# roytseng-tw/Detectron.pytorch

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Repository: https://github.com/roytseng-tw/Detectron.pytorch
Canonical: https://ross.abutalabs.com/products/detectronpytorch
Language: Python
License: MIT
License Family: permissive
Topics: mask-rcnn, pytorch, detection, pose-estimation, segmentation, detectron
Archived: true
Last push: 2019-09-05T07:44:45+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3128, "days_push": 2554, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2808, forks 528 (observed 2026-08-28T04:07:22.898262+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python
- tags: object-detection, instance-segmentation, mask-rcnn, keypoint-detection, detectron, pytorch, pretrained-weights, pose-estimation, panoptic-segmentation, linux, gpu

## Member repositories
- roytseng-tw/Detectron.pytorch (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.898262+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 2026-08-30T08:14:26.562251+00:00, confidence not recorded.
  - readme: https://github.com/roytseng-tw/Detectron.pytorch (fetched 2026-08-28T04:07:22.898262+00:00, sha 110864f2733d)
- Data as of 2026-08-30T08:39:29.467469+00:00.