Official Fast AutoAugment implementation in PyTorch.

• Fast AutoAugment learns augmentation policies using a more efficient search strategy based on density matching.
• Fast AutoAugment speeds up the search time by orders of magnitude while maintaining the comparable performances.

Search : 3.5 GPU Hours (1428x faster than AutoAugment), WResNet-40x2 on Reduced CIFAR-10

Search : 450 GPU Hours (33x faster than AutoAugment), ResNet-50 on Reduced ImageNet

Search : 1.5 GPU Hours

We conducted experiments under

• python 3.6.9
• pytorch 1.2.0, torchvision 0.4.0, cuda10

Please read ray's document to construct a proper ray cluster : https://github.com/ray-project/ray, and run search.py with the master's redis address.

$ python search.py -c confs/wresnet40x2_cifar10_b512.yaml --dataroot ... --redis ...

You can train network architectures on CIFAR-10 / 100 and ImageNet with our searched policies.

• fa_reduced_cifar10 : reduced CIFAR-10(4k images), WResNet-40x2
• fa_reduced_imagenet : reduced ImageNet(50k images, 120 classes), ResNet-50

$ export PYTHONPATH=$PYTHONPATH:$PWD
$ python FastAutoAugment/train.py -c confs/wresnet40x2_cifar10_b512.yaml --aug fa_reduced_cifar10 --dataset cifar10
$ python FastAutoAugment/train.py -c confs/wresnet40x2_cifar10_b512.yaml --aug fa_reduced_cifar10 --dataset cifar100
$ python FastAutoAugment/train.py -c confs/wresnet28x10_cifar10_b512.yaml --aug fa_reduced_cifar10 --dataset cifar10
$ python FastAutoAugment/train.py -c confs/wresnet28x10_cifar10_b512.yaml --aug fa_reduced_cifar10 --dataset cifar100
...
$ python FastAutoAugment/train.py -c confs/resnet50_b512.yaml --aug fa_reduced_imagenet
$ python FastAutoAugment/train.py -c confs/resnet200_b512.yaml --aug fa_reduced_imagenet

By adding --only-eval and --save arguments, you can test trained models without training.

If you use any part of this code in your research, please cite our paper.

@inproceedings{lim2019fast,
  title={Fast AutoAugment},
  author={Lim, Sungbin and Kim, Ildoo and Kim, Taesup and Kim, Chiheon and Kim, Sungwoong},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2019}
}

• Ildoo Kim, [email protected]
• Sungbin Lim, [email protected]

We increase the batch size and adapt the learning rate accordingly to boost the training. Otherwise, we set other hyperparameters equal to AutoAugment if possible. For the unknown hyperparameters, we follow values from the original references or we tune them to match baseline performances.

• ResNet : paper1, paper2, code
• PyramidNet : paper, code
• Wide-ResNet : code
• Shake-Shake : code
• ShakeDrop Regularization : paper, code
• AutoAugment : code
• Ray : code
• HyperOpt : code