facebookresearch/maskrcnn-benchmark

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

9360 stars · 2454 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity abandoned

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python object-detection instance-segmentation mask-r-cnn faster-r-cnn pytorch deprecated computer-vision-models gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/maskrcnn-benchmark")