rAIght.move is an AI-powered tool designed to help you analyze and improve your workout form with real-time feedback. Using advanced pose estimation technology, this gym assistant evaluates your form during exercises such as squats and bench presses, ensuring that you get the most out of your workout safely and effectively.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
A step-by-step series of examples that tell you how to get a development environment running:
Clone the repository to your local machine:
git clone https://github.com/hbrt-rdzk/move.rAIght.gitNavigate to the cloned directory:
cd move.rAIghtCreate virtual environments:
python3 -m venv venvInstall the necessary dependencies:
pip install -e .To run the Gym Assistant, use the following command:
python3 scripts/cli.pyYou have to provide the following arguments:
-a,--app: One of the app types (LIVE, VIDEO)-i,--input: Specify the camera number or path to the video file you wish to analyze.--exercise: Type of analyzing exercise
Optional arguments:
-o,--output: Directory path for output data (CSV)--save_results: If data should be saved or not
Example of running with a video file:
python3 scripts/cli.py --app="LIVE" -i="path/to/video.mp4" --exercise="squat" --save_resultsExample of running with a webcam:
python3 scripts/cli.py --app="LIVE" -i=0 --exercise="squat" -o="squat.csv" --save_resultsTo analyze the video:
python3 scripts/cli.py --app="VIDEO" -i="path/to/video.mp4" --exercise="squat" --save_resultsThe configs/config.yaml file contains all the configuration parameters that Gym Assistant needs to know before analyzing your workout. Make sure to review and modify it if needed according to your specific requirements.
The data/ directory should contain your workout videos categorized by exercise type. This can be used to train the model or for personal record-keeping.
This project is licensed under the MIT License - see the LICENSE.md file for details.