 12, train, False, simplify) # opset 12 + model.model[-1].anchor_grid = grid + else: # TensorRT >= 8 + check_version(trt.__version__, '8.0.0', hard=True) # require tensorrt>=8.0.0 + export_onnx(model, im, file, 13, train, False, simplify) # opset 13 + onnx = file.with_suffix('.onnx') + + LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...') + assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`' + assert onnx.exists(), f'failed to export ONNX file: {onnx}' + f = file.with_suffix('.engine') # TensorRT engine file + logger = trt.Logger(trt.Logger.INFO) + if verbose: + logger.min_severity = trt.Logger.Severity.VERBOSE + + builder = trt.Builder(logger) + config = builder.create_builder_config() + config.max_workspace_size = workspace * 1 << 30 + + flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)) + network = builder.create_network(flag) + parser = trt.OnnxParser(network, logger) + if not parser.parse_from_file(str(onnx)): + raise RuntimeError(f'failed to load ONNX file: {onnx}') + + inputs = [network.get_input(i) for i in range(network.num_inputs)] + outputs = [network.get_output(i) for i in range(network.num_outputs)] + LOGGER.info(f'{prefix} Network Description:') + for inp in inputs: + LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}') + for out in outputs: + LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}') + + half &= builder.platform_has_fast_fp16 + LOGGER.info(f'{prefix} building FP{16 if half else 32} engine in {f}') + if half: + config.set_flag(trt.BuilderFlag.FP16) + with builder.build_engine(network, config) as engine, open(f, 'wb') as t: + t.write(engine.serialize()) + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +def export_saved_model(model, im, file, dynamic, + tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, + conf_thres=0.25, keras=False, prefix=colorstr('TensorFlow SavedModel:')): + # YOLOv5 TensorFlow SavedModel export + try: + import tensorflow as tf + from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 + + from models.tf import TFDetect, TFModel + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + f = str(file).replace('.pt', '_saved_model') + batch_size, ch, *imgsz = list(im.shape) # BCHW + + tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz) + im = tf.zeros((batch_size, *imgsz, 3)) # BHWC order for TensorFlow + _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres) + inputs = tf.keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size) + outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres) + keras_model = tf.keras.Model(inputs=inputs, outputs=outputs) + keras_model.trainable = False + keras_model.summary() + if keras: + keras_model.save(f, save_format='tf') + else: + m = tf.function(lambda x: keras_model(x)) # full model + spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype) + m = m.get_concrete_function(spec) + frozen_func = convert_variables_to_constants_v2(m) + tfm = tf.Module() + tfm.__call__ = tf.function(lambda x: frozen_func(x), [spec]) + tfm.__call__(im) + tf.saved_model.save( + tfm, + f, + options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if + check_version(tf.__version__, '2.6') else tf.saved_model.SaveOptions()) + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return keras_model, f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + return None, None + + +def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')): + # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow + try: + import tensorflow as tf + from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + f = file.with_suffix('.pb') + + m = tf.function(lambda x: keras_model(x)) # full model + m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)) + frozen_func = convert_variables_to_constants_v2(m) + frozen_func.graph.as_graph_def() + tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')): + # YOLOv5 TensorFlow Lite export + try: + import tensorflow as tf + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + batch_size, ch, *imgsz = list(im.shape) # BCHW + f = str(file).replace('.pt', '-fp16.tflite') + + converter = tf.lite.TFLiteConverter.from_keras_model(keras_model) + converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS] + converter.target_spec.supported_types = [tf.float16] + converter.optimizations = [tf.lite.Optimize.DEFAULT] + if int8: + from models.tf import representative_dataset_gen + dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False) # representative data + converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib) + converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] + converter.target_spec.supported_types = [] + converter.inference_input_type = tf.uint8 # or tf.int8 + converter.inference_output_type = tf.uint8 # or tf.int8 + converter.experimental_new_quantizer = False + f = str(file).replace('.pt', '-int8.tflite') + + tflite_model = converter.convert() + open(f, "wb").write(tflite_model) + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')): + # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/ + try: + cmd = 'edgetpu_compiler --version' + help_url = 'https://coral.ai/docs/edgetpu/compiler/' + assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}' + if subprocess.run(cmd + ' >/dev/null', shell=True).returncode != 0: + LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}') + sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system + for c in ['curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -', + 'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list', + 'sudo apt-get update', + 'sudo apt-get install edgetpu-compiler']: + subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True) + ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1] + + LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...') + f = str(file).replace('.pt', '-int8_edgetpu.tflite') # Edge TPU model + f_tfl = str(file).replace('.pt', '-int8.tflite') # TFLite model + + cmd = f"edgetpu_compiler -s {f_tfl}" + subprocess.run(cmd, shell=True, check=True) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')): + # YOLOv5 TensorFlow.js export + try: + check_requirements(('tensorflowjs',)) + import re + + import tensorflowjs as tfjs + + LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...') + f = str(file).replace('.pt', '_web_model') # js dir + f_pb = file.with_suffix('.pb') # *.pb path + f_json = f + '/model.json' # *.json path + + cmd = f'tensorflowjs_converter --input_format=tf_frozen_model ' \ + f'--output_node_names="Identity,Identity_1,Identity_2,Identity_3" {f_pb} {f}' + subprocess.run(cmd, shell=True) + + json = open(f_json).read() + with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order + subst = re.sub( + r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}}}', + r'{"outputs": {"Identity": {"name": "Identity"}, ' + r'"Identity_1": {"name": "Identity_1"}, ' + r'"Identity_2": {"name": "Identity_2"}, ' + r'"Identity_3": {"name": "Identity_3"}}}', + json) + j.write(subst) + + LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') + return f + except Exception as e: + LOGGER.info(f'\n{prefix} export failure: {e}') + + +@torch.no_grad() +def run(data=ROOT / 'data/coco128.yaml', # 'dataset.yaml path' + weights=ROOT / 'yolov5s.pt', # weights path + imgsz=(640, 640), # image (height, width) + batch_size=1, # batch size + device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu + include=('torchscript', 'onnx'), # include formats + half=False, # FP16 half-precision export + inplace=False, # set YOLOv5 Detect() inplace=True + train=False, # model.train() mode + optimize=False, # TorchScript: optimize for mobile + int8=False, # CoreML/TF INT8 quantization + dynamic=False, # ONNX/TF: dynamic axes + simplify=False, # ONNX: simplify model + opset=12, # ONNX: opset version + verbose=False, # TensorRT: verbose log + workspace=4, # TensorRT: workspace size (GB) + nms=False, # TF: add NMS to model + agnostic_nms=False, # TF: add agnostic NMS to model + topk_per_class=100, # TF.js NMS: topk per class to keep + topk_all=100, # TF.js NMS: topk for all classes to keep + iou_thres=0.45, # TF.js NMS: IoU threshold + conf_thres=0.25 # TF.js NMS: confidence threshold + ): + t = time.time() + include = [x.lower() for x in include] # to lowercase + formats = tuple(export_formats()['Argument'][1:]) # --include arguments + flags = [x in include for x in formats] + assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {formats}' + jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = flags # export booleans + file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights) # PyTorch weights + + # Load PyTorch model + device = select_device(device) + assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0' + model = attempt_load(weights, map_location=device, inplace=True, fuse=True) # load FP32 model + nc, names = model.nc, model.names # number of classes, class names + + # Checks + imgsz *= 2 if len(imgsz) == 1 else 1 # expand + opset = 12 if ('openvino' in include) else opset # OpenVINO requires opset <= 12 + assert nc == len(names), f'Model class count {nc} != len(names) {len(names)}' + + # Input + gs = int(max(model.stride)) # grid size (max stride) + imgsz = [check_img_size(x, gs) for x in imgsz] # verify img_size are gs-multiples + im = torch.zeros(batch_size, 3, *imgsz).to(device) # image size(1,3,320,192) BCHW iDetection + + # Update model + if half: + im, model = im.half(), model.half() # to FP16 + model.train() if train else model.eval() # training mode = no Detect() layer grid construction + for k, m in model.named_modules(): + if isinstance(m, Conv): # assign export-friendly activations + if isinstance(m.act, nn.SiLU): + m.act = SiLU() + elif isinstance(m, Detect): + m.inplace = inplace + m.onnx_dynamic = dynamic + if hasattr(m, 'forward_export'): + m.forward = m.forward_export # assign custom forward (optional) + + for _ in range(2): + y = model(im) # dry runs + shape = tuple(y[0].shape) # model output shape + LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)") + + # Exports + f = [''] * 10 # exported filenames + warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning) # suppress TracerWarning + if jit: + f[0] = export_torchscript(model, im, file, optimize) + if engine: # TensorRT required before ONNX + f[1] = export_engine(model, im, file, train, half, simplify, workspace, verbose) + if onnx or xml: # OpenVINO requires ONNX + f[2] = export_onnx(model, im, file, opset, train, dynamic, simplify) + if xml: # OpenVINO + f[3] = export_openvino(model, im, file) + if coreml: + _, f[4] = export_coreml(model, im, file) + + # TensorFlow Exports + if any((saved_model, pb, tflite, edgetpu, tfjs)): + if int8 or edgetpu: # TFLite --int8 bug https://github.com/ultralytics/yolov5/issues/5707 + check_requirements(('flatbuffers==1.12',)) # required before `import tensorflow` + assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.' + model, f[5] = export_saved_model(model, im, file, dynamic, tf_nms=nms or agnostic_nms or tfjs, + agnostic_nms=agnostic_nms or tfjs, topk_per_class=topk_per_class, + topk_all=topk_all, conf_thres=conf_thres, iou_thres=iou_thres) # keras model + if pb or tfjs: # pb prerequisite to tfjs + f[6] = export_pb(model, im, file) + if tflite or edgetpu: + f[7] = export_tflite(model, im, file, int8=int8 or edgetpu, data=data, ncalib=100) + if edgetpu: + f[8] = export_edgetpu(model, im, file) + if tfjs: + f[9] = export_tfjs(model, im, file) + + # Finish + f = [str(x) for x in f if x] # filter out '' and None + if any(f): + LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)' + f"\nResults saved to {colorstr('bold', file.parent.resolve())}" + f"\nDetect: python detect.py --weights {f[-1]}" + f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')" + f"\nValidate: python val.py --weights {f[-1]}" + f"\nVisualize: https://netron.app") + return f # return list of exported files/dirs + + +def parse_opt(): + parser = argparse.ArgumentParser() + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') + parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)') + parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--half', action='store_true', help='FP16 half-precision export') + parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') + parser.add_argument('--train', action='store_true', help='model.train() mode') + parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile') + parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization') + parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes') + parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model') + parser.add_argument('--opset', type=int, default=12, help='ONNX: opset version') + parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log') + parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)') + parser.add_argument('--nms', action='store_true', help='TF: add NMS to model') + parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model') + parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep') + parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep') + parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold') + parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold') + parser.add_argument('--include', nargs='+', + default=['torchscript', 'onnx'], + help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs') + opt = parser.parse_args() + print_args(FILE.stem, opt) + return opt + + +def main(opt): + for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]): + run(**vars(opt)) + + +if __name__ == "__main__": + opt = parse_opt() + main(opt) diff --git a/yolov5_Monocular_social_ranging/hubconf.py b/yolov5_Monocular_social_ranging/hubconf.py new file mode 100644 index 0000000..39fa614 --- /dev/null +++ b/yolov5_Monocular_social_ranging/hubconf.py @@ -0,0 +1,143 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/ + +Usage: + import torch + model = torch.hub.load('ultralytics/yolov5', 'yolov5s') + model = torch.hub.load('ultralytics/yolov5:master', 'custom', 'path/to/yolov5s.onnx') # file from branch +""" + +import torch + + +def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + """Creates or loads a YOLOv5 model + + Arguments: + name (str): model name 'yolov5s' or path 'path/to/best.pt' + pretrained (bool): load pretrained weights into the model + channels (int): number of input channels + classes (int): number of model classes + autoshape (bool): apply YOLOv5 .autoshape() wrapper to model + verbose (bool): print all information to screen + device (str, torch.device, None): device to use for model parameters + + Returns: + YOLOv5 model + """ + from pathlib import Path + + from models.common import AutoShape, DetectMultiBackend + from models.yolo import Model + from utils.downloads import attempt_download + from utils.general import LOGGER, check_requirements, intersect_dicts, logging + from utils.torch_utils import select_device + + if not verbose: + LOGGER.setLevel(logging.WARNING) + check_requirements(exclude=('tensorboard', 'thop', 'opencv-python')) + name = Path(name) + path = name.with_suffix('.pt') if name.suffix == '' else name # checkpoint path + try: + device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device) + + if pretrained and channels == 3 and classes == 80: + model = DetectMultiBackend(path, device=device) # download/load FP32 model + # model = models.experimental.attempt_load(path, map_location=device) # download/load FP32 model + else: + cfg = list((Path(__file__).parent / 'models').rglob(f'{path.stem}.yaml'))[0] # model.yaml path + model = Model(cfg, channels, classes) # create model + if pretrained: + ckpt = torch.load(attempt_download(path), map_location=device) # load + csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 + csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors']) # intersect + model.load_state_dict(csd, strict=False) # load + if len(ckpt['model'].names) == classes: + model.names = ckpt['model'].names # set class names attribute + if autoshape: + model = AutoShape(model) # for file/URI/PIL/cv2/np inputs and NMS + return model.to(device) + + except Exception as e: + help_url = 'https://github.com/ultralytics/yolov5/issues/36' + s = f'{e}. Cache may be out of date, try `force_reload=True` or see {help_url} for help.' + raise Exception(s) from e + + +def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None): + # YOLOv5 custom or local model + return _create(path, autoshape=autoshape, verbose=verbose, device=device) + + +def yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-nano model https://github.com/ultralytics/yolov5 + return _create('yolov5n', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-small model https://github.com/ultralytics/yolov5 + return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-medium model https://github.com/ultralytics/yolov5 + return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-large model https://github.com/ultralytics/yolov5 + return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-xlarge model https://github.com/ultralytics/yolov5 + return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5 + return _create('yolov5n6', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5 + return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5 + return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5 + return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device) + + +def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): + # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5 + return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device) + + +if __name__ == '__main__': + model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained + # model = custom(path='path/to/model.pt') # custom + + # Verify inference + from pathlib import Path + + import cv2 + import numpy as np + from PIL import Image + + imgs = ['data/images/zidane.jpg', # filename + Path('data/images/zidane.jpg'), # Path + 'https://ultralytics.com/images/zidane.jpg', # URI + cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV + Image.open('data/images/bus.jpg'), # PIL + np.zeros((320, 640, 3))] # numpy + + results = model(imgs, size=320) # batched inference + results.print() + results.save() diff --git a/yolov5_Monocular_social_ranging/models/__init__.py b/yolov5_Monocular_social_ranging/models/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/yolov5_Monocular_social_ranging/models/common.py b/yolov5_Monocular_social_ranging/models/common.py new file mode 100644 index 0000000..0dae024 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/common.py @@ -0,0 +1,677 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Common modules +""" + +import json +import math +import platform +import warnings +from collections import OrderedDict, namedtuple +from copy import copy +from pathlib import Path + +import cv2 +import numpy as np +import pandas as pd +import requests +import torch +import torch.nn as nn +import yaml +from PIL import Image +from torch.cuda import amp + +from utils.datasets import exif_transpose, letterbox +from utils.general import (LOGGER, check_requirements, check_suffix, check_version, colorstr, increment_path, + make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh) +from utils.plots import Annotator, colors, save_one_box +from utils.torch_utils import copy_attr, time_sync + + +def autopad(k, p=None): # kernel, padding + # Pad to 'same' + if p is None: + p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad + return p + + +class Conv(nn.Module): + # Standard convolution + def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups + super().__init__() + self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False) + self.bn = nn.BatchNorm2d(c2) + self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity()) + + def forward(self, x): + return self.act(self.bn(self.conv(x))) + + def forward_fuse(self, x): + return self.act(self.conv(x)) + + +class DWConv(Conv): + # Depth-wise convolution class + def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups + super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act) + + +class TransformerLayer(nn.Module): + # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance) + def __init__(self, c, num_heads): + super().__init__() + self.q = nn.Linear(c, c, bias=False) + self.k = nn.Linear(c, c, bias=False) + self.v = nn.Linear(c, c, bias=False) + self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads) + self.fc1 = nn.Linear(c, c, bias=False) + self.fc2 = nn.Linear(c, c, bias=False) + + def forward(self, x): + x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x + x = self.fc2(self.fc1(x)) + x + return x + + +class TransformerBlock(nn.Module): + # Vision Transformer https://arxiv.org/abs/2010.11929 + def __init__(self, c1, c2, num_heads, num_layers): + super().__init__() + self.conv = None + if c1 != c2: + self.conv = Conv(c1, c2) + self.linear = nn.Linear(c2, c2) # learnable position embedding + self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers))) + self.c2 = c2 + + def forward(self, x): + if self.conv is not None: + x = self.conv(x) + b, _, w, h = x.shape + p = x.flatten(2).permute(2, 0, 1) + return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h) + + +class Bottleneck(nn.Module): + # Standard bottleneck + def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = Conv(c1, c_, 1, 1) + self.cv2 = Conv(c_, c2, 3, 1, g=g) + self.add = shortcut and c1 == c2 + + def forward(self, x): + return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) + + +class BottleneckCSP(nn.Module): + # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = Conv(c1, c_, 1, 1) + self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False) + self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False) + self.cv4 = Conv(2 * c_, c2, 1, 1) + self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3) + self.act = nn.SiLU() + self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) + + def forward(self, x): + y1 = self.cv3(self.m(self.cv1(x))) + y2 = self.cv2(x) + return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1)))) + + +class C3(nn.Module): + # CSP Bottleneck with 3 convolutions + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = Conv(c1, c_, 1, 1) + self.cv2 = Conv(c1, c_, 1, 1) + self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2) + self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) + # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)]) + + def forward(self, x): + return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1)) + + +class C3TR(C3): + # C3 module with TransformerBlock() + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): + super().__init__(c1, c2, n, shortcut, g, e) + c_ = int(c2 * e) + self.m = TransformerBlock(c_, c_, 4, n) + + +class C3SPP(C3): + # C3 module with SPP() + def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5): + super().__init__(c1, c2, n, shortcut, g, e) + c_ = int(c2 * e) + self.m = SPP(c_, c_, k) + + +class C3Ghost(C3): + # C3 module with GhostBottleneck() + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): + super().__init__(c1, c2, n, shortcut, g, e) + c_ = int(c2 * e) # hidden channels + self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n))) + + +class SPP(nn.Module): + # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729 + def __init__(self, c1, c2, k=(5, 9, 13)): + super().__init__() + c_ = c1 // 2 # hidden channels + self.cv1 = Conv(c1, c_, 1, 1) + self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) + self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) + + def forward(self, x): + x = self.cv1(x) + with warnings.catch_warnings(): + warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning + return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) + + +class SPPF(nn.Module): + # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher + def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13)) + super().__init__() + c_ = c1 // 2 # hidden channels + self.cv1 = Conv(c1, c_, 1, 1) + self.cv2 = Conv(c_ * 4, c2, 1, 1) + self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) + + def forward(self, x): + x = self.cv1(x) + with warnings.catch_warnings(): + warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning + y1 = self.m(x) + y2 = self.m(y1) + return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1)) + + +class Focus(nn.Module): + # Focus wh information into c-space + def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups + super().__init__() + self.conv = Conv(c1 * 4, c2, k, s, p, g, act) + # self.contract = Contract(gain=2) + + def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2) + return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)) + # return self.conv(self.contract(x)) + + +class GhostConv(nn.Module): + # Ghost Convolution https://github.com/huawei-noah/ghostnet + def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups + super().__init__() + c_ = c2 // 2 # hidden channels + self.cv1 = Conv(c1, c_, k, s, None, g, act) + self.cv2 = Conv(c_, c_, 5, 1, None, c_, act) + + def forward(self, x): + y = self.cv1(x) + return torch.cat([y, self.cv2(y)], 1) + + +class GhostBottleneck(nn.Module): + # Ghost Bottleneck https://github.com/huawei-noah/ghostnet + def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride + super().__init__() + c_ = c2 // 2 + self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw + DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw + GhostConv(c_, c2, 1, 1, act=False)) # pw-linear + self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), + Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity() + + def forward(self, x): + return self.conv(x) + self.shortcut(x) + + +class Contract(nn.Module): + # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40) + def __init__(self, gain=2): + super().__init__() + self.gain = gain + + def forward(self, x): + b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain' + s = self.gain + x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2) + x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40) + return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40) + + +class Expand(nn.Module): + # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160) + def __init__(self, gain=2): + super().__init__() + self.gain = gain + + def forward(self, x): + b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain' + s = self.gain + x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80) + x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2) + return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160) + + +class Concat(nn.Module): + # Concatenate a list of tensors along dimension + def __init__(self, dimension=1): + super().__init__() + self.d = dimension + + def forward(self, x): + return torch.cat(x, self.d) + + +class DetectMultiBackend(nn.Module): + # YOLOv5 MultiBackend class for python inference on various backends + def __init__(self, weights='yolov5s.pt', device=None, dnn=False, data=None): + # Usage: + # PyTorch: weights = *.pt + # TorchScript: *.torchscript + # ONNX Runtime: *.onnx + # ONNX OpenCV DNN: *.onnx with --dnn + # OpenVINO: *.xml + # CoreML: *.mlmodel + # TensorRT: *.engine + # TensorFlow SavedModel: *_saved_model + # TensorFlow GraphDef: *.pb + # TensorFlow Lite: *.tflite + # TensorFlow Edge TPU: *_edgetpu.tflite + from models.experimental import attempt_download, attempt_load # scoped to avoid circular import + + super().__init__() + w = str(weights[0] if isinstance(weights, list) else weights) + pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self.model_type(w) # get backend + stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults + w = attempt_download(w) # download if not local + if data: # data.yaml path (optional) + with open(data, errors='ignore') as f: + names = yaml.safe_load(f)['names'] # class names + + if pt: # PyTorch + model = attempt_load(weights if isinstance(weights, list) else w, map_location=device) + stride = max(int(model.stride.max()), 32) # model stride + names = model.module.names if hasattr(model, 'module') else model.names # get class names + self.model = model # explicitly assign for to(), cpu(), cuda(), half() + elif jit: # TorchScript + LOGGER.info(f'Loading {w} for TorchScript inference...') + extra_files = {'config.txt': ''} # model metadata + model = torch.jit.load(w, _extra_files=extra_files) + if extra_files['config.txt']: + d = json.loads(extra_files['config.txt']) # extra_files dict + stride, names = int(d['stride']), d['names'] + elif dnn: # ONNX OpenCV DNN + LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...') + check_requirements(('opencv-python>=4.5.4',)) + net = cv2.dnn.readNetFromONNX(w) + elif onnx: # ONNX Runtime + LOGGER.info(f'Loading {w} for ONNX Runtime inference...') + cuda = torch.cuda.is_available() + check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime')) + import onnxruntime + providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider'] + session = onnxruntime.InferenceSession(w, providers=providers) + elif xml: # OpenVINO + LOGGER.info(f'Loading {w} for OpenVINO inference...') + check_requirements(('openvino-dev',)) # requires openvino-dev: https://pypi.org/project/openvino-dev/ + import openvino.inference_engine as ie + core = ie.IECore() + if not Path(w).is_file(): # if not *.xml + w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir + network = core.read_network(model=w, weights=Path(w).with_suffix('.bin')) # *.xml, *.bin paths + executable_network = core.load_network(network, device_name='CPU', num_requests=1) + elif engine: # TensorRT + LOGGER.info(f'Loading {w} for TensorRT inference...') + import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download + check_version(trt.__version__, '7.0.0', hard=True) # require tensorrt>=7.0.0 + Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr')) + logger = trt.Logger(trt.Logger.INFO) + with open(w, 'rb') as f, trt.Runtime(logger) as runtime: + model = runtime.deserialize_cuda_engine(f.read()) + bindings = OrderedDict() + for index in range(model.num_bindings): + name = model.get_binding_name(index) + dtype = trt.nptype(model.get_binding_dtype(index)) + shape = tuple(model.get_binding_shape(index)) + data = torch.from_numpy(np.empty(shape, dtype=np.dtype(dtype))).to(device) + bindings[name] = Binding(name, dtype, shape, data, int(data.data_ptr())) + binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items()) + context = model.create_execution_context() + batch_size = bindings['images'].shape[0] + elif coreml: # CoreML + LOGGER.info(f'Loading {w} for CoreML inference...') + import coremltools as ct + model = ct.models.MLModel(w) + else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) + if saved_model: # SavedModel + LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...') + import tensorflow as tf + keras = False # assume TF1 saved_model + model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w) + elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt + LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...') + import tensorflow as tf + + def wrap_frozen_graph(gd, inputs, outputs): + x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped + ge = x.graph.as_graph_element + return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs)) + + gd = tf.Graph().as_graph_def() # graph_def + gd.ParseFromString(open(w, 'rb').read()) + frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0") + elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python + try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu + from tflite_runtime.interpreter import Interpreter, load_delegate + except ImportError: + import tensorflow as tf + Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate, + if edgetpu: # Edge TPU https://coral.ai/software/#edgetpu-runtime + LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...') + delegate = {'Linux': 'libedgetpu.so.1', + 'Darwin': 'libedgetpu.1.dylib', + 'Windows': 'edgetpu.dll'}[platform.system()] + interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)]) + else: # Lite + LOGGER.info(f'Loading {w} for TensorFlow Lite inference...') + interpreter = Interpreter(model_path=w) # load TFLite model + interpreter.allocate_tensors() # allocate + input_details = interpreter.get_input_details() # inputs + output_details = interpreter.get_output_details() # outputs + elif tfjs: + raise Exception('ERROR: YOLOv5 TF.js inference is not supported') + self.__dict__.update(locals()) # assign all variables to self + + def forward(self, im, augment=False, visualize=False, val=False): + # YOLOv5 MultiBackend inference + b, ch, h, w = im.shape # batch, channel, height, width + if self.pt or self.jit: # PyTorch + y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize) + return y if val else y[0] + elif self.dnn: # ONNX OpenCV DNN + im = im.cpu().numpy() # torch to numpy + self.net.setInput(im) + y = self.net.forward() + elif self.onnx: # ONNX Runtime + im = im.cpu().numpy() # torch to numpy + y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0] + elif self.xml: # OpenVINO + im = im.cpu().numpy() # FP32 + desc = self.ie.TensorDesc(precision='FP32', dims=im.shape, layout='NCHW') # Tensor Description + request = self.executable_network.requests[0] # inference request + request.set_blob(blob_name='images', blob=self.ie.Blob(desc, im)) # name=next(iter(request.input_blobs)) + request.infer() + y = request.output_blobs['output'].buffer # name=next(iter(request.output_blobs)) + elif self.engine: # TensorRT + assert im.shape == self.bindings['images'].shape, (im.shape, self.bindings['images'].shape) + self.binding_addrs['images'] = int(im.data_ptr()) + self.context.execute_v2(list(self.binding_addrs.values())) + y = self.bindings['output'].data + elif self.coreml: # CoreML + im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) + im = Image.fromarray((im[0] * 255).astype('uint8')) + # im = im.resize((192, 320), Image.ANTIALIAS) + y = self.model.predict({'image': im}) # coordinates are xywh normalized + if 'confidence' in y: + box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels + conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float) + y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) + else: + k = 'var_' + str(sorted(int(k.replace('var_', '')) for k in y)[-1]) # output key + y = y[k] # output + else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) + im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3) + if self.saved_model: # SavedModel + y = (self.model(im, training=False) if self.keras else self.model(im)[0]).numpy() + elif self.pb: # GraphDef + y = self.frozen_func(x=self.tf.constant(im)).numpy() + else: # Lite or Edge TPU + input, output = self.input_details[0], self.output_details[0] + int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model + if int8: + scale, zero_point = input['quantization'] + im = (im / scale + zero_point).astype(np.uint8) # de-scale + self.interpreter.set_tensor(input['index'], im) + self.interpreter.invoke() + y = self.interpreter.get_tensor(output['index']) + if int8: + scale, zero_point = output['quantization'] + y = (y.astype(np.float32) - zero_point) * scale # re-scale + y[..., :4] *= [w, h, w, h] # xywh normalized to pixels + + y = torch.tensor(y) if isinstance(y, np.ndarray) else y + return (y, []) if val else y + + def warmup(self, imgsz=(1, 3, 640, 640), half=False): + # Warmup model by running inference once + if self.pt or self.jit or self.onnx or self.engine: # warmup types + if isinstance(self.device, torch.device) and self.device.type != 'cpu': # only warmup GPU models + im = torch.zeros(*imgsz).to(self.device).type(torch.half if half else torch.float) # input image + self.forward(im) # warmup + + @staticmethod + def model_type(p='path/to/model.pt'): + # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx + from export import export_formats + suffixes = list(export_formats().Suffix) + ['.xml'] # export suffixes + check_suffix(p, suffixes) # checks + p = Path(p).name # eliminate trailing separators + pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes) + xml |= xml2 # *_openvino_model or *.xml + tflite &= not edgetpu # *.tflite + return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs + + +class AutoShape(nn.Module): + # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS + conf = 0.25 # NMS confidence threshold + iou = 0.45 # NMS IoU threshold + agnostic = False # NMS class-agnostic + multi_label = False # NMS multiple labels per box + classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs + max_det = 1000 # maximum number of detections per image + amp = False # Automatic Mixed Precision (AMP) inference + + def __init__(self, model): + super().__init__() + LOGGER.info('Adding AutoShape... ') + copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=()) # copy attributes + self.dmb = isinstance(model, DetectMultiBackend) # DetectMultiBackend() instance + self.pt = not self.dmb or model.pt # PyTorch model + self.model = model.eval() + + def _apply(self, fn): + # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers + self = super()._apply(fn) + if self.pt: + m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect() + m.stride = fn(m.stride) + m.grid = list(map(fn, m.grid)) + if isinstance(m.anchor_grid, list): + m.anchor_grid = list(map(fn, m.anchor_grid)) + return self + + @torch.no_grad() + def forward(self, imgs, size=640, augment=False, profile=False): + # Inference from various sources. For height=640, width=1280, RGB images example inputs are: + # file: imgs = 'data/images/zidane.jpg' # str or PosixPath + # URI: = 'https://ultralytics.com/images/zidane.jpg' + # OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3) + # PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3) + # numpy: = np.zeros((640,1280,3)) # HWC + # torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values) + # multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images + + t = [time_sync()] + p = next(self.model.parameters()) if self.pt else torch.zeros(1) # for device and type + autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference + if isinstance(imgs, torch.Tensor): # torch + with amp.autocast(enabled=autocast): + return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference + + # Pre-process + n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images + shape0, shape1, files = [], [], [] # image and inference shapes, filenames + for i, im in enumerate(imgs): + f = f'image{i}' # filename + if isinstance(im, (str, Path)): # filename or uri + im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im + im = np.asarray(exif_transpose(im)) + elif isinstance(im, Image.Image): # PIL Image + im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f + files.append(Path(f).with_suffix('.jpg').name) + if im.shape[0] < 5: # image in CHW + im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1) + im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3) # enforce 3ch input + s = im.shape[:2] # HWC + shape0.append(s) # image shape + g = (size / max(s)) # gain + shape1.append([y * g for y in s]) + imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update + shape1 = [make_divisible(x, self.stride) for x in np.stack(shape1, 0).max(0)] # inference shape + x = [letterbox(im, new_shape=shape1 if self.pt else size, auto=False)[0] for im in imgs] # pad + x = np.stack(x, 0) if n > 1 else x[0][None] # stack + x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW + x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32 + t.append(time_sync()) + + with amp.autocast(enabled=autocast): + # Inference + y = self.model(x, augment, profile) # forward + t.append(time_sync()) + + # Post-process + y = non_max_suppression(y if self.dmb else y[0], self.conf, iou_thres=self.iou, classes=self.classes, + agnostic=self.agnostic, multi_label=self.multi_label, max_det=self.max_det) # NMS + for i in range(n): + scale_coords(shape1, y[i][:, :4], shape0[i]) + + t.append(time_sync()) + return Detections(imgs, y, files, t, self.names, x.shape) + + +class Detections: + # YOLOv5 detections class for inference results + def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None): + super().__init__() + d = pred[0].device # device + gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations + self.imgs = imgs # list of images as numpy arrays + self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls) + self.names = names # class names + self.files = files # image filenames + self.times = times # profiling times + self.xyxy = pred # xyxy pixels + self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels + self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized + self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized + self.n = len(self.pred) # number of images (batch size) + self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms) + self.s = shape # inference BCHW shape + + def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')): + crops = [] + for i, (im, pred) in enumerate(zip(self.imgs, self.pred)): + s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string + if pred.shape[0]: + for c in pred[:, -1].unique(): + n = (pred[:, -1] == c).sum() # detections per class + s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string + if show or save or render or crop: + annotator = Annotator(im, example=str(self.names)) + for *box, conf, cls in reversed(pred): # xyxy, confidence, class + label = f'{self.names[int(cls)]} {conf:.2f}' + if crop: + file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None + crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label, + 'im': save_one_box(box, im, file=file, save=save)}) + else: # all others + annotator.box_label(box, label, color=colors(cls)) + im = annotator.im + else: + s += '(no detections)' + + im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np + if pprint: + LOGGER.info(s.rstrip(', ')) + if show: + im.show(self.files[i]) # show + if save: + f = self.files[i] + im.save(save_dir / f) # save + if i == self.n - 1: + LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}") + if render: + self.imgs[i] = np.asarray(im) + if crop: + if save: + LOGGER.info(f'Saved results to {save_dir}\n') + return crops + + def print(self): + self.display(pprint=True) # print results + LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % + self.t) + + def show(self): + self.display(show=True) # show results + + def save(self, save_dir='runs/detect/exp'): + save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir + self.display(save=True, save_dir=save_dir) # save results + + def crop(self, save=True, save_dir='runs/detect/exp'): + save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None + return self.display(crop=True, save=save, save_dir=save_dir) # crop results + + def render(self): + self.display(render=True) # render results + return self.imgs + + def pandas(self): + # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0]) + new = copy(self) # return copy + ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns + cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns + for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]): + a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update + setattr(new, k, [pd.DataFrame(x, columns=c) for x in a]) + return new + + def tolist(self): + # return a list of Detections objects, i.e. 'for result in results.tolist():' + r = range(self.n) # iterable + x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r] + # for d in x: + # for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']: + # setattr(d, k, getattr(d, k)[0]) # pop out of list + return x + + def __len__(self): + return self.n + + +class Classify(nn.Module): + # Classification head, i.e. x(b,c1,20,20) to x(b,c2) + def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups + super().__init__() + self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1) + self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1) + self.flat = nn.Flatten() + + def forward(self, x): + z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list + return self.flat(self.conv(z)) # flatten to x(b,c2) diff --git a/yolov5_Monocular_social_ranging/models/experimental.py b/yolov5_Monocular_social_ranging/models/experimental.py new file mode 100644 index 0000000..463e551 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/experimental.py @@ -0,0 +1,120 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Experimental modules +""" +import math + +import numpy as np +import torch +import torch.nn as nn + +from models.common import Conv +from utils.downloads import attempt_download + + +class CrossConv(nn.Module): + # Cross Convolution Downsample + def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): + # ch_in, ch_out, kernel, stride, groups, expansion, shortcut + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = Conv(c1, c_, (1, k), (1, s)) + self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) + self.add = shortcut and c1 == c2 + + def forward(self, x): + return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) + + +class Sum(nn.Module): + # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 + def __init__(self, n, weight=False): # n: number of inputs + super().__init__() + self.weight = weight # apply weights boolean + self.iter = range(n - 1) # iter object + if weight: + self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights + + def forward(self, x): + y = x[0] # no weight + if self.weight: + w = torch.sigmoid(self.w) * 2 + for i in self.iter: + y = y + x[i + 1] * w[i] + else: + for i in self.iter: + y = y + x[i + 1] + return y + + +class MixConv2d(nn.Module): + # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595 + def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy + super().__init__() + n = len(k) # number of convolutions + if equal_ch: # equal c_ per group + i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices + c_ = [(i == g).sum() for g in range(n)] # intermediate channels + else: # equal weight.numel() per group + b = [c2] + [0] * n + a = np.eye(n + 1, n, k=-1) + a -= np.roll(a, 1, axis=1) + a *= np.array(k) ** 2 + a[0] = 1 + c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b + + self.m = nn.ModuleList( + [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)]) + self.bn = nn.BatchNorm2d(c2) + self.act = nn.SiLU() + + def forward(self, x): + return self.act(self.bn(torch.cat([m(x) for m in self.m], 1))) + + +class Ensemble(nn.ModuleList): + # Ensemble of models + def __init__(self): + super().__init__() + + def forward(self, x, augment=False, profile=False, visualize=False): + y = [] + for module in self: + y.append(module(x, augment, profile, visualize)[0]) + # y = torch.stack(y).max(0)[0] # max ensemble + # y = torch.stack(y).mean(0) # mean ensemble + y = torch.cat(y, 1) # nms ensemble + return y, None # inference, train output + + +def attempt_load(weights, map_location=None, inplace=True, fuse=True): + from models.yolo import Detect, Model + + # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a + model = Ensemble() + for w in weights if isinstance(weights, list) else [weights]: + ckpt = torch.load(attempt_download(w), map_location=map_location) # load + if fuse: + model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model + else: + model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse + + # Compatibility updates + for m in model.modules(): + if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]: + m.inplace = inplace # pytorch 1.7.0 compatibility + if type(m) is Detect: + if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility + delattr(m, 'anchor_grid') + setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl) + elif type(m) is Conv: + m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility + + if len(model) == 1: + return model[-1] # return model + else: + print(f'Ensemble created with {weights}\n') + for k in ['names']: + setattr(model, k, getattr(model[-1], k)) + model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride + return model # return ensemble diff --git a/yolov5_Monocular_social_ranging/models/hub/anchors.yaml b/yolov5_Monocular_social_ranging/models/hub/anchors.yaml new file mode 100644 index 0000000..e4d7beb --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/anchors.yaml @@ -0,0 +1,59 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +# Default anchors for COCO data + + +# P5 ------------------------------------------------------------------------------------------------------------------- +# P5-640: +anchors_p5_640: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + + +# P6 ------------------------------------------------------------------------------------------------------------------- +# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387 +anchors_p6_640: + - [9,11, 21,19, 17,41] # P3/8 + - [43,32, 39,70, 86,64] # P4/16 + - [65,131, 134,130, 120,265] # P5/32 + - [282,180, 247,354, 512,387] # P6/64 + +# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 +anchors_p6_1280: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187 +anchors_p6_1920: + - [28,41, 67,59, 57,141] # P3/8 + - [144,103, 129,227, 270,205] # P4/16 + - [209,452, 455,396, 358,812] # P5/32 + - [653,922, 1109,570, 1387,1187] # P6/64 + + +# P7 ------------------------------------------------------------------------------------------------------------------- +# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372 +anchors_p7_640: + - [11,11, 13,30, 29,20] # P3/8 + - [30,46, 61,38, 39,92] # P4/16 + - [78,80, 146,66, 79,163] # P5/32 + - [149,150, 321,143, 157,303] # P6/64 + - [257,402, 359,290, 524,372] # P7/128 + +# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818 +anchors_p7_1280: + - [19,22, 54,36, 32,77] # P3/8 + - [70,83, 138,71, 75,173] # P4/16 + - [165,159, 148,334, 375,151] # P5/32 + - [334,317, 251,626, 499,474] # P6/64 + - [750,326, 534,814, 1079,818] # P7/128 + +# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227 +anchors_p7_1920: + - [29,34, 81,55, 47,115] # P3/8 + - [105,124, 207,107, 113,259] # P4/16 + - [247,238, 222,500, 563,227] # P5/32 + - [501,476, 376,939, 749,711] # P6/64 + - [1126,489, 801,1222, 1618,1227] # P7/128 diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov3-spp.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov3-spp.yaml new file mode 100644 index 0000000..c669821 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov3-spp.yaml @@ -0,0 +1,51 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# darknet53 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [32, 3, 1]], # 0 + [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 + [-1, 1, Bottleneck, [64]], + [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 + [-1, 2, Bottleneck, [128]], + [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 + [-1, 8, Bottleneck, [256]], + [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 + [-1, 8, Bottleneck, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 + [-1, 4, Bottleneck, [1024]], # 10 + ] + +# YOLOv3-SPP head +head: + [[-1, 1, Bottleneck, [1024, False]], + [-1, 1, SPP, [512, [5, 9, 13]]], + [-1, 1, Conv, [1024, 3, 1]], + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) + + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P4 + [-1, 1, Bottleneck, [512, False]], + [-1, 1, Bottleneck, [512, False]], + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) + + [-2, 1, Conv, [128, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P3 + [-1, 1, Bottleneck, [256, False]], + [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) + + [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov3-tiny.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov3-tiny.yaml new file mode 100644 index 0000000..b28b443 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov3-tiny.yaml @@ -0,0 +1,41 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,14, 23,27, 37,58] # P4/16 + - [81,82, 135,169, 344,319] # P5/32 + +# YOLOv3-tiny backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [16, 3, 1]], # 0 + [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2 + [-1, 1, Conv, [32, 3, 1]], + [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4 + [-1, 1, Conv, [64, 3, 1]], + [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8 + [-1, 1, Conv, [128, 3, 1]], + [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16 + [-1, 1, Conv, [256, 3, 1]], + [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32 + [-1, 1, Conv, [512, 3, 1]], + [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11 + [-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12 + ] + +# YOLOv3-tiny head +head: + [[-1, 1, Conv, [1024, 3, 1]], + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large) + + [-2, 1, Conv, [128, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P4 + [-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium) + + [[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov3.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov3.yaml new file mode 100644 index 0000000..d1ef912 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov3.yaml @@ -0,0 +1,51 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# darknet53 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [32, 3, 1]], # 0 + [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 + [-1, 1, Bottleneck, [64]], + [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 + [-1, 2, Bottleneck, [128]], + [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 + [-1, 8, Bottleneck, [256]], + [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 + [-1, 8, Bottleneck, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 + [-1, 4, Bottleneck, [1024]], # 10 + ] + +# YOLOv3 head +head: + [[-1, 1, Bottleneck, [1024, False]], + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, Conv, [1024, 3, 1]], + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) + + [-2, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P4 + [-1, 1, Bottleneck, [512, False]], + [-1, 1, Bottleneck, [512, False]], + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) + + [-2, 1, Conv, [128, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P3 + [-1, 1, Bottleneck, [256, False]], + [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) + + [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-bifpn.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-bifpn.yaml new file mode 100644 index 0000000..504815f --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-bifpn.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 BiFPN head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14, 6], 1, Concat, [1]], # cat P4 <--- BiFPN change + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-fpn.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-fpn.yaml new file mode 100644 index 0000000..a23e9c6 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-fpn.yaml @@ -0,0 +1,42 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 FPN head +head: + [[-1, 3, C3, [1024, False]], # 10 (P5/32-large) + + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 1, Conv, [512, 1, 1]], + [-1, 3, C3, [512, False]], # 14 (P4/16-medium) + + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 1, Conv, [256, 1, 1]], + [-1, 3, C3, [256, False]], # 18 (P3/8-small) + + [[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-p2.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-p2.yaml new file mode 100644 index 0000000..554117d --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-p2.yaml @@ -0,0 +1,54 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: 3 # AutoAnchor evolves 3 anchors per P output layer + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [128, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 2], 1, Concat, [1]], # cat backbone P2 + [-1, 1, C3, [128, False]], # 21 (P2/4-xsmall) + + [-1, 1, Conv, [128, 3, 2]], + [[-1, 18], 1, Concat, [1]], # cat head P3 + [-1, 3, C3, [256, False]], # 24 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 27 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 30 (P5/32-large) + + [[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-p34.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-p34.yaml new file mode 100644 index 0000000..dbf0f85 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-p34.yaml @@ -0,0 +1,41 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.50 # layer channel multiple +anchors: 3 # AutoAnchor evolves 3 anchors per P output layer + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [ [ -1, 1, Conv, [ 64, 6, 2, 2 ] ], # 0-P1/2 + [ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4 + [ -1, 3, C3, [ 128 ] ], + [ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8 + [ -1, 6, C3, [ 256 ] ], + [ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16 + [ -1, 9, C3, [ 512 ] ], + [ -1, 1, Conv, [ 1024, 3, 2 ] ], # 7-P5/32 + [ -1, 3, C3, [ 1024 ] ], + [ -1, 1, SPPF, [ 1024, 5 ] ], # 9 + ] + +# YOLOv5 v6.0 head with (P3, P4) outputs +head: + [ [ -1, 1, Conv, [ 512, 1, 1 ] ], + [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], + [ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4 + [ -1, 3, C3, [ 512, False ] ], # 13 + + [ -1, 1, Conv, [ 256, 1, 1 ] ], + [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], + [ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3 + [ -1, 3, C3, [ 256, False ] ], # 17 (P3/8-small) + + [ -1, 1, Conv, [ 256, 3, 2 ] ], + [ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P4 + [ -1, 3, C3, [ 512, False ] ], # 20 (P4/16-medium) + + [ [ 17, 20 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-p6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-p6.yaml new file mode 100644 index 0000000..a17202f --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-p6.yaml @@ -0,0 +1,56 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: 3 # AutoAnchor evolves 3 anchors per P output layer + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-p7.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-p7.yaml new file mode 100644 index 0000000..edd7d13 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-p7.yaml @@ -0,0 +1,67 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: 3 # AutoAnchor evolves 3 anchors per P output layer + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, Conv, [1280, 3, 2]], # 11-P7/128 + [-1, 3, C3, [1280]], + [-1, 1, SPPF, [1280, 5]], # 13 + ] + +# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs +head: + [[-1, 1, Conv, [1024, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 10], 1, Concat, [1]], # cat backbone P6 + [-1, 3, C3, [1024, False]], # 17 + + [-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 21 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 25 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 29 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 26], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 32 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 22], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 35 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 18], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge) + + [-1, 1, Conv, [1024, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P7 + [-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge) + + [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5-panet.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5-panet.yaml new file mode 100644 index 0000000..ccfbf90 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5-panet.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 PANet head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5l6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5l6.yaml new file mode 100644 index 0000000..632c2cb --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5l6.yaml @@ -0,0 +1,60 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5m6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5m6.yaml new file mode 100644 index 0000000..ecc53fd --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5m6.yaml @@ -0,0 +1,60 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.67 # model depth multiple +width_multiple: 0.75 # layer channel multiple +anchors: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5n6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5n6.yaml new file mode 100644 index 0000000..0c0c71d --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5n6.yaml @@ -0,0 +1,60 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.25 # layer channel multiple +anchors: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5s-ghost.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5s-ghost.yaml new file mode 100644 index 0000000..ff9519c --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5s-ghost.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.50 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3Ghost, [128]], + [-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3Ghost, [256]], + [-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3Ghost, [512]], + [-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3Ghost, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, GhostConv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3Ghost, [512, False]], # 13 + + [-1, 1, GhostConv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small) + + [-1, 1, GhostConv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium) + + [-1, 1, GhostConv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5s-transformer.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5s-transformer.yaml new file mode 100644 index 0000000..100d7c4 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5s-transformer.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.50 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3TR, [1024]], # 9 <--- C3TR() Transformer module + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5s6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5s6.yaml new file mode 100644 index 0000000..a28fb55 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5s6.yaml @@ -0,0 +1,60 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.50 # layer channel multiple +anchors: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/hub/yolov5x6.yaml b/yolov5_Monocular_social_ranging/models/hub/yolov5x6.yaml new file mode 100644 index 0000000..ba795c4 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/hub/yolov5x6.yaml @@ -0,0 +1,60 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.33 # model depth multiple +width_multiple: 1.25 # layer channel multiple +anchors: + - [19,27, 44,40, 38,94] # P3/8 + - [96,68, 86,152, 180,137] # P4/16 + - [140,301, 303,264, 238,542] # P5/32 + - [436,615, 739,380, 925,792] # P6/64 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 + [-1, 3, C3, [768]], + [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 11 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [768, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 8], 1, Concat, [1]], # cat backbone P5 + [-1, 3, C3, [768, False]], # 15 + + [-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 19 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 23 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 20], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 26 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 16], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [768, False]], # 29 (P5/32-large) + + [-1, 1, Conv, [768, 3, 2]], + [[-1, 12], 1, Concat, [1]], # cat head P6 + [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) + + [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) + ] diff --git a/yolov5_Monocular_social_ranging/models/tf.py b/yolov5_Monocular_social_ranging/models/tf.py new file mode 100644 index 0000000..74681e4 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/tf.py @@ -0,0 +1,464 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +TensorFlow, Keras and TFLite versions of YOLOv5 +Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127 + +Usage: + $ python models/tf.py --weights yolov5s.pt + +Export: + $ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs +""" + +import argparse +import sys +from copy import deepcopy +from pathlib import Path + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[1] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +# ROOT = ROOT.relative_to(Path.cwd()) # relative + +import numpy as np +import tensorflow as tf +import torch +import torch.nn as nn +from tensorflow import keras + +from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad +from models.experimental import CrossConv, MixConv2d, attempt_load +from models.yolo import Detect +from utils.activations import SiLU +from utils.general import LOGGER, make_divisible, print_args + + +class TFBN(keras.layers.Layer): + # TensorFlow BatchNormalization wrapper + def __init__(self, w=None): + super().__init__() + self.bn = keras.layers.BatchNormalization( + beta_initializer=keras.initializers.Constant(w.bias.numpy()), + gamma_initializer=keras.initializers.Constant(w.weight.numpy()), + moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()), + moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()), + epsilon=w.eps) + + def call(self, inputs): + return self.bn(inputs) + + +class TFPad(keras.layers.Layer): + def __init__(self, pad): + super().__init__() + self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]]) + + def call(self, inputs): + return tf.pad(inputs, self.pad, mode='constant', constant_values=0) + + +class TFConv(keras.layers.Layer): + # Standard convolution + def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None): + # ch_in, ch_out, weights, kernel, stride, padding, groups + super().__init__() + assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument" + assert isinstance(k, int), "Convolution with multiple kernels are not allowed." + # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding) + # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch + + conv = keras.layers.Conv2D( + c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True, + kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()), + bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy())) + self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv]) + self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity + + # YOLOv5 activations + if isinstance(w.act, nn.LeakyReLU): + self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity + elif isinstance(w.act, nn.Hardswish): + self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity + elif isinstance(w.act, (nn.SiLU, SiLU)): + self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity + else: + raise Exception(f'no matching TensorFlow activation found for {w.act}') + + def call(self, inputs): + return self.act(self.bn(self.conv(inputs))) + + +class TFFocus(keras.layers.Layer): + # Focus wh information into c-space + def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None): + # ch_in, ch_out, kernel, stride, padding, groups + super().