AutoAugment - Learning Augmentation Policies from Data
Unofficial implementation of the ImageNet, CIFAR10 and SVHN Augmentation Policies learned by AutoAugment, described in this Google AI Blogpost.
Update July 13th, 2018: Wrote a Blogpost about AutoAugment and Double Transfer Learning.
Tested with Python 3.6. Needs pillow>=5.0.0
Example
from autoaugment import ImageNetPolicy
image = PIL.Image.open(path)
policy = ImageNetPolicy()
transformed = policy(image)
To see examples of all operations and magnitudes applied to images, take a look at AutoAugment_Exploration.ipynb.
Example as a PyTorch Transform - ImageNet
from autoaugment import ImageNetPolicy
data = ImageFolder(rootdir, transform=transforms.Compose(
[transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(), ImageNetPolicy(),
transforms.ToTensor(), transforms.Normalize(...)]))
loader = DataLoader(data, ...)
Example as a PyTorch Transform - CIFAR10
from autoaugment import CIFAR10Policy
data = ImageFolder(rootdir, transform=transforms.Compose(
[transforms.RandomCrop(32, padding=4, fill=128), # fill parameter needs torchvision installed from source
transforms.RandomHorizontalFlip(), CIFAR10Policy(),
transforms.ToTensor(),
Cutout(n_holes=1, length=16), # (https://github.com/uoguelph-mlrg/Cutout/blob/master/util/cutout.py)
transforms.Normalize(...)]))
loader = DataLoader(data, ...)
Example as a PyTorch Transform - SVHN
from autoaugment import SVHNPolicy
data = ImageFolder(rootdir, transform=transforms.Compose(
[SVHNPolicy(),
transforms.ToTensor(),
Cutout(n_holes=1, length=20), # (https://github.com/uoguelph-mlrg/Cutout/blob/master/util/cutout.py)
transforms.Normalize(...)]))
loader = DataLoader(data, ...)
Results with AutoAugment
Generalizable Data Augmentations
Finally, we show that policies found on one task can generalize well across different models and datasets. For example, the policy found on ImageNet leads to significant improvements on a variety of FGVC datasets. Even on datasets for which fine-tuning weights pre-trained on ImageNet does not help significantly [26], e.g. Stanford Cars [27] and FGVC Aircraft [28], training with the ImageNet policy reduces test set error by 1.16% and 1.76%, respectively. This result suggests that transferring data augmentation policies offers an alternative method for transfer learning.
CIFAR 10
CIFAR 100
ImageNet
SVHN
Fine Grained Visual Classification Datasets
122 Dec 07, 2022
36 Oct 04, 2022
51 Dec 24, 2022
2k Jan 05, 2023
4 May 04, 2022
163 Nov 21, 2022
5 Aug 13, 2022
2 Nov 09, 2021
1.5k Jan 06, 2023
235 Dec 27, 2022
1.5k Jan 07, 2023
29 Dec 03, 2022
64 Dec 14, 2022
64 Dec 13, 2022
13 Dec 06, 2022
50 Nov 22, 2022
262 Dec 21, 2022
460 Jan 05, 2023
648 Jan 08, 2023
76 Dec 12, 2022