Model Capable of Detecting chess pieces, and augmenting the next move in realtime !
- The model is completely trained on synthetic data generated using blender
- Each Chess Piece is Crafted using the existing real-life piece taken as a reference
- The blend file also includes the python script to automate the making of dataset
- Randomize camera and lighting positions
- place chess pieces according to FEN
- Capture image and Save annotations
Follow the steps below to set up and run the project.
git clone https://github.com/akhil838/ChessBot-Computer-Vision.git
cd ChessBot-Computer-Vision- (Optional) Create and activate a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install required Python packages
pip install -r requirements.txt
- Install PyTorch If you have a CUDA-compatible GPU
Visit the official PyTorch installation guide and install the appropriate version based on your CUDA version. Example for CUDA 12.1:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
If you are using CPU only
pip install torch torchvision torchaudio
Running the Program
Start the Jupyter notebook:
jupyter notebook run.ipynb