# open-mmlab/mmskeleton

A OpenMMLAB toolbox  for human pose estimation, skeleton-based action recognition, and action synthesis.

Repository: https://github.com/open-mmlab/mmskeleton
Canonical: https://ross.abutalabs.com/products/mmskeleton
Language: Python
License: Apache-2.0
License Family: permissive
Topics: action-recognition, deep-learning, graph-convolutional-network, pytorch, skeleton-based-action-recognition
Last push: 2022-11-25T20:02:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3207, "days_push": 1377, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3127, forks 1063 (observed 2026-08-28T04:07:44.535277+00:00)

## What it is
MMSkeleton is an OpenMMLAB toolbox for skeleton-based human understanding, built on PyTorch. It supports 2D pose estimation, skeleton-based action recognition with ST-GCN, and custom skeleton dataset creation.

## Use cases
- recognize human actions from skeleton sequences
- estimate 2D human poses in videos
- train ST-GCN models for skeleton-based action recognition
- build custom skeleton-based datasets
- create pose estimation demo applications

## When to choose
- you need skeleton-based action recognition with graph convolutional networks
- you want an extensible PyTorch framework for human pose and action research
- you need pretrained ST-GCN models from a model zoo

## When to avoid
- you need actively maintained code with recent updates
- you need 3D pose estimation or pose tracking, which are unimplemented
- you want a production-ready application rather than a research toolbox

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: pose-estimation, action-recognition, skeleton-based, graph-convolutional-network, pytorch, st-gcn, human-understanding, linux, gpu

## Member repositories
- open-mmlab/mmskeleton (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:44.535277+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 2026-08-30T07:26:21.697441+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/mmskeleton (fetched 2026-08-28T04:07:44.535277+00:00, sha 3569b2dc0432)
- Data as of 2026-08-30T08:39:29.467469+00:00.