# DeepLabCut/DeepLabCut

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

Repository: https://github.com/DeepLabCut/DeepLabCut
Canonical: https://ross.abutalabs.com/products/deeplabcut
Homepage: http://deeplabcut.org
Language: Python
License: LGPL-3.0
License Family: copyleft
Topics: behavior-analysis, deep-learning, pose-estimation, feature-detectors, toolbox, deeplabcut, animal-pose-estimation, labeling-tool, keypoint-tracking, keypoint-detection
Last push: 2026-08-26T12:46:37+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 71, longevity 100
- inputs: {"age_days": 3082, "days_push": 7, "days_rel": 36, "gap_med": 99.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5745, forks 1788 (observed 2026-08-28T04:09:28.466659+00:00)

## What it is
DeepLabCut is an open-source Python toolbox for markerless 2D and 3D pose estimation of user-defined body parts using deep neural networks and transfer learning. It works across species including humans and animals, requiring only 50-200 labeled frames for training, and includes a GUI, model zoo, and multi-animal tracking support.

## Use cases
- track animal body parts in videos without physical markers
- estimate 3D pose from multi-camera video
- label and annotate video frames for pose training
- analyze animal behavior in neuroscience experiments
- track multiple animals simultaneously in a video
- detect human pose keypoints from video

## When to choose
- you need markerless pose tracking for animals or humans with minimal training data
- you want a well-established, research-validated tool with a model zoo and GUI
- you need multi-animal or 3D pose estimation from video

## When to avoid
- you need real-time pose estimation on low-power edge devices
- you only need simple object detection or tracking rather than fine-grained keypoints
- you cannot use GPU acceleration for training or inference

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, computer-vision, image-processing, video-processing, ui-components
- domain: computer-vision, machine-learning, deep-learning, bioinformatics, healthcare, robotics, data-science
- platform: python, cross-platform, windows
- tags: pose-estimation, keypoint-detection, animal-behavior, markerless-tracking, neuroscience, labeling-tool, transfer-learning, multi-animal-tracking, 3d-pose, gpu, linux, macos

## Member repositories
- DeepLabCut/DeepLabCut (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.466659+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 2026-08-29T17:53:19.816570+00:00, confidence not recorded.
  - readme: https://github.com/DeepLabCut/DeepLabCut (fetched 2026-08-28T04:09:28.466659+00:00, sha 46fcff813ac4)
  - homepage: http://deeplabcut.org (fetched 2026-08-29T08:48:46.970591+00:00, sha 21191fbd7cbf)
  - registry_pypi: https://pypi.org/pypi/deeplabcut/json (fetched 2026-08-29T08:48:46.980082+00:00, sha 23f97846c0f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.