# princeton-vl/CornerNet-Lite

Repository: https://github.com/princeton-vl/CornerNet-Lite
Canonical: https://ross.abutalabs.com/products/cornernet-lite
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2019-04-19T04:41:03+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": 2695, "days_push": 2693, "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 1771, forks 413 (observed 2026-08-28T04:05:34.140569+00:00)

## What it is
CornerNet-Lite is the official PyTorch implementation of the paper 'CornerNet-Lite: Efficient Keypoint Based Object Detection', providing training, evaluation, and testing code for keypoint-based object detectors. It includes three pretrained detectors (CornerNet-Saccade, CornerNet-Squeeze, and CornerNet) that can be applied to images via a simple Python API.

## Use cases
- run object detection on images with pretrained models
- reproduce results from the CornerNet-Lite paper
- train a keypoint-based object detector
- evaluate object detection accuracy on benchmarks
- use a fast lightweight detector for real-time inference
- detect objects in photos and draw bounding boxes

## When to choose
- you need efficient keypoint-based object detection with pretrained models
- you want to reproduce or build on the CornerNet-Lite research
- you need a lightweight detector like CornerNet-Squeeze for faster inference

## When to avoid
- you need a maintained production-ready detection framework with broad model support
- you require Windows or non-CUDA environments
- you want the latest detection architectures or active community support

## 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, pytorch, cornernet, research-code, efficient-inference, linux, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.140569+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 2026-08-30T03:26:01.386290+00:00, confidence not recorded.
  - readme: https://github.com/princeton-vl/CornerNet-Lite (fetched 2026-08-28T04:05:34.140569+00:00, sha 85d20d6f1efc)
- Data as of 2026-08-30T08:39:29.467469+00:00.