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

Constructing Neural Network-Based Models for Simulating Dynamical Systems

Pytorch implementation of CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation"

Colab notebook and additional materials for Python-driven analysis of redlining data in Philadelphia

Perturb-and-max-product: Sampling and learning in discrete energy-based models

Deep learning models for classification of 15 common weeds in the southern U.S. cotton production systems.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

This is an open source python repository for various python tests

FAST Aiming at the problems of cumbersome steps and slow download speed of GNSS data

FID calculation with proper image resizing and quantization steps

particle tracking model, works with the ROMS output file(qck.nc, his.nc)

FairMOT - A simple baseline for one-shot multi-object tracking

End-to-End Object Detection with Fully Convolutional Network

Multi-task Learning of Order-Consistent Causal Graphs (NeuRIPs 2021)

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Pytorch code for "Text-Independent Speaker Verification Using 3D Convolutional Neural Networks".

Code for classifying international patents based on the text of their titles/abstracts

AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations

PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021.

ESGD-M - A stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch

My 1st place solution at Kaggle Hotel-ID 2021