__init__() + self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv) + + def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c) + # inputs = inputs / 255 # normalize 0-255 to 0-1 + return self.conv(tf.concat([inputs[:, ::2, ::2, :], + inputs[:, 1::2, ::2, :], + inputs[:, ::2, 1::2, :], + inputs[:, 1::2, 1::2, :]], 3)) + + +class TFBottleneck(keras.layers.Layer): + # Standard bottleneck + def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1) + self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2) + self.add = shortcut and c1 == c2 + + def call(self, inputs): + return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs)) + + +class TFConv2d(keras.layers.Layer): + # Substitution for PyTorch nn.Conv2D + def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None): + super().__init__() + assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument" + self.conv = keras.layers.Conv2D( + c2, k, s, 'VALID', use_bias=bias, + kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()), + bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, ) + + def call(self, inputs): + return self.conv(inputs) + + +class TFBottleneckCSP(keras.layers.Layer): + # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None): + # ch_in, ch_out, number, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1) + self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2) + self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3) + self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4) + self.bn = TFBN(w.bn) + self.act = lambda x: keras.activations.relu(x, alpha=0.1) + self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)]) + + def call(self, inputs): + y1 = self.cv3(self.m(self.cv1(inputs))) + y2 = self.cv2(inputs) + return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3)))) + + +class TFC3(keras.layers.Layer): + # CSP Bottleneck with 3 convolutions + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None): + # ch_in, ch_out, number, shortcut, groups, expansion + super().__init__() + c_ = int(c2 * e) # hidden channels + self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1) + self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2) + self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3) + self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)]) + + def call(self, inputs): + return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3)) + + +class TFSPP(keras.layers.Layer): + # Spatial pyramid pooling layer used in YOLOv3-SPP + def __init__(self, c1, c2, k=(5, 9, 13), w=None): + super().__init__() + c_ = c1 // 2 # hidden channels + self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1) + self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2) + self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k] + + def call(self, inputs): + x = self.cv1(inputs) + return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3)) + + +class TFSPPF(keras.layers.Layer): + # Spatial pyramid pooling-Fast layer + def __init__(self, c1, c2, k=5, w=None): + super().__init__() + c_ = c1 // 2 # hidden channels + self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1) + self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2) + self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME') + + def call(self, inputs): + x = self.cv1(inputs) + y1 = self.m(x) + y2 = self.m(y1) + return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3)) + + +class TFDetect(keras.layers.Layer): + def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer + super().__init__() + self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32) + self.nc = nc # number of classes + self.no = nc + 5 # number of outputs per anchor + self.nl = len(anchors) # number of detection layers + self.na = len(anchors[0]) // 2 # number of anchors + self.grid = [tf.zeros(1)] * self.nl # init grid + self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32) + self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]), + [self.nl, 1, -1, 1, 2]) + self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)] + self.training = False # set to False after building model + self.imgsz = imgsz + for i in range(self.nl): + ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i] + self.grid[i] = self._make_grid(nx, ny) + + def call(self, inputs): + z = [] # inference output + x = [] + for i in range(self.nl): + x.append(self.m[i](inputs[i])) + # x(bs,20,20,255) to x(bs,3,20,20,85) + ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i] + x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3]) + + if not self.training: # inference + y = tf.sigmoid(x[i]) + xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy + wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] + # Normalize xywh to 0-1 to reduce calibration error + xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32) + wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32) + y = tf.concat([xy, wh, y[..., 4:]], -1) + z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no])) + + return x if self.training else (tf.concat(z, 1), x) + + @staticmethod + def _make_grid(nx=20, ny=20): + # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)]) + # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float() + xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny)) + return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32) + + +class TFUpsample(keras.layers.Layer): + def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w' + super().__init__() + assert scale_factor == 2, "scale_factor must be 2" + self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode) + # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode) + # with default arguments: align_corners=False, half_pixel_centers=False + # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x, + # size=(x.shape[1] * 2, x.shape[2] * 2)) + + def call(self, inputs): + return self.upsample(inputs) + + +class TFConcat(keras.layers.Layer): + def __init__(self, dimension=1, w=None): + super().__init__() + assert dimension == 1, "convert only NCHW to NHWC concat" + self.d = 3 + + def call(self, inputs): + return tf.concat(inputs, self.d) + + +def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3) + LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}") + anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] + na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors + no = na * (nc + 5) # number of outputs = anchors * (classes + 5) + + layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out + for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args + m_str = m + m = eval(m) if isinstance(m, str) else m # eval strings + for j, a in enumerate(args): + try: + args[j] = eval(a) if isinstance(a, str) else a # eval strings + except NameError: + pass + + n = max(round(n * gd), 1) if n > 1 else n # depth gain + if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]: + c1, c2 = ch[f], args[0] + c2 = make_divisible(c2 * gw, 8) if c2 != no else c2 + + args = [c1, c2, *args[1:]] + if m in [BottleneckCSP, C3]: + args.insert(2, n) + n = 1 + elif m is nn.BatchNorm2d: + args = [ch[f]] + elif m is Concat: + c2 = sum(ch[-1 if x == -1 else x + 1] for x in f) + elif m is Detect: + args.append([ch[x + 1] for x in f]) + if isinstance(args[1], int): # number of anchors + args[1] = [list(range(args[1] * 2))] * len(f) + args.append(imgsz) + else: + c2 = ch[f] + + tf_m = eval('TF' + m_str.replace('nn.', '')) + m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \ + else tf_m(*args, w=model.model[i]) # module + + torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module + t = str(m)[8:-2].replace('__main__.', '') # module type + np = sum(x.numel() for x in torch_m_.parameters()) # number params + m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params + LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print + save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist + layers.append(m_) + ch.append(c2) + return keras.Sequential(layers), sorted(save) + + +class TFModel: + def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes + super().__init__() + if isinstance(cfg, dict): + self.yaml = cfg # model dict + else: # is *.yaml + import yaml # for torch hub + self.yaml_file = Path(cfg).name + with open(cfg) as f: + self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict + + # Define model + if nc and nc != self.yaml['nc']: + LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}") + self.yaml['nc'] = nc # override yaml value + self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz) + + def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, + conf_thres=0.25): + y = [] # outputs + x = inputs + for i, m in enumerate(self.model.layers): + if m.f != -1: # if not from previous layer + x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers + + x = m(x) # run + y.append(x if m.i in self.savelist else None) # save output + + # Add TensorFlow NMS + if tf_nms: + boxes = self._xywh2xyxy(x[0][..., :4]) + probs = x[0][:, :, 4:5] + classes = x[0][:, :, 5:] + scores = probs * classes + if agnostic_nms: + nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres) + return nms, x[1] + else: + boxes = tf.expand_dims(boxes, 2) + nms = tf.image.combined_non_max_suppression( + boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False) + return nms, x[1] + + return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...] + # x = x[0][0] # [x(1,6300,85), ...] to x(6300,85) + # xywh = x[..., :4] # x(6300,4) boxes + # conf = x[..., 4:5] # x(6300,1) confidences + # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes + # return tf.concat([conf, cls, xywh], 1) + + @staticmethod + def _xywh2xyxy(xywh): + # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right + x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1) + return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1) + + +class AgnosticNMS(keras.layers.Layer): + # TF Agnostic NMS + def call(self, input, topk_all, iou_thres, conf_thres): + # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450 + return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input, + fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32), + name='agnostic_nms') + + @staticmethod + def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS + boxes, classes, scores = x + class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32) + scores_inp = tf.reduce_max(scores, -1) + selected_inds = tf.image.non_max_suppression( + boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres) + selected_boxes = tf.gather(boxes, selected_inds) + padded_boxes = tf.pad(selected_boxes, + paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]], + mode="CONSTANT", constant_values=0.0) + selected_scores = tf.gather(scores_inp, selected_inds) + padded_scores = tf.pad(selected_scores, + paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]], + mode="CONSTANT", constant_values=-1.0) + selected_classes = tf.gather(class_inds, selected_inds) + padded_classes = tf.pad(selected_classes, + paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]], + mode="CONSTANT", constant_values=-1.0) + valid_detections = tf.shape(selected_inds)[0] + return padded_boxes, padded_scores, padded_classes, valid_detections + + +def representative_dataset_gen(dataset, ncalib=100): + # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays + for n, (path, img, im0s, vid_cap, string) in enumerate(dataset): + input = np.transpose(img, [1, 2, 0]) + input = np.expand_dims(input, axis=0).astype(np.float32) + input /= 255 + yield [input] + if n >= ncalib: + break + + +def run(weights=ROOT / 'yolov5s.pt', # weights path + imgsz=(640, 640), # inference size h,w + batch_size=1, # batch size + dynamic=False, # dynamic batch size + ): + # PyTorch model + im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image + model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False) + _ = model(im) # inference + model.info() + + # TensorFlow model + im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image + tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz) + _ = tf_model.predict(im) # inference + + # Keras model + im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size) + keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im)) + keras_model.summary() + + LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.') + + +def parse_opt(): + parser = argparse.ArgumentParser() + parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path') + parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + parser.add_argument('--dynamic', action='store_true', help='dynamic batch size') + opt = parser.parse_args() + opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand + print_args(FILE.stem, opt) + return opt + + +def main(opt): + run(**vars(opt)) + + +if __name__ == "__main__": + opt = parse_opt() + main(opt) diff --git a/yolov5_Monocular_social_ranging/models/yolo.py b/yolov5_Monocular_social_ranging/models/yolo.py new file mode 100644 index 0000000..f659a04 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolo.py @@ -0,0 +1,329 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +YOLO-specific modules + +Usage: + $ python path/to/models/yolo.py --cfg yolov5s.yaml +""" + +import argparse +import sys +from copy import deepcopy +from pathlib import Path + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[1] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +# ROOT = ROOT.relative_to(Path.cwd()) # relative + +from models.common import * +from models.experimental import * +from utils.autoanchor import check_anchor_order +from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args +from utils.plots import feature_visualization +from utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device, time_sync + +try: + import thop # for FLOPs computation +except ImportError: + thop = None + + +class Detect(nn.Module): + stride = None # strides computed during build + onnx_dynamic = False # ONNX export parameter + + def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer + super().__init__() + self.nc = nc # number of classes + self.no = nc + 5 # number of outputs per anchor + self.nl = len(anchors) # number of detection layers + self.na = len(anchors[0]) // 2 # number of anchors + self.grid = [torch.zeros(1)] * self.nl # init grid + self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid + self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2) + self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv + self.inplace = inplace # use in-place ops (e.g. slice assignment) + + def forward(self, x): + z = [] # inference output + for i in range(self.nl): + x[i] = self.m[i](x[i]) # conv + bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85) + x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous() + + if not self.training: # inference + if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]: + self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i) + + y = x[i].sigmoid() + if self.inplace: + y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy + y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh + else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953 + xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy + wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh + y = torch.cat((xy, wh, y[..., 4:]), -1) + z.append(y.view(bs, -1, self.no)) + + return x if self.training else (torch.cat(z, 1), x) + + def _make_grid(self, nx=20, ny=20, i=0): + d = self.anchors[i].device + if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility + yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)], indexing='ij') + else: + yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)]) + grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float() + anchor_grid = (self.anchors[i].clone() * self.stride[i]) \ + .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float() + return grid, anchor_grid + + +class Model(nn.Module): + def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes + super().__init__() + if isinstance(cfg, dict): + self.yaml = cfg # model dict + else: # is *.yaml + import yaml # for torch hub + self.yaml_file = Path(cfg).name + with open(cfg, encoding='ascii', errors='ignore') as f: + self.yaml = yaml.safe_load(f) # model dict + + # Define model + ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels + if nc and nc != self.yaml['nc']: + LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") + self.yaml['nc'] = nc # override yaml value + if anchors: + LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}') + self.yaml['anchors'] = round(anchors) # override yaml value + self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist + self.names = [str(i) for i in range(self.yaml['nc'])] # default names + self.inplace = self.yaml.get('inplace', True) + + # Build strides, anchors + m = self.model[-1] # Detect() + if isinstance(m, Detect): + s = 256 # 2x min stride + m.inplace = self.inplace + m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward + m.anchors /= m.stride.view(-1, 1, 1) + check_anchor_order(m) + self.stride = m.stride + self._initialize_biases() # only run once + + # Init weights, biases + initialize_weights(self) + self.info() + LOGGER.info('') + + def forward(self, x, augment=False, profile=False, visualize=False): + if augment: + return self._forward_augment(x) # augmented inference, None + return self._forward_once(x, profile, visualize) # single-scale inference, train + + def _forward_augment(self, x): + img_size = x.shape[-2:] # height, width + s = [1, 0.83, 0.67] # scales + f = [None, 3, None] # flips (2-ud, 3-lr) + y = [] # outputs + for si, fi in zip(s, f): + xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max())) + yi = self._forward_once(xi)[0] # forward + # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save + yi = self._descale_pred(yi, fi, si, img_size) + y.append(yi) + y = self._clip_augmented(y) # clip augmented tails + return torch.cat(y, 1), None # augmented inference, train + + def _forward_once(self, x, profile=False, visualize=False): + y, dt = [], [] # outputs + for m in self.model: + if m.f != -1: # if not from previous layer + x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers + if profile: + self._profile_one_layer(m, x, dt) + x = m(x) # run + y.append(x if m.i in self.save else None) # save output + if visualize: + feature_visualization(x, m.type, m.i, save_dir=visualize) + return x + + def _descale_pred(self, p, flips, scale, img_size): + # de-scale predictions following augmented inference (inverse operation) + if self.inplace: + p[..., :4] /= scale # de-scale + if flips == 2: + p[..., 1] = img_size[0] - p[..., 1] # de-flip ud + elif flips == 3: + p[..., 0] = img_size[1] - p[..., 0] # de-flip lr + else: + x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale + if flips == 2: + y = img_size[0] - y # de-flip ud + elif flips == 3: + x = img_size[1] - x # de-flip lr + p = torch.cat((x, y, wh, p[..., 4:]), -1) + return p + + def _clip_augmented(self, y): + # Clip YOLOv5 augmented inference tails + nl = self.model[-1].nl # number of detection layers (P3-P5) + g = sum(4 ** x for x in range(nl)) # grid points + e = 1 # exclude layer count + i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices + y[0] = y[0][:, :-i] # large + i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices + y[-1] = y[-1][:, i:] # small + return y + + def _profile_one_layer(self, m, x, dt): + c = isinstance(m, Detect) # is final layer, copy input as inplace fix + o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs + t = time_sync() + for _ in range(10): + m(x.copy() if c else x) + dt.append((time_sync() - t) * 100) + if m == self.model[0]: + LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}") + LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}') + if c: + LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total") + + def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency + # https://arxiv.org/abs/1708.02002 section 3.3 + # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1. + m = self.model[-1] # Detect() module + for mi, s in zip(m.m, m.stride): # from + b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85) + b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image) + b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls + mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True) + + def _print_biases(self): + m = self.model[-1] # Detect() module + for mi in m.m: # from + b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85) + LOGGER.info( + ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean())) + + # def _print_weights(self): + # for m in self.model.modules(): + # if type(m) is Bottleneck: + # LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights + + def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers + LOGGER.info('Fusing layers... ') + for m in self.model.modules(): + if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'): + m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv + delattr(m, 'bn') # remove batchnorm + m.forward = m.forward_fuse # update forward + self.info() + return self + + def info(self, verbose=False, img_size=640): # print model information + model_info(self, verbose, img_size) + + def _apply(self, fn): + # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers + self = super()._apply(fn) + m = self.model[-1] # Detect() + if isinstance(m, Detect): + m.stride = fn(m.stride) + m.grid = list(map(fn, m.grid)) + if isinstance(m.anchor_grid, list): + m.anchor_grid = list(map(fn, m.anchor_grid)) + return self + + +def parse_model(d, ch): # model_dict, input_channels(3) + LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}") + anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] + na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors + no = na * (nc + 5) # number of outputs = anchors * (classes + 5) + + layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out + for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args + m = eval(m) if isinstance(m, str) else m # eval strings + for j, a in enumerate(args): + try: + args[j] = eval(a) if isinstance(a, str) else a # eval strings + except NameError: + pass + + n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain + if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, + BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]: + c1, c2 = ch[f], args[0] + if c2 != no: # if not output + c2 = make_divisible(c2 * gw, 8) + + args = [c1, c2, *args[1:]] + if m in [BottleneckCSP, C3, C3TR, C3Ghost]: + args.insert(2, n) # number of repeats + n = 1 + elif m is nn.BatchNorm2d: + args = [ch[f]] + elif m is Concat: + c2 = sum(ch[x] for x in f) + elif m is Detect: + args.append([ch[x] for x in f]) + if isinstance(args[1], int): # number of anchors + args[1] = [list(range(args[1] * 2))] * len(f) + elif m is Contract: + c2 = ch[f] * args[0] ** 2 + elif m is Expand: + c2 = ch[f] // args[0] ** 2 + else: + c2 = ch[f] + + m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module + t = str(m)[8:-2].replace('__main__.', '') # module type + np = sum(x.numel() for x in m_.parameters()) # number params + m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params + LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print + save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist + layers.append(m_) + if i == 0: + ch = [] + ch.append(c2) + return nn.Sequential(*layers), sorted(save) + + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml') + parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--profile', action='store_true', help='profile model speed') + parser.add_argument('--test', action='store_true', help='test all yolo*.yaml') + opt = parser.parse_args() + opt.cfg = check_yaml(opt.cfg) # check YAML + print_args(FILE.stem, opt) + device = select_device(opt.device) + + # Create model + model = Model(opt.cfg).to(device) + model.train() + + # Profile + if opt.profile: + img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device) + y = model(img, profile=True) + + # Test all models + if opt.test: + for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'): + try: + _ = Model(cfg) + except Exception as e: + print(f'Error in {cfg}: {e}') + + # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898) + # from torch.utils.tensorboard import SummaryWriter + # tb_writer = SummaryWriter('.') + # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/") + # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph diff --git a/yolov5_Monocular_social_ranging/models/yolov5l.yaml b/yolov5_Monocular_social_ranging/models/yolov5l.yaml new file mode 100644 index 0000000..ce8a5de --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolov5l.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.0 # model depth multiple +width_multiple: 1.0 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/yolov5m.yaml b/yolov5_Monocular_social_ranging/models/yolov5m.yaml new file mode 100644 index 0000000..ad13ab3 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolov5m.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.67 # model depth multiple +width_multiple: 0.75 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/yolov5n.yaml b/yolov5_Monocular_social_ranging/models/yolov5n.yaml new file mode 100644 index 0000000..8a28a40 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolov5n.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.25 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/yolov5s.yaml b/yolov5_Monocular_social_ranging/models/yolov5s.yaml new file mode 100644 index 0000000..f35beab --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolov5s.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 0.33 # model depth multiple +width_multiple: 0.50 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/models/yolov5x.yaml b/yolov5_Monocular_social_ranging/models/yolov5x.yaml new file mode 100644 index 0000000..f617a02 --- /dev/null +++ b/yolov5_Monocular_social_ranging/models/yolov5x.yaml @@ -0,0 +1,48 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# Parameters +nc: 80 # number of classes +depth_multiple: 1.33 # model depth multiple +width_multiple: 1.25 # layer channel multiple +anchors: + - [10,13, 16,30, 33,23] # P3/8 + - [30,61, 62,45, 59,119] # P4/16 + - [116,90, 156,198, 373,326] # P5/32 + +# YOLOv5 v6.0 backbone +backbone: + # [from, number, module, args] + [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 + [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 + [-1, 3, C3, [128]], + [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 + [-1, 6, C3, [256]], + [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 + [-1, 9, C3, [512]], + [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 + [-1, 3, C3, [1024]], + [-1, 1, SPPF, [1024, 5]], # 9 + ] + +# YOLOv5 v6.0 head +head: + [[-1, 1, Conv, [512, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 6], 1, Concat, [1]], # cat backbone P4 + [-1, 3, C3, [512, False]], # 13 + + [-1, 1, Conv, [256, 1, 1]], + [-1, 1, nn.Upsample, [None, 2, 'nearest']], + [[-1, 4], 1, Concat, [1]], # cat backbone P3 + [-1, 3, C3, [256, False]], # 17 (P3/8-small) + + [-1, 1, Conv, [256, 3, 2]], + [[-1, 14], 1, Concat, [1]], # cat head P4 + [-1, 3, C3, [512, False]], # 20 (P4/16-medium) + + [-1, 1, Conv, [512, 3, 2]], + [[-1, 10], 1, Concat, [1]], # cat head P5 + [-1, 3, C3, [1024, False]], # 23 (P5/32-large) + + [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) + ] diff --git a/yolov5_Monocular_social_ranging/requirements.txt b/yolov5_Monocular_social_ranging/requirements.txt new file mode 100644 index 0000000..96fc9d1 --- /dev/null +++ b/yolov5_Monocular_social_ranging/requirements.txt @@ -0,0 +1,37 @@ +# pip install -r requirements.txt + +# Base ---------------------------------------- +matplotlib>=3.2.2 +numpy>=1.18.5 +opencv-python>=4.1.2 +Pillow>=7.1.2 +PyYAML>=5.3.1 +requests>=2.23.0 +scipy>=1.4.1 +torch>=1.7.0 +torchvision>=0.8.1 +tqdm>=4.41.0 + +# Logging ------------------------------------- +tensorboard>=2.4.1 +# wandb + +# Plotting ------------------------------------ +pandas>=1.1.4 +seaborn>=0.11.0 + +# Export -------------------------------------- +# coremltools>=4.1 # CoreML export +# onnx>=1.9.0 # ONNX export +# onnx-simplifier>=0.3.6 # ONNX simplifier +# scikit-learn==0.19.2 # CoreML quantization +# tensorflow>=2.4.1 # TFLite export +# tensorflowjs>=3.9.0 # TF.js export +# openvino-dev # OpenVINO export + +# Extras -------------------------------------- +# albumentations>=1.0.3 +# Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172 +# pycocotools>=2.0 # COCO mAP +# roboflow +thop # FLOPs computation diff --git a/yolov5_Monocular_social_ranging/setup.cfg b/yolov5_Monocular_social_ranging/setup.cfg new file mode 100644 index 0000000..20ea49a --- /dev/null +++ b/yolov5_Monocular_social_ranging/setup.cfg @@ -0,0 +1,45 @@ +# Project-wide configuration file, can be used for package metadata and other toll configurations +# Example usage: global configuration for PEP8 (via flake8) setting or default pytest arguments + +[metadata] +license_file = LICENSE +description-file = README.md + + +[tool:pytest] +norecursedirs = + .git + dist + build +addopts = + --doctest-modules + --durations=25 + --color=yes + + +[flake8] +max-line-length = 120 +exclude = .tox,*.egg,build,temp +select = E,W,F +doctests = True +verbose = 2 +# https://pep8.readthedocs.io/en/latest/intro.html#error-codes +format = pylint +# see: https://www.flake8rules.com/ +ignore = + E731 # Do not assign a lambda expression, use a def + F405 # name may be undefined, or defined from star imports: module + E402 # module level import not at top of file + F401 # module imported but unused + W504 # line break after binary operator + E127 # continuation line over-indented for visual indent + W504 # line break after binary operator + E231 # missing whitespace after ‘,’, ‘;’, or ‘:’ + E501 # line too long + F403 # ‘from module import *’ used; unable to detect undefined names + + +[isort] +# https://pycqa.github.io/isort/docs/configuration/options.html +line_length = 120 +multi_line_output = 0 diff --git a/yolov5_Monocular_social_ranging/train.py b/yolov5_Monocular_social_ranging/train.py new file mode 100644 index 0000000..d8df31b --- /dev/null +++ b/yolov5_Monocular_social_ranging/train.py @@ -0,0 +1,643 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Train a YOLOv5 model on a custom dataset. + +Models and datasets download automatically from the latest YOLOv5 release. +Models: https://github.com/ultralytics/yolov5/tree/master/models +Datasets: https://github.com/ultralytics/yolov5/tree/master/data +Tutorial: https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data + +Usage: + $ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640 # from pretrained (RECOMMENDED) + $ python path/to/train.py --data coco128.yaml --weights '' --cfg yolov5s.yaml --img 640 # from scratch +""" + +import argparse +import math +import os +import random +import sys +import time +from copy import deepcopy +from datetime import datetime +from pathlib import Path + +import numpy as np +import torch +import torch.distributed as dist +import torch.nn as nn +import yaml +from torch.cuda import amp +from torch.nn.parallel import DistributedDataParallel as DDP +from torch.optim import SGD, Adam, AdamW, lr_scheduler +from tqdm import tqdm + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[0] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative + +import val # for end-of-epoch mAP +from models.experimental import attempt_load +from models.yolo import Model +from utils.autoanchor import check_anchors +from utils.autobatch import check_train_batch_size +from utils.callbacks import Callbacks +from utils.datasets import create_dataloader +from utils.downloads import attempt_download +from utils.general import (LOGGER, check_dataset, check_file, check_git_status, check_img_size, check_requirements, + check_suffix, check_yaml, colorstr, get_latest_run, increment_path, init_seeds, + intersect_dicts, labels_to_class_weights, labels_to_image_weights, methods, one_cycle, + print_args, print_mutation, strip_optimizer) +from utils.loggers import Loggers +from utils.loggers.wandb.wandb_utils import check_wandb_resume +from utils.loss import ComputeLoss +from utils.metrics import fitness +from utils.plots import plot_evolve, plot_labels +from utils.torch_utils import EarlyStopping, ModelEMA, de_parallel, select_device, torch_distributed_zero_first + +LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html +RANK = int(os.getenv('RANK', -1)) +WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) + + +def train(hyp, # path/to/hyp.yaml or hyp dictionary + opt, + device, + callbacks + ): + save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze = \ + Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \ + opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze + + # Directories + w = save_dir / 'weights' # weights dir + (w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir + last, best = w / 'last.pt', w / 'best.pt' + + # Hyperparameters + if isinstance(hyp, str): + with open(hyp, errors='ignore') as f: + hyp = yaml.safe_load(f) # load hyps dict + LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items())) + + # Save run settings + if not evolve: + with open(save_dir / 'hyp.yaml', 'w') as f: + yaml.safe_dump(hyp, f, sort_keys=False) + with open(save_dir / 'opt.yaml', 'w') as f: + yaml.safe_dump(vars(opt), f, sort_keys=False) + + # Loggers + data_dict = None + if RANK in [-1, 0]: + loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance + if loggers.wandb: + data_dict = loggers.wandb.data_dict + if resume: + weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size + + # Register actions + for k in methods(loggers): + callbacks.register_action(k, callback=getattr(loggers, k)) + + # Config + plots = not evolve # create plots + cuda = device.type != 'cpu' + init_seeds(1 + RANK) + with torch_distributed_zero_first(LOCAL_RANK): + data_dict = data_dict or check_dataset(data) # check if None + train_path, val_path = data_dict['train'], data_dict['val'] + nc = 1 if single_cls else int(data_dict['nc']) # number of classes + names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names + assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # check + is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO dataset + + # Model + check_suffix(weights, '.pt') # check weights + pretrained = weights.endswith('.pt') + if pretrained: + with torch_distributed_zero_first(LOCAL_RANK): + weights = attempt_download(weights) # download if not found locally + ckpt = torch.load(weights, map_location='cpu') # load checkpoint to CPU to avoid CUDA memory leak + model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create + exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys + csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 + csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect + model.load_state_dict(csd, strict=False) # load + LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report + else: + model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create + + # Freeze + freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # layers to freeze + for k, v in model.named_parameters(): + v.requires_grad = True # train all layers + if any(x in k for x in freeze): + LOGGER.info(f'freezing {k}') + v.requires_grad = False + + # Image size + gs = max(int(model.stride.max()), 32) # grid size (max stride) + imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple + + # Batch size + if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size + batch_size = check_train_batch_size(model, imgsz) + loggers.on_params_update({"batch_size": batch_size}) + + # Optimizer + nbs = 64 # nominal batch size + accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing + hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay + LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}") + + g0, g1, g2 = [], [], [] # optimizer parameter groups + for v in model.modules(): + if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias + g2.append(v.bias) + if isinstance(v, nn.BatchNorm2d): # weight (no decay) + g0.append(v.weight) + elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay) + g1.append(v.weight) + + if opt.optimizer == 'Adam': + optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum + elif opt.optimizer == 'AdamW': + optimizer = AdamW(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum + else: + optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True) + + optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay + optimizer.add_param_group({'params': g2}) # add g2 (biases) + LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups " + f"{len(g0)} weight (no decay), {len(g1)} weight, {len(g2)} bias") + del g0, g1, g2 + + # Scheduler + if opt.cos_lr: + lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf'] + else: + lf = lambda x: (1 - x / epochs) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear + scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs) + + # EMA + ema = ModelEMA(model) if RANK in [-1, 0] else None + + # Resume + start_epoch, best_fitness = 0, 0.0 + if pretrained: + # Optimizer + if ckpt['optimizer'] is not None: + optimizer.load_state_dict(ckpt['optimizer']) + best_fitness = ckpt['best_fitness'] + + # EMA + if ema and ckpt.get('ema'): + ema.ema.load_state_dict(ckpt['ema'].float().state_dict()) + ema.updates = ckpt['updates'] + + # Epochs + start_epoch = ckpt['epoch'] + 1 + if resume: + assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.' + if epochs < start_epoch: + LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.") + epochs += ckpt['epoch'] # finetune additional epochs + + del ckpt, csd + + # DP mode + if cuda and RANK == -1 and torch.cuda.device_count() > 1: + LOGGER.warning('WARNING: DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n' + 'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.') + model = torch.nn.DataParallel(model) + + # SyncBatchNorm + if opt.sync_bn and cuda and RANK != -1: + model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device) + LOGGER.info('Using SyncBatchNorm()') + + # Trainloader + train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls, + hyp=hyp, augment=True, cache=None if opt.cache == 'val' else opt.cache, + rect=opt.rect, rank=LOCAL_RANK, workers=workers, + image_weights=opt.image_weights, quad=opt.quad, + prefix=colorstr('train: '), shuffle=True) + mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max()) # max label class + nb = len(train_loader) # number of batches + assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}' + + # Process 0 + if RANK in [-1, 0]: + val_loader = create_dataloader(val_path, imgsz, batch_size // WORLD_SIZE * 2, gs, single_cls, + hyp=hyp, cache=None if noval else opt.cache, + rect=True, rank=-1, workers=workers * 2, pad=0.5, + prefix=colorstr('val: '))[0] + + if not resume: + labels = np.concatenate(dataset.labels, 0) + # c = torch.tensor(labels[:, 0]) # classes + # cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency + # model._initialize_biases(cf.to(device)) + if plots: + plot_labels(labels, names, save_dir) + + # Anchors + if not opt.noautoanchor: + check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz) + model.half().float() # pre-reduce anchor precision + + callbacks.run('on_pretrain_routine_end') + + # DDP mode + if cuda and RANK != -1: + model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK) + + # Model attributes + nl = de_parallel(model).model[-1].nl # number of detection layers (to scale hyps) + hyp['box'] *= 3 / nl # scale to layers + hyp['cls'] *= nc / 80 * 3 / nl # scale to classes and layers + hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers + hyp['label_smoothing'] = opt.label_smoothing + model.nc = nc # attach number of classes to model + model.hyp = hyp # attach hyperparameters to model + model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights + model.names = names + + # Start training + t0 = time.time() + nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations) + # nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training + last_opt_step = -1 + maps = np.zeros(nc) # mAP per class + results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls) + scheduler.last_epoch = start_epoch - 1 # do not move + scaler = amp.GradScaler(enabled=cuda) + stopper = EarlyStopping(patience=opt.patience) + compute_loss = ComputeLoss(model) # init loss class + LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n' + f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n' + f"Logging results to {colorstr('bold', save_dir)}\n" + f'Starting training for {epochs} epochs...') + for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------ + model.train() + + # Update image weights (optional, single-GPU only) + if opt.image_weights: + cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights + iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights + dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx + + # Update mosaic border (optional) + # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs) + # dataset.mosaic_border = [b - imgsz, -b] # height, width borders + + mloss = torch.zeros(3, device=device) # mean losses + if RANK != -1: + train_loader.sampler.set_epoch(epoch) + pbar = enumerate(train_loader) + LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size')) + if RANK in [-1, 0]: + pbar = tqdm(pbar, total=nb, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar + optimizer.zero_grad() + for i, (imgs, targets, paths, _) in pbar: # batch ------------------------------------------------------------- + ni = i + nb * epoch # number integrated batches (since train start) + imgs = imgs.to(device, non_blocking=True).float() / 255 # uint8 to float32, 0-255 to 0.0-1.0 + + # Warmup + if ni <= nw: + xi = [0, nw] # x interp + # compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou) + accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round()) + for j, x in enumerate(optimizer.param_groups): + # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0 + x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)]) + if 'momentum' in x: + x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']]) + + # Multi-scale + if opt.multi_scale: + sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size + sf = sz / max(imgs.shape[2:]) # scale factor + if sf != 1: + ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple) + imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False) + + # Forward + with amp.autocast(enabled=cuda): + pred = model(imgs) # forward + loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size + if RANK != -1: + loss *= WORLD_SIZE # gradient averaged between devices in DDP mode + if opt.quad: + loss *= 4. + + # Backward + scaler.scale(loss).backward() + + # Optimize + if ni - last_opt_step >= accumulate: + scaler.step(optimizer) # optimizer.step + scaler.update() + optimizer.zero_grad() + if ema: + ema.update(model) + last_opt_step = ni + + # Log + if RANK in [-1, 0]: + mloss = (mloss * i + loss_items) / (i + 1) # update mean losses + mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB) + pbar.set_description(('%10s' * 2 + '%10.4g' * 5) % ( + f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1])) + callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots, opt.sync_bn) + if callbacks.stop_training: + return + # end batch ------------------------------------------------------------------------------------------------ + + # Scheduler + lr = [x['lr'] for x in optimizer.param_groups] # for loggers + scheduler.step() + + if RANK in [-1, 0]: + # mAP + callbacks.run('on_train_epoch_end', epoch=epoch) + ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights']) + final_epoch = (epoch + 1 == epochs) or stopper.possible_stop + if not noval or final_epoch: # Calculate mAP + results, maps, _ = val.run(data_dict, + batch_size=batch_size // WORLD_SIZE * 2, + imgsz=imgsz, + model=ema.ema, + single_cls=single_cls, + dataloader=val_loader, + save_dir=save_dir, + plots=False, + callbacks=callbacks, + compute_loss=compute_loss) + + # Update best mAP + fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95] + if fi > best_fitness: + best_fitness = fi + log_vals = list(mloss) + list(results) + lr + callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi) + + # Save model + if (not nosave) or (final_epoch and not evolve): # if save + ckpt = {'epoch': epoch, + 'best_fitness': best_fitness, + 'model': deepcopy(de_parallel(model)).half(), + 'ema': deepcopy(ema.ema).half(), + 'updates': ema.updates, + 'optimizer': optimizer.state_dict(), + 'wandb_id': loggers.wandb.wandb_run.id if loggers.wandb else None, + 'date': datetime.now().isoformat()} + + # Save last, best and delete + torch.save(ckpt, last) + if best_fitness == fi: + torch.save(ckpt, best) + if (epoch > 0) and (opt.save_period > 0) and (epoch % opt.save_period == 0): + torch.save(ckpt, w / f'epoch{epoch}.pt') + del ckpt + callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi) + + # Stop Single-GPU + if RANK == -1 and stopper(epoch=epoch, fitness=fi): + break + + # Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576 + # stop = stopper(epoch=epoch, fitness=fi) + # if RANK == 0: + # dist.broadcast_object_list([stop], 0) # broadcast 'stop' to all ranks + + # Stop DPP + # with torch_distributed_zero_first(RANK): + # if stop: + # break # must break all DDP ranks + + # end epoch ---------------------------------------------------------------------------------------------------- + # end training ----------------------------------------------------------------------------------------------------- + if RANK in [-1, 0]: + LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.') + for f in last, best: + if f.exists(): + strip_optimizer(f) # strip optimizers + if f is best: + LOGGER.info(f'\nValidating {f}...') + results, _, _ = val.run(data_dict, + batch_size=batch_size // WORLD_SIZE * 2, + imgsz=imgsz, + model=attempt_load(f, device).half(), + iou_thres=0.65 if is_coco else 0.60, # best pycocotools results at 0.65 + single_cls=single_cls, + dataloader=val_loader, + save_dir=save_dir, + save_json=is_coco, + verbose=True, + plots=True, + callbacks=callbacks, + compute_loss=compute_loss) # val best model with plots + if is_coco: + callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi) + + callbacks.run('on_train_end', last, best, plots, epoch, results) + LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}") + + torch.cuda.empty_cache() + return results + + +def parse_opt(known=False): + parser = argparse.ArgumentParser() + parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path') + parser.add_argument('--cfg', type=str, default='', help='model.yaml path') + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') + parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path') + parser.add_argument('--epochs', type=int, default=300) + parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch') + parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)') + parser.add_argument('--rect', action='store_true', help='rectangular training') + parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training') + parser.add_argument('--nosave', action='store_true', help='only save final checkpoint') + parser.add_argument('--noval', action='store_true', help='only validate final epoch') + parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor') + parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations') + parser.add_argument('--bucket', type=str, default='', help='gsutil bucket') + parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"') + parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training') + parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%') + parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class') + parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer') + parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode') + parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)') + parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name') + parser.add_argument('--name', default='exp', help='save to project/name') + parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') + parser.add_argument('--quad', action='store_true', help='quad dataloader') + parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler') + parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon') + parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)') + parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2') + parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)') + parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify') + + # Weights & Biases arguments + parser.add_argument('--entity', default=None, help='W&B: Entity') + parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option') + parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval') + parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use') + + opt = parser.parse_known_args()[0] if known else parser.parse_args() + return opt + + +def main(opt, callbacks=Callbacks()): + # Checks + if RANK in [-1, 0]: + print_args(FILE.stem, opt) + check_git_status() + check_requirements(exclude=['thop']) + + # Resume + if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run + ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path + assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist' + with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f: + opt = argparse.Namespace(**yaml.safe_load(f)) # replace + opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate + LOGGER.info(f'Resuming training from {ckpt}') + else: + opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \ + check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks + assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified' + if opt.evolve: + if opt.project == str(ROOT / 'runs/train'): # if default project name, rename to runs/evolve + opt.project = str(ROOT / 'runs/evolve') + opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume + opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) + + # DDP mode + device = select_device(opt.device, batch_size=opt.batch_size) + if LOCAL_RANK != -1: + msg = 'is not compatible with YOLOv5 Multi-GPU DDP training' + assert not opt.image_weights, f'--image-weights {msg}' + assert not opt.evolve, f'--evolve {msg}' + assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size' + assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE' + assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command' + torch.cuda.set_device(LOCAL_RANK) + device = torch.device('cuda', LOCAL_RANK) + dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo") + + # Train + if not opt.evolve: + train(opt.hyp, opt, device, callbacks) + if WORLD_SIZE > 1 and RANK == 0: + LOGGER.info('Destroying process group... ') + dist.destroy_process_group() + + # Evolve hyperparameters (optional) + else: + # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit) + meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3) + 'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf) + 'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1 + 'weight_decay': (1, 0.0, 0.001), # optimizer weight decay + 'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok) + 'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum + 'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr + 'box': (1, 0.02, 0.2), # box loss gain + 'cls': (1, 0.2, 4.0), # cls loss gain + 'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight + 'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels) + 'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight + 'iou_t': (0, 0.1, 0.7), # IoU training threshold + 'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold + 'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore) + 'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5) + 'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction) + 'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction) + 'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction) + 'degrees': (1, 0.0, 45.0), # image rotation (+/- deg) + 'translate': (1, 0.0, 0.9), # image translation (+/- fraction) + 'scale': (1, 0.0, 0.9), # image scale (+/- gain) + 'shear': (1, 0.0, 10.0), # image shear (+/- deg) + 'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001 + 'flipud': (1, 0.0, 1.0), # image flip up-down (probability) + 'fliplr': (0, 0.0, 1.0), # image flip left-right (probability) + 'mosaic': (1, 0.0, 1.0), # image mixup (probability) + 'mixup': (1, 0.0, 1.0), # image mixup (probability) + 'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability) + + with open(opt.hyp, errors='ignore') as f: + hyp = yaml.safe_load(f) # load hyps dict + if 'anchors' not in hyp: # anchors commented in hyp.yaml + hyp['anchors'] = 3 + opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch + # ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices + evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv' + if opt.bucket: + os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {evolve_csv}') # download evolve.csv if exists + + for _ in range(opt.evolve): # generations to evolve + if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate + # Select parent(s) + parent = 'single' # parent selection method: 'single' or 'weighted' + x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1) + n = min(5, len(x)) # number of previous results to consider + x = x[np.argsort(-fitness(x))][:n] # top n mutations + w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0) + if parent == 'single' or len(x) == 1: + # x = x[random.randint(0, n - 1)] # random selection + x = x[random.choices(range(n), weights=w)[0]] # weighted selection + elif parent == 'weighted': + x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination + + # Mutate + mp, s = 0.8, 0.2 # mutation probability, sigma + npr = np.random + npr.seed(int(time.time())) + g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1 + ng = len(meta) + v = np.ones(ng) + while all(v == 1): # mutate until a change occurs (prevent duplicates) + v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0) + for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300) + hyp[k] = float(x[i + 7] * v[i]) # mutate + + # Constrain to limits + for k, v in meta.items(): + hyp[k] = max(hyp[k], v[1]) # lower limit + hyp[k] = min(hyp[k], v[2]) # upper limit + hyp[k] = round(hyp[k], 5) # significant digits + + # Train mutation + results = train(hyp.copy(), opt, device, callbacks) + callbacks = Callbacks() + # Write mutation results + print_mutation(results, hyp.copy(), save_dir, opt.bucket) + + # Plot results + plot_evolve(evolve_csv) + LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n' + f"Results saved to {colorstr('bold', save_dir)}\n" + f'Usage example: $ python train.py --hyp {evolve_yaml}') + + +def run(**kwargs): + # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt') + opt = parse_opt(True) + for k, v in kwargs.items(): + setattr(opt, k, v) + main(opt) + return opt + + +if __name__ == "__main__": + opt = parse_opt() + main(opt) diff --git a/yolov5_Monocular_social_ranging/tutorial.ipynb b/yolov5_Monocular_social_ranging/tutorial.ipynb new file mode 100644 index 0000000..09b2b33 --- /dev/null +++ b/yolov5_Monocular_social_ranging/tutorial.ipynb @@ -0,0 +1,1102 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "YOLOv5 Tutorial", + "provenance": [], + "collapsed_sections": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "eb95db7cae194218b3fcefb439b6352f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "HBoxView", + "_dom_classes": [], + "_model_name": "HBoxModel", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_view_count": null, + "_view_module_version": "1.5.0", + "box_style": "", + "layout": "IPY_MODEL_769ecde6f2e64bacb596ce972f8d3d2d", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_384a001876054c93b0af45cd1e960bfe", + "IPY_MODEL_dded0aeae74440f7ba2ffa0beb8dd612", + "IPY_MODEL_5296d28be75740b2892ae421bbec3657" + ] + } + }, + "769ecde6f2e64bacb596ce972f8d3d2d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_view_name": "LayoutView", + "grid_template_rows": null, + "right": null, + "justify_content": null, + "_view_module": "@jupyter-widgets/base", + "overflow": null, + "_model_module_version": "1.2.0", + "_view_count": null, + "flex_flow": null, + "width": null, + "min_width": null, + "border": null, + "align_items": null, + "bottom": null, + "_model_module": "@jupyter-widgets/base", + "top": null, + "grid_column": null, + "overflow_y": null, + "overflow_x": null, + "grid_auto_flow": null, + "grid_area": null, + "grid_template_columns": null, + "flex": null, + "_model_name": "LayoutModel", + "justify_items": null, + "grid_row": null, + "max_height": null, + "align_content": null, + "visibility": null, + "align_self": null, + "height": null, + "min_height": null, + "padding": null, + "grid_auto_rows": null, + "grid_gap": null, + "max_width": null, + "order": null, + "_view_module_version": "1.2.0", + "grid_template_areas": null, + "object_position": null, + "object_fit": null, + "grid_auto_columns": null, + "margin": null, + "display": null, + "left": null + } + }, + "384a001876054c93b0af45cd1e960bfe": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_9f09facb2a6c4a7096810d327c8b551c", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": "100%", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_25621cff5d16448cb7260e839fd0f543" + } + }, + "dded0aeae74440f7ba2ffa0beb8dd612": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_0ce7164fc0c74bb9a2b5c7037375a727", + "_dom_classes": [], + "description": "", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 818322941, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 818322941, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_c4c4593c10904cb5b8a5724d60c7e181" + } + }, + "5296d28be75740b2892ae421bbec3657": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_473371611126476c88d5d42ec7031ed6", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 780M/780M [00:11<00:00, 91.9MB/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_65efdfd0d26c46e79c8c5ff3b77126cc" + } + }, + "9f09facb2a6c4a7096810d327c8b551c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "StyleView", + "_model_name": "DescriptionStyleModel", + "description_width": "", + "_view_module": "@jupyter-widgets/base", + "_model_module_version": "1.5.0", + "_view_count": null, + "_view_module_version": "1.2.0", + "_model_module": "@jupyter-widgets/controls" + } + }, + "25621cff5d16448cb7260e839fd0f543": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_view_name": "LayoutView", + "grid_template_rows": null, + "right": null, + "justify_content": null, + "_view_module": "@jupyter-widgets/base", + "overflow": null, + "_model_module_version": "1.2.0", + "_view_count": null, + "flex_flow": null, + "width": null, + "min_width": null, + "border": null, + "align_items": null, + "bottom": null, + "_model_module": "@jupyter-widgets/base", + "top": null, + "grid_column": null, + "overflow_y": null, + "overflow_x": null, + "grid_auto_flow": null, + "grid_area": null, + "grid_template_columns": null, + "flex": null, + "_model_name": "LayoutModel", + "justify_items": null, + "grid_row": null, + "max_height": null, + "align_content": null, + "visibility": null, + "align_self": null, + "height": null, + "min_height": null, + "padding": null, + "grid_auto_rows": null, + "grid_gap": null, + "max_width": null, + "order": null, + "_view_module_version": "1.2.0", + "grid_template_areas": null, + "object_position": null, + "object_fit": null, + "grid_auto_columns": null, + "margin": null, + "display": null, + "left": null + } + }, + "0ce7164fc0c74bb9a2b5c7037375a727": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "StyleView", + "_model_name": "ProgressStyleModel", + "description_width": "", + "_view_module": "@jupyter-widgets/base", + "_model_module_version": "1.5.0", + "_view_count": null, + "_view_module_version": "1.2.0", + "bar_color": null, + "_model_module": "@jupyter-widgets/controls" + } + }, + "c4c4593c10904cb5b8a5724d60c7e181": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_view_name": "LayoutView", + "grid_template_rows": null, + "right": null, + "justify_content": null, + "_view_module": "@jupyter-widgets/base", + "overflow": null, + "_model_module_version": "1.2.0", + "_view_count": null, + "flex_flow": null, + "width": null, + "min_width": null, + "border": null, + "align_items": null, + "bottom": null, + "_model_module": "@jupyter-widgets/base", + "top": null, + "grid_column": null, + "overflow_y": null, + "overflow_x": null, + "grid_auto_flow": null, + "grid_area": null, + "grid_template_columns": null, + "flex": null, + "_model_name": "LayoutModel", + "justify_items": null, + "grid_row": null, + "max_height": null, + "align_content": null, + "visibility": null, + "align_self": null, + "height": null, + "min_height": null, + "padding": null, + "grid_auto_rows": null, + "grid_gap": null, + "max_width": null, + "order": null, + "_view_module_version": "1.2.0", + "grid_template_areas": null, + "object_position": null, + "object_fit": null, + "grid_auto_columns": null, + "margin": null, + "display": null, + "left": null + } + }, + "473371611126476c88d5d42ec7031ed6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_view_name": "StyleView", + "_model_name": "DescriptionStyleModel", + "description_width": "", + "_view_module": "@jupyter-widgets/base", + "_model_module_version": "1.5.0", + "_view_count": null, + "_view_module_version": "1.2.0", + "_model_module": "@jupyter-widgets/controls" + } + }, + "65efdfd0d26c46e79c8c5ff3b77126cc": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_view_name": "LayoutView", + "grid_template_rows": null, + "right": null, + "justify_content": null, + "_view_module": "@jupyter-widgets/base", + "overflow": null, + "_model_module_version": "1.2.0", + "_view_count": null, + "flex_flow": null, + "width": null, + "min_width": null, + "border": null, + "align_items": null, + "bottom": null, + "_model_module": "@jupyter-widgets/base", + "top": null, + "grid_column": null, + "overflow_y": null, + "overflow_x": null, + "grid_auto_flow": null, + "grid_area": null, + "grid_template_columns": null, + "flex": null, + "_model_name": "LayoutModel", + "justify_items": null, + "grid_row": null, + "max_height": null, + "align_content": null, + "visibility": null, + "align_self": null, + "height": null, + "min_height": null, + "padding": null, + "grid_auto_rows": null, + "grid_gap": null, + "max_width": null, + "order": null, + "_view_module_version": "1.2.0", + "grid_template_areas": null, + "object_position": null, + "object_fit": null, + "grid_auto_columns": null, + "margin": null, + "display": null, + "left": null + } + } + } + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "t6MPjfT5NrKQ" + }, + "source": [ + "\n", + "\n", + "\n", + "This is the **official YOLOv5 🚀 notebook** by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n", + "For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7mGmQbAO5pQb" + }, + "source": [ + "# Setup\n", + "\n", + "Clone repo, install dependencies and check PyTorch and GPU." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "wbvMlHd_QwMG", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "3809e5a9-dd41-4577-fe62-5531abf7cca2" + }, + "source": [ + "!git clone https://github.com/ultralytics/yolov5 # clone\n", + "%cd yolov5\n", + "%pip install -qr requirements.txt # install\n", + "\n", + "import torch\n", + "from yolov5 import utils\n", + "display = utils.notebook_init() # checks" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", + "Setup complete ✅\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4JnkELT0cIJg" + }, + "source": [ + "# 1. Inference\n", + "\n", + "`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n", + "\n", + "```shell\n", + "python detect.py --source 0 # webcam\n", + " img.jpg # image \n", + " vid.mp4 # video\n", + " path/ # directory\n", + " path/*.jpg # glob\n", + " 'https://youtu.be/Zgi9g1ksQHc' # YouTube\n", + " 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream\n", + "```" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "zR9ZbuQCH7FX", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "8f7e6588-215d-4ebd-93af-88b871e770a7" + }, + "source": [ + "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n", + "display.Image(filename='runs/detect/exp/zidane.jpg', width=600)" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n", + "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", + "\n", + "Fusing layers... \n", + "Model Summary: 213 layers, 7225885 parameters, 0 gradients\n", + "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.007s)\n", + "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.007s)\n", + "Speed: 0.5ms pre-process, 6.9ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n", + "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "hkAzDWJ7cWTr" + }, + "source": [ + "        \n", + "" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0eq1SMWl6Sfn" + }, + "source": [ + "# 2. Validate\n", + "Validate a model's accuracy on [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "eyTZYGgRjnMc" + }, + "source": [ + "## COCO val\n", + "Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "WQPtK1QYVaD_", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 48, + "referenced_widgets": [ + "eb95db7cae194218b3fcefb439b6352f", + "769ecde6f2e64bacb596ce972f8d3d2d", + "384a001876054c93b0af45cd1e960bfe", + "dded0aeae74440f7ba2ffa0beb8dd612", + "5296d28be75740b2892ae421bbec3657", + "9f09facb2a6c4a7096810d327c8b551c", + "25621cff5d16448cb7260e839fd0f543", + "0ce7164fc0c74bb9a2b5c7037375a727", + "c4c4593c10904cb5b8a5724d60c7e181", + "473371611126476c88d5d42ec7031ed6", + "65efdfd0d26c46e79c8c5ff3b77126cc" + ] + }, + "outputId": "bcf9a448-1f9b-4a41-ad49-12f181faf05a" + }, + "source": [ + "# Download COCO val\n", + "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n", + "!unzip -q tmp.zip -d ../datasets && rm tmp.zip" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "eb95db7cae194218b3fcefb439b6352f", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + " 0%| | 0.00/780M [00:00

