Keras implementation of AutoAugment

This repository contains code for AutoAugment (only using paper's best policies) based on AutoAugment: Learning Augmentation Policies from Data implemented in Keras.

Requirements

WideResNet28-10 baseline on CIFAR-10:

python train.py

WideResNet28-10 +Cutout, AutoAugment on CIFAR-10:

python train.py --cutout True --auto-augment True

Model	Accuracy (%)	Loss
WideResNet28-10 baseline	95.32	0.3717
WideResNet28-10 +Cutout, AutoAugment	96.06	0.3565

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
LICENSE		LICENSE
README.md		README.md
auto_augment.py		auto_augment.py
cosine_annealing.py		cosine_annealing.py
dataset.py		dataset.py
train.py		train.py
utils.py		utils.py
wide_resnet.py		wide_resnet.py