# rbgirshick/py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

Repository: https://github.com/rbgirshick/py-faster-rcnn
Canonical: https://ross.abutalabs.com/products/py-faster-rcnn
Language: Python
License: NOASSERTION
License Family: other
Last push: 2019-11-07T04:31:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3995, "days_push": 2491, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8289, forks 4067 (observed 2026-08-28T04:10:20.096438+00:00)

## What it is
A Python reimplementation of the Faster R-CNN object detection model built on a fork of Fast R-CNN and Caffe. The repository is officially deprecated in favor of Detectron and is no longer maintained.

## Use cases
- run object detection on images with Faster R-CNN
- train a region proposal network detector in Python
- reproduce NIPS 2015 Faster R-CNN paper experiments
- run the Faster R-CNN demo on pretrained VGG16 models
- study a classic deep learning object detection implementation

## When to choose
- you need to reproduce the original Faster R-CNN paper results in Python
- you are studying or extending legacy Caffe-based detection code
- you need approximate joint training for Faster R-CNN on old CUDA toolchains

## When to avoid
- you are starting a new object detection project - use Detectron, Detectron2, MMDetection, or torchvision instead
- you need compatibility with MATLAB-trained Faster R-CNN models
- you need modern CUDA/cuDNN support or active maintenance

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: object-detection, faster-rcnn, caffe, region-proposal-network, deprecated, research-code, linux, gpu

## Member repositories
- rbgirshick/py-faster-rcnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:20.096438+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 2026-08-29T17:28:06.065714+00:00, confidence not recorded.
  - readme: https://github.com/rbgirshick/py-faster-rcnn (fetched 2026-08-28T04:10:20.096438+00:00, sha f844b3f418f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.