ruotianluo/pytorch-faster-rcnn

Health v2 · maintenance only

Adoption not part of the score

1811 stars · 461 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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 The repository is no longer actively maintained and its author recommends using detectron2 or mmdetection instead.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

library · maturity abandoned

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python object-detection faster-rcnn pytorch vgg16 resnet pascal-voc deprecated gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ruotianluo/pytorch-faster-rcnn")