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

SegNet model implemented using keras framework

Script that attempts to force M1 macs into RGB mode when used with monitors that are defaulting to YPbPr.

基于Pytorch实现优秀的自然图像分割框架！(包括FCN、U-Net和Deeplab)

Implementation of popular bandit algorithms in batch environments.

StyleGAN2 - Official TensorFlow Implementation

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

OSLO: Open Source framework for Large-scale transformer Optimization

This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

An Abstract Cyber Security Simulation and Markov Game for OpenAI Gym

PIXIE: Collaborative Regression of Expressive Bodies

Hand Gesture Volume Control is AIML based project which uses image processing to control the volume of your Computer.

[BMVC2021] "TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation"

Physics-informed Neural Operator for Learning Partial Differential Equation

Real-time Object Detection for Streaming Perception, CVPR 2022

An implementation of IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification

Tensorflow implementation of Swin Transformer model.

DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

Offline Reinforcement Learning with Implicit Q-Learning

Code accompanying "Learning What To Do by Simulating the Past", ICLR 2021.