# Cysu/open-reid

Open source person re-identification library in python

Repository: https://github.com/Cysu/open-reid
Canonical: https://ross.abutalabs.com/products/open-reid
Homepage: https://cysu.github.io/open-reid/
Language: Python
License: MIT
License Family: permissive
Topics: person-reidentification, deep-learning, metric-learning, pytorch, python
Last push: 2019-04-23T11:49:54+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3481, "days_push": 2689, "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 1368, forks 349 (observed 2026-08-28T04:04:31.675466+00:00)

## What it is
Open-ReID is a lightweight Python library for person re-identification built on PyTorch, providing a uniform dataset interface, models, and evaluation metrics. It includes examples to reproduce near state-of-the-art results for research purposes.

## Use cases
- train person re-identification models in pytorch
- evaluate reid models on datasets like VIPeR and Market-1501
- compare metric learning losses for re-identification
- reproduce state-of-the-art person reid benchmarks
- get a uniform interface for reid datasets
- research deep metric learning for image retrieval

## When to choose
- you need a lightweight, research-oriented reid library in PyTorch
- you want reproducible benchmarks for person re-identification
- you need uniform dataset handling across multiple reid datasets

## When to avoid
- you need production-ready person re-identification with recent architectures
- you require active maintenance or support for modern PyTorch versions
- you need general object detection or tracking rather than re-identification

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, benchmarking
- domain: computer-vision, deep-learning, machine-learning
- platform: python, windows
- tags: person-reidentification, metric-learning, pytorch, computer-vision, research, linux, macos

## Member repositories
- Cysu/open-reid (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.675466+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 2026-08-30T04:41:01.517373+00:00, confidence not recorded.
  - readme: https://github.com/Cysu/open-reid (fetched 2026-08-28T04:04:31.675466+00:00, sha 1f325114fb23)
  - homepage: https://cysu.github.io/open-reid/ (fetched 2026-08-29T11:57:58.430064+00:00, sha e29925d6a8a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.