\n", + "Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n", + "

\n", + "\n", + "Train a YOLOv5s model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`.\n", + "\n", + "- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n", + "automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n", + "- **[Datasets](https://github.com/ultralytics/yolov5/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov5/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov5/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov5/blob/master/data/SKU-110K.yaml).\n", + "- **Training Results** are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n", + "

\n", + "\n", + "## Train on Custom Data with Roboflow 🌟 NEW\n", + "\n", + "[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n", + "\n", + "- Custom Training Example: [https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/](https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/?ref=ultralytics)\n", + "- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb)\n", + "
\n", + "\n", + "

Label images lightning fast (including with model-assisted labeling)" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "bOy5KI2ncnWd" + }, + "source": [ + "# Tensorboard (optional)\n", + "%load_ext tensorboard\n", + "%tensorboard --logdir runs/train" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "2fLAV42oNb7M" + }, + "source": [ + "# Weights & Biases (optional)\n", + "%pip install -q wandb\n", + "import wandb\n", + "wandb.login()" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "1NcFxRcFdJ_O", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "8724d13d-6711-4a12-d96a-1c655e5c3549" + }, + "source": [ + "# Train YOLOv5s on COCO128 for 3 epochs\n", + "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n", + "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n", + "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", + "\n", + "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n", + "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n", + "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n", + "\n", + " from n params module arguments \n", + " 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n", + " 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n", + " 2 -1 1 18816 models.common.C3 [64, 64, 1] \n", + " 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n", + " 4 -1 2 115712 models.common.C3 [128, 128, 2] \n", + " 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n", + " 6 -1 3 625152 models.common.C3 [256, 256, 3] \n", + " 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n", + " 8 -1 1 1182720 models.common.C3 [512, 512, 1] \n", + " 9 -1 1 656896 models.common.SPPF [512, 512, 5] \n", + " 10 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n", + " 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", + " 12 [-1, 6] 1 0 models.common.Concat [1] \n", + " 13 -1 1 361984 models.common.C3 [512, 256, 1, False] \n", + " 14 -1 1 33024 models.common.Conv [256, 128, 1, 1] \n", + " 15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", + " 16 [-1, 4] 1 0 models.common.Concat [1] \n", + " 17 -1 1 90880 models.common.C3 [256, 128, 1, False] \n", + " 18 -1 1 147712 models.common.Conv [128, 128, 3, 2] \n", + " 19 [-1, 14] 1 0 models.common.Concat [1] \n", + " 20 -1 1 296448 models.common.C3 [256, 256, 1, False] \n", + " 21 -1 1 590336 models.common.Conv [256, 256, 3, 2] \n", + " 22 [-1, 10] 1 0 models.common.Concat [1] \n", + " 23 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n", + " 24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n", + "Model Summary: 270 layers, 7235389 parameters, 7235389 gradients, 16.5 GFLOPs\n", + "\n", + "Transferred 349/349 items from yolov5s.pt\n", + "Scaled weight_decay = 0.0005\n", + "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight, 60 weight (no decay), 60 bias\n", + "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n", + "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00\"Weights

" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-WPvRbS5Swl6" + }, + "source": [ + "## Local Logging\n", + "\n", + "All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics **Mosaic Dataloader** is used for training (shown below), which combines 4 images into 1 mosaic during training.\n", + "\n", + "> \n", + "`train_batch0.jpg` shows train batch 0 mosaics and labels\n", + "\n", + "> \n", + "`test_batch0_labels.jpg` shows val batch 0 labels\n", + "\n", + "> \n", + "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n", + "\n", + "Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n", + "\n", + "```python\n", + "from utils.plots import plot_results \n", + "plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png'\n", + "```\n", + "\n", + "\"COCO128" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Zelyeqbyt3GD" + }, + "source": [ + "# Environments\n", + "\n", + "YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n", + "\n", + "- **Google Colab and Kaggle** notebooks with free GPU: \"Open \"Open\n", + "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n", + "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n", + "- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) \"Docker\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6Qu7Iesl0p54" + }, + "source": [ + "# Status\n", + "\n", + "![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n", + "\n", + "If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "IEijrePND_2I" + }, + "source": [ + "# Appendix\n", + "\n", + "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "mcKoSIK2WSzj" + }, + "source": [ + "# Reproduce\n", + "for x in 'yolov5n', 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n", + " !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # speed\n", + " !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "GMusP4OAxFu6" + }, + "source": [ + "# PyTorch Hub\n", + "import torch\n", + "\n", + "# Model\n", + "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n", + "\n", + "# Images\n", + "dir = 'https://ultralytics.com/images/'\n", + "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images\n", + "\n", + "# Inference\n", + "results = model(imgs)\n", + "results.print() # or .show(), .save()" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "FGH0ZjkGjejy" + }, + "source": [ + "# CI Checks\n", + "%%shell\n", + "export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n", + "rm -rf runs # remove runs/\n", + "for m in yolov5n; do # models\n", + " python train.py --img 64 --batch 32 --weights $m.pt --epochs 1 --device 0 # train pretrained\n", + " python train.py --img 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device 0 # train scratch\n", + " for d in 0 cpu; do # devices\n", + " python val.py --weights $m.pt --device $d # val official\n", + " python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n", + " python detect.py --weights $m.pt --device $d # detect official\n", + " python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n", + " done\n", + " python hubconf.py # hub\n", + " python models/yolo.py --cfg $m.yaml # build PyTorch model\n", + " python models/tf.py --weights $m.pt # build TensorFlow model\n", + " python export.py --img 64 --batch 1 --weights $m.pt --include torchscript onnx # export\n", + "done" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "gogI-kwi3Tye" + }, + "source": [ + "# Profile\n", + "from utils.torch_utils import profile\n", + "\n", + "m1 = lambda x: x * torch.sigmoid(x)\n", + "m2 = torch.nn.SiLU()\n", + "results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "RVRSOhEvUdb5" + }, + "source": [ + "# Evolve\n", + "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n", + "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket # upload results (optional)" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "BSgFCAcMbk1R" + }, + "source": [ + "# VOC\n", + "for b, m in zip([64, 64, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']): # zip(batch_size, model)\n", + " !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "VTRwsvA9u7ln" + }, + "source": [ + "# TensorRT \n", + "# https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip\n", + "!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # install\n", + "!python export.py --weights yolov5s.pt --include engine --imgsz 640 640 --device 0 # export\n", + "!python detect.py --weights yolov5s.engine --imgsz 640 640 --device 0 # inference" + ], + "execution_count": null, + "outputs": [] + } + ] +} diff --git a/yolov5_Monocular_social_ranging/utils/__init__.py b/yolov5_Monocular_social_ranging/utils/__init__.py new file mode 100644 index 0000000..295aebf --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/__init__.py @@ -0,0 +1,37 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +utils/initialization +""" + + +def notebook_init(verbose=True): + # Check system software and hardware + print('Checking setup...') + + import os + import shutil + + from utils.general import check_requirements, emojis, is_colab + from utils.torch_utils import select_device # imports + + check_requirements(('psutil', 'IPython')) + import psutil + from IPython import display # to display images and clear console output + + if is_colab(): + shutil.rmtree('/content/sample_data', ignore_errors=True) # remove colab /sample_data directory + + if verbose: + # System info + # gb = 1 / 1000 ** 3 # bytes to GB + gib = 1 / 1024 ** 3 # bytes to GiB + ram = psutil.virtual_memory().total + total, used, free = shutil.disk_usage("/") + display.clear_output() + s = f'({os.cpu_count()} CPUs, {ram * gib:.1f} GB RAM, {(total - free) * gib:.1f}/{total * gib:.1f} GB disk)' + else: + s = '' + + select_device(newline=False) + print(emojis(f'Setup complete ✅ {s}')) + return display diff --git a/yolov5_Monocular_social_ranging/utils/activations.py b/yolov5_Monocular_social_ranging/utils/activations.py new file mode 100644 index 0000000..a4ff789 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/activations.py @@ -0,0 +1,101 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Activation functions +""" + +import torch +import torch.nn as nn +import torch.nn.functional as F + + +# SiLU https://arxiv.org/pdf/1606.08415.pdf ---------------------------------------------------------------------------- +class SiLU(nn.Module): # export-friendly version of nn.SiLU() + @staticmethod + def forward(x): + return x * torch.sigmoid(x) + + +class Hardswish(nn.Module): # export-friendly version of nn.Hardswish() + @staticmethod + def forward(x): + # return x * F.hardsigmoid(x) # for TorchScript and CoreML + return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for TorchScript, CoreML and ONNX + + +# Mish https://github.com/digantamisra98/Mish -------------------------------------------------------------------------- +class Mish(nn.Module): + @staticmethod + def forward(x): + return x * F.softplus(x).tanh() + + +class MemoryEfficientMish(nn.Module): + class F(torch.autograd.Function): + @staticmethod + def forward(ctx, x): + ctx.save_for_backward(x) + return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) + + @staticmethod + def backward(ctx, grad_output): + x = ctx.saved_tensors[0] + sx = torch.sigmoid(x) + fx = F.softplus(x).tanh() + return grad_output * (fx + x * sx * (1 - fx * fx)) + + def forward(self, x): + return self.F.apply(x) + + +# FReLU https://arxiv.org/abs/2007.11824 ------------------------------------------------------------------------------- +class FReLU(nn.Module): + def __init__(self, c1, k=3): # ch_in, kernel + super().__init__() + self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False) + self.bn = nn.BatchNorm2d(c1) + + def forward(self, x): + return torch.max(x, self.bn(self.conv(x))) + + +# ACON https://arxiv.org/pdf/2009.04759.pdf ---------------------------------------------------------------------------- +class AconC(nn.Module): + r""" ACON activation (activate or not). + AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter + according to "Activate or Not: Learning Customized Activation" . + """ + + def __init__(self, c1): + super().__init__() + self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) + self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) + self.beta = nn.Parameter(torch.ones(1, c1, 1, 1)) + + def forward(self, x): + dpx = (self.p1 - self.p2) * x + return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x + + +class MetaAconC(nn.Module): + r""" ACON activation (activate or not). + MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network + according to "Activate or Not: Learning Customized Activation" . + """ + + def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r + super().__init__() + c2 = max(r, c1 // r) + self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) + self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) + self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True) + self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True) + # self.bn1 = nn.BatchNorm2d(c2) + # self.bn2 = nn.BatchNorm2d(c1) + + def forward(self, x): + y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True) + # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891 + # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable + beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed + dpx = (self.p1 - self.p2) * x + return dpx * torch.sigmoid(beta * dpx) + self.p2 * x diff --git a/yolov5_Monocular_social_ranging/utils/augmentations.py b/yolov5_Monocular_social_ranging/utils/augmentations.py new file mode 100644 index 0000000..0311b97 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/augmentations.py @@ -0,0 +1,277 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Image augmentation functions +""" + +import math +import random + +import cv2 +import numpy as np + +from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box +from utils.metrics import bbox_ioa + + +class Albumentations: + # YOLOv5 Albumentations class (optional, only used if package is installed) + def __init__(self): + self.transform = None + try: + import albumentations as A + check_version(A.__version__, '1.0.3', hard=True) # version requirement + + self.transform = A.Compose([ + A.Blur(p=0.01), + A.MedianBlur(p=0.01), + A.ToGray(p=0.01), + A.CLAHE(p=0.01), + A.RandomBrightnessContrast(p=0.0), + A.RandomGamma(p=0.0), + A.ImageCompression(quality_lower=75, p=0.0)], + bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels'])) + + LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p)) + except ImportError: # package not installed, skip + pass + except Exception as e: + LOGGER.info(colorstr('albumentations: ') + f'{e}') + + def __call__(self, im, labels, p=1.0): + if self.transform and random.random() < p: + new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed + im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) + return im, labels + + +def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5): + # HSV color-space augmentation + if hgain or sgain or vgain: + r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains + hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV)) + dtype = im.dtype # uint8 + + x = np.arange(0, 256, dtype=r.dtype) + lut_hue = ((x * r[0]) % 180).astype(dtype) + lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) + lut_val = np.clip(x * r[2], 0, 255).astype(dtype) + + im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) + cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed + + +def hist_equalize(im, clahe=True, bgr=False): + # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255 + yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) + if clahe: + c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) + yuv[:, :, 0] = c.apply(yuv[:, :, 0]) + else: + yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram + return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB + + +def replicate(im, labels): + # Replicate labels + h, w = im.shape[:2] + boxes = labels[:, 1:].astype(int) + x1, y1, x2, y2 = boxes.T + s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) + for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices + x1b, y1b, x2b, y2b = boxes[i] + bh, bw = y2b - y1b, x2b - x1b + yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y + x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] + im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax] + labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) + + return im, labels + + +def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): + # Resize and pad image while meeting stride-multiple constraints + shape = im.shape[:2] # current shape [height, width] + if isinstance(new_shape, int): + new_shape = (new_shape, new_shape) + + # Scale ratio (new / old) + r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) + if not scaleup: # only scale down, do not scale up (for better val mAP) + r = min(r, 1.0) + + # Compute padding + ratio = r, r # width, height ratios + new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) + dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding + if auto: # minimum rectangle + dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding + elif scaleFill: # stretch + dw, dh = 0.0, 0.0 + new_unpad = (new_shape[1], new_shape[0]) + ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios + + dw /= 2 # divide padding into 2 sides + dh /= 2 + + if shape[::-1] != new_unpad: # resize + im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) + top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) + left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) + im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border + return im, ratio, (dw, dh) + + +def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, + border=(0, 0)): + # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10)) + # targets = [cls, xyxy] + + height = im.shape[0] + border[0] * 2 # shape(h,w,c) + width = im.shape[1] + border[1] * 2 + + # Center + C = np.eye(3) + C[0, 2] = -im.shape[1] / 2 # x translation (pixels) + C[1, 2] = -im.shape[0] / 2 # y translation (pixels) + + # Perspective + P = np.eye(3) + P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) + P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) + + # Rotation and Scale + R = np.eye(3) + a = random.uniform(-degrees, degrees) + # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations + s = random.uniform(1 - scale, 1 + scale) + # s = 2 ** random.uniform(-scale, scale) + R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) + + # Shear + S = np.eye(3) + S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) + S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) + + # Translation + T = np.eye(3) + T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) + T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) + + # Combined rotation matrix + M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT + if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed + if perspective: + im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) + else: # affine + im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) + + # Visualize + # import matplotlib.pyplot as plt + # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() + # ax[0].imshow(im[:, :, ::-1]) # base + # ax[1].imshow(im2[:, :, ::-1]) # warped + + # Transform label coordinates + n = len(targets) + if n: + use_segments = any(x.any() for x in segments) + new = np.zeros((n, 4)) + if use_segments: # warp segments + segments = resample_segments(segments) # upsample + for i, segment in enumerate(segments): + xy = np.ones((len(segment), 3)) + xy[:, :2] = segment + xy = xy @ M.T # transform + xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine + + # clip + new[i] = segment2box(xy, width, height) + + else: # warp boxes + xy = np.ones((n * 4, 3)) + xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 + xy = xy @ M.T # transform + xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine + + # create new boxes + x = xy[:, [0, 2, 4, 6]] + y = xy[:, [1, 3, 5, 7]] + new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T + + # clip + new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) + new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) + + # filter candidates + i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) + targets = targets[i] + targets[:, 1:5] = new[i] + + return im, targets + + +def copy_paste(im, labels, segments, p=0.5): + # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) + n = len(segments) + if p and n: + h, w, c = im.shape # height, width, channels + im_new = np.zeros(im.shape, np.uint8) + for j in random.sample(range(n), k=round(p * n)): + l, s = labels[j], segments[j] + box = w - l[3], l[2], w - l[1], l[4] + ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area + if (ioa < 0.30).all(): # allow 30% obscuration of existing labels + labels = np.concatenate((labels, [[l[0], *box]]), 0) + segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) + cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) + + result = cv2.bitwise_and(src1=im, src2=im_new) + result = cv2.flip(result, 1) # augment segments (flip left-right) + i = result > 0 # pixels to replace + # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch + im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug + + return im, labels, segments + + +def cutout(im, labels, p=0.5): + # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 + if random.random() < p: + h, w = im.shape[:2] + scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction + for s in scales: + mask_h = random.randint(1, int(h * s)) # create random masks + mask_w = random.randint(1, int(w * s)) + + # box + xmin = max(0, random.randint(0, w) - mask_w // 2) + ymin = max(0, random.randint(0, h) - mask_h // 2) + xmax = min(w, xmin + mask_w) + ymax = min(h, ymin + mask_h) + + # apply random color mask + im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] + + # return unobscured labels + if len(labels) and s > 0.03: + box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) + ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area + labels = labels[ioa < 0.60] # remove >60% obscured labels + + return labels + + +def mixup(im, labels, im2, labels2): + # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf + r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 + im = (im * r + im2 * (1 - r)).astype(np.uint8) + labels = np.concatenate((labels, labels2), 0) + return im, labels + + +def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) + # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio + w1, h1 = box1[2] - box1[0], box1[3] - box1[1] + w2, h2 = box2[2] - box2[0], box2[3] - box2[1] + ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio + return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates diff --git a/yolov5_Monocular_social_ranging/utils/autoanchor.py b/yolov5_Monocular_social_ranging/utils/autoanchor.py new file mode 100644 index 0000000..27d6fb6 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/autoanchor.py @@ -0,0 +1,165 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +AutoAnchor utils +""" + +import random + +import numpy as np +import torch +import yaml +from tqdm import tqdm + +from utils.general import LOGGER, colorstr, emojis + +PREFIX = colorstr('AutoAnchor: ') + + +def check_anchor_order(m): + # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary + a = m.anchors.prod(-1).view(-1) # anchor area + da = a[-1] - a[0] # delta a + ds = m.stride[-1] - m.stride[0] # delta s + if da.sign() != ds.sign(): # same order + LOGGER.info(f'{PREFIX}Reversing anchor order') + m.anchors[:] = m.anchors.flip(0) + + +def check_anchors(dataset, model, thr=4.0, imgsz=640): + # Check anchor fit to data, recompute if necessary + m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() + shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) + scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale + wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh + + def metric(k): # compute metric + r = wh[:, None] / k[None] + x = torch.min(r, 1 / r).min(2)[0] # ratio metric + best = x.max(1)[0] # best_x + aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold + bpr = (best > 1 / thr).float().mean() # best possible recall + return bpr, aat + + anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors + bpr, aat = metric(anchors.cpu().view(-1, 2)) + s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). ' + if bpr > 0.98: # threshold to recompute + LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅')) + else: + LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...')) + na = m.anchors.numel() // 2 # number of anchors + try: + anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) + except Exception as e: + LOGGER.info(f'{PREFIX}ERROR: {e}') + new_bpr = metric(anchors)[0] + if new_bpr > bpr: # replace anchors + anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) + m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss + check_anchor_order(m) + LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.') + else: + LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.') + + +def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): + """ Creates kmeans-evolved anchors from training dataset + + Arguments: + dataset: path to data.yaml, or a loaded dataset + n: number of anchors + img_size: image size used for training + thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 + gen: generations to evolve anchors using genetic algorithm + verbose: print all results + + Return: + k: kmeans evolved anchors + + Usage: + from utils.autoanchor import *; _ = kmean_anchors() + """ + from scipy.cluster.vq import kmeans + + npr = np.random + thr = 1 / thr + + def metric(k, wh): # compute metrics + r = wh[:, None] / k[None] + x = torch.min(r, 1 / r).min(2)[0] # ratio metric + # x = wh_iou(wh, torch.tensor(k)) # iou metric + return x, x.max(1)[0] # x, best_x + + def anchor_fitness(k): # mutation fitness + _, best = metric(torch.tensor(k, dtype=torch.float32), wh) + return (best * (best > thr).float()).mean() # fitness + + def print_results(k, verbose=True): + k = k[np.argsort(k.prod(1))] # sort small to large + x, best = metric(k, wh0) + bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr + s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \ + f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \ + f'past_thr={x[x > thr].mean():.3f}-mean: ' + for i, x in enumerate(k): + s += '%i,%i, ' % (round(x[0]), round(x[1])) + if verbose: + LOGGER.info(s[:-2]) + return k + + if isinstance(dataset, str): # *.yaml file + with open(dataset, errors='ignore') as f: + data_dict = yaml.safe_load(f) # model dict + from utils.datasets import LoadImagesAndLabels + dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) + + # Get label wh + shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) + wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh + + # Filter + i = (wh0 < 3.0).any(1).sum() + if i: + LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.') + wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels + # wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1 + + # Kmeans calculation + LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...') + s = wh.std(0) # sigmas for whitening + k = kmeans(wh / s, n, iter=30)[0] * s # points + if len(k) != n: # kmeans may return fewer points than requested if wh is insufficient or too similar + LOGGER.warning(f'{PREFIX}WARNING: scipy.cluster.vq.kmeans returned only {len(k)} of {n} requested points') + k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size # random init + wh = torch.tensor(wh, dtype=torch.float32) # filtered + wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered + k = print_results(k, verbose=False) + + # Plot + # k, d = [None] * 20, [None] * 20 + # for i in tqdm(range(1, 21)): + # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance + # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True) + # ax = ax.ravel() + # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') + # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh + # ax[0].hist(wh[wh[:, 0]<100, 0],400) + # ax[1].hist(wh[wh[:, 1]<100, 1],400) + # fig.savefig('wh.png', dpi=200) + + # Evolve + f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma + pbar = tqdm(range(gen), desc=f'{PREFIX}Evolving anchors with Genetic Algorithm:') # progress bar + for _ in pbar: + v = np.ones(sh) + while (v == 1).all(): # mutate until a change occurs (prevent duplicates) + v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) + kg = (k.copy() * v).clip(min=2.0) + fg = anchor_fitness(kg) + if fg > f: + f, k = fg, kg.copy() + pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}' + if verbose: + print_results(k, verbose) + + return print_results(k) diff --git a/yolov5_Monocular_social_ranging/utils/autobatch.py b/yolov5_Monocular_social_ranging/utils/autobatch.py new file mode 100644 index 0000000..cb94f04 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/autobatch.py @@ -0,0 +1,57 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Auto-batch utils +""" + +from copy import deepcopy + +import numpy as np +import torch +from torch.cuda import amp + +from utils.general import LOGGER, colorstr +from utils.torch_utils import profile + + +def check_train_batch_size(model, imgsz=640): + # Check YOLOv5 training batch size + with amp.autocast(): + return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size + + +def autobatch(model, imgsz=640, fraction=0.9, batch_size=16): + # Automatically estimate best batch size to use `fraction` of available CUDA memory + # Usage: + # import torch + # from utils.autobatch import autobatch + # model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False) + # print(autobatch(model)) + + prefix = colorstr('AutoBatch: ') + LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}') + device = next(model.parameters()).device # get model device + if device.type == 'cpu': + LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}') + return batch_size + + d = str(device).upper() # 'CUDA:0' + properties = torch.cuda.get_device_properties(device) # device properties + t = properties.total_memory / 1024 ** 3 # (GiB) + r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GiB) + a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GiB) + f = t - (r + a) # free inside reserved + LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free') + + batch_sizes = [1, 2, 4, 8, 16] + try: + img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes] + y = profile(img, model, n=3, device=device) + except Exception as e: + LOGGER.warning(f'{prefix}{e}') + + y = [x[2] for x in y if x] # memory [2] + batch_sizes = batch_sizes[:len(y)] + p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit + b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) + LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)') + return b diff --git a/yolov5_Monocular_social_ranging/utils/aws/__init__.py b/yolov5_Monocular_social_ranging/utils/aws/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/yolov5_Monocular_social_ranging/utils/aws/mime.sh b/yolov5_Monocular_social_ranging/utils/aws/mime.sh new file mode 100644 index 0000000..c319a83 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/aws/mime.sh @@ -0,0 +1,26 @@ +# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/ +# This script will run on every instance restart, not only on first start +# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA --- + +Content-Type: multipart/mixed; boundary="//" +MIME-Version: 1.0 + +--// +Content-Type: text/cloud-config; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Content-Disposition: attachment; filename="cloud-config.txt" + +#cloud-config +cloud_final_modules: +- [scripts-user, always] + +--// +Content-Type: text/x-shellscript; charset="us-ascii" +MIME-Version: 1.0 +Content-Transfer-Encoding: 7bit +Content-Disposition: attachment; filename="userdata.txt" + +#!/bin/bash +# --- paste contents of userdata.sh here --- +--// diff --git a/yolov5_Monocular_social_ranging/utils/aws/resume.py b/yolov5_Monocular_social_ranging/utils/aws/resume.py new file mode 100644 index 0000000..b21731c --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/aws/resume.py @@ -0,0 +1,40 @@ +# Resume all interrupted trainings in yolov5/ dir including DDP trainings +# Usage: $ python utils/aws/resume.py + +import os +import sys +from pathlib import Path + +import torch +import yaml + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[2] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH + +port = 0 # --master_port +path = Path('').resolve() +for last in path.rglob('*/**/last.pt'): + ckpt = torch.load(last) + if ckpt['optimizer'] is None: + continue + + # Load opt.yaml + with open(last.parent.parent / 'opt.yaml', errors='ignore') as f: + opt = yaml.safe_load(f) + + # Get device count + d = opt['device'].split(',') # devices + nd = len(d) # number of devices + ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel + + if ddp: # multi-GPU + port += 1 + cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}' + else: # single-GPU + cmd = f'python train.py --resume {last}' + + cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread + print(cmd) + os.system(cmd) diff --git a/yolov5_Monocular_social_ranging/utils/aws/userdata.sh b/yolov5_Monocular_social_ranging/utils/aws/userdata.sh new file mode 100644 index 0000000..5fc1332 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/aws/userdata.sh @@ -0,0 +1,27 @@ +#!/bin/bash +# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html +# This script will run only once on first instance start (for a re-start script see mime.sh) +# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir +# Use >300 GB SSD + +cd home/ubuntu +if [ ! -d yolov5 ]; then + echo "Running first-time script." # install dependencies, download COCO, pull Docker + git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5 + cd yolov5 + bash data/scripts/get_coco.sh && echo "COCO done." & + sudo docker pull ultralytics/yolov5:latest && echo "Docker done." & + python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." & + wait && echo "All tasks done." # finish background tasks +else + echo "Running re-start script." # resume interrupted runs + i=0 + list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour' + while IFS= read -r id; do + ((i++)) + echo "restarting container $i: $id" + sudo docker start $id + # sudo docker exec -it $id python train.py --resume # single-GPU + sudo docker exec -d $id python utils/aws/resume.py # multi-scenario + done <<<"$list" +fi diff --git a/yolov5_Monocular_social_ranging/utils/benchmarks.py b/yolov5_Monocular_social_ranging/utils/benchmarks.py new file mode 100644 index 0000000..962df81 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/benchmarks.py @@ -0,0 +1,92 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Run YOLOv5 benchmarks on all supported export formats + +Format | `export.py --include` | Model +--- | --- | --- +PyTorch | - | yolov5s.pt +TorchScript | `torchscript` | yolov5s.torchscript +ONNX | `onnx` | yolov5s.onnx +OpenVINO | `openvino` | yolov5s_openvino_model/ +TensorRT | `engine` | yolov5s.engine +CoreML | `coreml` | yolov5s.mlmodel +TensorFlow SavedModel | `saved_model` | yolov5s_saved_model/ +TensorFlow GraphDef | `pb` | yolov5s.pb +TensorFlow Lite | `tflite` | yolov5s.tflite +TensorFlow Edge TPU | `edgetpu` | yolov5s_edgetpu.tflite +TensorFlow.js | `tfjs` | yolov5s_web_model/ + +Requirements: + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU + +Usage: + $ python utils/benchmarks.py --weights yolov5s.pt --img 640 +""" + +import argparse +import sys +import time +from pathlib import Path + +import pandas as pd + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[1] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +# ROOT = ROOT.relative_to(Path.cwd()) # relative + +import export +import val +from utils import notebook_init +from utils.general import LOGGER, print_args + + +def run(weights=ROOT / 'yolov5s.pt', # weights path + imgsz=640, # inference size (pixels) + batch_size=1, # batch size + data=ROOT / 'data/coco128.yaml', # dataset.yaml path + ): + y, t = [], time.time() + formats = export.export_formats() + for i, (name, f, suffix) in formats.iterrows(): # index, (name, file, suffix) + try: + w = weights if f == '-' else export.run(weights=weights, imgsz=[imgsz], include=[f], device='cpu')[-1] + assert suffix in str(w), 'export failed' + result = val.run(data, w, batch_size, imgsz=imgsz, plots=False, device='cpu', task='benchmark') + metrics = result[0] # metrics (mp, mr, map50, map, *losses(box, obj, cls)) + speeds = result[2] # times (preprocess, inference, postprocess) + y.append([name, metrics[3], speeds[1]]) # mAP, t_inference + except Exception as e: + LOGGER.warning(f'WARNING: Benchmark failure for {name}: {e}') + y.append([name, None, None]) # mAP, t_inference + + # Print results + LOGGER.info('\n') + parse_opt() + notebook_init() # print system info + py = pd.DataFrame(y, columns=['Format', 'mAP@0.5:0.95', 'Inference time (ms)']) + LOGGER.info(f'\nBenchmarks complete ({time.time() - t:.2f}s)') + LOGGER.info(str(py)) + return py + + +def parse_opt(): + parser = argparse.ArgumentParser() + parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path') + parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') + opt = parser.parse_args() + print_args(FILE.stem, opt) + return opt + + +def main(opt): + run(**vars(opt)) + + +if __name__ == "__main__": + opt = parse_opt() + main(opt) diff --git a/yolov5_Monocular_social_ranging/utils/callbacks.py b/yolov5_Monocular_social_ranging/utils/callbacks.py new file mode 100644 index 0000000..c51c268 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/callbacks.py @@ -0,0 +1,78 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Callback utils +""" + + +class Callbacks: + """" + Handles all registered callbacks for YOLOv5 Hooks + """ + + def __init__(self): + # Define the available callbacks + self._callbacks = { + 'on_pretrain_routine_start': [], + 'on_pretrain_routine_end': [], + + 'on_train_start': [], + 'on_train_epoch_start': [], + 'on_train_batch_start': [], + 'optimizer_step': [], + 'on_before_zero_grad': [], + 'on_train_batch_end': [], + 'on_train_epoch_end': [], + + 'on_val_start': [], + 'on_val_batch_start': [], + 'on_val_image_end': [], + 'on_val_batch_end': [], + 'on_val_end': [], + + 'on_fit_epoch_end': [], # fit = train + val + 'on_model_save': [], + 'on_train_end': [], + 'on_params_update': [], + 'teardown': [], + } + self.stop_training = False # set True to interrupt training + + def register_action(self, hook, name='', callback=None): + """ + Register a new action to a callback hook + + Args: + hook The callback hook name to register the action to + name The name of the action for later reference + callback The callback to fire + """ + assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" + assert callable(callback), f"callback '{callback}' is not callable" + self._callbacks[hook].append({'name': name, 'callback': callback}) + + def get_registered_actions(self, hook=None): + """" + Returns all the registered actions by callback hook + + Args: + hook The name of the hook to check, defaults to all + """ + if hook: + return self._callbacks[hook] + else: + return self._callbacks + + def run(self, hook, *args, **kwargs): + """ + Loop through the registered actions and fire all callbacks + + Args: + hook The name of the hook to check, defaults to all + args Arguments to receive from YOLOv5 + kwargs Keyword Arguments to receive from YOLOv5 + """ + + assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" + + for logger in self._callbacks[hook]: + logger['callback'](*args, **kwargs) diff --git a/yolov5_Monocular_social_ranging/utils/datasets.py b/yolov5_Monocular_social_ranging/utils/datasets.py new file mode 100644 index 0000000..e132e04 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/datasets.py @@ -0,0 +1,1037 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Dataloaders and dataset utils +""" + +import glob +import hashlib +import json +import math +import os +import random +import shutil +import time +from itertools import repeat +from multiprocessing.pool import Pool, ThreadPool +from pathlib import Path +from threading import Thread +from zipfile import ZipFile + +import cv2 +import numpy as np +import torch +import torch.nn.functional as F +import yaml +from PIL import ExifTags, Image, ImageOps +from torch.utils.data import DataLoader, Dataset, dataloader, distributed +from tqdm import tqdm + +from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective +from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, check_dataset, check_requirements, check_yaml, clean_str, + segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn) +from utils.torch_utils import torch_distributed_zero_first + +# Parameters +HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data' +IMG_FORMATS = ['bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp'] # include image suffixes +VID_FORMATS = ['asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'wmv'] # include video suffixes + +# Get orientation exif tag +for orientation in ExifTags.TAGS.keys(): + if ExifTags.TAGS[orientation] == 'Orientation': + break + + +def get_hash(paths): + # Returns a single hash value of a list of paths (files or dirs) + size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes + h = hashlib.md5(str(size).encode()) # hash sizes + h.update(''.join(paths).encode()) # hash paths + return h.hexdigest() # return hash + + +def exif_size(img): + # Returns exif-corrected PIL size + s = img.size # (width, height) + try: + rotation = dict(img._getexif().items())[orientation] + if rotation == 6: # rotation 270 + s = (s[1], s[0]) + elif rotation == 8: # rotation 90 + s = (s[1], s[0]) + except Exception: + pass + + return s + + +def exif_transpose(image): + """ + Transpose a PIL image accordingly if it has an EXIF Orientation tag. + Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose() + + :param image: The image to transpose. + :return: An image. + """ + exif = image.getexif() + orientation = exif.get(0x0112, 1) # default 1 + if orientation > 1: + method = {2: Image.FLIP_LEFT_RIGHT, + 3: Image.ROTATE_180, + 4: Image.FLIP_TOP_BOTTOM, + 5: Image.TRANSPOSE, + 6: Image.ROTATE_270, + 7: Image.TRANSVERSE, + 8: Image.ROTATE_90, + }.get(orientation) + if method is not None: + image = image.transpose(method) + del exif[0x0112] + image.info["exif"] = exif.tobytes() + return image + + +def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0, + rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix='', shuffle=False): + if rect and shuffle: + LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False') + shuffle = False + with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP + dataset = LoadImagesAndLabels(path, imgsz, batch_size, + augment=augment, # augmentation + hyp=hyp, # hyperparameters + rect=rect, # rectangular batches + cache_images=cache, + single_cls=single_cls, + stride=int(stride), + pad=pad, + image_weights=image_weights, + prefix=prefix) + + batch_size = min(batch_size, len(dataset)) + nd = torch.cuda.device_count() # number of CUDA devices + nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers + sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle) + loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates + return loader(dataset, + batch_size=batch_size, + shuffle=shuffle and sampler is None, + num_workers=nw, + sampler=sampler, + pin_memory=True, + collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset + + +class InfiniteDataLoader(dataloader.DataLoader): + """ Dataloader that reuses workers + + Uses same syntax as vanilla DataLoader + """ + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler)) + self.iterator = super().__iter__() + + def __len__(self): + return len(self.batch_sampler.sampler) + + def __iter__(self): + for i in range(len(self)): + yield next(self.iterator) + + +class _RepeatSampler: + """ Sampler that repeats forever + + Args: + sampler (Sampler) + """ + + def __init__(self, sampler): + self.sampler = sampler + + def __iter__(self): + while True: + yield from iter(self.sampler) + + +class LoadImages: + # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4` + def __init__(self, path, img_size=640, stride=32, auto=True): + p = str(Path(path).resolve()) # os-agnostic absolute path + if '*' in p: + files = sorted(glob.glob(p, recursive=True)) # glob + elif os.path.isdir(p): + files = sorted(glob.glob(os.path.join(p, '*.*'))) # dir + elif os.path.isfile(p): + files = [p] # files + else: + raise Exception(f'ERROR: {p} does not exist') + + images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS] + videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS] + ni, nv = len(images), len(videos) + + self.img_size = img_size + self.stride = stride + self.files = images + videos + self.nf = ni + nv # number of files + self.video_flag = [False] * ni + [True] * nv + self.mode = 'image' + self.auto = auto + if any(videos): + self.new_video(videos[0]) # new video + else: + self.cap = None + assert self.nf > 0, f'No images or videos found in {p}. ' \ + f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}' + + def __iter__(self): + self.count = 0 + return self + + def __next__(self): + if self.count == self.nf: + raise StopIteration + path = self.files[self.count] + + if self.video_flag[self.count]: + # Read video + self.mode = 'video' + ret_val, img0 = self.cap.read() + while not ret_val: + self.count += 1 + self.cap.release() + if self.count == self.nf: # last video + raise StopIteration + else: + path = self.files[self.count] + self.new_video(path) + ret_val, img0 = self.cap.read() + + self.frame += 1 + s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ' + + else: + # Read image + self.count += 1 + img0 = cv2.imread(path) # BGR + assert img0 is not None, f'Image Not Found {path}' + s = f'image {self.count}/{self.nf} {path}: ' + + # Padded resize + img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0] + + # Convert + img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB + img = np.ascontiguousarray(img) + + return path, img, img0, self.cap, s + + def new_video(self, path): + self.frame = 0 + self.cap = cv2.VideoCapture(path) + self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT)) + + def __len__(self): + return self.nf # number of files + + +class LoadWebcam: # for inference + # YOLOv5 local webcam dataloader, i.e. `python detect.py --source 0` + def __init__(self, pipe='0', img_size=640, stride=32): + self.img_size = img_size + self.stride = stride + self.pipe = eval(pipe) if pipe.isnumeric() else pipe + self.cap = cv2.VideoCapture(self.pipe) # video capture object + self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3) # set buffer size + + def __iter__(self): + self.count = -1 + return self + + def __next__(self): + self.count += 1 + if cv2.waitKey(1) == ord('q'): # q to quit + self.cap.release() + cv2.destroyAllWindows() + raise StopIteration + + # Read frame + ret_val, img0 = self.cap.read() + img0 = cv2.flip(img0, 1) # flip left-right + + # Print + assert ret_val, f'Camera Error {self.pipe}' + img_path = 'webcam.jpg' + s = f'webcam {self.count}: ' + + # Padded resize + img = letterbox(img0, self.img_size, stride=self.stride)[0] + + # Convert + img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB + img = np.ascontiguousarray(img) + + return img_path, img, img0, None, s + + def __len__(self): + return 0 + + +class LoadStreams: + # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams` + def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True): + self.mode = 'stream' + self.img_size = img_size + self.stride = stride + + if os.path.isfile(sources): + with open(sources) as f: + sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())] + else: + sources = [sources] + + n = len(sources) + self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n + self.sources = [clean_str(x) for x in sources] # clean source names for later + self.auto = auto + for i, s in enumerate(sources): # index, source + # Start thread to read frames from video stream + st = f'{i + 1}/{n}: {s}... ' + if 'youtube.com/' in s or 'youtu.be/' in s: # if source is YouTube video + check_requirements(('pafy', 'youtube_dl==2020.12.2')) + import pafy + s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL + s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam + cap = cv2.VideoCapture(s) + assert cap.isOpened(), f'{st}Failed to open {s}' + w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) + h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) + fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan + self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback + self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback + + _, self.imgs[i] = cap.read() # guarantee first frame + self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True) + LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)") + self.threads[i].start() + LOGGER.info('') # newline + + # check for common shapes + s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs]) + self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal + if not self.rect: + LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.') + + def update(self, i, cap, stream): + # Read stream `i` frames in daemon thread + n, f, read = 0, self.frames[i], 1 # frame number, frame array, inference every 'read' frame + while cap.isOpened() and n < f: + n += 1 + # _, self.imgs[index] = cap.read() + cap.grab() + if n % read == 0: + success, im = cap.retrieve() + if success: + self.imgs[i] = im + else: + LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.') + self.imgs[i] = np.zeros_like(self.imgs[i]) + cap.open(stream) # re-open stream if signal was lost + time.sleep(1 / self.fps[i]) # wait time + + def __iter__(self): + self.count = -1 + return self + + def __next__(self): + self.count += 1 + if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit + cv2.destroyAllWindows() + raise StopIteration + + # Letterbox + img0 = self.imgs.copy() + img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0] + + # Stack + img = np.stack(img, 0) + + # Convert + img = img[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW + img = np.ascontiguousarray(img) + + return self.sources, img, img0, None, '' + + def __len__(self): + return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years + + +def img2label_paths(img_paths): + # Define label paths as a function of image paths + sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings + return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths] + + +class LoadImagesAndLabels(Dataset): + # YOLOv5 train_loader/val_loader, loads images and labels for training and validation + cache_version = 0.6 # dataset labels *.cache version + + def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, + cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''): + self.img_size = img_size + self.augment = augment + self.hyp = hyp + self.image_weights = image_weights + self.rect = False if image_weights else rect + self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) + self.mosaic_border = [-img_size // 2, -img_size // 2] + self.stride = stride + self.path = path + self.albumentations = Albumentations() if augment else None + + try: + f = [] # image files + for p in path if isinstance(path, list) else [path]: + p = Path(p) # os-agnostic + if p.is_dir(): # dir + f += glob.glob(str(p / '**' / '*.*'), recursive=True) + # f = list(p.rglob('*.*')) # pathlib + elif p.is_file(): # file + with open(p) as t: + t = t.read().strip().splitlines() + parent = str(p.parent) + os.sep + f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path + # f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib) + else: + raise Exception(f'{prefix}{p} does not exist') + self.img_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS) + # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib + assert self.img_files, f'{prefix}No images found' + except Exception as e: + raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}') + + # Check cache + self.label_files = img2label_paths(self.img_files) # labels + cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache') + try: + cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict + assert cache['version'] == self.cache_version # same version + assert cache['hash'] == get_hash(self.label_files + self.img_files) # same hash + except Exception: + cache, exists = self.cache_labels(cache_path, prefix), False # cache + + # Display cache + nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total + if exists: + d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt" + tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results + if cache['msgs']: + LOGGER.info('\n'.join(cache['msgs'])) # display warnings + assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}' + + # Read cache + [cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items + labels, shapes, self.segments = zip(*cache.values()) + self.labels = list(labels) + self.shapes = np.array(shapes, dtype=np.float64) + self.img_files = list(cache.keys()) # update + self.label_files = img2label_paths(cache.keys()) # update + n = len(shapes) # number of images + bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index + nb = bi[-1] + 1 # number of batches + self.batch = bi # batch index of image + self.n = n + self.indices = range(n) + + # Update labels + include_class = [] # filter labels to include only these classes (optional) + include_class_array = np.array(include_class).reshape(1, -1) + for i, (label, segment) in enumerate(zip(self.labels, self.segments)): + if include_class: + j = (label[:, 0:1] == include_class_array).any(1) + self.labels[i] = label[j] + if segment: + self.segments[i] = segment[j] + if single_cls: # single-class training, merge all classes into 0 + self.labels[i][:, 0] = 0 + if segment: + self.segments[i][:, 0] = 0 + + # Rectangular Training + if self.rect: + # Sort by aspect ratio + s = self.shapes # wh + ar = s[:, 1] / s[:, 0] # aspect ratio + irect = ar.argsort() + self.img_files = [self.img_files[i] for i in irect] + self.label_files = [self.label_files[i] for i in irect] + self.labels = [self.labels[i] for i in irect] + self.shapes = s[irect] # wh + ar = ar[irect] + + # Set training image shapes + shapes = [[1, 1]] * nb + for i in range(nb): + ari = ar[bi == i] + mini, maxi = ari.min(), ari.max() + if maxi < 1: + shapes[i] = [maxi, 1] + elif mini > 1: + shapes[i] = [1, 1 / mini] + + self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride + + # Cache images into RAM/disk for faster training (WARNING: large datasets may exceed system resources) + self.imgs, self.img_npy = [None] * n, [None] * n + if cache_images: + if cache_images == 'disk': + self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy') + self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files] + self.im_cache_dir.mkdir(parents=True, exist_ok=True) + gb = 0 # Gigabytes of cached images + self.img_hw0, self.img_hw = [None] * n, [None] * n + results = ThreadPool(NUM_THREADS).imap(self.load_image, range(n)) + pbar = tqdm(enumerate(results), total=n) + for i, x in pbar: + if cache_images == 'disk': + if not self.img_npy[i].exists(): + np.save(self.img_npy[i].as_posix(), x[0]) + gb += self.img_npy[i].stat().st_size + else: # 'ram' + self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i) + gb += self.imgs[i].nbytes + pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})' + pbar.close() + + def cache_labels(self, path=Path('./labels.cache'), prefix=''): + # Cache dataset labels, check images and read shapes + x = {} # dict + nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages + desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..." + with Pool(NUM_THREADS) as pool: + pbar = tqdm(pool.imap(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))), + desc=desc, total=len(self.img_files)) + for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar: + nm += nm_f + nf += nf_f + ne += ne_f + nc += nc_f + if im_file: + x[im_file] = [lb, shape, segments] + if msg: + msgs.append(msg) + pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupt" + + pbar.close() + if msgs: + LOGGER.info('\n'.join(msgs)) + if nf == 0: + LOGGER.warning(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}') + x['hash'] = get_hash(self.label_files + self.img_files) + x['results'] = nf, nm, ne, nc, len(self.img_files) + x['msgs'] = msgs # warnings + x['version'] = self.cache_version # cache version + try: + np.save(path, x) # save cache for next time + path.with_suffix('.cache.npy').rename(path) # remove .npy suffix + LOGGER.info(f'{prefix}New cache created: {path}') + except Exception as e: + LOGGER.warning(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # not writeable + return x + + def __len__(self): + return len(self.img_files) + + # def __iter__(self): + # self.count = -1 + # print('ran dataset iter') + # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF) + # return self + + def __getitem__(self, index): + index = self.indices[index] # linear, shuffled, or image_weights + + hyp = self.hyp + mosaic = self.mosaic and random.random() < hyp['mosaic'] + if mosaic: + # Load mosaic + img, labels = self.load_mosaic(index) + shapes = None + + # MixUp augmentation + if random.random() < hyp['mixup']: + img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1))) + + else: + # Load image + img, (h0, w0), (h, w) = self.load_image(index) + + # Letterbox + shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape + img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) + shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling + + labels = self.labels[index].copy() + if labels.size: # normalized xywh to pixel xyxy format + labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1]) + + if self.augment: + img, labels = random_perspective(img, labels, + degrees=hyp['degrees'], + translate=hyp['translate'], + scale=hyp['scale'], + shear=hyp['shear'], + perspective=hyp['perspective']) + + nl = len(labels) # number of labels + if nl: + labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3) + + if self.augment: + # Albumentations + img, labels = self.albumentations(img, labels) + nl = len(labels) # update after albumentations + + # HSV color-space + augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) + + # Flip up-down + if random.random() < hyp['flipud']: + img = np.flipud(img) + if nl: + labels[:, 2] = 1 - labels[:, 2] + + # Flip left-right + if random.random() < hyp['fliplr']: + img = np.fliplr(img) + if nl: + labels[:, 1] = 1 - labels[:, 1] + + # Cutouts + # labels = cutout(img, labels, p=0.5) + # nl = len(labels) # update after cutout + + labels_out = torch.zeros((nl, 6)) + if nl: + labels_out[:, 1:] = torch.from_numpy(labels) + + # Convert + img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB + img = np.ascontiguousarray(img) + + return torch.from_numpy(img), labels_out, self.img_files[index], shapes + + def load_image(self, i): + # loads 1 image from dataset index 'i', returns (im, original hw, resized hw) + im = self.imgs[i] + if im is None: # not cached in RAM + npy = self.img_npy[i] + if npy and npy.exists(): # load npy + im = np.load(npy) + else: # read image + f = self.img_files[i] + im = cv2.imread(f) # BGR + assert im is not None, f'Image Not Found {f}' + h0, w0 = im.shape[:2] # orig hw + r = self.img_size / max(h0, w0) # ratio + if r != 1: # if sizes are not equal + im = cv2.resize(im, + (int(w0 * r), int(h0 * r)), + interpolation=cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA) + return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized + else: + return self.imgs[i], self.img_hw0[i], self.img_hw[i] # im, hw_original, hw_resized + + def load_mosaic(self, index): + # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic + labels4, segments4 = [], [] + s = self.img_size + yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y + indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices + random.shuffle(indices) + for i, index in enumerate(indices): + # Load image + img, _, (h, w) = self.load_image(index) + + # place img in img4 + if i == 0: # top left + img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles + x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) + x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) + elif i == 1: # top right + x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc + x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h + elif i == 2: # bottom left + x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) + x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) + elif i == 3: # bottom right + x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) + x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) + + img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] + padw = x1a - x1b + padh = y1a - y1b + + # Labels + labels, segments = self.labels[index].copy(), self.segments[index].copy() + if labels.size: + labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format + segments = [xyn2xy(x, w, h, padw, padh) for x in segments] + labels4.append(labels) + segments4.extend(segments) + + # Concat/clip labels + labels4 = np.concatenate(labels4, 0) + for x in (labels4[:, 1:], *segments4): + np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() + # img4, labels4 = replicate(img4, labels4) # replicate + + # Augment + img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste']) + img4, labels4 = random_perspective(img4, labels4, segments4, + degrees=self.hyp['degrees'], + translate=self.hyp['translate'], + scale=self.hyp['scale'], + shear=self.hyp['shear'], + perspective=self.hyp['perspective'], + border=self.mosaic_border) # border to remove + + return img4, labels4 + + def load_mosaic9(self, index): + # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic + labels9, segments9 = [], [] + s = self.img_size + indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices + random.shuffle(indices) + hp, wp = -1, -1 # height, width previous + for i, index in enumerate(indices): + # Load image + img, _, (h, w) = self.load_image(index) + + # place img in img9 + if i == 0: # center + img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles + h0, w0 = h, w + c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates + elif i == 1: # top + c = s, s - h, s + w, s + elif i == 2: # top right + c = s + wp, s - h, s + wp + w, s + elif i == 3: # right + c = s + w0, s, s + w0 + w, s + h + elif i == 4: # bottom right + c = s + w0, s + hp, s + w0 + w, s + hp + h + elif i == 5: # bottom + c = s + w0 - w, s + h0, s + w0, s + h0 + h + elif i == 6: # bottom left + c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h + elif i == 7: # left + c = s - w, s + h0 - h, s, s + h0 + elif i == 8: # top left + c = s - w, s + h0 - hp - h, s, s + h0 - hp + + padx, pady = c[:2] + x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords + + # Labels + labels, segments = self.labels[index].copy(), self.segments[index].copy() + if labels.size: + labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format + segments = [xyn2xy(x, w, h, padx, pady) for x in segments] + labels9.append(labels) + segments9.extend(segments) + + # Image + img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax] + hp, wp = h, w # height, width previous + + # Offset + yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border) # mosaic center x, y + img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s] + + # Concat/clip labels + labels9 = np.concatenate(labels9, 0) + labels9[:, [1, 3]] -= xc + labels9[:, [2, 4]] -= yc + c = np.array([xc, yc]) # centers + segments9 = [x - c for x in segments9] + + for x in (labels9[:, 1:], *segments9): + np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() + # img9, labels9 = replicate(img9, labels9) # replicate + + # Augment + img9, labels9 = random_perspective(img9, labels9, segments9, + degrees=self.hyp['degrees'], + translate=self.hyp['translate'], + scale=self.hyp['scale'], + shear=self.hyp['shear'], + perspective=self.hyp['perspective'], + border=self.mosaic_border) # border to remove + + return img9, labels9 + + @staticmethod + def collate_fn(batch): + img, label, path, shapes = zip(*batch) # transposed + for i, lb in enumerate(label): + lb[:, 0] = i # add target image index for build_targets() + return torch.stack(img, 0), torch.cat(label, 0), path, shapes + + @staticmethod + def collate_fn4(batch): + img, label, path, shapes = zip(*batch) # transposed + n = len(shapes) // 4 + img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n] + + ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]]) + wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]]) + s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]]) # scale + for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW + i *= 4 + if random.random() < 0.5: + im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', align_corners=False)[ + 0].type(img[i].type()) + lb = label[i] + else: + im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2) + lb = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s + img4.append(im) + label4.append(lb) + + for i, lb in enumerate(label4): + lb[:, 0] = i # add target image index for build_targets() + + return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4 + + +# Ancillary functions -------------------------------------------------------------------------------------------------- +def create_folder(path='./new'): + # Create folder + if os.path.exists(path): + shutil.rmtree(path) # delete output folder + os.makedirs(path) # make new output folder + + +def flatten_recursive(path=DATASETS_DIR / 'coco128'): + # Flatten a recursive directory by bringing all files to top level + new_path = Path(str(path) + '_flat') + create_folder(new_path) + for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)): + shutil.copyfile(file, new_path / Path(file).name) + + +def extract_boxes(path=DATASETS_DIR / 'coco128'): # from utils.datasets import *; extract_boxes() + # Convert detection dataset into classification dataset, with one directory per class + path = Path(path) # images dir + shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None # remove existing + files = list(path.rglob('*.