Welcome to Albumentations documentation
Albumentations is a fast and flexible image augmentation library. The library is widely used industry, deep learning research, machine learning competitions, and open source projects.
If you are new to image augmentation, start with articles in the "Introduction to image augmentation" section. They describe what image augmentation is, how it can boost deep neural networks' performance, and why you should use Albumentations.
Articles in the "Getting started with Albumentations" section show how you can use the library for different computer vision tasks: image classification, semantic segmentation, instance segmentation, and object detection.
"API Reference" contains Albumentations' methods and classes.
Introduction to image augmentation
- What is image augmentation and how it can improve the performance of deep neural networks
- Why you need a dedicated library for image augmentation
- Why Albumentations
Getting started with Albumentations
- Image augmentation for classification
- Mask augmentation for segmentation
- Bounding boxes augmentation for object detection
- Keypoints augmentation
- Simultaneous augmentation of multiple targets: masks, bounding boxes, keypoints