PyRetri/PyRetri
Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥 observed · 2026-08-28
Health v2 · maintenance only
32/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2325
- days_rel: n/a
- days_push: 2046
- n_releases_24m: 0
Adoption not part of the score
1183 stars · 177 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
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
library · maturity maintenance
deep-learning image-processing search-engine computer-vision image-processing deep-learning python image-retrieval pytorch unsupervised-learning person-re-identification toolbox search
1 source
- readme: https://github.com/PyRetri/PyRetri · fetched 2026-08-28 · 9f520adde3ad
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| PyRetri/PyRetri | main | 32 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem