Augmentor.jl is a fast Julia library designed to make the process of image augmentation more convenient, less error-prone, and easier to reproduce. It offers a simple way to build flexible augmentation pipelines. For our purposes, an augmentation pipeline can be understood as a sequence of operations for which the parameters can (but need not) be random variables.

When augmenting, Augmentor.jl uses multiple heuristics to generate efficient tailor-made code for the concrete user-specified augmentation pipeline. In particular, Augmentor tries to avoid the need for any intermediate images and aims to compute the output image directly from the input in one single pass.

Overview

Augmentor.jl provides many augmentation operations such as rotations, flipping, blurring, and more. See the documentation for the complete list of available operations.

The package uses the |> operator to compose operations into a pipeline.

Prepared pipelines are applied to images by calling one of the higher-level functions: augment, augment!, or augmentbatch!.

The full documentation is available at evizero.github.io/Augmentor.jl/.

Example

julia> pl = ElasticDistortion(6, scale=0.3, border=true) |>
            Rotate([10, -5, -3, 0, 3, 5, 10]) |>
            ShearX(-10:10) * ShearY(-10:10) |>
            CropSize(28, 28) |>
            Zoom(0.9:0.1:1.2)
5-step Augmentor.ImmutablePipeline:
 1.) Distort using a smoothed and normalized 6×6 grid
 2.) Rotate by θ ∈ [10, -5, -3, 0, 3, 5, 10] degree
 3.) Either: (50%) ShearX by ϕ ∈ -10:10 degree. (50%) ShearY by ψ ∈ -10:10 degree.
 4.) Crop a 28×28 window around the center
 5.) Zoom by I ∈ {0.9×0.9, 1.0×1.0, 1.1×1.1, 1.2×1.2}

julia> augment(img, pl)

For more examples, see the documentation.

Contributing

Contributions are greatly appreciated!

To report a potential bug or propose a new feature, please file a new issue. Pull requests are always welcome. However, to make sure the PR gets accepted, it is generally preferred when it follows a particular issue to which it refers.

Citing Augmentor

If you use Augmentor for academic research and wish to cite it, please use the following paper.

Marcus D. Bloice, Christof Stocker, and Andreas Holzinger, Augmentor: An Image Augmentation Library for Machine Learning, arXiv preprint arXiv:1708.04680, https://arxiv.org/abs/1708.04680, 2017.

Acknowledgments

A Python version of the package is also being developed as a sister project and is available at mdbloice/Augmentor

To provide most of the operations, Augmentor.jl makes heavy use of many packages. To name a few:

Project Name	Stars	Repos Using This	Packages Using This	Most Recent Commit	Total Releases	Latest Release	Open Issues	License	Language
Imgaug	11,905	278	98	a year ago	11	February 05, 2020	256	mit	Python
Image augmentation for machine learning experiments.
Albumentations	11,723	64	155	7 days ago	52	June 15, 2022	355	mit	Python
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Augmentor	4,849	21	8	2 months ago	22	April 27, 2022	132	mit	Python
Image augmentation library in Python for machine learning.
Nlpaug	3,825	1	18	19 days ago	37	July 07, 2022	61	mit	Jupyter Notebook
Data augmentation for NLP
Stylegan2 Pytorch	3,147		2	8 months ago	146	January 27, 2022	120	mit	Python
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Textattack	2,263		7	17 days ago	44	May 25, 2022	29	mit	Python
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
Torchio	1,648		15	16 days ago	231	July 04, 2022	42	apache-2.0	Python
Medical imaging toolkit for deep learning
Pytorch Toolbelt	1,363	1	5	4 days ago	24	June 27, 2022	1	mit	Python
PyTorch extensions for fast R&D prototyping and Kaggle farming
Audiomentations	1,294		1	4 days ago	28	June 15, 2022	45	mit	Python
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Data Augmentation Review	1,194			10 months ago
List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.