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

An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).

Face recognize and crop them

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Data pipelines for both TensorFlow and PyTorch!

Groceries ARL: Association Rules (Birliktelik Kuralı)

Emotion classification of online comments based on RNN

Paper list of log-based anomaly detection

Learning Open-World Object Proposals without Learning to Classify

A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."

NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

PyTorch implementation of "Representing Shape Collections with Alignment-Aware Linear Models" paper.

Flower - A Friendly Federated Learning Framework

An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Improving Compound Activity Classification via Deep Transfer and Representation Learning

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Code for our paper "MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction" published at ICCV 2021.