AutoAlbument is an AutoML tool that learns image augmentation policies from data using the Faster AutoAugment algorithm. It relieves the user from manually selecting augmentations and tuning their parameters. AutoAlbument provides a complete ready-to-use configuration for an augmentation pipeline.
AutoAlbument supports image classification and semantic segmentation tasks. The library requires Python 3.6 or higher.
The source code and issue tracker are available at https://github.com/albumentations-team/autoalbument
Table of contents:
- AutoAlbument introduction and core concepts
- Benchmarks and a comparison with baseline augmentation strategies
- How to use AutoAlbument
- How to use an AutoAlbument Docker image
- How to use a custom classification or semantic segmentation model
- Metrics and their meaning
- Tuning parameters
- Search algorithms