# longcw/faster_rcnn_pytorch

Faster RCNN with PyTorch

Repository: https://github.com/longcw/faster_rcnn_pytorch
Canonical: https://ross.abutalabs.com/products/faster_rcnn_pytorch
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, detection, faster-rcnn, computer-vision
Last push: 2021-09-25T16:46:09+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": 3502, "days_push": 1803, "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 1776, forks 460 (observed 2026-08-28T04:05:34.558423+00:00)

## What it is
A PyTorch re-implementation of Faster R-CNN for object detection, based on the original py-faster-rcnn and TFFRCNN projects. It supports training and evaluation on Pascal VOC 2007 with a VGG16 backbone, including Cython-based RoI pooling and NMS modules.

## Use cases
- train faster rcnn on pascal voc with pytorch
- run object detection inference with a pretrained faster rcnn model
- study how faster rcnn is implemented from scratch in pytorch
- understand roi pooling and region proposal networks in code
- reproduce faster rcnn training with vgg16 backbone

## When to choose
- you want to read and learn from a from-scratch Faster R-CNN implementation
- you need a simple educational codebase for object detection internals

## When to avoid
- you need a maintained implementation compatible with modern PyTorch (0.4.0+)
- you want state-of-the-art mAP matching the original caffe results
- you need production object detection - use Detectron.pytorch or torchvision instead

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, faster-rcnn, pytorch, vgg16, pascal-voc, roi-pooling, unmaintained, gpu, linux

## Member repositories
- longcw/faster_rcnn_pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.558423+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 2026-08-30T03:25:16.667277+00:00, confidence not recorded.
  - readme: https://github.com/longcw/faster_rcnn_pytorch (fetched 2026-08-28T04:05:34.558423+00:00, sha 9a8bb52d96e9)
- Data as of 2026-08-30T08:39:29.467469+00:00.