Skip to content

Evolutionary Deep Learning. Evolve PyTorch Lightning models from scratch using Genetic Algorithms & Backpropagation. All using default PyTorch and Lightning-AI (PyTorch Lightning & Bolts).

License

Notifications You must be signed in to change notification settings

fredericosantos/pytorch-genesis

Repository files navigation

🚧 Under construction 🚧

PyTorch Genesis

Paper

Description

Evolve PyTorch Lightning models from scratch using Genetic Algorithms & Backpropagation. All using default PyTorch and Lightning-AI (PyTorch Lightning & Bolts).

How to run

First, install dependencies

# clone project   
git clone https://github.com/fredericosantos/pytorch-genesis

# install project   
cd pytorch-genesis 
pip install -e .   
pip install -r requirements.txt

Next, navigate to the example notebook and open it.

Citation

@article{Frederico J.J.B. Santos, 
  title={Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks},
  author={Ivo Gonçalves, Mauro Castelli},
  journal={Applied Soft Computing},
  year={2023}
}

About

Evolutionary Deep Learning. Evolve PyTorch Lightning models from scratch using Genetic Algorithms & Backpropagation. All using default PyTorch and Lightning-AI (PyTorch Lightning & Bolts).

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages