Skip to content

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Notifications You must be signed in to change notification settings

nielseni6/yolov7_mavrc

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

XAI Branch Info

Main script to run is test_plaus_or_faith.py. Plausibility Guided Training implemented (run train_pgt.py). Accuracy of training not yet tested.

Turret Gunner Survivability and Simulation Environment Project (Main Code)

This project is a collaborative effort between the Machine Learning, AI, and Virtual Reality Center at Rowan University and the Picatinny Arsenal. We, the AI team at Rowan, have been tasked with developing a drone detection algorithm that enhances the survivability of turret gunners.

Our solution leverages a forked version of YOLOv7, which we have modified to include a special metric for small object detection known as the Normalized Wasserstein Distance. This metric improves the model's ability to detect small objects, a crucial requirement for our simulation environment.

Setting Up a Virtual Environment

This guide will walk you through the steps to create a new virtual environment, install the required dependencies specified in the requirements.txt file.

Prerequisites

Make sure you have the following installed on your system:

  • Python 3.6 or later
  • Git
  • W&B account (sign up here)

Creating a Virtual Environment

  1. Clone the repository to your local machine.

    git clone https://github.com/naddeok96/yolov7_mavrc
  2. Navigate to the project directory.

    cd yolov7_mavrc
  3. Create a new virtual environment.

    python3 -m venv venv_name
  4. Activate the virtual environment.

    source venv_name/bin/activate

Installing Dependencies

  1. Install the dependencies specified in the requirements.txt file.
    pip3 install -r requirements.txt

About

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 97.4%
  • Python 2.6%