# albumentations-team/albumentations

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Repository: https://github.com/albumentations-team/albumentations
Canonical: https://ross.abutalabs.com/products/albumentations
Homepage: https://albumentations.ai
Language: Python
License: MIT
License Family: permissive
Topics: image-augmentation, machine-learning, augmentation, deep-learning, detection, fast-augmentations, segmentation, image-segmentation, image-processing, image-classification, python, object-detection
Archived: true
Last push: 2025-06-25T23:21:43+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 28, release rhythm 40, longevity 100
- inputs: {"age_days": 3010, "days_push": 434, "days_rel": 463, "gap_med": 9.5, "n_releases_24m": 19}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15315, forks 1709 (observed 2026-08-28T04:11:09.625989+00:00)

## What it is
Albumentations is a fast, flexible Python image augmentation library for computer vision, supporting images, masks, bounding boxes, keypoints, volumes, and 3D data with a broad transform catalog. This MIT-licensed repository is archived and no longer maintained; active development has moved to the dual-licensed (AGPL-3.0/commercial) AlbumentationsX successor.

## Use cases
- augment images for training deep learning models
- augment images and masks together for segmentation
- augment bounding boxes for object detection datasets
- build fast reproducible augmentation pipelines in PyTorch DataLoader workers
- apply test-time augmentation for computer vision
- create custom image transforms for domain-specific data

## When to choose
- you need a permissively MIT-licensed augmentation library and your current version works fine
- you want target-aware transforms that keep masks, boxes, and keypoints consistent with images
- you need a mature, widely adopted library with a large transform catalog

## When to avoid
- you need bug fixes, new features, or compatibility with newer Python/PyTorch versions
- you want active development and support - use AlbumentationsX instead
- you need commercial support guarantees

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, machine-learning, image-processing
- platform: python, cross-platform
- tags: image-augmentation, data-augmentation, object-detection, segmentation, pytorch, training-pipelines, archived

## Member repositories
- albumentations-team/albumentations (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.625989+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:22.446987+00:00, confidence not recorded.
  - readme: https://github.com/albumentations-team/albumentations (fetched 2026-08-28T04:11:09.625989+00:00, sha eea4b5f1661b)
  - homepage: https://albumentations.ai (fetched 2026-08-29T08:04:32.562159+00:00, sha 2367a9cd1637)
  - site_page: https://albumentations.ai/docs (fetched 2026-08-29T08:04:32.565065+00:00, sha 140aa1c52ca9)
  - site_page: https://albumentations.ai/docs/reference/supported-targets-by-transform (fetched 2026-08-29T08:04:32.569378+00:00, sha 51afd8460dc8)
  - site_page: https://albumentations.ai/docs/benchmarks/image-benchmarks (fetched 2026-08-29T08:04:32.571277+00:00, sha f1c81c2c6759)
  - site_page: https://albumentations.ai/docs/4-advanced-guides/creating-custom-transforms (fetched 2026-08-29T08:04:32.573310+00:00, sha d186b853d65d)
  - site_page: https://albumentations.ai/pricing (fetched 2026-08-29T08:04:32.567259+00:00, sha d36081473792)
- Data as of 2026-08-30T08:39:29.467469+00:00.