*')) + n = len(files) # number of files + for im_file in tqdm(files, total=n): + if im_file.suffix[1:] in IMG_FORMATS: + # image + im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB + h, w = im.shape[:2] + + # labels + lb_file = Path(img2label_paths([str(im_file)])[0]) + if Path(lb_file).exists(): + with open(lb_file) as f: + lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels + + for j, x in enumerate(lb): + c = int(x[0]) # class + f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename + if not f.parent.is_dir(): + f.parent.mkdir(parents=True) + + b = x[1:] * [w, h, w, h] # box + # b[2:] = b[2:].max() # rectangle to square + b[2:] = b[2:] * 1.2 + 3 # pad + b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int) + + b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image + b[[1, 3]] = np.clip(b[[1, 3]], 0, h) + assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}' + + +def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False): + """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files + Usage: from utils.datasets import *; autosplit() + Arguments + path: Path to images directory + weights: Train, val, test weights (list, tuple) + annotated_only: Only use images with an annotated txt file + """ + path = Path(path) # images dir + files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only + n = len(files) # number of files + random.seed(0) # for reproducibility + indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split + + txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files + [(path.parent / x).unlink(missing_ok=True) for x in txt] # remove existing + + print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only) + for i, img in tqdm(zip(indices, files), total=n): + if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label + with open(path.parent / txt[i], 'a') as f: + f.write('./' + img.relative_to(path.parent).as_posix() + '\n') # add image to txt file + + +def verify_image_label(args): + # Verify one image-label pair + im_file, lb_file, prefix = args + nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [] # number (missing, found, empty, corrupt), message, segments + try: + # verify images + im = Image.open(im_file) + im.verify() # PIL verify + shape = exif_size(im) # image size + assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels' + assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}' + if im.format.lower() in ('jpg', 'jpeg'): + with open(im_file, 'rb') as f: + f.seek(-2, 2) + if f.read() != b'\xff\xd9': # corrupt JPEG + ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100) + msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved' + + # verify labels + if os.path.isfile(lb_file): + nf = 1 # label found + with open(lb_file) as f: + lb = [x.split() for x in f.read().strip().splitlines() if len(x)] + if any([len(x) > 8 for x in lb]): # is segment + classes = np.array([x[0] for x in lb], dtype=np.float32) + segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb] # (cls, xy1...) + lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh) + lb = np.array(lb, dtype=np.float32) + nl = len(lb) + if nl: + assert lb.shape[1] == 5, f'labels require 5 columns, {lb.shape[1]} columns detected' + assert (lb >= 0).all(), f'negative label values {lb[lb < 0]}' + assert (lb[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}' + _, i = np.unique(lb, axis=0, return_index=True) + if len(i) < nl: # duplicate row check + lb = lb[i] # remove duplicates + if segments: + segments = segments[i] + msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed' + else: + ne = 1 # label empty + lb = np.zeros((0, 5), dtype=np.float32) + else: + nm = 1 # label missing + lb = np.zeros((0, 5), dtype=np.float32) + return im_file, lb, shape, segments, nm, nf, ne, nc, msg + except Exception as e: + nc = 1 + msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}' + return [None, None, None, None, nm, nf, ne, nc, msg] + + +def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False): + """ Return dataset statistics dictionary with images and instances counts per split per class + To run in parent directory: export PYTHONPATH="$PWD/yolov5" + Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True) + Usage2: from utils.datasets import *; dataset_stats('path/to/coco128_with_yaml.zip') + Arguments + path: Path to data.yaml or data.zip (with data.yaml inside data.zip) + autodownload: Attempt to download dataset if not found locally + verbose: Print stats dictionary + """ + + def round_labels(labels): + # Update labels to integer class and 6 decimal place floats + return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels] + + def unzip(path): + # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/' + if str(path).endswith('.zip'): # path is data.zip + assert Path(path).is_file(), f'Error unzipping {path}, file not found' + ZipFile(path).extractall(path=path.parent) # unzip + dir = path.with_suffix('') # dataset directory == zip name + return True, str(dir), next(dir.rglob('*.yaml')) # zipped, data_dir, yaml_path + else: # path is data.yaml + return False, None, path + + def hub_ops(f, max_dim=1920): + # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing + f_new = im_dir / Path(f).name # dataset-hub image filename + try: # use PIL + im = Image.open(f) + r = max_dim / max(im.height, im.width) # ratio + if r < 1.0: # image too large + im = im.resize((int(im.width * r), int(im.height * r))) + im.save(f_new, 'JPEG', quality=75, optimize=True) # save + except Exception as e: # use OpenCV + print(f'WARNING: HUB ops PIL failure {f}: {e}') + im = cv2.imread(f) + im_height, im_width = im.shape[:2] + r = max_dim / max(im_height, im_width) # ratio + if r < 1.0: # image too large + im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA) + cv2.imwrite(str(f_new), im) + + zipped, data_dir, yaml_path = unzip(Path(path)) + with open(check_yaml(yaml_path), errors='ignore') as f: + data = yaml.safe_load(f) # data dict + if zipped: + data['path'] = data_dir # TODO: should this be dir.resolve()? + check_dataset(data, autodownload) # download dataset if missing + hub_dir = Path(data['path'] + ('-hub' if hub else '')) + stats = {'nc': data['nc'], 'names': data['names']} # statistics dictionary + for split in 'train', 'val', 'test': + if data.get(split) is None: + stats[split] = None # i.e. no test set + continue + x = [] + dataset = LoadImagesAndLabels(data[split]) # load dataset + for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'): + x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc'])) + x = np.array(x) # shape(128x80) + stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()}, + 'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()), + 'per_class': (x > 0).sum(0).tolist()}, + 'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in + zip(dataset.img_files, dataset.labels)]} + + if hub: + im_dir = hub_dir / 'images' + im_dir.mkdir(parents=True, exist_ok=True) + for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.img_files), total=dataset.n, desc='HUB Ops'): + pass + + # Profile + stats_path = hub_dir / 'stats.json' + if profile: + for _ in range(1): + file = stats_path.with_suffix('.npy') + t1 = time.time() + np.save(file, stats) + t2 = time.time() + x = np.load(file, allow_pickle=True) + print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write') + + file = stats_path.with_suffix('.json') + t1 = time.time() + with open(file, 'w') as f: + json.dump(stats, f) # save stats *.json + t2 = time.time() + with open(file) as f: + x = json.load(f) # load hyps dict + print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write') + + # Save, print and return + if hub: + print(f'Saving {stats_path.resolve()}...') + with open(stats_path, 'w') as f: + json.dump(stats, f) # save stats.json + if verbose: + print(json.dumps(stats, indent=2, sort_keys=False)) + return stats diff --git a/yolov5_Monocular_social_ranging/utils/downloads.py b/yolov5_Monocular_social_ranging/utils/downloads.py new file mode 100644 index 0000000..d7b87cb --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/downloads.py @@ -0,0 +1,153 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Download utils +""" + +import os +import platform +import subprocess +import time +import urllib +from pathlib import Path +from zipfile import ZipFile + +import requests +import torch + + +def gsutil_getsize(url=''): + # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du + s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') + return eval(s.split(' ')[0]) if len(s) else 0 # bytes + + +def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): + # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes + file = Path(file) + assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}" + try: # url1 + print(f'Downloading {url} to {file}...') + torch.hub.download_url_to_file(url, str(file)) + assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check + except Exception as e: # url2 + file.unlink(missing_ok=True) # remove partial downloads + print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') + os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail + finally: + if not file.exists() or file.stat().st_size < min_bytes: # check + file.unlink(missing_ok=True) # remove partial downloads + print(f"ERROR: {assert_msg}\n{error_msg}") + print('') + + +def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download() + # Attempt file download if does not exist + file = Path(str(file).strip().replace("'", '')) + + if not file.exists(): + # URL specified + name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc. + if str(file).startswith(('http:/', 'https:/')): # download + url = str(file).replace(':/', '://') # Pathlib turns :// -> :/ + file = name.split('?')[0] # parse authentication https://url.com/file.txt?auth... + if Path(file).is_file(): + print(f'Found {url} locally at {file}') # file already exists + else: + safe_download(file=file, url=url, min_bytes=1E5) + return file + + # GitHub assets + file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) + try: + response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api + assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...] + tag = response['tag_name'] # i.e. 'v1.0' + except Exception: # fallback plan + assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', + 'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt'] + try: + tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1] + except Exception: + tag = 'v6.0' # current release + + if name in assets: + safe_download(file, + url=f'https://github.com/{repo}/releases/download/{tag}/{name}', + # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional) + min_bytes=1E5, + error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/') + + return str(file) + + +def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'): + # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download() + t = time.time() + file = Path(file) + cookie = Path('cookie') # gdrive cookie + print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='') + file.unlink(missing_ok=True) # remove existing file + cookie.unlink(missing_ok=True) # remove existing cookie + + # Attempt file download + out = "NUL" if platform.system() == "Windows" else "/dev/null" + os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}') + if os.path.exists('cookie'): # large file + s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}' + else: # small file + s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"' + r = os.system(s) # execute, capture return + cookie.unlink(missing_ok=True) # remove existing cookie + + # Error check + if r != 0: + file.unlink(missing_ok=True) # remove partial + print('Download error ') # raise Exception('Download error') + return r + + # Unzip if archive + if file.suffix == '.zip': + print('unzipping... ', end='') + ZipFile(file).extractall(path=file.parent) # unzip + file.unlink() # remove zip + + print(f'Done ({time.time() - t:.1f}s)') + return r + + +def get_token(cookie="./cookie"): + with open(cookie) as f: + for line in f: + if "download" in line: + return line.split()[-1] + return "" + +# Google utils: https://cloud.google.com/storage/docs/reference/libraries ---------------------------------------------- +# +# +# def upload_blob(bucket_name, source_file_name, destination_blob_name): +# # Uploads a file to a bucket +# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python +# +# storage_client = storage.Client() +# bucket = storage_client.get_bucket(bucket_name) +# blob = bucket.blob(destination_blob_name) +# +# blob.upload_from_filename(source_file_name) +# +# print('File {} uploaded to {}.'.format( +# source_file_name, +# destination_blob_name)) +# +# +# def download_blob(bucket_name, source_blob_name, destination_file_name): +# # Uploads a blob from a bucket +# storage_client = storage.Client() +# bucket = storage_client.get_bucket(bucket_name) +# blob = bucket.blob(source_blob_name) +# +# blob.download_to_filename(destination_file_name) +# +# print('Blob {} downloaded to {}.'.format( +# source_blob_name, +# destination_file_name)) diff --git a/yolov5_Monocular_social_ranging/utils/flask_rest_api/README.md b/yolov5_Monocular_social_ranging/utils/flask_rest_api/README.md new file mode 100644 index 0000000..a726acb --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/flask_rest_api/README.md @@ -0,0 +1,73 @@ +# Flask REST API + +[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are +commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API +created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/). + +## Requirements + +[Flask](https://palletsprojects.com/p/flask/) is required. Install with: + +```shell +$ pip install Flask +``` + +## Run + +After Flask installation run: + +```shell +$ python3 restapi.py --port 5000 +``` + +Then use [curl](https://curl.se/) to perform a request: + +```shell +$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s' +``` + +The model inference results are returned as a JSON response: + +```json +[ + { + "class": 0, + "confidence": 0.8900438547, + "height": 0.9318675399, + "name": "person", + "width": 0.3264600933, + "xcenter": 0.7438579798, + "ycenter": 0.5207948685 + }, + { + "class": 0, + "confidence": 0.8440024257, + "height": 0.7155083418, + "name": "person", + "width": 0.6546785235, + "xcenter": 0.427829951, + "ycenter": 0.6334488392 + }, + { + "class": 27, + "confidence": 0.3771208823, + "height": 0.3902671337, + "name": "tie", + "width": 0.0696444362, + "xcenter": 0.3675483763, + "ycenter": 0.7991207838 + }, + { + "class": 27, + "confidence": 0.3527112305, + "height": 0.1540903747, + "name": "tie", + "width": 0.0336618312, + "xcenter": 0.7814827561, + "ycenter": 0.5065554976 + } +] +``` + +An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given +in `example_request.py` diff --git a/yolov5_Monocular_social_ranging/utils/flask_rest_api/example_request.py b/yolov5_Monocular_social_ranging/utils/flask_rest_api/example_request.py new file mode 100644 index 0000000..ff21f30 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/flask_rest_api/example_request.py @@ -0,0 +1,13 @@ +"""Perform test request""" +import pprint + +import requests + +DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s" +TEST_IMAGE = "zidane.jpg" + +image_data = open(TEST_IMAGE, "rb").read() + +response = requests.post(DETECTION_URL, files={"image": image_data}).json() + +pprint.pprint(response) diff --git a/yolov5_Monocular_social_ranging/utils/flask_rest_api/restapi.py b/yolov5_Monocular_social_ranging/utils/flask_rest_api/restapi.py new file mode 100644 index 0000000..b93ad16 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/flask_rest_api/restapi.py @@ -0,0 +1,37 @@ +""" +Run a rest API exposing the yolov5s object detection model +""" +import argparse +import io + +import torch +from flask import Flask, request +from PIL import Image + +app = Flask(__name__) + +DETECTION_URL = "/v1/object-detection/yolov5s" + + +@app.route(DETECTION_URL, methods=["POST"]) +def predict(): + if not request.method == "POST": + return + + if request.files.get("image"): + image_file = request.files["image"] + image_bytes = image_file.read() + + img = Image.open(io.BytesIO(image_bytes)) + + results = model(img, size=640) # reduce size=320 for faster inference + return results.pandas().xyxy[0].to_json(orient="records") + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model") + parser.add_argument("--port", default=5000, type=int, help="port number") + args = parser.parse_args() + + model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache + app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat diff --git a/yolov5_Monocular_social_ranging/utils/general.py b/yolov5_Monocular_social_ranging/utils/general.py new file mode 100644 index 0000000..3044b9c --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/general.py @@ -0,0 +1,880 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +General utils +""" + +import contextlib +import glob +import logging +import math +import os +import platform +import random +import re +import shutil +import signal +import time +import urllib +from itertools import repeat +from multiprocessing.pool import ThreadPool +from pathlib import Path +from subprocess import check_output +from zipfile import ZipFile + +import cv2 +import numpy as np +import pandas as pd +import pkg_resources as pkg +import torch +import torchvision +import yaml + +from utils.downloads import gsutil_getsize +from utils.metrics import box_iou, fitness + +# Settings +FILE = Path(__file__).resolve() +ROOT = FILE.parents[1] # YOLOv5 root directory +DATASETS_DIR = ROOT.parent / 'datasets' # YOLOv5 datasets directory +NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiprocessing threads +VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true' # global verbose mode +FONT = 'Arial.ttf' # https://ultralytics.com/assets/Arial.ttf + +torch.set_printoptions(linewidth=320, precision=5, profile='long') +np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5 +pd.options.display.max_columns = 10 +cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader) +os.environ['NUMEXPR_MAX_THREADS'] = str(NUM_THREADS) # NumExpr max threads + + +def is_kaggle(): + # Is environment a Kaggle Notebook? + try: + assert os.environ.get('PWD') == '/kaggle/working' + assert os.environ.get('KAGGLE_URL_BASE') == 'https://www.kaggle.com' + return True + except AssertionError: + return False + + +def is_writeable(dir, test=False): + # Return True if directory has write permissions, test opening a file with write permissions if test=True + if test: # method 1 + file = Path(dir) / 'tmp.txt' + try: + with open(file, 'w'): # open file with write permissions + pass + file.unlink() # remove file + return True + except OSError: + return False + else: # method 2 + return os.access(dir, os.R_OK) # possible issues on Windows + + +def set_logging(name=None, verbose=VERBOSE): + # Sets level and returns logger + if is_kaggle(): + for h in logging.root.handlers: + logging.root.removeHandler(h) # remove all handlers associated with the root logger object + rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings + logging.basicConfig(format="%(message)s", level=logging.INFO if (verbose and rank in (-1, 0)) else logging.WARNING) + return logging.getLogger(name) + + +LOGGER = set_logging('yolov5') # define globally (used in train.py, val.py, detect.py, etc.) + + +def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'): + # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required. + env = os.getenv(env_var) + if env: + path = Path(env) # use environment variable + else: + cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs + path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir + path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable + path.mkdir(exist_ok=True) # make if required + return path + + +CONFIG_DIR = user_config_dir() # Ultralytics settings dir + + +class Profile(contextlib.ContextDecorator): + # Usage: @Profile() decorator or 'with Profile():' context manager + def __enter__(self): + self.start = time.time() + + def __exit__(self, type, value, traceback): + print(f'Profile results: {time.time() - self.start:.5f}s') + + +class Timeout(contextlib.ContextDecorator): + # Usage: @Timeout(seconds) decorator or 'with Timeout(seconds):' context manager + def __init__(self, seconds, *, timeout_msg='', suppress_timeout_errors=True): + self.seconds = int(seconds) + self.timeout_message = timeout_msg + self.suppress = bool(suppress_timeout_errors) + + def _timeout_handler(self, signum, frame): + raise TimeoutError(self.timeout_message) + + def __enter__(self): + signal.signal(signal.SIGALRM, self._timeout_handler) # Set handler for SIGALRM + signal.alarm(self.seconds) # start countdown for SIGALRM to be raised + + def __exit__(self, exc_type, exc_val, exc_tb): + signal.alarm(0) # Cancel SIGALRM if it's scheduled + if self.suppress and exc_type is TimeoutError: # Suppress TimeoutError + return True + + +class WorkingDirectory(contextlib.ContextDecorator): + # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager + def __init__(self, new_dir): + self.dir = new_dir # new dir + self.cwd = Path.cwd().resolve() # current dir + + def __enter__(self): + os.chdir(self.dir) + + def __exit__(self, exc_type, exc_val, exc_tb): + os.chdir(self.cwd) + + +def try_except(func): + # try-except function. Usage: @try_except decorator + def handler(*args, **kwargs): + try: + func(*args, **kwargs) + except Exception as e: + print(e) + + return handler + + +def methods(instance): + # Get class/instance methods + return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")] + + +def print_args(name, opt): + # Print argparser arguments + LOGGER.info(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items())) + + +def init_seeds(seed=0): + # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html + # cudnn seed 0 settings are slower and more reproducible, else faster and less reproducible + import torch.backends.cudnn as cudnn + random.seed(seed) + np.random.seed(seed) + torch.manual_seed(seed) + cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False) + + +def intersect_dicts(da, db, exclude=()): + # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values + return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape} + + +def get_latest_run(search_dir='.'): + # Return path to most recent 'last.pt' in /runs (i.e. to --resume from) + last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True) + return max(last_list, key=os.path.getctime) if last_list else '' + + +def is_docker(): + # Is environment a Docker container? + return Path('/workspace').exists() # or Path('/.dockerenv').exists() + + +def is_colab(): + # Is environment a Google Colab instance? + try: + import google.colab + return True + except ImportError: + return False + + +def is_pip(): + # Is file in a pip package? + return 'site-packages' in Path(__file__).resolve().parts + + +def is_ascii(s=''): + # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7) + s = str(s) # convert list, tuple, None, etc. to str + return len(s.encode().decode('ascii', 'ignore')) == len(s) + + +def is_chinese(s='人工智能'): + # Is string composed of any Chinese characters? + return True if re.search('[\u4e00-\u9fff]', str(s)) else False + + +def emojis(str=''): + # Return platform-dependent emoji-safe version of string + return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str + + +def file_size(path): + # Return file/dir size (MB) + path = Path(path) + if path.is_file(): + return path.stat().st_size / 1E6 + elif path.is_dir(): + return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / 1E6 + else: + return 0.0 + + +def check_online(): + # Check internet connectivity + import socket + try: + socket.create_connection(("1.1.1.1", 443), 5) # check host accessibility + return True + except OSError: + return False + + +@try_except +@WorkingDirectory(ROOT) +def check_git_status(): + # Recommend 'git pull' if code is out of date + msg = ', for updates see https://github.com/ultralytics/yolov5' + s = colorstr('github: ') # string + assert Path('.git').exists(), s + 'skipping check (not a git repository)' + msg + assert not is_docker(), s + 'skipping check (Docker image)' + msg + assert check_online(), s + 'skipping check (offline)' + msg + + cmd = 'git fetch && git config --get remote.origin.url' + url = check_output(cmd, shell=True, timeout=5).decode().strip().rstrip('.git') # git fetch + branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out + n = int(check_output(f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind + if n > 0: + s += f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `git pull` or `git clone {url}` to update." + else: + s += f'up to date with {url} ✅' + LOGGER.info(emojis(s)) # emoji-safe + + +def check_python(minimum='3.6.2'): + # Check current python version vs. required python version + check_version(platform.python_version(), minimum, name='Python ', hard=True) + + +def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False, hard=False, verbose=False): + # Check version vs. required version + current, minimum = (pkg.parse_version(x) for x in (current, minimum)) + result = (current == minimum) if pinned else (current >= minimum) # bool + s = f'{name}{minimum} required by YOLOv5, but {name}{current} is currently installed' # string + if hard: + assert result, s # assert min requirements met + if verbose and not result: + LOGGER.warning(s) + return result + + +@try_except +def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True): + # Check installed dependencies meet requirements (pass *.txt file or list of packages) + prefix = colorstr('red', 'bold', 'requirements:') + check_python() # check python version + if isinstance(requirements, (str, Path)): # requirements.txt file + file = Path(requirements) + assert file.exists(), f"{prefix} {file.resolve()} not found, check failed." + with file.open() as f: + requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude] + else: # list or tuple of packages + requirements = [x for x in requirements if x not in exclude] + + n = 0 # number of packages updates + for r in requirements: + try: + pkg.require(r) + except Exception: # DistributionNotFound or VersionConflict if requirements not met + s = f"{prefix} {r} not found and is required by YOLOv5" + if install: + LOGGER.info(f"{s}, attempting auto-update...") + try: + assert check_online(), f"'pip install {r}' skipped (offline)" + LOGGER.info(check_output(f"pip install '{r}'", shell=True).decode()) + n += 1 + except Exception as e: + LOGGER.warning(f'{prefix} {e}') + else: + LOGGER.info(f'{s}. Please install and rerun your command.') + + if n: # if packages updated + source = file.resolve() if 'file' in locals() else requirements + s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \ + f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n" + LOGGER.info(emojis(s)) + + +def check_img_size(imgsz, s=32, floor=0): + # Verify image size is a multiple of stride s in each dimension + if isinstance(imgsz, int): # integer i.e. img_size=640 + new_size = max(make_divisible(imgsz, int(s)), floor) + else: # list i.e. img_size=[640, 480] + new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz] + if new_size != imgsz: + LOGGER.warning(f'WARNING: --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}') + return new_size + + +def check_imshow(): + # Check if environment supports image displays + try: + assert not is_docker(), 'cv2.imshow() is disabled in Docker environments' + assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments' + cv2.imshow('test', np.zeros((1, 1, 3))) + cv2.waitKey(1) + cv2.destroyAllWindows() + cv2.waitKey(1) + return True + except Exception as e: + LOGGER.warning(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}') + return False + + +def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''): + # Check file(s) for acceptable suffix + if file and suffix: + if isinstance(suffix, str): + suffix = [suffix] + for f in file if isinstance(file, (list, tuple)) else [file]: + s = Path(f).suffix.lower() # file suffix + if len(s): + assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}" + + +def check_yaml(file, suffix=('.yaml', '.yml')): + # Search/download YAML file (if necessary) and return path, checking suffix + return check_file(file, suffix) + + +def check_file(file, suffix=''): + # Search/download file (if necessary) and return path + check_suffix(file, suffix) # optional + file = str(file) # convert to str() + if Path(file).is_file() or file == '': # exists + return file + elif file.startswith(('http:/', 'https:/')): # download + url = str(Path(file)).replace(':/', '://') # Pathlib turns :// -> :/ + file = Path(urllib.parse.unquote(file).split('?')[0]).name # '%2F' to '/', split https://url.com/file.txt?auth + if Path(file).is_file(): + LOGGER.info(f'Found {url} locally at {file}') # file already exists + else: + LOGGER.info(f'Downloading {url} to {file}...') + torch.hub.download_url_to_file(url, file) + assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}' # check + return file + else: # search + files = [] + for d in 'data', 'models', 'utils': # search directories + files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True)) # find file + assert len(files), f'File not found: {file}' # assert file was found + assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique + return files[0] # return file + + +def check_font(font=FONT): + # Download font to CONFIG_DIR if necessary + font = Path(font) + if not font.exists() and not (CONFIG_DIR / font.name).exists(): + url = "https://ultralytics.com/assets/" + font.name + LOGGER.info(f'Downloading {url} to {CONFIG_DIR / font.name}...') + torch.hub.download_url_to_file(url, str(font), progress=False) + + +def check_dataset(data, autodownload=True): + # Download and/or unzip dataset if not found locally + # Usage: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128_with_yaml.zip + + # Download (optional) + extract_dir = '' + if isinstance(data, (str, Path)) and str(data).endswith('.zip'): # i.e. gs://bucket/dir/coco128.zip + download(data, dir=DATASETS_DIR, unzip=True, delete=False, curl=False, threads=1) + data = next((DATASETS_DIR / Path(data).stem).rglob('*.yaml')) + extract_dir, autodownload = data.parent, False + + # Read yaml (optional) + if isinstance(data, (str, Path)): + with open(data, errors='ignore') as f: + data = yaml.safe_load(f) # dictionary + + # Resolve paths + path = Path(extract_dir or data.get('path') or '') # optional 'path' default to '.' + if not path.is_absolute(): + path = (ROOT / path).resolve() + for k in 'train', 'val', 'test': + if data.get(k): # prepend path + data[k] = str(path / data[k]) if isinstance(data[k], str) else [str(path / x) for x in data[k]] + + # Parse yaml + assert 'nc' in data, "Dataset 'nc' key missing." + if 'names' not in data: + data['names'] = [f'class{i}' for i in range(data['nc'])] # assign class names if missing + train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download')) + if val: + val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path + if not all(x.exists() for x in val): + LOGGER.info('\nDataset not found, missing paths: %s' % [str(x) for x in val if not x.exists()]) + if s and autodownload: # download script + root = path.parent if 'path' in data else '..' # unzip directory i.e. '../' + if s.startswith('http') and s.endswith('.zip'): # URL + f = Path(s).name # filename + LOGGER.info(f'Downloading {s} to {f}...') + torch.hub.download_url_to_file(s, f) + Path(root).mkdir(parents=True, exist_ok=True) # create root + ZipFile(f).extractall(path=root) # unzip + Path(f).unlink() # remove zip + r = None # success + elif s.startswith('bash '): # bash script + LOGGER.info(f'Running {s} ...') + r = os.system(s) + else: # python script + r = exec(s, {'yaml': data}) # return None + LOGGER.info(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}\n") + else: + raise Exception('Dataset not found.') + + return data # dictionary + + +def url2file(url): + # Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt + url = str(Path(url)).replace(':/', '://') # Pathlib turns :// -> :/ + file = Path(urllib.parse.unquote(url)).name.split('?')[0] # '%2F' to '/', split https://url.com/file.txt?auth + return file + + +def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1): + # Multi-threaded file download and unzip function, used in data.yaml for autodownload + def download_one(url, dir): + # Download 1 file + f = dir / Path(url).name # filename + if Path(url).is_file(): # exists in current path + Path(url).rename(f) # move to dir + elif not f.exists(): + LOGGER.info(f'Downloading {url} to {f}...') + if curl: + os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -") # curl download, retry and resume on fail + else: + torch.hub.download_url_to_file(url, f, progress=True) # torch download + if unzip and f.suffix in ('.zip', '.gz'): + LOGGER.info(f'Unzipping {f}...') + if f.suffix == '.zip': + ZipFile(f).extractall(path=dir) # unzip + elif f.suffix == '.gz': + os.system(f'tar xfz {f} --directory {f.parent}') # unzip + if delete: + f.unlink() # remove zip + + dir = Path(dir) + dir.mkdir(parents=True, exist_ok=True) # make directory + if threads > 1: + pool = ThreadPool(threads) + pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multi-threaded + pool.close() + pool.join() + else: + for u in [url] if isinstance(url, (str, Path)) else url: + download_one(u, dir) + + +def make_divisible(x, divisor): + # Returns nearest x divisible by divisor + if isinstance(divisor, torch.Tensor): + divisor = int(divisor.max()) # to int + return math.ceil(x / divisor) * divisor + + +def clean_str(s): + # Cleans a string by replacing special characters with underscore _ + return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s) + + +def one_cycle(y1=0.0, y2=1.0, steps=100): + # lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf + return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1 + + +def colorstr(*input): + # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world') + *args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string + colors = {'black': '\033[30m', # basic colors + 'red': '\033[31m', + 'green': '\033[32m', + 'yellow': '\033[33m', + 'blue': '\033[34m', + 'magenta': '\033[35m', + 'cyan': '\033[36m', + 'white': '\033[37m', + 'bright_black': '\033[90m', # bright colors + 'bright_red': '\033[91m', + 'bright_green': '\033[92m', + 'bright_yellow': '\033[93m', + 'bright_blue': '\033[94m', + 'bright_magenta': '\033[95m', + 'bright_cyan': '\033[96m', + 'bright_white': '\033[97m', + 'end': '\033[0m', # misc + 'bold': '\033[1m', + 'underline': '\033[4m'} + return ''.join(colors[x] for x in args) + f'{string}' + colors['end'] + + +def labels_to_class_weights(labels, nc=80): + # Get class weights (inverse frequency) from training labels + if labels[0] is None: # no labels loaded + return torch.Tensor() + + labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO + classes = labels[:, 0].astype(np.int) # labels = [class xywh] + weights = np.bincount(classes, minlength=nc) # occurrences per class + + # Prepend gridpoint count (for uCE training) + # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image + # weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start + + weights[weights == 0] = 1 # replace empty bins with 1 + weights = 1 / weights # number of targets per class + weights /= weights.sum() # normalize + return torch.from_numpy(weights) + + +def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)): + # Produces image weights based on class_weights and image contents + class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels]) + image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1) + # index = random.choices(range(n), weights=image_weights, k=1) # weight image sample + return image_weights + + +def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper) + # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/ + # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n') + # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n') + # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco + # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet + x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34, + 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, + 64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90] + return x + + +def xyxy2xywh(x): + # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center + y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center + y[:, 2] = x[:, 2] - x[:, 0] # width + y[:, 3] = x[:, 3] - x[:, 1] # height + return y + + +def xywh2xyxy(x): + # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x + y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y + y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x + y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y + return y + + +def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): + # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x + y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y + y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x + y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y + return y + + +def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0): + # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right + if clip: + clip_coords(x, (h - eps, w - eps)) # warning: inplace clip + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w # x center + y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h # y center + y[:, 2] = (x[:, 2] - x[:, 0]) / w # width + y[:, 3] = (x[:, 3] - x[:, 1]) / h # height + return y + + +def xyn2xy(x, w=640, h=640, padw=0, padh=0): + # Convert normalized segments into pixel segments, shape (n,2) + y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x) + y[:, 0] = w * x[:, 0] + padw # top left x + y[:, 1] = h * x[:, 1] + padh # top left y + return y + + +def segment2box(segment, width=640, height=640): + # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy) + x, y = segment.T # segment xy + inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height) + x, y, = x[inside], y[inside] + return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy + + +def segments2boxes(segments): + # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh) + boxes = [] + for s in segments: + x, y = s.T # segment xy + boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy + return xyxy2xywh(np.array(boxes)) # cls, xywh + + +def resample_segments(segments, n=1000): + # Up-sample an (n,2) segment + for i, s in enumerate(segments): + x = np.linspace(0, len(s) - 1, n) + xp = np.arange(len(s)) + segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy + return segments + + +def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None): + # Rescale coords (xyxy) from img1_shape to img0_shape + if ratio_pad is None: # calculate from img0_shape + gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new + pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding + else: + gain = ratio_pad[0][0] + pad = ratio_pad[1] + + coords[:, [0, 2]] -= pad[0] # x padding + coords[:, [1, 3]] -= pad[1] # y padding + coords[:, :4] /= gain + clip_coords(coords, img0_shape) + return coords + + +def clip_coords(boxes, shape): + # Clip bounding xyxy bounding boxes to image shape (height, width) + if isinstance(boxes, torch.Tensor): # faster individually + boxes[:, 0].clamp_(0, shape[1]) # x1 + boxes[:, 1].clamp_(0, shape[0]) # y1 + boxes[:, 2].clamp_(0, shape[1]) # x2 + boxes[:, 3].clamp_(0, shape[0]) # y2 + else: # np.array (faster grouped) + boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2 + boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2 + + +def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False, + labels=(), max_det=300): + """Runs Non-Maximum Suppression (NMS) on inference results + + Returns: + list of detections, on (n,6) tensor per image [xyxy, conf, cls] + """ + + nc = prediction.shape[2] - 5 # number of classes + xc = prediction[..., 4] > conf_thres # candidates + + # Checks + assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0' + assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0' + + # Settings + min_wh, max_wh = 2, 7680 # (pixels) minimum and maximum box width and height + max_nms = 30000 # maximum number of boxes into torchvision.ops.nms() + time_limit = 10.0 # seconds to quit after + redundant = True # require redundant detections + multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img) + merge = False # use merge-NMS + + t = time.time() + output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0] + for xi, x in enumerate(prediction): # image index, image inference + # Apply constraints + x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height + x = x[xc[xi]] # confidence + + # Cat apriori labels if autolabelling + if labels and len(labels[xi]): + lb = labels[xi] + v = torch.zeros((len(lb), nc + 5), device=x.device) + v[:, :4] = lb[:, 1:5] # box + v[:, 4] = 1.0 # conf + v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls + x = torch.cat((x, v), 0) + + # If none remain process next image + if not x.shape[0]: + continue + + # Compute conf + x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf + + # Box (center x, center y, width, height) to (x1, y1, x2, y2) + box = xywh2xyxy(x[:, :4]) + + # Detections matrix nx6 (xyxy, conf, cls) + if multi_label: + i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T + x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1) + else: # best class only + conf, j = x[:, 5:].max(1, keepdim=True) + x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres] + + # Filter by class + if classes is not None: + x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)] + + # Apply finite constraint + # if not torch.isfinite(x).all(): + # x = x[torch.isfinite(x).all(1)] + + # Check shape + n = x.shape[0] # number of boxes + if not n: # no boxes + continue + elif n > max_nms: # excess boxes + x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence + + # Batched NMS + c = x[:, 5:6] * (0 if agnostic else max_wh) # classes + boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores + i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS + if i.shape[0] > max_det: # limit detections + i = i[:max_det] + if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean) + # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4) + iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix + weights = iou * scores[None] # box weights + x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes + if redundant: + i = i[iou.sum(1) > 1] # require redundancy + + output[xi] = x[i] + if (time.time() - t) > time_limit: + LOGGER.warning(f'WARNING: NMS time limit {time_limit}s exceeded') + break # time limit exceeded + + return output + + +def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_optimizer() + # Strip optimizer from 'f' to finalize training, optionally save as 's' + x = torch.load(f, map_location=torch.device('cpu')) + if x.get('ema'): + x['model'] = x['ema'] # replace model with ema + for k in 'optimizer', 'best_fitness', 'wandb_id', 'ema', 'updates': # keys + x[k] = None + x['epoch'] = -1 + x['model'].half() # to FP16 + for p in x['model'].parameters(): + p.requires_grad = False + torch.save(x, s or f) + mb = os.path.getsize(s or f) / 1E6 # filesize + LOGGER.info(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB") + + +def print_mutation(results, hyp, save_dir, bucket, prefix=colorstr('evolve: ')): + evolve_csv = save_dir / 'evolve.csv' + evolve_yaml = save_dir / 'hyp_evolve.yaml' + keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', + 'val/box_loss', 'val/obj_loss', 'val/cls_loss') + tuple(hyp.keys()) # [results + hyps] + keys = tuple(x.strip() for x in keys) + vals = results + tuple(hyp.values()) + n = len(keys) + + # Download (optional) + if bucket: + url = f'gs://{bucket}/evolve.csv' + if gsutil_getsize(url) > (evolve_csv.stat().st_size if evolve_csv.exists() else 0): + os.system(f'gsutil cp {url} {save_dir}') # download evolve.csv if larger than local + + # Log to evolve.csv + s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n') # add header + with open(evolve_csv, 'a') as f: + f.write(s + ('%20.5g,' * n % vals).rstrip(',') + '\n') + + # Save yaml + with open(evolve_yaml, 'w') as f: + data = pd.read_csv(evolve_csv) + data = data.rename(columns=lambda x: x.strip()) # strip keys + i = np.argmax(fitness(data.values[:, :4])) # + generations = len(data) + f.write('# YOLOv5 Hyperparameter Evolution Results\n' + + f'# Best generation: {i}\n' + + f'# Last generation: {generations - 1}\n' + + '# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + '\n' + + '# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n') + yaml.safe_dump(data.loc[i][7:].to_dict(), f, sort_keys=False) + + # Print to screen + LOGGER.info(prefix + f'{generations} generations finished, current result:\n' + + prefix + ', '.join(f'{x.strip():>20s}' for x in keys) + '\n' + + prefix + ', '.join(f'{x:20.5g}' for x in vals) + '\n\n') + + if bucket: + os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}') # upload + + +def apply_classifier(x, model, img, im0): + # Apply a second stage classifier to YOLO outputs + # Example model = torchvision.models.__dict__['efficientnet_b0'](pretrained=True).to(device).eval() + im0 = [im0] if isinstance(im0, np.ndarray) else im0 + for i, d in enumerate(x): # per image + if d is not None and len(d): + d = d.clone() + + # Reshape and pad cutouts + b = xyxy2xywh(d[:, :4]) # boxes + b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square + b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad + d[:, :4] = xywh2xyxy(b).long() + + # Rescale boxes from img_size to im0 size + scale_coords(img.shape[2:], d[:, :4], im0[i].shape) + + # Classes + pred_cls1 = d[:, 5].long() + ims = [] + for j, a in enumerate(d): # per item + cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])] + im = cv2.resize(cutout, (224, 224)) # BGR + # cv2.imwrite('example%i.jpg' % j, cutout) + + im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 + im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32 + im /= 255 # 0 - 255 to 0.0 - 1.0 + ims.append(im) + + pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction + x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections + + return x + + +def increment_path(path, exist_ok=False, sep='', mkdir=False): + # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. + path = Path(path) # os-agnostic + if path.exists() and not exist_ok: + path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '') + dirs = glob.glob(f"{path}{sep}*") # similar paths + matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs] + i = [int(m.groups()[0]) for m in matches if m] # indices + n = max(i) + 1 if i else 2 # increment number + path = Path(f"{path}{sep}{n}{suffix}") # increment path + if mkdir: + path.mkdir(parents=True, exist_ok=True) # make directory + return path + + +# Variables +NCOLS = 0 if is_docker() else shutil.get_terminal_size().columns # terminal window size for tqdm diff --git a/yolov5_Monocular_social_ranging/utils/google_app_engine/Dockerfile b/yolov5_Monocular_social_ranging/utils/google_app_engine/Dockerfile new file mode 100644 index 0000000..0155618 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/google_app_engine/Dockerfile @@ -0,0 +1,25 @@ +FROM gcr.io/google-appengine/python + +# Create a virtualenv for dependencies. This isolates these packages from +# system-level packages. +# Use -p python3 or -p python3.7 to select python version. Default is version 2. +RUN virtualenv /env -p python3 + +# Setting these environment variables are the same as running +# source /env/bin/activate. +ENV VIRTUAL_ENV /env +ENV PATH /env/bin:$PATH + +RUN apt-get update && apt-get install -y python-opencv + +# Copy the application's requirements.txt and run pip to install all +# dependencies into the virtualenv. +ADD requirements.txt /app/requirements.txt +RUN pip install -r /app/requirements.txt + +# Add the application source code. +ADD . /app + +# Run a WSGI server to serve the application. gunicorn must be declared as +# a dependency in requirements.txt. +CMD gunicorn -b :$PORT main:app diff --git a/yolov5_Monocular_social_ranging/utils/google_app_engine/additional_requirements.txt b/yolov5_Monocular_social_ranging/utils/google_app_engine/additional_requirements.txt new file mode 100644 index 0000000..42d7ffc --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/google_app_engine/additional_requirements.txt @@ -0,0 +1,4 @@ +# add these requirements in your app on top of the existing ones +pip==21.1 +Flask==1.0.2 +gunicorn==19.9.0 diff --git a/yolov5_Monocular_social_ranging/utils/google_app_engine/app.yaml b/yolov5_Monocular_social_ranging/utils/google_app_engine/app.yaml new file mode 100644 index 0000000..5056b7c --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/google_app_engine/app.yaml @@ -0,0 +1,14 @@ +runtime: custom +env: flex + +service: yolov5app + +liveness_check: + initial_delay_sec: 600 + +manual_scaling: + instances: 1 +resources: + cpu: 1 + memory_gb: 4 + disk_size_gb: 20 diff --git a/yolov5_Monocular_social_ranging/utils/loggers/__init__.py b/yolov5_Monocular_social_ranging/utils/loggers/__init__.py new file mode 100644 index 0000000..86ccf38 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/__init__.py @@ -0,0 +1,168 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Logging utils +""" + +import os +import warnings +from threading import Thread + +import pkg_resources as pkg +import torch +from torch.utils.tensorboard import SummaryWriter + +from utils.general import colorstr, emojis +from utils.loggers.wandb.wandb_utils import WandbLogger +from utils.plots import plot_images, plot_results +from utils.torch_utils import de_parallel + +LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases +RANK = int(os.getenv('RANK', -1)) + +try: + import wandb + + assert hasattr(wandb, '__version__') # verify package import not local dir + if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]: + try: + wandb_login_success = wandb.login(timeout=30) + except wandb.errors.UsageError: # known non-TTY terminal issue + wandb_login_success = False + if not wandb_login_success: + wandb = None +except (ImportError, AssertionError): + wandb = None + + +class Loggers(): + # YOLOv5 Loggers class + def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS): + self.save_dir = save_dir + self.weights = weights + self.opt = opt + self.hyp = hyp + self.logger = logger # for printing results to console + self.include = include + self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss + 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics + 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss + 'x/lr0', 'x/lr1', 'x/lr2'] # params + self.best_keys = ['best/epoch', 'best/precision', 'best/recall', 'best/mAP_0.5', 'best/mAP_0.5:0.95',] + for k in LOGGERS: + setattr(self, k, None) # init empty logger dictionary + self.csv = True # always log to csv + + # Message + if not wandb: + prefix = colorstr('Weights & Biases: ') + s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)" + print(emojis(s)) + + # TensorBoard + s = self.save_dir + if 'tb' in self.include and not self.opt.evolve: + prefix = colorstr('TensorBoard: ') + self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/") + self.tb = SummaryWriter(str(s)) + + # W&B + if wandb and 'wandb' in self.include: + wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') + run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None + self.opt.hyp = self.hyp # add hyperparameters + self.wandb = WandbLogger(self.opt, run_id) + else: + self.wandb = None + + def on_pretrain_routine_end(self): + # Callback runs on pre-train routine end + paths = self.save_dir.glob('*labels*.jpg') # training labels + if self.wandb: + self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) + + def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn): + # Callback runs on train batch end + if plots: + if ni == 0: + if not sync_bn: # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754 + with warnings.catch_warnings(): + warnings.simplefilter('ignore') # suppress jit trace warning + self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), []) + if ni < 3: + f = self.save_dir / f'train_batch{ni}.jpg' # filename + Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start() + if self.wandb and ni == 10: + files = sorted(self.save_dir.glob('train*.jpg')) + self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]}) + + def on_train_epoch_end(self, epoch): + # Callback runs on train epoch end + if self.wandb: + self.wandb.current_epoch = epoch + 1 + + def on_val_image_end(self, pred, predn, path, names, im): + # Callback runs on val image end + if self.wandb: + self.wandb.val_one_image(pred, predn, path, names, im) + + def on_val_end(self): + # Callback runs on val end + if self.wandb: + files = sorted(self.save_dir.glob('val*.jpg')) + self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) + + def on_fit_epoch_end(self, vals, epoch, best_fitness, fi): + # Callback runs at the end of each fit (train+val) epoch + x = {k: v for k, v in zip(self.keys, vals)} # dict + if self.csv: + file = self.save_dir / 'results.csv' + n = len(x) + 1 # number of cols + s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header + with open(file, 'a') as f: + f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') + + if self.tb: + for k, v in x.items(): + self.tb.add_scalar(k, v, epoch) + + if self.wandb: + if best_fitness == fi: + best_results = [epoch] + vals[3:7] + for i, name in enumerate(self.best_keys): + self.wandb.wandb_run.summary[name] = best_results[i] # log best results in the summary + self.wandb.log(x) + self.wandb.end_epoch(best_result=best_fitness == fi) + + def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): + # Callback runs on model save event + if self.wandb: + if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1: + self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) + + def on_train_end(self, last, best, plots, epoch, results): + # Callback runs on training end + if plots: + plot_results(file=self.save_dir / 'results.csv') # save results.png + files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))] + files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter + + if self.tb: + import cv2 + for f in files: + self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') + + if self.wandb: + self.wandb.log({k: v for k, v in zip(self.keys[3:10], results)}) # log best.pt val results + self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) + # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model + if not self.opt.evolve: + wandb.log_artifact(str(best if best.exists() else last), type='model', + name='run_' + self.wandb.wandb_run.id + '_model', + aliases=['latest', 'best', 'stripped']) + self.wandb.finish_run() + + def on_params_update(self, params): + # Update hyperparams or configs of the experiment + # params: A dict containing {param: value} pairs + if self.wandb: + self.wandb.wandb_run.config.update(params, allow_val_change=True) diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/README.md b/yolov5_Monocular_social_ranging/utils/loggers/wandb/README.md new file mode 100644 index 0000000..63d9998 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/wandb/README.md @@ -0,0 +1,152 @@ +📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 29 September 2021. +* [About Weights & Biases](#about-weights-&-biases) +* [First-Time Setup](#first-time-setup) +* [Viewing runs](#viewing-runs) +* [Disabling wandb](#disabling-wandb) +* [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) +* [Reports: Share your work with the world!](#reports) + +## About Weights & Biases +Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions. + +Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows: + + * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time + * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically + * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization + * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators + * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently + * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models + +## First-Time Setup +
+ Toggle Details +When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device. + +W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as: + + ```shell + $ python train.py --project ... --name ... + ``` + +YOLOv5 notebook example: Open In Colab Open In Kaggle +Screen Shot 2021-09-29 at 10 23 13 PM + + +
+ +## Viewing Runs +
+ Toggle Details +Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged: + + * Training & Validation losses + * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 + * Learning Rate over time + * A bounding box debugging panel, showing the training progress over time + * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** + * System: Disk I/0, CPU utilization, RAM memory usage + * Your trained model as W&B Artifact + * Environment: OS and Python types, Git repository and state, **training command** + +

