longcw/faster_rcnn_pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1776 stars · 460 forks observed · 2026-08-28

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

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

library · maturity abandoned

machine-learning deep-learning computer-vision computer-vision deep-learning machine-learning python object-detection faster-rcnn pytorch vgg16 pascal-voc roi-pooling unmaintained gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="longcw/faster_rcnn_pytorch")