# jwyang/faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

Repository: https://github.com/jwyang/faster-rcnn.pytorch
Canonical: https://ross.abutalabs.com/products/faster-rcnnpytorch
Language: Python
License: MIT
License Family: permissive
Topics: faster-rcnn, pytorch
Last push: 2022-05-20T09:01:28+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": 3317, "days_push": 1566, "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 7858, forks 2294 (observed 2026-08-28T04:10:07.721151+00:00)

## What it is
A pure PyTorch implementation of Faster R-CNN for object detection, supporting multi-image batch training and multi-GPU training with several ROI pooling methods. It was the first open-source object detection repo with multi-GPU support but is now explicitly unmaintained.

## Use cases
- train a faster r-cnn object detection model in pytorch
- run object detection on custom images with a pretrained model
- train faster r-cnn on pascal voc or coco with multiple gpus
- compare roi pooling, roi align, and roi crop implementations
- learn how faster r-cnn works by reading a pure pytorch codebase

## When to choose
- you need a simple, readable pure-PyTorch Faster R-CNN reference implementation
- you want a lightweight playground for experimenting with R-CNN internals
- you are reproducing older research that builds on this codebase

## When to avoid
- you need an actively maintained or up-to-date detection framework
- you want modern architectures like Mask R-CNN, DETR, or YOLO
- you are starting a new production object detection project

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, faster-rcnn, pytorch, rpn, roi-pooling, multi-gpu-training, gpu, linux

## Member repositories
- jwyang/faster-rcnn.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:07.721151+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 2026-08-29T17:33:47.204373+00:00, confidence not recorded.
  - readme: https://github.com/jwyang/faster-rcnn.pytorch (fetched 2026-08-28T04:10:07.721151+00:00, sha 34e607a8b54f)
- Data as of 2026-08-30T08:39:29.467469+00:00.