# ruotianluo/pytorch-faster-rcnn

pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

Repository: https://github.com/ruotianluo/pytorch-faster-rcnn
Canonical: https://ross.abutalabs.com/products/pytorch-faster-rcnn
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2020-11-12T03:12:48+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3331, "days_push": 2120, "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 1811, forks 461 (observed 2026-08-28T04:05:39.613458+00:00)

## What it is
A PyTorch 1.0 implementation of the Faster R-CNN object detection framework, based on Xinlei Chen's tf-faster-rcnn, supporting VGG16, ResNet, and MobileNet backbones on Pascal VOC. The repository is no longer actively maintained and its author recommends using detectron2 or mmdetection instead.

## Use cases
- train a faster r-cnn object detector in pytorch
- run object detection demo on images with pretrained vgg16 or resnet101
- convert tensorflow faster r-cnn pretrained models to pytorch
- reproduce pascal voc 2007 detection baselines
- study faster r-cnn implementation details like region sampling
- test object detection models on cpu

## When to choose
- you need a minimal, readable faster r-cnn reference implementation for study
- you must match the exact training details of tf-faster-rcnn or the original paper's ablations
- you are working with legacy pytorch 1.0 codebases

## When to avoid
- you want a maintained, modern object detection framework - use detectron2 or mmdetection
- you need state-of-the-art detectors like transformers or mask r-cnn support
- you are starting a new production 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, vgg16, resnet, pascal-voc, deprecated, gpu, linux

## Member repositories
- ruotianluo/pytorch-faster-rcnn (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:39.613458+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 2026-08-30T03:21:16.478867+00:00, confidence not recorded.
  - readme: https://github.com/ruotianluo/pytorch-faster-rcnn (fetched 2026-08-28T04:05:39.613458+00:00, sha d64e7b73e057)
- Data as of 2026-08-30T08:39:29.467469+00:00.