# facebookresearch/Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Repository: https://github.com/facebookresearch/Detectron
Canonical: https://ross.abutalabs.com/products/detectron
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2023-11-20T09:13:34+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": 3254, "days_push": 1017, "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 26358, forks 5378 (observed 2026-08-28T04:11:46.854321+00:00)

## What it is
Facebook AI Research's Python software system implementing state-of-the-art object detection algorithms such as Mask R-CNN, RetinaNet, and Faster R-CNN, built on the Caffe2 deep learning framework. It is now deprecated in favor of its PyTorch rewrite, detectron2.

## Use cases
- run object detection on images
- train a Mask R-CNN instance segmentation model
- reproduce research baselines like RetinaNet or Faster R-CNN
- experiment with novel object detection architectures
- get pretrained detection models from a model zoo

## When to choose
- you need to reproduce legacy FAIR research results from 2017-2018 papers
- you must work within a Caffe2-based pipeline
- you are studying the original Detectron codebase for academic purposes

## When to avoid
- you are starting a new project - use detectron2 instead
- you need maintained software with active support
- you cannot install the deprecated Caffe2 framework
- you need production-ready detection rather than a research codebase

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: object-detection, instance-segmentation, mask-r-cnn, retinanet, caffe2, deprecated, computer-vision-research, research, linux, gpu

## Member repositories
- facebookresearch/Detectron (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:46.854321+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 2026-08-29T16:55:53.139518+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/Detectron (fetched 2026-08-28T04:11:46.854321+00:00, sha 68ce76369523)
- Data as of 2026-08-30T08:39:29.467469+00:00.