Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

Last update: Jan 02, 2023

Related tags

Overview

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.

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

Related tags

Overview

AutoAugment - Learning Augmentation Policies from Data

Tested with Python 3.6. Needs pillow>=5.0.0

Example

Example as a PyTorch Transform - ImageNet

Example as a PyTorch Transform - CIFAR10

Example as a PyTorch Transform - SVHN

Results with AutoAugment

Generalizable Data Augmentations

CIFAR 10

CIFAR 100

ImageNet

SVHN

Fine Grained Visual Classification Datasets

Owner

Philip Popien

Code for "CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds" @ICRA2021

PyTorch-LIT is the Lite Inference Toolkit (LIT) for PyTorch which focuses on easy and fast inference of large models on end-devices.

Source code related to the article submitted to the International Conference on Computational Science ICCS 2022 in London

Code for the paper "Graph Attention Tracking". (CVPR2021)

Self-Supervised Image Denoising via Iterative Data Refinement

Source codes for the paper "Local Additivity Based Data Augmentation for Semi-supervised NER"

Deep Reinforcement Learning for Multiplayer Online Battle Arena

Complementary Patch for Weakly Supervised Semantic Segmentation, ICCV21 (poster)

Improving Contrastive Learning by Visualizing Feature Transformation, ICCV 2021 Oral

Compressed Video Action Recognition

Dataloader tools for language modelling

Model Zoo for AI Model Efficiency Toolkit

Semi-supervised Representation Learning for Remote Sensing Image Classification Based on Generative Adversarial Networks

A new data augmentation method for extreme lighting conditions.

Notes taking website build with Docker + Django + React.

Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

Collection of generative models in Tensorflow

A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by Mathieu, Couprie & LeCun.

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch