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

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

Fuzzing the Kernel Using Unicornafl and AFL++

Official implementation of the Neurips 2021 paper Searching Parameterized AP Loss for Object Detection.

This is a classifier which basically predicts whether there is a gun law in a state or not, depending on various things like murder rates etc.

Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

Official Implementation of LARGE: Latent-Based Regression through GAN Semantics

Introducing neural networks to predict stock prices

code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

This is a repository for a semantic segmentation inference API using the OpenVINO toolkit

Codecov coverage standard for Python

Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language

Learning to Estimate Hidden Motions with Global Motion Aggregation

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

People log into different sites every day to get information and browse through these sites one by one

Level Based Customer Segmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020)

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks