# zhaoweicai/cascade-rcnn

Caffe implementation of multiple popular object detection frameworks

Repository: https://github.com/zhaoweicai/cascade-rcnn
Canonical: https://ross.abutalabs.com/products/cascade-rcnn
Language: C++
License Family: other
Topics: object-detection
Last push: 2019-09-10T01:56:40+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": 3194, "days_push": 2550, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1061, forks 289 (observed 2026-08-28T04:03:25.973466+00:00)

## What it is
A C++/Caffe implementation of Cascade R-CNN and other popular two-stage object detection frameworks such as Faster R-CNN, R-FCN, and FPN. It supports training and benchmarking on MS-COCO and PASCAL VOC with multiple backbone networks.

## Use cases
- train a Cascade R-CNN object detector on MS-COCO
- reproduce CVPR 2018 Cascade R-CNN paper results
- benchmark Faster R-CNN, R-FCN, and FPN detectors on PASCAL VOC
- implement high-quality object detection that rejects close false positives
- train object detection models with ResNet or VGG backbones in Caffe

## When to choose
- you need the original author's Caffe implementation of Cascade R-CNN
- your pipeline is built on Caffe and C++
- you want to reproduce the paper's MS-COCO benchmark numbers

## When to avoid
- you prefer a modern PyTorch or TensorFlow implementation (use mmdetection, Detectron, or tensorpack)
- you need Mask R-CNN or instance segmentation support
- you need an actively maintained project with a license

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, deep-learning, machine-learning, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: cpp
- tags: object-detection, cascade-rcnn, faster-rcnn, caffe, coco, pascal-voc, research-code, linux, gpu, docker

## Member repositories
- zhaoweicai/cascade-rcnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:25.973466+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 2026-08-30T06:56:53.286256+00:00, confidence not recorded.
  - readme: https://github.com/zhaoweicai/cascade-rcnn (fetched 2026-08-28T04:03:25.973466+00:00, sha a2fe628ea873)
- Data as of 2026-08-30T08:39:29.467469+00:00.