roytseng-tw/Detectron.pytorch

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

2808 stars · 528 forks observed · 2026-08-28

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

A PyTorch reimplementation of Facebook's Detectron object detection framework, supporting Mask R-CNN, keypoint/pose estimation, and instance segmentation models. It can train models from scratch or run inference directly using Detectron's official pretrained weight files.

Use cases

• run mask r-cnn inference with pretrained detectron weights in pytorch
• train an object detection model from scratch in pytorch
• detect objects and instance segmentation masks in images
• estimate human keypoints or pose from images
• reproduce detectron results without caffe2
• fine-tune a detection model on a custom dataset

When to choose

• you want Detectron-compatible results but prefer PyTorch over Caffe2
• you need to load official Detectron pretrained weights directly
• you want to train Mask R-CNN or keypoint R-CNN models with multi-GPU support
• you need a pure PyTorch codebase for detection research

When to avoid

• you are starting a new project - the README recommends facebookresearch/maskrcnn-benchmark instead
• you need the full Detectron feature set, since only part of the functionality is supported
• you need modern PyTorch versions, as this targets PyTorch 0.3-0.4 era APIs
• you need active maintenance, as the last release was in 2019

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning deep-learning image-processing python object-detection instance-segmentation mask-rcnn keypoint-detection detectron pytorch pretrained-weights pose-estimation panoptic-segmentation linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="roytseng-tw/Detectron.pytorch")