# filipradenovic/cnnimageretrieval-pytorch

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

Repository: https://github.com/filipradenovic/cnnimageretrieval-pytorch
Canonical: https://ross.abutalabs.com/products/cnnimageretrieval-pytorch
Homepage: http://cmp.felk.cvut.cz/cnnimageretrieval
Language: Python
License: MIT
License Family: permissive
Topics: image-retrieval, convolutional-neural-networks, cnn, python, pytorch
Last push: 2024-05-13T13:12:43+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": 3051, "days_push": 842, "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 1495, forks 318 (observed 2026-08-28T04:04:53.159956+00:00)

## What it is
A PyTorch toolbox for training and evaluating convolutional neural networks for image retrieval, implementing the authors' TPAMI 2018 and ECCV 2016 papers. It supports fine-tuning CNNs, learning supervised whitening for global image descriptors, and benchmarking on Oxford and Paris datasets.

## Use cases
- train a CNN for image retrieval in pytorch
- evaluate image retrieval on Oxford and Paris datasets
- fine-tune pretrained networks with no human annotation
- learn supervised whitening for global image descriptors
- extract global image descriptors for similarity search
- reproduce CNN image retrieval research papers

## When to avoid
- you need modern transformer-based retrieval models like CLIP or DINO
- you want local feature matching rather than global descriptors
- you need a production-ready retrieval service rather than research code
- you work outside PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, search-engine
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: image-retrieval, pytorch, cnn, fine-tuning, global-descriptors, whitening, oxford-paris-benchmark, research-code, gpu, linux

## Member repositories
- filipradenovic/cnnimageretrieval-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:53.159956+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 2026-08-30T04:33:16.739556+00:00, confidence not recorded.
  - readme: https://github.com/filipradenovic/cnnimageretrieval-pytorch (fetched 2026-08-28T04:04:53.159956+00:00, sha 03c540986052)
  - homepage: http://cmp.felk.cvut.cz/cnnimageretrieval (fetched 2026-08-29T11:38:39.715266+00:00, sha f60e78ba5d21)
- Data as of 2026-08-30T08:39:29.467469+00:00.