FastAPI TensorFlow Serving

GitHub project for Tensorflow-based Object Detection on the CIFAR-10 dataset, served with FastAPI.

Tech Stack

• Tensorflow 2
• FastAPI
• uv
• Docker

Up and Running

Developer Setup

1. Install the dependencies on pyproject.toml:

uv sync

2. Activate the virtualenv created by uv:

source .venv/bin/activate

3. Start the app with gunicorn with:

make run

4. Access the Swagger UI at:

open http://localhost:8080

Containerization and Testing

1. Build the Docker Image with:

make docker-image

2. Spin up the container with:

make docker-run

3. Access the Swagger UI at:

open http://localhost:8000

TODO

• PEP-517: Packaging and dependency management with uv
• Code format/lint with Ruff
• Run on Docker
• Serve it with Streamlit
• GitHub CI