# MIC-DKFZ/batchgenerators

A framework for data augmentation for 2D and 3D image classification and segmentation

Repository: https://github.com/MIC-DKFZ/batchgenerators
Canonical: https://ross.abutalabs.com/products/batchgenerators
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-06-16T11:41:24+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 100
- inputs: {"age_days": 3232, "days_push": 78, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1173, forks 230 (observed 2026-08-28T04:03:51.909007+00:00)

## What it is
A Python framework for data augmentation of 2D and 3D images, developed by the German Cancer Research Center for medical image classification and segmentation. It provides spatial, color, and noise transforms composable via a pipeline, plus a multithreaded augmenter for data loading.

## Use cases
- augment 3D medical images for segmentation training
- apply elastic deformations and rotations to image batches
- simulate misalignment between multi-modal image channels
- build a multithreaded data loading pipeline for deep learning
- add Gaussian and Rician noise to training images
- augment 2D images for classification models

## When to choose
- you train models on 2D or 3D images, especially medical imaging
- you need augmentations that work on volumetric (3D) data
- you want composable transforms with a multithreaded batch loader

## When to avoid
- you only need standard 2D photo augmentations for natural images
- you want a framework with GPU-side augmentation
- you need a general-purpose data loading library outside image augmentation

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, image-processing, data-generation
- domain: machine-learning, deep-learning, computer-vision, image-processing, healthcare
- platform: python, cross-platform
- tags: data-augmentation, medical-imaging, 3d-images, segmentation, multithreaded-dataloader

## Member repositories
- MIC-DKFZ/batchgenerators (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.909007+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 2026-08-30T06:28:20.625125+00:00, confidence not recorded.
  - readme: https://github.com/MIC-DKFZ/batchgenerators (fetched 2026-08-28T04:03:51.909007+00:00, sha 665b2a9a146a)
  - registry_pypi: https://pypi.org/pypi/batchgenerators/json (fetched 2026-08-29T12:33:41.445540+00:00, sha dd2edaeed423)
- Data as of 2026-08-30T08:39:29.467469+00:00.