An implementation of implementation of CoDeepNEAT, originally created by Risto Miikkulainen et al. with our own extensions. Implementation details were taken from their 2017 and 2019 paper.
Requires conda
conda create -n cdn --file requirements.txt
conda activate cdn
pip install tarjan wandb # these are not available from conda
Directory: src/main/
ft.py Fully trains a run from evo.py
evo.py Does an evolutionary run
batch_run.py Running many different configurations all the way from evolution to fully training. (See note below)
All config options are in src/configuration/configuration.py
Example configs are in src/configuration/configs directory
python src/main/evo.py -g 1 -c base
Extensions are detailed in the paper linked above
If you use this code, please cite our paper:
@INPROCEEDINGS{9308151,
author={S. {Acton} and S. {Abramowitz} and L. {Toledo} and G. {Nitschke}},
booktitle={2020 IEEE Symposium Series on Computational Intelligence (SSCI)},
title={Efficiently Coevolving Deep Neural Networks and Data Augmentations},
year={2020},
volume={},
number={},
pages={2543-2550},
doi={10.1109/SSCI47803.2020.9308151}}
For detailed results see:
convergence
evolution
The accuracies obtained on CIFAR-10
The best data augmentations found
The best genotype found. Using config configuration/configs/experiments/mms_da_pop_25e.json and a feature multiplier of 5
And its corresponding phenotype
This system was developed for rapid tuning of CDN's own hyperparameters on a cluster with a limited number of GPUs. It should not be used for normal training as it was created for our very specific case. Rather do a single run on evo.py and then fully train it with ft.py.