# princeton-vl/CornerNet

Repository: https://github.com/princeton-vl/CornerNet
Canonical: https://ross.abutalabs.com/products/cornernet
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2020-09-18T18:59:28+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2953, "days_push": 2175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2369, forks 464 (observed 2026-08-28T04:06:41.701663+00:00)

## What it is
Official research code for CornerNet, an object detection model that detects objects as paired keypoints, reproducing results from the ECCV 2018 paper. It includes training and evaluation scripts, model definitions, and setup for the MS COCO dataset.

## Use cases
- reproduce CornerNet object detection results on MS COCO
- train a keypoint-based object detector on custom data
- study anchor-free object detection implementations
- benchmark object detection models against CornerNet
- learn how corner pooling layers are implemented

## When to choose
- you need the reference implementation of the CornerNet paper
- you want to experiment with keypoint-based anchor-free detection
- you need a trained CornerNet model for COCO evaluation

## When to avoid
- you need efficient real-time detection - use CornerNet-Lite instead
- you want a production-ready or actively maintained detection framework
- you lack a CUDA-capable GPU

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, keypoint-detection, coco, pytorch, research-code, paper-reproduction, linux, gpu

## Member repositories
- princeton-vl/CornerNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:41.701663+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 2026-08-30T02:35:26.090735+00:00, confidence not recorded.
  - readme: https://github.com/princeton-vl/CornerNet (fetched 2026-08-28T04:06:41.701663+00:00, sha dac4b949a9ee)
- Data as of 2026-08-30T08:39:29.467469+00:00.