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.

Downloads (last 30 days)6.4MStar on GitHub14.6K
Open documentation
Albumentations example

Community-Driven Project, Supported By

Albumentations thrives on developer contributions. We appreciate our sponsors who help sustain the project's infrastructure.

Gold Sponsors
Your company could be here
Silver Sponsors
Datature
Bronze Sponsors
Roboflow
Become a Sponsor
View sponsorship tiers and benefits on GitHub Sponsors

Why Albumentations

The fastest and most flexible image augmentation library, trusted by thousands of AI engineers and researchers worldwide

Lightning Fast

Up to 10x faster than other libraries. See benchmarks

Versatile

Supports classification, segmentation, detection, and more tasks out of the box

Easy to Use

Simple, intuitive API with comprehensive documentation and examples

Albumentations is a Python library for image augmentations that provides:

  • Optimized performance for production environments
  • Rich variety of transform operations
  • Support for all major computer vision tasks
  • Seamless integration with PyTorch, TensorFlow, and other frameworks
Compare Albumentations with other libraries

Community Feedback

Community feedback
CEO of Datature
Community feedback
Kaggle Competitions Grandmaster. Top 1 in the world.
Community feedback
Computer Vision Engineer
View more feedback

Industry users of Albumentations

Apple
Google Research
Meta Research
NVIDIA Research Projects
Amazon Science
Microsoft Open Source
Salesforce Open Source
Stability AI
IBM Open Source
Hugging Face
Sony
Alibaba Open Source
Tencent Open Source
H2O.ai

Different tasks

Different tasks

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

Computer vision tasks

Different domains

Different domains

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

Different domains

Seamless integration with deep learning frameworks

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. MMDetection and YOLOv5 use Albumentations.

Deep learning frameworks

Getting started

Albumentations requires Python 3.9 or higher. To install the library from PyPI run

pip install -U albumentations
Open documentation

Support Open Source Development

Albumentations is a free, open-source project maintained by a dedicated team of developers

Your sponsorship helps us maintain high-quality code, provide timely updates, and develop new features

Individual Sponsors

Support open source with a monthly contribution of any size. Every dollar helps maintain and improve Albumentations.

Sponsor

Company Sponsorship

Companies using Albumentations can become official sponsors, getting their logo featured on our website and documentation.

View Sponsorship Tiers
100% of sponsorships go directly to supporting development and maintenance.

Citing

If you find this library useful for your research, please consider citing Albumentations: Fast and Flexible Image Augmentations:

@Article{info11020125,
    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 = {https://www.mdpi.com/2078-2489/11/2/125},
    ISSN = {2078-2489},
    DOI = {10.3390/info11020125}
}