# PyRetri/PyRetri

Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥

Repository: https://github.com/PyRetri/PyRetri
Canonical: https://ross.abutalabs.com/products/pyretri
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, image-retrieval, pytorch, toolbox
Last push: 2021-01-25T05:22:48+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": 2325, "days_push": 2046, "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 1183, forks 177 (observed 2026-08-28T04:03:54.498881+00:00)

## What it is
PyRetri is a unified deep learning based unsupervised image retrieval toolbox built on PyTorch. It provides a modular pipeline of pre-processing, feature representation, and post-processing methods for researchers and engineers.

## Use cases
- build an image similarity search system with deep features
- extract global descriptors like R-MAC, GeM, or CroW from images
- run unsupervised image retrieval experiments on benchmark datasets
- apply person re-identification feature extraction and re-ranking
- search optimal retrieval configurations with hyper-parameter tuning
- implement query expansion or database augmentation for retrieval

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, image-processing, search-engine
- domain: computer-vision, image-processing, deep-learning
- platform: python
- tags: image-retrieval, pytorch, unsupervised-learning, person-re-identification, toolbox, search

## Member repositories
- PyRetri/PyRetri (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.498881+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 2026-08-30T06:24:31.087690+00:00, confidence not recorded.
  - readme: https://github.com/PyRetri/PyRetri (fetched 2026-08-28T04:03:54.498881+00:00, sha 9f520adde3ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.