Weights & Biases dashboard

+
+ + ## Disabling wandb +* training after running `wandb disabled` inside that directory creates no wandb run +![Screenshot (84)](https://user-images.githubusercontent.com/15766192/143441777-c780bdd7-7cb4-4404-9559-b4316030a985.png) + +* To enable wandb again, run `wandb online` +![Screenshot (85)](https://user-images.githubusercontent.com/15766192/143441866-7191b2cb-22f0-4e0f-ae64-2dc47dc13078.png) + +## Advanced Usage +You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started. +
+

1: Train and Log Evaluation simultaneousy

+ This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table + Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, + so no images will be uploaded from your system more than once. +
+ Usage + Code $ python train.py --upload_data val + +![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png) +
+ +

2. Visualize and Version Datasets

+ Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact. +
+ Usage + Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. + + ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) +
+ +

3: Train using dataset artifact

+ When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that + can be used to train a model directly from the dataset artifact. This also logs evaluation +
+ Usage + Code $ python train.py --data {data}_wandb.yaml + +![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) +
+ +

4: Save model checkpoints as artifacts

+ To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. + You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged + +
+ Usage + Code $ python train.py --save_period 1 + +![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) +
+ +
+ +

5: Resume runs from checkpoint artifacts.

+Any run can be resumed using artifacts if the --resume argument starts with wandb-artifact:// prefix followed by the run path, i.e, wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system. + +
+ Usage + Code $ python train.py --resume wandb-artifact://{run_path} + +![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) +
+ +

6: Resume runs from dataset artifact & checkpoint artifacts.

+ Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device + The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset or + train from _wandb.yaml file and set --save_period + +
+ Usage + Code $ python train.py --resume wandb-artifact://{run_path} + +![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) +
+ + + +

Reports

+W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)). + +Weights & Biases Reports + + +## Environments + +YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): + +- **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle +- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) +- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) +- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls + + +## Status + +![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) + +If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit. diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/__init__.py b/yolov5_Monocular_social_ranging/utils/loggers/wandb/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/log_dataset.py b/yolov5_Monocular_social_ranging/utils/loggers/wandb/log_dataset.py new file mode 100644 index 0000000..06e81fb --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/wandb/log_dataset.py @@ -0,0 +1,27 @@ +import argparse + +from wandb_utils import WandbLogger + +from utils.general import LOGGER + +WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' + + +def create_dataset_artifact(opt): + logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused + if not logger.wandb: + LOGGER.info("install wandb using `pip install wandb` to log the dataset") + + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path') + parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') + parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project') + parser.add_argument('--entity', default=None, help='W&B entity') + parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run') + + opt = parser.parse_args() + opt.resume = False # Explicitly disallow resume check for dataset upload job + + create_dataset_artifact(opt) diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.py b/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.py new file mode 100644 index 0000000..206059b --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.py @@ -0,0 +1,41 @@ +import sys +from pathlib import Path + +import wandb + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[3] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH + +from train import parse_opt, train +from utils.callbacks import Callbacks +from utils.general import increment_path +from utils.torch_utils import select_device + + +def sweep(): + wandb.init() + # Get hyp dict from sweep agent + hyp_dict = vars(wandb.config).get("_items") + + # Workaround: get necessary opt args + opt = parse_opt(known=True) + opt.batch_size = hyp_dict.get("batch_size") + opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) + opt.epochs = hyp_dict.get("epochs") + opt.nosave = True + opt.data = hyp_dict.get("data") + opt.weights = str(opt.weights) + opt.cfg = str(opt.cfg) + opt.data = str(opt.data) + opt.hyp = str(opt.hyp) + opt.project = str(opt.project) + device = select_device(opt.device, batch_size=opt.batch_size) + + # train + train(hyp_dict, opt, device, callbacks=Callbacks()) + + +if __name__ == "__main__": + sweep() diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.yaml b/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.yaml new file mode 100644 index 0000000..c7790d7 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/wandb/sweep.yaml @@ -0,0 +1,143 @@ +# Hyperparameters for training +# To set range- +# Provide min and max values as: +# parameter: +# +# min: scalar +# max: scalar +# OR +# +# Set a specific list of search space- +# parameter: +# values: [scalar1, scalar2, scalar3...] +# +# You can use grid, bayesian and hyperopt search strategy +# For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration + +program: utils/loggers/wandb/sweep.py +method: random +metric: + name: metrics/mAP_0.5 + goal: maximize + +parameters: + # hyperparameters: set either min, max range or values list + data: + value: "data/coco128.yaml" + batch_size: + values: [64] + epochs: + values: [10] + + lr0: + distribution: uniform + min: 1e-5 + max: 1e-1 + lrf: + distribution: uniform + min: 0.01 + max: 1.0 + momentum: + distribution: uniform + min: 0.6 + max: 0.98 + weight_decay: + distribution: uniform + min: 0.0 + max: 0.001 + warmup_epochs: + distribution: uniform + min: 0.0 + max: 5.0 + warmup_momentum: + distribution: uniform + min: 0.0 + max: 0.95 + warmup_bias_lr: + distribution: uniform + min: 0.0 + max: 0.2 + box: + distribution: uniform + min: 0.02 + max: 0.2 + cls: + distribution: uniform + min: 0.2 + max: 4.0 + cls_pw: + distribution: uniform + min: 0.5 + max: 2.0 + obj: + distribution: uniform + min: 0.2 + max: 4.0 + obj_pw: + distribution: uniform + min: 0.5 + max: 2.0 + iou_t: + distribution: uniform + min: 0.1 + max: 0.7 + anchor_t: + distribution: uniform + min: 2.0 + max: 8.0 + fl_gamma: + distribution: uniform + min: 0.0 + max: 0.1 + hsv_h: + distribution: uniform + min: 0.0 + max: 0.1 + hsv_s: + distribution: uniform + min: 0.0 + max: 0.9 + hsv_v: + distribution: uniform + min: 0.0 + max: 0.9 + degrees: + distribution: uniform + min: 0.0 + max: 45.0 + translate: + distribution: uniform + min: 0.0 + max: 0.9 + scale: + distribution: uniform + min: 0.0 + max: 0.9 + shear: + distribution: uniform + min: 0.0 + max: 10.0 + perspective: + distribution: uniform + min: 0.0 + max: 0.001 + flipud: + distribution: uniform + min: 0.0 + max: 1.0 + fliplr: + distribution: uniform + min: 0.0 + max: 1.0 + mosaic: + distribution: uniform + min: 0.0 + max: 1.0 + mixup: + distribution: uniform + min: 0.0 + max: 1.0 + copy_paste: + distribution: uniform + min: 0.0 + max: 1.0 diff --git a/yolov5_Monocular_social_ranging/utils/loggers/wandb/wandb_utils.py b/yolov5_Monocular_social_ranging/utils/loggers/wandb/wandb_utils.py new file mode 100644 index 0000000..3835436 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loggers/wandb/wandb_utils.py @@ -0,0 +1,562 @@ +"""Utilities and tools for tracking runs with Weights & Biases.""" + +import logging +import os +import sys +from contextlib import contextmanager +from pathlib import Path +from typing import Dict + +import yaml +from tqdm import tqdm + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[3] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH + +from utils.datasets import LoadImagesAndLabels, img2label_paths +from utils.general import LOGGER, check_dataset, check_file + +try: + import wandb + + assert hasattr(wandb, '__version__') # verify package import not local dir +except (ImportError, AssertionError): + wandb = None + +RANK = int(os.getenv('RANK', -1)) +WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' + + +def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX): + return from_string[len(prefix):] + + +def check_wandb_config_file(data_config_file): + wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path + if Path(wandb_config).is_file(): + return wandb_config + return data_config_file + + +def check_wandb_dataset(data_file): + is_trainset_wandb_artifact = False + is_valset_wandb_artifact = False + if check_file(data_file) and data_file.endswith('.yaml'): + with open(data_file, errors='ignore') as f: + data_dict = yaml.safe_load(f) + is_trainset_wandb_artifact = (isinstance(data_dict['train'], str) and + data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX)) + is_valset_wandb_artifact = (isinstance(data_dict['val'], str) and + data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX)) + if is_trainset_wandb_artifact or is_valset_wandb_artifact: + return data_dict + else: + return check_dataset(data_file) + + +def get_run_info(run_path): + run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX)) + run_id = run_path.stem + project = run_path.parent.stem + entity = run_path.parent.parent.stem + model_artifact_name = 'run_' + run_id + '_model' + return entity, project, run_id, model_artifact_name + + +def check_wandb_resume(opt): + process_wandb_config_ddp_mode(opt) if RANK not in [-1, 0] else None + if isinstance(opt.resume, str): + if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): + if RANK not in [-1, 0]: # For resuming DDP runs + entity, project, run_id, model_artifact_name = get_run_info(opt.resume) + api = wandb.Api() + artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest') + modeldir = artifact.download() + opt.weights = str(Path(modeldir) / "last.pt") + return True + return None + + +def process_wandb_config_ddp_mode(opt): + with open(check_file(opt.data), errors='ignore') as f: + data_dict = yaml.safe_load(f) # data dict + train_dir, val_dir = None, None + if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX): + api = wandb.Api() + train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias) + train_dir = train_artifact.download() + train_path = Path(train_dir) / 'data/images/' + data_dict['train'] = str(train_path) + + if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX): + api = wandb.Api() + val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias) + val_dir = val_artifact.download() + val_path = Path(val_dir) / 'data/images/' + data_dict['val'] = str(val_path) + if train_dir or val_dir: + ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml') + with open(ddp_data_path, 'w') as f: + yaml.safe_dump(data_dict, f) + opt.data = ddp_data_path + + +class WandbLogger(): + """Log training runs, datasets, models, and predictions to Weights & Biases. + + This logger sends information to W&B at wandb.ai. By default, this information + includes hyperparameters, system configuration and metrics, model metrics, + and basic data metrics and analyses. + + By providing additional command line arguments to train.py, datasets, + models and predictions can also be logged. + + For more on how this logger is used, see the Weights & Biases documentation: + https://docs.wandb.com/guides/integrations/yolov5 + """ + + def __init__(self, opt, run_id=None, job_type='Training'): + """ + - Initialize WandbLogger instance + - Upload dataset if opt.upload_dataset is True + - Setup trainig processes if job_type is 'Training' + + arguments: + opt (namespace) -- Commandline arguments for this run + run_id (str) -- Run ID of W&B run to be resumed + job_type (str) -- To set the job_type for this run + + """ + # Pre-training routine -- + self.job_type = job_type + self.wandb, self.wandb_run = wandb, None if not wandb else wandb.run + self.val_artifact, self.train_artifact = None, None + self.train_artifact_path, self.val_artifact_path = None, None + self.result_artifact = None + self.val_table, self.result_table = None, None + self.bbox_media_panel_images = [] + self.val_table_path_map = None + self.max_imgs_to_log = 16 + self.wandb_artifact_data_dict = None + self.data_dict = None + # It's more elegant to stick to 1 wandb.init call, + # but useful config data is overwritten in the WandbLogger's wandb.init call + if isinstance(opt.resume, str): # checks resume from artifact + if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): + entity, project, run_id, model_artifact_name = get_run_info(opt.resume) + model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name + assert wandb, 'install wandb to resume wandb runs' + # Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config + self.wandb_run = wandb.init(id=run_id, + project=project, + entity=entity, + resume='allow', + allow_val_change=True) + opt.resume = model_artifact_name + elif self.wandb: + self.wandb_run = wandb.init(config=opt, + resume="allow", + project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem, + entity=opt.entity, + name=opt.name if opt.name != 'exp' else None, + job_type=job_type, + id=run_id, + allow_val_change=True) if not wandb.run else wandb.run + if self.wandb_run: + if self.job_type == 'Training': + if opt.upload_dataset: + if not opt.resume: + self.wandb_artifact_data_dict = self.check_and_upload_dataset(opt) + + if opt.resume: + # resume from artifact + if isinstance(opt.resume, str) and opt.resume.startswith(WANDB_ARTIFACT_PREFIX): + self.data_dict = dict(self.wandb_run.config.data_dict) + else: # local resume + self.data_dict = check_wandb_dataset(opt.data) + else: + self.data_dict = check_wandb_dataset(opt.data) + self.wandb_artifact_data_dict = self.wandb_artifact_data_dict or self.data_dict + + # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming. + self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict}, + allow_val_change=True) + self.setup_training(opt) + + if self.job_type == 'Dataset Creation': + self.wandb_run.config.update({"upload_dataset": True}) + self.data_dict = self.check_and_upload_dataset(opt) + + def check_and_upload_dataset(self, opt): + """ + Check if the dataset format is compatible and upload it as W&B artifact + + arguments: + opt (namespace)-- Commandline arguments for current run + + returns: + Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links. + """ + assert wandb, 'Install wandb to upload dataset' + config_path = self.log_dataset_artifact(opt.data, + opt.single_cls, + 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem) + with open(config_path, errors='ignore') as f: + wandb_data_dict = yaml.safe_load(f) + return wandb_data_dict + + def setup_training(self, opt): + """ + Setup the necessary processes for training YOLO models: + - Attempt to download model checkpoint and dataset artifacts if opt.resume stats with WANDB_ARTIFACT_PREFIX + - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded + - Setup log_dict, initialize bbox_interval + + arguments: + opt (namespace) -- commandline arguments for this run + + """ + self.log_dict, self.current_epoch = {}, 0 + self.bbox_interval = opt.bbox_interval + if isinstance(opt.resume, str): + modeldir, _ = self.download_model_artifact(opt) + if modeldir: + self.weights = Path(modeldir) / "last.pt" + config = self.wandb_run.config + opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp, opt.imgsz = str( + self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs,\ + config.hyp, config.imgsz + data_dict = self.data_dict + if self.val_artifact is None: # If --upload_dataset is set, use the existing artifact, don't download + self.train_artifact_path, self.train_artifact = self.download_dataset_artifact(data_dict.get('train'), + opt.artifact_alias) + self.val_artifact_path, self.val_artifact = self.download_dataset_artifact(data_dict.get('val'), + opt.artifact_alias) + + if self.train_artifact_path is not None: + train_path = Path(self.train_artifact_path) / 'data/images/' + data_dict['train'] = str(train_path) + if self.val_artifact_path is not None: + val_path = Path(self.val_artifact_path) / 'data/images/' + data_dict['val'] = str(val_path) + + if self.val_artifact is not None: + self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") + columns = ["epoch", "id", "ground truth", "prediction"] + columns.extend(self.data_dict['names']) + self.result_table = wandb.Table(columns) + self.val_table = self.val_artifact.get("val") + if self.val_table_path_map is None: + self.map_val_table_path() + if opt.bbox_interval == -1: + self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1 + if opt.evolve: + self.bbox_interval = opt.bbox_interval = opt.epochs + 1 + train_from_artifact = self.train_artifact_path is not None and self.val_artifact_path is not None + # Update the the data_dict to point to local artifacts dir + if train_from_artifact: + self.data_dict = data_dict + + def download_dataset_artifact(self, path, alias): + """ + download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX + + arguments: + path -- path of the dataset to be used for training + alias (str)-- alias of the artifact to be download/used for training + + returns: + (str, wandb.Artifact) -- path of the downladed dataset and it's corresponding artifact object if dataset + is found otherwise returns (None, None) + """ + if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX): + artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias) + dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\", "/")) + assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'" + datadir = dataset_artifact.download() + return datadir, dataset_artifact + return None, None + + def download_model_artifact(self, opt): + """ + download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX + + arguments: + opt (namespace) -- Commandline arguments for this run + """ + if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): + model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest") + assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist' + modeldir = model_artifact.download() + # epochs_trained = model_artifact.metadata.get('epochs_trained') + total_epochs = model_artifact.metadata.get('total_epochs') + is_finished = total_epochs is None + assert not is_finished, 'training is finished, can only resume incomplete runs.' + return modeldir, model_artifact + return None, None + + def log_model(self, path, opt, epoch, fitness_score, best_model=False): + """ + Log the model checkpoint as W&B artifact + + arguments: + path (Path) -- Path of directory containing the checkpoints + opt (namespace) -- Command line arguments for this run + epoch (int) -- Current epoch number + fitness_score (float) -- fitness score for current epoch + best_model (boolean) -- Boolean representing if the current checkpoint is the best yet. + """ + model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', type='model', metadata={ + 'original_url': str(path), + 'epochs_trained': epoch + 1, + 'save period': opt.save_period, + 'project': opt.project, + 'total_epochs': opt.epochs, + 'fitness_score': fitness_score + }) + model_artifact.add_file(str(path / 'last.pt'), name='last.pt') + wandb.log_artifact(model_artifact, + aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else '']) + LOGGER.info(f"Saving model artifact on epoch {epoch + 1}") + + def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False): + """ + Log the dataset as W&B artifact and return the new data file with W&B links + + arguments: + data_file (str) -- the .yaml file with information about the dataset like - path, classes etc. + single_class (boolean) -- train multi-class data as single-class + project (str) -- project name. Used to construct the artifact path + overwrite_config (boolean) -- overwrites the data.yaml file if set to true otherwise creates a new + file with _wandb postfix. Eg -> data_wandb.yaml + + returns: + the new .yaml file with artifact links. it can be used to start training directly from artifacts + """ + upload_dataset = self.wandb_run.config.upload_dataset + log_val_only = isinstance(upload_dataset, str) and upload_dataset == 'val' + self.data_dict = check_dataset(data_file) # parse and check + data = dict(self.data_dict) + nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names']) + names = {k: v for k, v in enumerate(names)} # to index dictionary + + # log train set + if not log_val_only: + self.train_artifact = self.create_dataset_table(LoadImagesAndLabels( + data['train'], rect=True, batch_size=1), names, name='train') if data.get('train') else None + if data.get('train'): + data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train') + + self.val_artifact = self.create_dataset_table(LoadImagesAndLabels( + data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None + if data.get('val'): + data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val') + + path = Path(data_file) + # create a _wandb.yaml file with artifacts links if both train and test set are logged + if not log_val_only: + path = (path.stem if overwrite_config else path.stem + '_wandb') + '.yaml' # updated data.yaml path + path = ROOT / 'data' / path + data.pop('download', None) + data.pop('path', None) + with open(path, 'w') as f: + yaml.safe_dump(data, f) + LOGGER.info(f"Created dataset config file {path}") + + if self.job_type == 'Training': # builds correct artifact pipeline graph + if not log_val_only: + self.wandb_run.log_artifact( + self.train_artifact) # calling use_artifact downloads the dataset. NOT NEEDED! + self.wandb_run.use_artifact(self.val_artifact) + self.val_artifact.wait() + self.val_table = self.val_artifact.get('val') + self.map_val_table_path() + else: + self.wandb_run.log_artifact(self.train_artifact) + self.wandb_run.log_artifact(self.val_artifact) + return path + + def map_val_table_path(self): + """ + Map the validation dataset Table like name of file -> it's id in the W&B Table. + Useful for - referencing artifacts for evaluation. + """ + self.val_table_path_map = {} + LOGGER.info("Mapping dataset") + for i, data in enumerate(tqdm(self.val_table.data)): + self.val_table_path_map[data[3]] = data[0] + + def create_dataset_table(self, dataset: LoadImagesAndLabels, class_to_id: Dict[int, str], name: str = 'dataset'): + """ + Create and return W&B artifact containing W&B Table of the dataset. + + arguments: + dataset -- instance of LoadImagesAndLabels class used to iterate over the data to build Table + class_to_id -- hash map that maps class ids to labels + name -- name of the artifact + + returns: + dataset artifact to be logged or used + """ + # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging + artifact = wandb.Artifact(name=name, type="dataset") + img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None + img_files = tqdm(dataset.img_files) if not img_files else img_files + for img_file in img_files: + if Path(img_file).is_dir(): + artifact.add_dir(img_file, name='data/images') + labels_path = 'labels'.join(dataset.path.rsplit('images', 1)) + artifact.add_dir(labels_path, name='data/labels') + else: + artifact.add_file(img_file, name='data/images/' + Path(img_file).name) + label_file = Path(img2label_paths([img_file])[0]) + artifact.add_file(str(label_file), + name='data/labels/' + label_file.name) if label_file.exists() else None + table = wandb.Table(columns=["id", "train_image", "Classes", "name"]) + class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()]) + for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)): + box_data, img_classes = [], {} + for cls, *xywh in labels[:, 1:].tolist(): + cls = int(cls) + box_data.append({"position": {"middle": [xywh[0], xywh[1]], "width": xywh[2], "height": xywh[3]}, + "class_id": cls, + "box_caption": "%s" % (class_to_id[cls])}) + img_classes[cls] = class_to_id[cls] + boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space + table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), list(img_classes.values()), + Path(paths).name) + artifact.add(table, name) + return artifact + + def log_training_progress(self, predn, path, names): + """ + Build evaluation Table. Uses reference from validation dataset table. + + arguments: + predn (list): list of predictions in the native space in the format - [xmin, ymin, xmax, ymax, confidence, class] + path (str): local path of the current evaluation image + names (dict(int, str)): hash map that maps class ids to labels + """ + class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()]) + box_data = [] + avg_conf_per_class = [0] * len(self.data_dict['names']) + pred_class_count = {} + for *xyxy, conf, cls in predn.tolist(): + if conf >= 0.25: + cls = int(cls) + box_data.append( + {"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]}, + "class_id": cls, + "box_caption": f"{names[cls]} {conf:.3f}", + "scores": {"class_score": conf}, + "domain": "pixel"}) + avg_conf_per_class[cls] += conf + + if cls in pred_class_count: + pred_class_count[cls] += 1 + else: + pred_class_count[cls] = 1 + + for pred_class in pred_class_count.keys(): + avg_conf_per_class[pred_class] = avg_conf_per_class[pred_class] / pred_class_count[pred_class] + + boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space + id = self.val_table_path_map[Path(path).name] + self.result_table.add_data(self.current_epoch, + id, + self.val_table.data[id][1], + wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set), + *avg_conf_per_class + ) + + def val_one_image(self, pred, predn, path, names, im): + """ + Log validation data for one image. updates the result Table if validation dataset is uploaded and log bbox media panel + + arguments: + pred (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class] + predn (list): list of predictions in the native space - [xmin, ymin, xmax, ymax, confidence, class] + path (str): local path of the current evaluation image + """ + if self.val_table and self.result_table: # Log Table if Val dataset is uploaded as artifact + self.log_training_progress(predn, path, names) + + if len(self.bbox_media_panel_images) < self.max_imgs_to_log and self.current_epoch > 0: + if self.current_epoch % self.bbox_interval == 0: + box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]}, + "class_id": int(cls), + "box_caption": f"{names[int(cls)]} {conf:.3f}", + "scores": {"class_score": conf}, + "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()] + boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space + self.bbox_media_panel_images.append(wandb.Image(im, boxes=boxes, caption=path.name)) + + def log(self, log_dict): + """ + save the metrics to the logging dictionary + + arguments: + log_dict (Dict) -- metrics/media to be logged in current step + """ + if self.wandb_run: + for key, value in log_dict.items(): + self.log_dict[key] = value + + def end_epoch(self, best_result=False): + """ + commit the log_dict, model artifacts and Tables to W&B and flush the log_dict. + + arguments: + best_result (boolean): Boolean representing if the result of this evaluation is best or not + """ + if self.wandb_run: + with all_logging_disabled(): + if self.bbox_media_panel_images: + self.log_dict["BoundingBoxDebugger"] = self.bbox_media_panel_images + try: + wandb.log(self.log_dict) + except BaseException as e: + LOGGER.info( + f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}") + self.wandb_run.finish() + self.wandb_run = None + + self.log_dict = {} + self.bbox_media_panel_images = [] + if self.result_artifact: + self.result_artifact.add(self.result_table, 'result') + wandb.log_artifact(self.result_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), + ('best' if best_result else '')]) + + wandb.log({"evaluation": self.result_table}) + columns = ["epoch", "id", "ground truth", "prediction"] + columns.extend(self.data_dict['names']) + self.result_table = wandb.Table(columns) + self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") + + def finish_run(self): + """ + Log metrics if any and finish the current W&B run + """ + if self.wandb_run: + if self.log_dict: + with all_logging_disabled(): + wandb.log(self.log_dict) + wandb.run.finish() + + +@contextmanager +def all_logging_disabled(highest_level=logging.CRITICAL): + """ source - https://gist.github.com/simon-weber/7853144 + A context manager that will prevent any logging messages triggered during the body from being processed. + :param highest_level: the maximum logging level in use. + This would only need to be changed if a custom level greater than CRITICAL is defined. + """ + previous_level = logging.root.manager.disable + logging.disable(highest_level) + try: + yield + finally: + logging.disable(previous_level) diff --git a/yolov5_Monocular_social_ranging/utils/loss.py b/yolov5_Monocular_social_ranging/utils/loss.py new file mode 100644 index 0000000..5aa9f01 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/loss.py @@ -0,0 +1,222 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Loss functions +""" + +import torch +import torch.nn as nn + +from utils.metrics import bbox_iou +from utils.torch_utils import de_parallel + + +def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441 + # return positive, negative label smoothing BCE targets + return 1.0 - 0.5 * eps, 0.5 * eps + + +class BCEBlurWithLogitsLoss(nn.Module): + # BCEwithLogitLoss() with reduced missing label effects. + def __init__(self, alpha=0.05): + super().__init__() + self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss() + self.alpha = alpha + + def forward(self, pred, true): + loss = self.loss_fcn(pred, true) + pred = torch.sigmoid(pred) # prob from logits + dx = pred - true # reduce only missing label effects + # dx = (pred - true).abs() # reduce missing label and false label effects + alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4)) + loss *= alpha_factor + return loss.mean() + + +class FocalLoss(nn.Module): + # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) + def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): + super().__init__() + self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() + self.gamma = gamma + self.alpha = alpha + self.reduction = loss_fcn.reduction + self.loss_fcn.reduction = 'none' # required to apply FL to each element + + def forward(self, pred, true): + loss = self.loss_fcn(pred, true) + # p_t = torch.exp(-loss) + # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability + + # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py + pred_prob = torch.sigmoid(pred) # prob from logits + p_t = true * pred_prob + (1 - true) * (1 - pred_prob) + alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) + modulating_factor = (1.0 - p_t) ** self.gamma + loss *= alpha_factor * modulating_factor + + if self.reduction == 'mean': + return loss.mean() + elif self.reduction == 'sum': + return loss.sum() + else: # 'none' + return loss + + +class QFocalLoss(nn.Module): + # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) + def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): + super().__init__() + self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() + self.gamma = gamma + self.alpha = alpha + self.reduction = loss_fcn.reduction + self.loss_fcn.reduction = 'none' # required to apply FL to each element + + def forward(self, pred, true): + loss = self.loss_fcn(pred, true) + + pred_prob = torch.sigmoid(pred) # prob from logits + alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) + modulating_factor = torch.abs(true - pred_prob) ** self.gamma + loss *= alpha_factor * modulating_factor + + if self.reduction == 'mean': + return loss.mean() + elif self.reduction == 'sum': + return loss.sum() + else: # 'none' + return loss + + +class ComputeLoss: + # Compute losses + def __init__(self, model, autobalance=False): + self.sort_obj_iou = False + device = next(model.parameters()).device # get model device + h = model.hyp # hyperparameters + + # Define criteria + BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) + BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) + + # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 + self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets + + # Focal loss + g = h['fl_gamma'] # focal loss gamma + if g > 0: + BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) + + det = de_parallel(model).model[-1] # Detect() module + self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7 + self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index + self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance + for k in 'na', 'nc', 'nl', 'anchors': + setattr(self, k, getattr(det, k)) + + def __call__(self, p, targets): # predictions, targets, model + device = targets.device + lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device) + tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets + + # Losses + for i, pi in enumerate(p): # layer index, layer predictions + b, a, gj, gi = indices[i] # image, anchor, gridy, gridx + tobj = torch.zeros_like(pi[..., 0], device=device) # target obj + + n = b.shape[0] # number of targets + if n: + ps = pi[b, a, gj, gi] # prediction subset corresponding to targets + + # Regression + pxy = ps[:, :2].sigmoid() * 2 - 0.5 + pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i] + pbox = torch.cat((pxy, pwh), 1) # predicted box + iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) + lbox += (1.0 - iou).mean() # iou loss + + # Objectness + score_iou = iou.detach().clamp(0).type(tobj.dtype) + if self.sort_obj_iou: + sort_id = torch.argsort(score_iou) + b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id] + tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio + + # Classification + if self.nc > 1: # cls loss (only if multiple classes) + t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets + t[range(n), tcls[i]] = self.cp + lcls += self.BCEcls(ps[:, 5:], t) # BCE + + # Append targets to text file + # with open('targets.txt', 'a') as file: + # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] + + obji = self.BCEobj(pi[..., 4], tobj) + lobj += obji * self.balance[i] # obj loss + if self.autobalance: + self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() + + if self.autobalance: + self.balance = [x / self.balance[self.ssi] for x in self.balance] + lbox *= self.hyp['box'] + lobj *= self.hyp['obj'] + lcls *= self.hyp['cls'] + bs = tobj.shape[0] # batch size + + return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach() + + def build_targets(self, p, targets): + # Build targets for compute_loss(), input targets(image,class,x,y,w,h) + na, nt = self.na, targets.shape[0] # number of anchors, targets + tcls, tbox, indices, anch = [], [], [], [] + gain = torch.ones(7, device=targets.device) # normalized to gridspace gain + ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) + targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices + + g = 0.5 # bias + off = torch.tensor([[0, 0], + [1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m + # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm + ], device=targets.device).float() * g # offsets + + for i in range(self.nl): + anchors = self.anchors[i] + gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain + + # Match targets to anchors + t = targets * gain + if nt: + # Matches + r = t[:, :, 4:6] / anchors[:, None] # wh ratio + j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare + # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) + t = t[j] # filter + + # Offsets + gxy = t[:, 2:4] # grid xy + gxi = gain[[2, 3]] - gxy # inverse + j, k = ((gxy % 1 < g) & (gxy > 1)).T + l, m = ((gxi % 1 < g) & (gxi > 1)).T + j = torch.stack((torch.ones_like(j), j, k, l, m)) + t = t.repeat((5, 1, 1))[j] + offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] + else: + t = targets[0] + offsets = 0 + + # Define + b, c = t[:, :2].long().T # image, class + gxy = t[:, 2:4] # grid xy + gwh = t[:, 4:6] # grid wh + gij = (gxy - offsets).long() + gi, gj = gij.T # grid xy indices + + # Append + a = t[:, 6].long() # anchor indices + indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices + tbox.append(torch.cat((gxy - gij, gwh), 1)) # box + anch.append(anchors[a]) # anchors + tcls.append(c) # class + + return tcls, tbox, indices, anch diff --git a/yolov5_Monocular_social_ranging/utils/metrics.py b/yolov5_Monocular_social_ranging/utils/metrics.py new file mode 100644 index 0000000..857fa5d --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/metrics.py @@ -0,0 +1,342 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Model validation metrics +""" + +import math +import warnings +from pathlib import Path + +import matplotlib.pyplot as plt +import numpy as np +import torch + + +def fitness(x): + # Model fitness as a weighted combination of metrics + w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] + return (x[:, :4] * w).sum(1) + + +def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=(), eps=1e-16): + """ Compute the average precision, given the recall and precision curves. + Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. + # Arguments + tp: True positives (nparray, nx1 or nx10). + conf: Objectness value from 0-1 (nparray). + pred_cls: Predicted object classes (nparray). + target_cls: True object classes (nparray). + plot: Plot precision-recall curve at mAP@0.5 + save_dir: Plot save directory + # Returns + The average precision as computed in py-faster-rcnn. + """ + + # Sort by objectness + i = np.argsort(-conf) + tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] + + # Find unique classes + unique_classes, nt = np.unique(target_cls, return_counts=True) + nc = unique_classes.shape[0] # number of classes, number of detections + + # Create Precision-Recall curve and compute AP for each class + px, py = np.linspace(0, 1, 1000), [] # for plotting + ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000)) + for ci, c in enumerate(unique_classes): + i = pred_cls == c + n_l = nt[ci] # number of labels + n_p = i.sum() # number of predictions + + if n_p == 0 or n_l == 0: + continue + else: + # Accumulate FPs and TPs + fpc = (1 - tp[i]).cumsum(0) + tpc = tp[i].cumsum(0) + + # Recall + recall = tpc / (n_l + eps) # recall curve + r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases + + # Precision + precision = tpc / (tpc + fpc) # precision curve + p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score + + # AP from recall-precision curve + for j in range(tp.shape[1]): + ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j]) + if plot and j == 0: + py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5 + + # Compute F1 (harmonic mean of precision and recall) + f1 = 2 * p * r / (p + r + eps) + names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data + names = {i: v for i, v in enumerate(names)} # to dict + if plot: + plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names) + plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1') + plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision') + plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall') + + i = f1.mean(0).argmax() # max F1 index + p, r, f1 = p[:, i], r[:, i], f1[:, i] + tp = (r * nt).round() # true positives + fp = (tp / (p + eps) - tp).round() # false positives + return tp, fp, p, r, f1, ap, unique_classes.astype('int32') + + +def compute_ap(recall, precision): + """ Compute the average precision, given the recall and precision curves + # Arguments + recall: The recall curve (list) + precision: The precision curve (list) + # Returns + Average precision, precision curve, recall curve + """ + + # Append sentinel values to beginning and end + mrec = np.concatenate(([0.0], recall, [1.0])) + mpre = np.concatenate(([1.0], precision, [0.0])) + + # Compute the precision envelope + mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) + + # Integrate area under curve + method = 'interp' # methods: 'continuous', 'interp' + if method == 'interp': + x = np.linspace(0, 1, 101) # 101-point interp (COCO) + ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate + else: # 'continuous' + i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes + ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve + + return ap, mpre, mrec + + +class ConfusionMatrix: + # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix + def __init__(self, nc, conf=0.25, iou_thres=0.45): + self.matrix = np.zeros((nc + 1, nc + 1)) + self.nc = nc # number of classes + self.conf = conf + self.iou_thres = iou_thres + + def process_batch(self, detections, labels): + """ + Return intersection-over-union (Jaccard index) of boxes. + Both sets of boxes are expected to be in (x1, y1, x2, y2) format. + Arguments: + detections (Array[N, 6]), x1, y1, x2, y2, conf, class + labels (Array[M, 5]), class, x1, y1, x2, y2 + Returns: + None, updates confusion matrix accordingly + """ + detections = detections[detections[:, 4] > self.conf] + gt_classes = labels[:, 0].int() + detection_classes = detections[:, 5].int() + iou = box_iou(labels[:, 1:], detections[:, :4]) + + x = torch.where(iou > self.iou_thres) + if x[0].shape[0]: + matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() + if x[0].shape[0] > 1: + matches = matches[matches[:, 2].argsort()[::-1]] + matches = matches[np.unique(matches[:, 1], return_index=True)[1]] + matches = matches[matches[:, 2].argsort()[::-1]] + matches = matches[np.unique(matches[:, 0], return_index=True)[1]] + else: + matches = np.zeros((0, 3)) + + n = matches.shape[0] > 0 + m0, m1, _ = matches.transpose().astype(np.int16) + for i, gc in enumerate(gt_classes): + j = m0 == i + if n and sum(j) == 1: + self.matrix[detection_classes[m1[j]], gc] += 1 # correct + else: + self.matrix[self.nc, gc] += 1 # background FP + + if n: + for i, dc in enumerate(detection_classes): + if not any(m1 == i): + self.matrix[dc, self.nc] += 1 # background FN + + def matrix(self): + return self.matrix + + def tp_fp(self): + tp = self.matrix.diagonal() # true positives + fp = self.matrix.sum(1) - tp # false positives + # fn = self.matrix.sum(0) - tp # false negatives (missed detections) + return tp[:-1], fp[:-1] # remove background class + + def plot(self, normalize=True, save_dir='', names=()): + try: + import seaborn as sn + + array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-9) if normalize else 1) # normalize columns + array[array < 0.005] = np.nan # don't annotate (would appear as 0.00) + + fig = plt.figure(figsize=(12, 9), tight_layout=True) + nc, nn = self.nc, len(names) # number of classes, names + sn.set(font_scale=1.0 if nc < 50 else 0.8) # for label size + labels = (0 < nn < 99) and (nn == nc) # apply names to ticklabels + with warnings.catch_warnings(): + warnings.simplefilter('ignore') # suppress empty matrix RuntimeWarning: All-NaN slice encountered + sn.heatmap(array, annot=nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True, vmin=0.0, + xticklabels=names + ['background FP'] if labels else "auto", + yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1)) + fig.axes[0].set_xlabel('True') + fig.axes[0].set_ylabel('Predicted') + fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250) + plt.close() + except Exception as e: + print(f'WARNING: ConfusionMatrix plot failure: {e}') + + def print(self): + for i in range(self.nc + 1): + print(' '.join(map(str, self.matrix[i]))) + + +def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): + # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4 + box2 = box2.T + + # Get the coordinates of bounding boxes + if x1y1x2y2: # x1, y1, x2, y2 = box1 + b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] + b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] + else: # transform from xywh to xyxy + b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2 + b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2 + b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2 + b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2 + + # Intersection area + inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \ + (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0) + + # Union Area + w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps + w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps + union = w1 * h1 + w2 * h2 - inter + eps + + iou = inter / union + if CIoU or DIoU or GIoU: + cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width + ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height + if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 + c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared + rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared + if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 + v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) + with torch.no_grad(): + alpha = v / (v - iou + (1 + eps)) + return iou - (rho2 / c2 + v * alpha) # CIoU + return iou - rho2 / c2 # DIoU + c_area = cw * ch + eps # convex area + return iou - (c_area - union) / c_area # GIoU https://arxiv.org/pdf/1902.09630.pdf + return iou # IoU + + +def box_iou(box1, box2): + # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py + """ + Return intersection-over-union (Jaccard index) of boxes. + Both sets of boxes are expected to be in (x1, y1, x2, y2) format. + Arguments: + box1 (Tensor[N, 4]) + box2 (Tensor[M, 4]) + Returns: + iou (Tensor[N, M]): the NxM matrix containing the pairwise + IoU values for every element in boxes1 and boxes2 + """ + + def box_area(box): + # box = 4xn + return (box[2] - box[0]) * (box[3] - box[1]) + + area1 = box_area(box1.T) + area2 = box_area(box2.T) + + # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) + inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2) + return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter) + + +def bbox_ioa(box1, box2, eps=1E-7): + """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2 + box1: np.array of shape(4) + box2: np.array of shape(nx4) + returns: np.array of shape(n) + """ + + box2 = box2.transpose() + + # Get the coordinates of bounding boxes + b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] + b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] + + # Intersection area + inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ + (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0) + + # box2 area + box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps + + # Intersection over box2 area + return inter_area / box2_area + + +def wh_iou(wh1, wh2): + # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 + wh1 = wh1[:, None] # [N,1,2] + wh2 = wh2[None] # [1,M,2] + inter = torch.min(wh1, wh2).prod(2) # [N,M] + return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter) + + +# Plots ---------------------------------------------------------------------------------------------------------------- + +def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()): + # Precision-recall curve + fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) + py = np.stack(py, axis=1) + + if 0 < len(names) < 21: # display per-class legend if < 21 classes + for i, y in enumerate(py.T): + ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision) + else: + ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision) + + ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean()) + ax.set_xlabel('Recall') + ax.set_ylabel('Precision') + ax.set_xlim(0, 1) + ax.set_ylim(0, 1) + plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") + fig.savefig(Path(save_dir), dpi=250) + plt.close() + + +def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'): + # Metric-confidence curve + fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) + + if 0 < len(names) < 21: # display per-class legend if < 21 classes + for i, y in enumerate(py): + ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric) + else: + ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric) + + y = py.mean(0) + ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}') + ax.set_xlabel(xlabel) + ax.set_ylabel(ylabel) + ax.set_xlim(0, 1) + ax.set_ylim(0, 1) + plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") + fig.savefig(Path(save_dir), dpi=250) + plt.close() diff --git a/yolov5_Monocular_social_ranging/utils/plots.py b/yolov5_Monocular_social_ranging/utils/plots.py new file mode 100644 index 0000000..6c3f5bc --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/plots.py @@ -0,0 +1,471 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Plotting utils +""" + +import math +import os +from copy import copy +from pathlib import Path + +import cv2 +import matplotlib +import matplotlib.pyplot as plt +import numpy as np +import pandas as pd +import seaborn as sn +import torch +from PIL import Image, ImageDraw, ImageFont + +from utils.general import (CONFIG_DIR, FONT, LOGGER, Timeout, check_font, check_requirements, clip_coords, + increment_path, is_ascii, is_chinese, try_except, xywh2xyxy, xyxy2xywh) +from utils.metrics import fitness + +# Settings +RANK = int(os.getenv('RANK', -1)) +matplotlib.rc('font', **{'size': 11}) +matplotlib.use('Agg') # for writing to files only + + +class Colors: + # Ultralytics color palette https://ultralytics.com/ + def __init__(self): + # hex = matplotlib.colors.TABLEAU_COLORS.values() + hex = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB', + '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7') + self.palette = [self.hex2rgb('#' + c) for c in hex] + self.n = len(self.palette) + + def __call__(self, i, bgr=False): + c = self.palette[int(i) % self.n] + return (c[2], c[1], c[0]) if bgr else c + + @staticmethod + def hex2rgb(h): # rgb order (PIL) + return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4)) + + +colors = Colors() # create instance for 'from utils.plots import colors' + + +def check_pil_font(font=FONT, size=10): + # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary + font = Path(font) + font = font if font.exists() else (CONFIG_DIR / font.name) + try: + return ImageFont.truetype(str(font) if font.exists() else font.name, size) + except Exception: # download if missing + check_font(font) + try: + return ImageFont.truetype(str(font), size) + except TypeError: + check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374 + + +class Annotator: + if RANK in (-1, 0): + check_pil_font() # download TTF if necessary + + # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations + def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): + assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.' + self.pil = pil or not is_ascii(example) or is_chinese(example) + if self.pil: # use PIL + self.im = im if isinstance(im, Image.Image) else Image.fromarray(im) + self.draw = ImageDraw.Draw(self.im) + self.font = check_pil_font(font='Arial.Unicode.ttf' if is_chinese(example) else font, + size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)) + else: # use cv2 + self.im = im + self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width + + def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)): + # Add one xyxy box to image with label + if self.pil or not is_ascii(label): + self.draw.rectangle(box, width=self.lw, outline=color) # box + if label: + w, h = self.font.getsize(label) # text width, height + outside = box[1] - h >= 0 # label fits outside box + self.draw.rectangle((box[0], + box[1] - h if outside else box[1], + box[0] + w + 1, + box[1] + 1 if outside else box[1] + h + 1), fill=color) + # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0 + self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font) + else: # cv2 + p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3])) + cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA) + if label: + tf = max(self.lw - 1, 1) # font thickness + w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height + outside = p1[1] - h - 3 >= 0 # label fits outside box + p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3 + cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled + cv2.putText(self.im, label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), 0, self.lw / 3, txt_color, + thickness=tf, lineType=cv2.LINE_AA) + + def rectangle(self, xy, fill=None, outline=None, width=1): + # Add rectangle to image (PIL-only) + self.draw.rectangle(xy, fill, outline, width) + + def text(self, xy, text, txt_color=(255, 255, 255)): + # Add text to image (PIL-only) + w, h = self.font.getsize(text) # text width, height + self.draw.text((xy[0], xy[1] - h + 1), text, fill=txt_color, font=self.font) + + def result(self): + # Return annotated image as array + return np.asarray(self.im) + + +def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')): + """ + x: Features to be visualized + module_type: Module type + stage: Module stage within model + n: Maximum number of feature maps to plot + save_dir: Directory to save results + """ + if 'Detect' not in module_type: + batch, channels, height, width = x.shape # batch, channels, height, width + if height > 1 and width > 1: + f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename + + blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels + n = min(n, channels) # number of plots + fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols + ax = ax.ravel() + plt.subplots_adjust(wspace=0.05, hspace=0.05) + for i in range(n): + ax[i].imshow(blocks[i].squeeze()) # cmap='gray' + ax[i].axis('off') + + LOGGER.info(f'Saving {f}... ({n}/{channels})') + plt.savefig(f, dpi=300, bbox_inches='tight') + plt.close() + np.save(str(f.with_suffix('.npy')), x[0].cpu().numpy()) # npy save + + +def hist2d(x, y, n=100): + # 2d histogram used in labels.png and evolve.png + xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n) + hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges)) + xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1) + yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1) + return np.log(hist[xidx, yidx]) + + +def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5): + from scipy.signal import butter, filtfilt + + # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy + def butter_lowpass(cutoff, fs, order): + nyq = 0.5 * fs + normal_cutoff = cutoff / nyq + return butter(order, normal_cutoff, btype='low', analog=False) + + b, a = butter_lowpass(cutoff, fs, order=order) + return filtfilt(b, a, data) # forward-backward filter + + +def output_to_target(output): + # Convert model output to target format [batch_id, class_id, x, y, w, h, conf] + targets = [] + for i, o in enumerate(output): + for *box, conf, cls in o.cpu().numpy(): + targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf]) + return np.array(targets) + + +def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=1920, max_subplots=16): + # Plot image grid with labels + if isinstance(images, torch.Tensor): + images = images.cpu().float().numpy() + if isinstance(targets, torch.Tensor): + targets = targets.cpu().numpy() + if np.max(images[0]) <= 1: + images *= 255 # de-normalise (optional) + bs, _, h, w = images.shape # batch size, _, height, width + bs = min(bs, max_subplots) # limit plot images + ns = np.ceil(bs ** 0.5) # number of subplots (square) + + # Build Image + mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init + for i, im in enumerate(images): + if i == max_subplots: # if last batch has fewer images than we expect + break + x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin + im = im.transpose(1, 2, 0) + mosaic[y:y + h, x:x + w, :] = im + + # Resize (optional) + scale = max_size / ns / max(h, w) + if scale < 1: + h = math.ceil(scale * h) + w = math.ceil(scale * w) + mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h))) + + # Annotate + fs = int((h + w) * ns * 0.01) # font size + annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names) + for i in range(i + 1): + x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin + annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders + if paths: + annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames + if len(targets) > 0: + ti = targets[targets[:, 0] == i] # image targets + boxes = xywh2xyxy(ti[:, 2:6]).T + classes = ti[:, 1].astype('int') + labels = ti.shape[1] == 6 # labels if no conf column + conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred) + + if boxes.shape[1]: + if boxes.max() <= 1.01: # if normalized with tolerance 0.01 + boxes[[0, 2]] *= w # scale to pixels + boxes[[1, 3]] *= h + elif scale < 1: # absolute coords need scale if image scales + boxes *= scale + boxes[[0, 2]] += x + boxes[[1, 3]] += y + for j, box in enumerate(boxes.T.tolist()): + cls = classes[j] + color = colors(cls) + cls = names[cls] if names else cls + if labels or conf[j] > 0.25: # 0.25 conf thresh + label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}' + annotator.box_label(box, label, color=color) + annotator.im.save(fname) # save + + +def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''): + # Plot LR simulating training for full epochs + optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals + y = [] + for _ in range(epochs): + scheduler.step() + y.append(optimizer.param_groups[0]['lr']) + plt.plot(y, '.-', label='LR') + plt.xlabel('epoch') + plt.ylabel('LR') + plt.grid() + plt.xlim(0, epochs) + plt.ylim(0) + plt.savefig(Path(save_dir) / 'LR.png', dpi=200) + plt.close() + + +def plot_val_txt(): # from utils.plots import *; plot_val() + # Plot val.txt histograms + x = np.loadtxt('val.txt', dtype=np.float32) + box = xyxy2xywh(x[:, :4]) + cx, cy = box[:, 0], box[:, 1] + + fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True) + ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0) + ax.set_aspect('equal') + plt.savefig('hist2d.png', dpi=300) + + fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True) + ax[0].hist(cx, bins=600) + ax[1].hist(cy, bins=600) + plt.savefig('hist1d.png', dpi=200) + + +def plot_targets_txt(): # from utils.plots import *; plot_targets_txt() + # Plot targets.txt histograms + x = np.loadtxt('targets.txt', dtype=np.float32).T + s = ['x targets', 'y targets', 'width targets', 'height targets'] + fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True) + ax = ax.ravel() + for i in range(4): + ax[i].hist(x[i], bins=100, label=f'{x[i].mean():.3g} +/- {x[i].std():.3g}') + ax[i].legend() + ax[i].set_title(s[i]) + plt.savefig('targets.jpg', dpi=200) + + +def plot_val_study(file='', dir='', x=None): # from utils.plots import *; plot_val_study() + # Plot file=study.txt generated by val.py (or plot all study*.txt in dir) + save_dir = Path(file).parent if file else Path(dir) + plot2 = False # plot additional results + if plot2: + ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)[1].ravel() + + fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True) + # for f in [save_dir / f'study_coco_{x}.txt' for x in ['yolov5n6', 'yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]: + for f in sorted(save_dir.glob('study*.txt')): + y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T + x = np.arange(y.shape[1]) if x is None else np.array(x) + if plot2: + s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_preprocess (ms/img)', 't_inference (ms/img)', 't_NMS (ms/img)'] + for i in range(7): + ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8) + ax[i].set_title(s[i]) + + j = y[3].argmax() + 1 + ax2.plot(y[5, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8, + label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO')) + + ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5], + 'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet') + + ax2.grid(alpha=0.2) + ax2.set_yticks(np.arange(20, 60, 5)) + ax2.set_xlim(0, 57) + ax2.set_ylim(25, 55) + ax2.set_xlabel('GPU Speed (ms/img)') + ax2.set_ylabel('COCO AP val') + ax2.legend(loc='lower right') + f = save_dir / 'study.png' + print(f'Saving {f}...') + plt.savefig(f, dpi=300) + + +@try_except # known issue https://github.com/ultralytics/yolov5/issues/5395 +@Timeout(30) # known issue https://github.com/ultralytics/yolov5/issues/5611 +def plot_labels(labels, names=(), save_dir=Path('')): + # plot dataset labels + LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ") + c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes + nc = int(c.max() + 1) # number of classes + x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height']) + + # seaborn correlogram + sn.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9)) + plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200) + plt.close() + + # matplotlib labels + matplotlib.use('svg') # faster + ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel() + y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8) + try: # color histogram bars by class + [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)] # known issue #3195 + except Exception: + pass + ax[0].set_ylabel('instances') + if 0 < len(names) < 30: + ax[0].set_xticks(range(len(names))) + ax[0].set_xticklabels(names, rotation=90, fontsize=10) + else: + ax[0].set_xlabel('classes') + sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9) + sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9) + + # rectangles + labels[:, 1:3] = 0.5 # center + labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000 + img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255) + for cls, *box in labels[:1000]: + ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot + ax[1].imshow(img) + ax[1].axis('off') + + for a in [0, 1, 2, 3]: + for s in ['top', 'right', 'left', 'bottom']: + ax[a].spines[s].set_visible(False) + + plt.savefig(save_dir / 'labels.jpg', dpi=200) + matplotlib.use('Agg') + plt.close() + + +def plot_evolve(evolve_csv='path/to/evolve.csv'): # from utils.plots import *; plot_evolve() + # Plot evolve.csv hyp evolution results + evolve_csv = Path(evolve_csv) + data = pd.read_csv(evolve_csv) + keys = [x.strip() for x in data.columns] + x = data.values + f = fitness(x) + j = np.argmax(f) # max fitness index + plt.figure(figsize=(10, 12), tight_layout=True) + matplotlib.rc('font', **{'size': 8}) + print(f'Best results from row {j} of {evolve_csv}:') + for i, k in enumerate(keys[7:]): + v = x[:, 7 + i] + mu = v[j] # best single result + plt.subplot(6, 5, i + 1) + plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none') + plt.plot(mu, f.max(), 'k+', markersize=15) + plt.title(f'{k} = {mu:.3g}', fontdict={'size': 9}) # limit to 40 characters + if i % 5 != 0: + plt.yticks([]) + print(f'{k:>15}: {mu:.3g}') + f = evolve_csv.with_suffix('.png') # filename + plt.savefig(f, dpi=200) + plt.close() + print(f'Saved {f}') + + +def plot_results(file='path/to/results.csv', dir=''): + # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv') + save_dir = Path(file).parent if file else Path(dir) + fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True) + ax = ax.ravel() + files = list(save_dir.glob('results*.csv')) + assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.' + for fi, f in enumerate(files): + try: + data = pd.read_csv(f) + s = [x.strip() for x in data.columns] + x = data.values[:, 0] + for i, j in enumerate([1, 2, 3, 4, 5, 8, 9, 10, 6, 7]): + y = data.values[:, j] + # y[y == 0] = np.nan # don't show zero values + ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=8) + ax[i].set_title(s[j], fontsize=12) + # if j in [8, 9, 10]: # share train and val loss y axes + # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) + except Exception as e: + LOGGER.info(f'Warning: Plotting error for {f}: {e}') + ax[1].legend() + fig.savefig(save_dir / 'results.png', dpi=200) + plt.close() + + +def profile_idetection(start=0, stop=0, labels=(), save_dir=''): + # Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection() + ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel() + s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS'] + files = list(Path(save_dir).glob('frames*.txt')) + for fi, f in enumerate(files): + try: + results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows + n = results.shape[1] # number of rows + x = np.arange(start, min(stop, n) if stop else n) + results = results[:, x] + t = (results[0] - results[0].min()) # set t0=0s + results[0] = x + for i, a in enumerate(ax): + if i < len(results): + label = labels[fi] if len(labels) else f.stem.replace('frames_', '') + a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5) + a.set_title(s[i]) + a.set_xlabel('time (s)') + # if fi == len(files) - 1: + # a.set_ylim(bottom=0) + for side in ['top', 'right']: + a.spines[side].set_visible(False) + else: + a.remove() + except Exception as e: + print(f'Warning: Plotting error for {f}; {e}') + ax[1].legend() + plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200) + + +def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True): + # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop + xyxy = torch.tensor(xyxy).view(-1, 4) + b = xyxy2xywh(xyxy) # boxes + if square: + b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square + b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad + xyxy = xywh2xyxy(b).long() + clip_coords(xyxy, im.shape) + crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)] + if save: + file.parent.mkdir(parents=True, exist_ok=True) # make directory + cv2.imwrite(str(increment_path(file).with_suffix('.jpg')), crop) + return crop diff --git a/yolov5_Monocular_social_ranging/utils/torch_utils.py b/yolov5_Monocular_social_ranging/utils/torch_utils.py new file mode 100644 index 0000000..c5257c6 --- /dev/null +++ b/yolov5_Monocular_social_ranging/utils/torch_utils.py @@ -0,0 +1,329 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +PyTorch utils +""" + +import datetime +import math +import os +import platform +import subprocess +import time +import warnings +from contextlib import contextmanager +from copy import deepcopy +from pathlib import Path + +import torch +import torch.distributed as dist +import torch.nn as nn +import torch.nn.functional as F + +from utils.general import LOGGER + +try: + import thop # for FLOPs computation +except ImportError: + thop = None + +# Suppress PyTorch warnings +warnings.filterwarnings('ignore', message='User provided device_type of \'cuda\', but CUDA is not available. Disabling') + + +@contextmanager +def torch_distributed_zero_first(local_rank: int): + """ + Decorator to make all processes in distributed training wait for each local_master to do something. + """ + if local_rank not in [-1, 0]: + dist.barrier(device_ids=[local_rank]) + yield + if local_rank == 0: + dist.barrier(device_ids=[0]) + + +def date_modified(path=__file__): + # return human-readable file modification date, i.e. '2021-3-26' + t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime) + return f'{t.year}-{t.month}-{t.day}' + + +def git_describe(path=Path(__file__).parent): # path must be a directory + # return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe + s = f'git -C {path} describe --tags --long --always' + try: + return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1] + except subprocess.CalledProcessError: + return '' # not a git repository + + +def device_count(): + # Returns number of CUDA devices available. Safe version of torch.cuda.device_count(). Only works on Linux. + assert platform.system() == 'Linux', 'device_count() function only works on Linux' + try: + cmd = 'nvidia-smi -L | wc -l' + return int(subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]) + except Exception: + return 0 + + +def select_device(device='', batch_size=0, newline=True): + # device = 'cpu' or '0' or '0,1,2,3' + s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string + device = str(device).strip().lower().replace('cuda:', '') # to string, 'cuda:0' to '0' + cpu = device == 'cpu' + if cpu: + os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False + elif device: # non-cpu device requested + os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable - must be before assert is_available() + assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \ + f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)" + + cuda = not cpu and torch.cuda.is_available() + if cuda: + devices = device.split(',') if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7 + n = len(devices) # device count + if n > 1 and batch_size > 0: # check batch_size is divisible by device_count + assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}' + space = ' ' * (len(s) + 1) + for i, d in enumerate(devices): + p = torch.cuda.get_device_properties(i) + s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2:.0f}MiB)\n" # bytes to MB + else: + s += 'CPU\n' + + if not newline: + s = s.rstrip() + LOGGER.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe + return torch.device('cuda:0' if cuda else 'cpu') + + +def time_sync(): + # pytorch-accurate time + if torch.cuda.is_available(): + torch.cuda.synchronize() + return time.time() + + +def profile(input, ops, n=10, device=None): + # YOLOv5 speed/memory/FLOPs profiler + # + # Usage: + # input = torch.randn(16, 3, 640, 640) + # m1 = lambda x: x * torch.sigmoid(x) + # m2 = nn.SiLU() + # profile(input, [m1, m2], n=100) # profile over 100 iterations + + results = [] + device = device or select_device() + print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}" + f"{'input':>24s}{'output':>24s}") + + for x in input if isinstance(input, list) else [input]: + x = x.to(device) + x.requires_grad = True + for m in ops if isinstance(ops, list) else [ops]: + m = m.to(device) if hasattr(m, 'to') else m # device + m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m + tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward + try: + flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs + except Exception: + flops = 0 + + try: + for _ in range(n): + t[0] = time_sync() + y = m(x) + t[1] = time_sync() + try: + _ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward() + t[2] = time_sync() + except Exception: # no backward method + # print(e) # for debug + t[2] = float('nan') + tf += (t[1] - t[0]) * 1000 / n # ms per op forward + tb += (t[2] - t[1]) * 1000 / n # ms per op backward + mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0 # (GB) + s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list' + s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list' + p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters + print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}') + results.append([p, flops, mem, tf, tb, s_in, s_out]) + except Exception as e: + print(e) + results.append(None) + torch.cuda.empty_cache() + return results + + +def is_parallel(model): + # Returns True if model is of type DP or DDP + return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel) + + +def de_parallel(model): + # De-parallelize a model: returns single-GPU model if model is of type DP or DDP + return model.module if is_parallel(model) else model + + +def initialize_weights(model): + for m in model.modules(): + t = type(m) + if t is nn.Conv2d: + pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') + elif t is nn.BatchNorm2d: + m.eps = 1e-3 + m.momentum = 0.03 + elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]: + m.inplace = True + + +def find_modules(model, mclass=nn.Conv2d): + # Finds layer indices matching module class 'mclass' + return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)] + + +def sparsity(model): + # Return global model sparsity + a, b = 0, 0 + for p in model.parameters(): + a += p.numel() + b += (p == 0).sum() + return b / a + + +def prune(model, amount=0.3): + # Prune model to requested global sparsity + import torch.nn.utils.prune as prune + print('Pruning model... ', end='') + for name, m in model.named_modules(): + if isinstance(m, nn.Conv2d): + prune.l1_unstructured(m, name='weight', amount=amount) # prune + prune.remove(m, 'weight') # make permanent + print(' %.3g global sparsity' % sparsity(model)) + + +def fuse_conv_and_bn(conv, bn): + # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/ + fusedconv = nn.Conv2d(conv.in_channels, + conv.out_channels, + kernel_size=conv.kernel_size, + stride=conv.stride, + padding=conv.padding, + groups=conv.groups, + bias=True).requires_grad_(False).to(conv.weight.device) + + # prepare filters + w_conv = conv.weight.clone().view(conv.out_channels, -1) + w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) + fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape)) + + # prepare spatial bias + b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias + b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) + fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn) + + return fusedconv + + +def model_info(model, verbose=False, img_size=640): + # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320] + n_p = sum(x.numel() for x in model.parameters()) # number parameters + n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients + if verbose: + print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}") + for i, (name, p) in enumerate(model.named_parameters()): + name = name.replace('module_list.', '') + print('%5g %40s %9s %12g %20s %10.3g %10.3g' % + (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std())) + + try: # FLOPs + from thop import profile + stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32 + img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input + flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPs + img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float + fs = ', %.1f GFLOPs' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPs + except (ImportError, Exception): + fs = '' + + LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}") + + +def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416) + # scales img(bs,3,y,x) by ratio constrained to gs-multiple + if ratio == 1.0: + return img + else: + h, w = img.shape[2:] + s = (int(h * ratio), int(w * ratio)) # new size + img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize + if not same_shape: # pad/crop img + h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w)) + return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean + + +def copy_attr(a, b, include=(), exclude=()): + # Copy attributes from b to a, options to only include [...] and to exclude [...] + for k, v in b.__dict__.items(): + if (len(include) and k not in include) or k.startswith('_') or k in exclude: + continue + else: + setattr(a, k, v) + + +class EarlyStopping: + # YOLOv5 simple early stopper + def __init__(self, patience=30): + self.best_fitness = 0.0 # i.e. mAP + self.best_epoch = 0 + self.patience = patience or float('inf') # epochs to wait after fitness stops improving to stop + self.possible_stop = False # possible stop may occur next epoch + + def __call__(self, epoch, fitness): + if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training + self.best_epoch = epoch + self.best_fitness = fitness + delta = epoch - self.best_epoch # epochs without improvement + self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch + stop = delta >= self.patience # stop training if patience exceeded + if stop: + LOGGER.info(f'Stopping training early as no improvement observed in last {self.patience} epochs. ' + f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n' + f'To update EarlyStopping(patience={self.patience}) pass a new patience value, ' + f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.') + return stop + + +class ModelEMA: + """ Updated Exponential Moving Average (EMA) from https://github.com/rwightman/pytorch-image-models + Keeps a moving average of everything in the model state_dict (parameters and buffers) + For EMA details see https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage + """ + + def __init__(self, model, decay=0.9999, updates=0): + # Create EMA + self.ema = deepcopy(de_parallel(model)).eval() # FP32 EMA + # if next(model.parameters()).device.type != 'cpu': + # self.ema.half() # FP16 EMA + self.updates = updates # number of EMA updates + self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs) + for p in self.ema.parameters(): + p.requires_grad_(False) + + def update(self, model): + # Update EMA parameters + with torch.no_grad(): + self.updates += 1 + d = self.decay(self.updates) + + msd = de_parallel(model).state_dict() # model state_dict + for k, v in self.ema.state_dict().items(): + if v.dtype.is_floating_point: + v *= d + v += (1 - d) * msd[k].detach() + + def update_attr(self, model, include=(), exclude=('process_group', 'reducer')): + # Update EMA attributes + copy_attr(self.ema, model, include, exclude) diff --git a/yolov5_Monocular_social_ranging/val.py b/yolov5_Monocular_social_ranging/val.py new file mode 100644 index 0000000..78abbda --- /dev/null +++ b/yolov5_Monocular_social_ranging/val.py @@ -0,0 +1,383 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Validate a trained YOLOv5 model accuracy on a custom dataset + +Usage: + $ python path/to/val.py --weights yolov5s.pt --data coco128.yaml --img 640 + +Usage - formats: + $ python path/to/val.py --weights yolov5s.pt # PyTorch + yolov5s.torchscript # TorchScript + yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn + yolov5s.xml # OpenVINO + yolov5s.engine # TensorRT + yolov5s.mlmodel # CoreML (MacOS-only) + yolov5s_saved_model # TensorFlow SavedModel + yolov5s.pb # TensorFlow GraphDef + yolov5s.tflite # TensorFlow Lite + yolov5s_edgetpu.tflite # TensorFlow Edge TPU +""" + +import argparse +import json +import os +import sys +from pathlib import Path +from threading import Thread + +import numpy as np +import torch +from tqdm import tqdm + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[0] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative + +from models.common import DetectMultiBackend +from utils.callbacks import Callbacks +from utils.datasets import create_dataloader +from utils.general import (LOGGER, box_iou, check_dataset, check_img_size, check_requirements, check_yaml, + coco80_to_coco91_class, colorstr, increment_path, non_max_suppression, print_args, + scale_coords, xywh2xyxy, xyxy2xywh) +from utils.metrics import ConfusionMatrix, ap_per_class +from utils.plots import output_to_target, plot_images, plot_val_study +from utils.torch_utils import select_device, time_sync + + +def save_one_txt(predn, save_conf, shape, file): + # Save one txt result + gn = torch.tensor(shape)[[1, 0, 1, 0]] # normalization gain whwh + for *xyxy, conf, cls in predn.tolist(): + xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh + line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format + with open(file, 'a') as f: + f.write(('%g ' * len(line)).rstrip() % line + '\n') + + +def save_one_json(predn, jdict, path, class_map): + # Save one JSON result {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236} + image_id = int(path.stem) if path.stem.isnumeric() else path.stem + box = xyxy2xywh(predn[:, :4]) # xywh + box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner + for p, b in zip(predn.tolist(), box.tolist()): + jdict.append({'image_id': image_id, + 'category_id': class_map[int(p[5])], + 'bbox': [round(x, 3) for x in b], + 'score': round(p[4], 5)}) + + +def process_batch(detections, labels, iouv): + """ + Return correct predictions matrix. Both sets of boxes are in (x1, y1, x2, y2) format. + Arguments: + detections (Array[N, 6]), x1, y1, x2, y2, conf, class + labels (Array[M, 5]), class, x1, y1, x2, y2 + Returns: + correct (Array[N, 10]), for 10 IoU levels + """ + correct = torch.zeros(detections.shape[0], iouv.shape[0], dtype=torch.bool, device=iouv.device) + iou = box_iou(labels[:, 1:], detections[:, :4]) + x = torch.where((iou >= iouv[0]) & (labels[:, 0:1] == detections[:, 5])) # IoU above threshold and classes match + if x[0].shape[0]: + matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() # [label, detection, iou] + if x[0].shape[0] > 1: + matches = matches[matches[:, 2].argsort()[::-1]] + matches = matches[np.unique(matches[:, 1], return_index=True)[1]] + # matches = matches[matches[:, 2].argsort()[::-1]] + matches = matches[np.unique(matches[:, 0], return_index=True)[1]] + matches = torch.Tensor(matches).to(iouv.device) + correct[matches[:, 1].long()] = matches[:, 2:3] >= iouv + return correct + + +@torch.no_grad() +def run(data, + weights=None, # model.pt path(s) + batch_size=32, # batch size + imgsz=640, # inference size (pixels) + conf_thres=0.001, # confidence threshold + iou_thres=0.6, # NMS IoU threshold + task='val', # train, val, test, speed or study + device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu + workers=8, # max dataloader workers (per RANK in DDP mode) + single_cls=False, # treat as single-class dataset + augment=False, # augmented inference + verbose=False, # verbose output + save_txt=False, # save results to *.txt + save_hybrid=False, # save label+prediction hybrid results to *.txt + save_conf=False, # save confidences in --save-txt labels + save_json=False, # save a COCO-JSON results file + project=ROOT / 'runs/val', # save to project/name + name='exp', # save to project/name + exist_ok=False, # existing project/name ok, do not increment + half=True, # use FP16 half-precision inference + dnn=False, # use OpenCV DNN for ONNX inference + model=None, + dataloader=None, + save_dir=Path(''), + plots=True, + callbacks=Callbacks(), + compute_loss=None, + ): + # Initialize/load model and set device + training = model is not None + if training: # called by train.py + device, pt, jit, engine = next(model.parameters()).device, True, False, False # get model device, PyTorch model + + half &= device.type != 'cpu' # half precision only supported on CUDA + model.half() if half else model.float() + else: # called directly + device = select_device(device, batch_size=batch_size) + + # Directories + save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run + (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir + + # Load model + model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data) + stride, pt, jit, onnx, engine = model.stride, model.pt, model.jit, model.onnx, model.engine + imgsz = check_img_size(imgsz, s=stride) # check image size + half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA + if pt or jit: + model.model.half() if half else model.model.float() + elif engine: + batch_size = model.batch_size + else: + half = False + batch_size = 1 # export.py models default to batch-size 1 + device = torch.device('cpu') + LOGGER.info(f'Forcing --batch-size 1 square inference shape(1,3,{imgsz},{imgsz}) for non-PyTorch backends') + + # Data + data = check_dataset(data) # check + + # Configure + model.eval() + is_coco = isinstance(data.get('val'), str) and data['val'].endswith('coco/val2017.txt') # COCO dataset + nc = 1 if single_cls else int(data['nc']) # number of classes + iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for mAP@0.5:0.95 + niou = iouv.numel() + + # Dataloader + if not training: + model.warmup(imgsz=(1 if pt else batch_size, 3, imgsz, imgsz), half=half) # warmup + pad = 0.0 if task in ('speed', 'benchmark') else 0.5 + rect = False if task == 'benchmark' else pt # square inference for benchmarks + task = task if task in ('train', 'val', 'test') else 'val' # path to train/val/test images + dataloader = create_dataloader(data[task], imgsz, batch_size, stride, single_cls, pad=pad, rect=rect, + workers=workers, prefix=colorstr(f'{task}: '))[0] + + seen = 0 + confusion_matrix = ConfusionMatrix(nc=nc) + names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)} + class_map = coco80_to_coco91_class() if is_coco else list(range(1000)) + s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95') + dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 + loss = torch.zeros(3, device=device) + jdict, stats, ap, ap_class = [], [], [], [] + pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar + for batch_i, (im, targets, paths, shapes) in enumerate(pbar): + t1 = time_sync() + if pt or jit or engine: + im = im.to(device, non_blocking=True) + targets = targets.to(device) + im = im.half() if half else im.float() # uint8 to fp16/32 + im /= 255 # 0 - 255 to 0.0 - 1.0 + nb, _, height, width = im.shape # batch size, channels, height, width + t2 = time_sync() + dt[0] += t2 - t1 + + # Inference + out, train_out = model(im) if training else model(im, augment=augment, val=True) # inference, loss outputs + dt[1] += time_sync() - t2 + + # Loss + if compute_loss: + loss += compute_loss([x.float() for x in train_out], targets)[1] # box, obj, cls + + # NMS + targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels + lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling + t3 = time_sync() + out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) + dt[2] += time_sync() - t3 + + # Metrics + for si, pred in enumerate(out): + labels = targets[targets[:, 0] == si, 1:] + nl = len(labels) + tcls = labels[:, 0].tolist() if nl else [] # target class + path, shape = Path(paths[si]), shapes[si][0] + seen += 1 + + if len(pred) == 0: + if nl: + stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) + continue + + # Predictions + if single_cls: + pred[:, 5] = 0 + predn = pred.clone() + scale_coords(im[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred + + # Evaluate + if nl: + tbox = xywh2xyxy(labels[:, 1:5]) # target boxes + scale_coords(im[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels + labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels + correct = process_batch(predn, labelsn, iouv) + if plots: + confusion_matrix.process_batch(predn, labelsn) + else: + correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool) + stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # (correct, conf, pcls, tcls) + + # Save/log + if save_txt: + save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt')) + if save_json: + save_one_json(predn, jdict, path, class_map) # append to COCO-JSON dictionary + callbacks.run('on_val_image_end', pred, predn, path, names, im[si]) + + # Plot images + if plots and batch_i < 3: + f = save_dir / f'val_batch{batch_i}_labels.jpg' # labels + Thread(target=plot_images, args=(im, targets, paths, f, names), daemon=True).start() + f = save_dir / f'val_batch{batch_i}_pred.jpg' # predictions + Thread(target=plot_images, args=(im, output_to_target(out), paths, f, names), daemon=True).start() + + # Compute metrics + stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy + if len(stats) and stats[0].any(): + tp, fp, p, r, f1, ap, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names) + ap50, ap = ap[:, 0], ap.mean(1) # AP@0.5, AP@0.5:0.95 + mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() + nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class + else: + nt = torch.zeros(1) + + # Print results + pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format + LOGGER.info(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) + + # Print results per class + if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats): + for i, c in enumerate(ap_class): + LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) + + # Print speeds + t = tuple(x / seen * 1E3 for x in dt) # speeds per image + if not training: + shape = (batch_size, 3, imgsz, imgsz) + LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t) + + # Plots + if plots: + confusion_matrix.plot(save_dir=save_dir, names=list(names.values())) + callbacks.run('on_val_end') + + # Save JSON + if save_json and len(jdict): + w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else '' # weights + anno_json = str(Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json') # annotations json + pred_json = str(save_dir / f"{w}_predictions.json") # predictions json + LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...') + with open(pred_json, 'w') as f: + json.dump(jdict, f) + + try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb + check_requirements(['pycocotools']) + from pycocotools.coco import COCO + from pycocotools.cocoeval import COCOeval + + anno = COCO(anno_json) # init annotations api + pred = anno.loadRes(pred_json) # init predictions api + eval = COCOeval(anno, pred, 'bbox') + if is_coco: + eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files] # image IDs to evaluate + eval.evaluate() + eval.accumulate() + eval.summarize() + map, map50 = eval.stats[:2] # update results (mAP@0.5:0.95, mAP@0.5) + except Exception as e: + LOGGER.info(f'pycocotools unable to run: {e}') + + # Return results + model.float() # for training + if not training: + s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' + LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") + maps = np.zeros(nc) + map + for i, c in enumerate(ap_class): + maps[c] = ap[i] + return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t + + +def parse_opt(): + parser = argparse.ArgumentParser() + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') + parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)') + parser.add_argument('--batch-size', type=int, default=32, help='batch size') + parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)') + parser.add_argument('--conf-thres', type=float, default=0.001, help='confidence threshold') + parser.add_argument('--iou-thres', type=float, default=0.6, help='NMS IoU threshold') + parser.add_argument('--task', default='val', help='train, val, test, speed or study') + parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)') + parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset') + parser.add_argument('--augment', action='store_true', help='augmented inference') + parser.add_argument('--verbose', action='store_true', help='report mAP by class') + parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') + parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt') + parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') + parser.add_argument('--save-json', action='store_true', help='save a COCO-JSON results file') + parser.add_argument('--project', default=ROOT / 'runs/val', help='save to project/name') + parser.add_argument('--name', default='exp', help='save to project/name') + parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') + parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference') + parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference') + opt = parser.parse_args() + opt.data = check_yaml(opt.data) # check YAML + opt.save_json |= opt.data.endswith('coco.yaml') + opt.save_txt |= opt.save_hybrid + print_args(FILE.stem, opt) + return opt + + +def main(opt): + check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) + + if opt.task in ('train', 'val', 'test'): # run normally + if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466 + LOGGER.info(f'WARNING: confidence threshold {opt.conf_thres} >> 0.001 will produce invalid mAP values.') + run(**vars(opt)) + + else: + weights = opt.weights if isinstance(opt.weights, list) else [opt.weights] + opt.half = True # FP16 for fastest results + if opt.task == 'speed': # speed benchmarks + # python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt... + opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False + for opt.weights in weights: + run(**vars(opt), plots=False) + + elif opt.task == 'study': # speed vs mAP benchmarks + # python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt... + for opt.weights in weights: + f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt' # filename to save to + x, y = list(range(256, 1536 + 128, 128)), [] # x axis (image sizes), y axis + for opt.imgsz in x: # img-size + LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...') + r, _, t = run(**vars(opt), plots=False) + y.append(r + t) # results and times + np.savetxt(f, y, fmt='%10.4g') # save + os.system('zip -r study.zip study_*.txt') + plot_val_study(x=x) # plot + + +if __name__ == "__main__": + opt = parse_opt() + main(opt)