# tianzhi0549/FCOS

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Repository: https://github.com/tianzhi0549/FCOS
Canonical: https://ross.abutalabs.com/products/fcos
Homepage: https://arxiv.org/abs/1904.01355
Language: Python
License: NOASSERTION
License Family: other
Topics: fcos, object-detection, one-stage, anchor-free, pytorch, computer-vision, iccv2019
Last push: 2023-12-09T17:32:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2702, "days_push": 998, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3345, forks 621 (observed 2026-08-28T04:07:57.587545+00:00)

## What it is
Official PyTorch implementation of FCOS, a fully convolutional one-stage, anchor-free object detector published at ICCV 2019. It provides training and inference code with pretrained COCO models, ONNX export scripts, and real-time variants.

## Use cases
- train an anchor-free object detection model on COCO
- run object detection inference on images with a pretrained FCOS model
- compare anchor-free vs anchor-based detector performance
- export an object detection model to ONNX
- build a real-time object detector with high FPS
- reproduce ICCV 2019 object detection paper results

## When to choose
- you need a simple, anchor-free one-stage detector with strong COCO accuracy
- you want a PyTorch research codebase for object detection experiments
- you need fast training and inference compared to Faster R-CNN

## When to avoid
- you need a production-supported detector with active maintenance or a permissive license
- you want the latest detection architectures or a maintained framework - prefer Detectron2/AdelaiDet or mmdetection which include FCOS
- you need multi-task vision models beyond detection

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, deep-learning
- platform: python
- tags: object-detection, anchor-free, one-stage-detector, pytorch, coco, research-code, iccv2019, gpu, linux

## Member repositories
- tianzhi0549/FCOS (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:57.587545+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 2026-08-29T18:41:01.483862+00:00, confidence not recorded.
  - readme: https://github.com/tianzhi0549/FCOS (fetched 2026-08-28T04:07:57.587545+00:00, sha f9f49c0cc42b)
  - homepage: https://arxiv.org/abs/1904.01355 (fetched 2026-08-29T09:34:24.594928+00:00, sha 1a6876988d97)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:34:24.604969+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:34:24.609021+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:34:24.611009+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:34:24.607181+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.