# biubug6/Pytorch_Retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Repository: https://github.com/biubug6/Pytorch_Retinaface
Canonical: https://ross.abutalabs.com/products/pytorch_retinaface
Language: Python
License: MIT
License Family: permissive
Last push: 2023-06-28T07:07:53+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": 2544, "days_push": 1162, "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 2976, forks 804 (observed 2026-08-28T04:07:32.985636+00:00)

## What it is
A PyTorch implementation of the RetinaFace single-stage face detection model, supporting mobilenet0.25 and resnet50 backbones with pretrained weights. It detects faces and five facial landmarks, achieving strong WIDER FACE and FDDB benchmark results with a compact 1.7M-parameter mobile model.

## Use cases
- detect faces in images with pytorch
- find facial landmarks in photos
- run face detection on mobile or edge devices
- train a custom face detector on widerface
- convert face detection model to tensorrt for inference

## When to choose
- you need accurate face detection with landmarks in Python
- you want a tiny model for edge or mobile deployment
- you want to train or fine-tune RetinaFace yourself

## When to avoid
- you need a maintained library with regular updates and support
- you need general object detection beyond faces
- you prefer not to manage PyTorch and dataset setup yourself

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: face-detection, retinaface, pytorch, facial-landmarks, widerface, mobilenet, tensorrt, edge-deployment, gpu

## Member repositories
- biubug6/Pytorch_Retinaface (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.985636+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 2026-08-30T07:31:34.614378+00:00, confidence not recorded.
  - readme: https://github.com/biubug6/Pytorch_Retinaface (fetched 2026-08-28T04:07:32.985636+00:00, sha e3aeba7bb180)
- Data as of 2026-08-30T08:39:29.467469+00:00.