This project enables interaction with computers using hand gestures by leveraging machine learning and computer vision techniques.
- Prerequisites
- Environment Setup
- Dependency Installation
- Usage
- Contributions
- License and Support
Please ensure you have Python version 3.11.0 or later installed, but not version 3.12 or later. You can download the appropriate version of Python from the official website. Additionally, you should have the model required for this project.
- Create a Conda environment:
conda env create -f environment.yml
- Activate the Python virtual environment:
conda activate major
- Deactivate the Python virtual environment when done:
conda deactivate
Install CUDA (required only for training). This requires Python 3.10 and TensorFlow 2.10. Note that Tensorflow does not support Windows natively after version 2.10. All training must be done in WSL2:
conda create -n major_tensorflow python=3.10
conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0
conda install -c nvidia cuda-nvcc
To test if your GPU is detected, run the following command:
python -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"
To use the application, run the following command:
python3 gesture_efficientnet.py
CLOSED UNTIL FURTHER NOTICE
This project is licensed under the Apache License. You are free to use, modify, and distribute the code as per the terms of the license.
While the code is open-source, please note that any support or assistance provided in relation to this project is not free. If you require support or assistance in using this project, please contact me for details about support options and pricing.