Do more with less data

Albumentations is a computer vision tool that boosts the performance of deep convolutional neural networks.

The library is widely used in industry, deep learning research, machine learning competitions, and open source projects.

Why Albumentations

Albumentations is a Python library for fast and flexible image augmentations. Albumentations efficiently implements a rich variety of image transform operations that are optimized for performance, and does so while providing a concise, yet powerful image augmentation interface for different computer vision tasks, including object classification, segmentation, and detection.

Different tasks

Albumentations supports different computer vision tasks such as classification, semantic segmentation, instance segmentation, object detection, and pose estimation.

Different domains

Albumentations works well with data from different domains: photos, medical images, satellite imagery, manufacturing and industrial applications, Generative Adversarial Networks.

Seamless integration with deep learning frameworks

Albumentations can work with various deep learning frameworks such as PyTorch and Keras. The library is a part of the PyTorch ecosystem.

It is free and open source

Albumentations is MIT licensed. See the project on GitHub.

Member of the NVIDIA Inception program

The NVIDIA Inception program nurtures cutting-edge AI startups who are revolutionizing industries.

Getting started

Albumentations requires Python 3.5 or higher. To install the library from PyPI run
pip install albumentations


If you find this library useful for your research, please consider citing Albumentations: Fast and Flexible Image Augmentations:
    AUTHOR = {Buslaev, Alexander and Iglovikov, Vladimir I. and Khvedchenya, Eugene and Parinov, Alex and Druzhinin, Mikhail and Kalinin, Alexandr A.},
    TITLE = {Albumentations: Fast and Flexible Image Augmentations},
    JOURNAL = {Information},
    VOLUME = {11},
    YEAR = {2020},
    NUMBER = {2},
    ARTICLE-NUMBER = {125},
    URL = {},
    ISSN = {2078-2489},
    DOI = {10.3390/info11020125}