# rbgirshick/fast-rcnn

Fast R-CNN

Repository: https://github.com/rbgirshick/fast-rcnn
Canonical: https://ross.abutalabs.com/products/fast-rcnn
Language: Python
License: NOASSERTION
License Family: other
Last push: 2018-01-23T05:59:26+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": 4172, "days_push": 3144, "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 3460, forks 1562 (observed 2026-08-28T04:08:05.610469+00:00)

## What it is
Fast R-CNN is Ross Girshick's ICCV 2015 framework for fast object detection with deep convolutional networks, written in Python and C++/Caffe. It is explicitly deprecated and unmaintained, kept only as a historical artifact with pointers to Detectron and py-faster-rcnn.

## Use cases
- train object detection models on PASCAL VOC
- reproduce Fast R-CNN paper results
- run object detection demo with VGG16
- study historical region-based CNN detection code
- compare Fast R-CNN against R-CNN and SPPnet baselines

## When to choose
- you need to reproduce or verify the original ICCV 2015 Fast R-CNN paper
- you are studying the evolution of region-based object detectors
- you need the exact historical codebase for research citation or comparison

## When to avoid
- you want a maintained object detection framework
- you need modern detectors like Faster R-CNN or Mask R-CNN
- you are starting a new object detection project
- you cannot build legacy Caffe with Python layers

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, computer-vision, machine-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, rcnn, caffe, iccv-2015, deprecated, historical, linux, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.610469+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 2026-08-29T18:36:56.372679+00:00, confidence not recorded.
  - readme: https://github.com/rbgirshick/fast-rcnn (fetched 2026-08-28T04:08:05.610469+00:00, sha 309856996d02)
- Data as of 2026-08-30T08:39:29.467469+00:00.