AutoAlbument is an AutoML tool that learns image augmentation policies from data using the Faster AutoAugment algorithm. It relieves the user from the burden of manually selecting augmentations and tuning their parameters. AutoAlbument provides a complete ready-to-use configuration for an augmentation pipeline.
The library supports image classification and semantic segmentation tasks. You can use Albumentations to utilize policies discovered by AutoAlbument in your computer vision pipelines.
AutoAlbument requires Python 3.6 or higher. To install the latest stable version from PyPI:
pip install -U autoalbument
How to use AutoAlbument
You need to create a configuration file with AutoAlbument parameters and a Python file that implements a custom PyTorch Dataset for your data. Next, you need to pass those files to AutoAlbument.
AutoAlbument will use Generative Adversarial Network to discover augmentation policies and then create a file containing those policies.
Finally, you can use Albumentations to load augmentation policies from the file and utilize them in your computer vision pipelines.
The examples directory in the repository contains example configs for different tasks and datasets:
Publish benchmarks of how much augmentation policies from AutoAlbument improves the quality of models trained on popular classification and semantic segmentation datasets.
Add support for object detection and instance segmentation tasks.
Add support for all popular augmentations available in Albumentations so AutoAlbument could use them in a search phase.
Slack ODS.ai: #tool_albumentations