# deepcam-cn/yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)       ECCV Workshops 2022)

Repository: https://github.com/deepcam-cn/yolov5-face
Canonical: https://ross.abutalabs.com/products/yolov5-face
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: yolov5, tensorrt, retinaface, scrfd, tinaface, yolo, pytorch, arcface, shufflenet, blazeface, yolov7
Last push: 2024-07-22T12:26:33+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": 1955, "days_push": 772, "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 2406, forks 524 (observed 2026-08-28T04:06:44.132663+00:00)

## What it is
YOLOv5-Face is a real-time, high-accuracy face detector built on the YOLOv5 object detection framework in PyTorch, with TensorRT deployment support. It provides pretrained models across multiple sizes and benchmarks against other face detectors like RetinaFace, SCRFD, and BlazeFace.

## Use cases
- detect faces in images and video in real time
- deploy a fast face detector with TensorRT
- benchmark face detection accuracy on WiderFace
- run face detection on edge devices with lightweight models
- train a custom YOLO-based face detector

## When to choose
- you need a real-time face detector with strong accuracy on hard cases
- you want YOLO-style detection with pretrained weights and TensorRT export
- you need a range of model sizes from tiny to large

## When to avoid
- you need face recognition or landmarks beyond detection
- you require a permissively licensed model (GPL-3.0)
- you need a maintained project with active development

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, image-processing
- platform: python, cross-platform
- tags: face-detection, yolov5, pytorch, tensorrt, object-detection, real-time, gpu

## Member repositories
- deepcam-cn/yolov5-face (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:44.132663+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 2026-08-30T02:34:06.778277+00:00, confidence not recorded.
  - readme: https://github.com/deepcam-cn/yolov5-face (fetched 2026-08-28T04:06:44.132663+00:00, sha cceb8fabca2f)
  - registry_pypi: https://pypi.org/pypi/yolov5-face/json (fetched 2026-08-29T10:14:20.359798+00:00, sha 6e28c2dc93a3)
- Data as of 2026-08-30T08:39:29.467469+00:00.