# facebookresearch/maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Repository: https://github.com/facebookresearch/maskrcnn-benchmark
Canonical: https://ross.abutalabs.com/products/maskrcnn-benchmark
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2023-02-16T04:01:32+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2870, "days_push": 1294, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9360, forks 2454 (observed 2026-08-28T04:10:30.845154+00:00)

## What it is
A fast, modular PyTorch reference implementation of instance segmentation and object detection algorithms including Mask R-CNN, Faster R-CNN, and RPN. It provides pre-trained models, multi-GPU training, and mixed-precision support, but is now deprecated in favor of detectron2.

## Use cases
- train a Mask R-CNN model for instance segmentation
- run object detection inference on images with pre-trained models
- benchmark Faster R-CNN training speed in PyTorch
- fine-tune object detection models on custom datasets
- run instance segmentation on CPU or webcam feed

## When to choose
- you need a fast, memory-efficient Mask R-CNN or Faster R-CNN implementation in PyTorch 1.0
- you want pre-trained detection models matching Detectron accuracy
- you need multi-GPU or mixed-precision training for detection models

## When to avoid
- you are starting a new project - use detectron2 instead, as this repo is deprecated
- you need PyTorch 2.x compatibility or recent maintenance
- you need detection architectures beyond RPN/Faster R-CNN/Mask R-CNN

## 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, instance-segmentation, mask-r-cnn, faster-r-cnn, pytorch, deprecated, computer-vision-models, gpu, linux, macos

## Member repositories
- facebookresearch/maskrcnn-benchmark (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:30.845154+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 2026-08-29T17:22:26.030569+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/maskrcnn-benchmark (fetched 2026-08-28T04:10:30.845154+00:00, sha f4ef8c699bb6)
- Data as of 2026-08-30T08:39:29.467469+00:00.