# ShiqiYu/OpenGait

A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.

Repository: https://github.com/ShiqiYu/OpenGait
Canonical: https://ross.abutalabs.com/products/opengait
Language: Python
License Family: other
Last push: 2026-08-20T03:26:22+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 1781, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1146, forks 235 (observed 2026-08-28T04:03:45.873630+00:00)

## What it is
OpenGait is a flexible and extensible Python framework for gait recognition research, providing implementations of state-of-the-art models and benchmark datasets. It lets researchers focus on designing their own models and easily compare against the state of the art.

## Use cases
- train and benchmark gait recognition models
- compare my gait model against state-of-the-art baselines
- run person identification from walking patterns
- reproduce CVPR gait recognition paper results
- evaluate gait models on CASIA or GREW datasets
- research framework for pedestrian gait analysis

## When to choose
- you are doing gait recognition research and want ready-made baselines
- you need a reproducible benchmarking setup for gait models
- you want access to recent SOTA models like DeepGaitV2, SkeletonGait++, or BiggerGait

## When to avoid
- you need a production-ready biometric identification system rather than a research framework
- your task is general video action recognition, not gait
- you need a license-cleared solution for commercial deployment (no license is specified)

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, computer-vision, benchmarking
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: gait-recognition, person-identification, biometrics, pytorch, research-framework, model-zoo, gpu, linux

## Member repositories
- ShiqiYu/OpenGait (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:45.873630+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 2026-08-30T06:34:09.331907+00:00, confidence not recorded.
  - readme: https://github.com/ShiqiYu/OpenGait (fetched 2026-08-28T04:03:45.873630+00:00, sha a6bdd4564869)
- Data as of 2026-08-30T08:39:29.467469+00:00.