imgaug

This python library helps you with augmenting images for your machine learning projects. It converts a set of input images into a new, much larger set of slightly altered images.

	Image	Heatmaps	Seg. Maps	Keypoints	Bounding Boxes, Polygons
Original Input
Gauss. Noise + Contrast + Sharpen
Affine
Crop + Pad
Fliplr + Perspective

More (strong) example augmentations of one input image:

Table of Contents

1. Features
2. Installation
3. Documentation
4. Recent Changes
5. Example Images
6. Code Examples
7. Citation

• Many augmentation techniques
• E.g. affine transformations, perspective transformations, contrast changes, gaussian noise, dropout of regions, hue/saturation changes, cropping/padding, blurring, ...
• Optimized for high performance
• Easy to apply augmentations only to some images
• Easy to apply augmentations in random order
• Support for
• Images (full support for uint8, for other dtypes see documentation)
• Heatmaps (float32), Segmentation Maps (int), Masks (bool)
  • May be smaller/larger than their corresponding images. No extra lines of code needed for e.g. crop.
• Keypoints/Landmarks (int/float coordinates)
• Bounding Boxes (int/float coordinates)
• Polygons (int/float coordinates)
• Line Strings (int/float coordinates)
• Automatic alignment of sampled random values
• Example: Rotate image and segmentation map on it by the same value sampled from uniform(-10°, 45°). (0 extra lines of code.)
• Probability distributions as parameters
• Example: Rotate images by values sampled from uniform(-10°, 45°).
• Example: Rotate images by values sampled from ABS(N(0, 20.0))*(1+B(1.0, 1.0))", where ABS(.) is the absolute function, N(.) the gaussian distribution and B(.) the beta distribution.
• Many helper functions
• Example: Draw heatmaps, segmentation maps, keypoints, bounding boxes, ...
• Example: Scale segmentation maps, average/max pool of images/maps, pad images to aspect ratios (e.g. to square them)
• Example: Convert keypoints to distance maps, extract pixels within bounding boxes from images, clip polygon to the image plane, ...
• Support for augmentation on multiple CPU cores

conda config --add channels conda-forge
conda install imgaug

pip install imgaug

pip install git+https://github.com/aleju/imgaug.git

For more details, see the install guide

To deinstall the library, just execute pip uninstall imgaug.

Example jupyter notebooks: * Load and Augment an Image * Multicore Augmentation * Augment and work with: Keypoints/Landmarks, Bounding Boxes, Polygons, Line Strings, Heatmaps, Segmentation Maps

More notebooks: imgaug-doc/notebooks.

Example ReadTheDocs pages: * Quick example code on how to use the library * Overview of all Augmenters * API

More RTD documentation: imgaug.readthedocs.io.

All documentation related files of this project are hosted in the repository imgaug-doc.

See changelogs/ for more details.

Example Images

The images below show examples for most augmentation techniques.

Values written in the form (a, b) denote a uniform distribution, i.e. the value is randomly picked from the interval [a, b]. Line strings are supported by (almost) all augmenters, but are not explicitly visualized here.

meta
Identity	ChannelShuffle
See also: Sequential, SomeOf, OneOf, Sometimes, WithChannels, Lambda, AssertLambda, AssertShap