# biubug6/Face-Detector-1MB-with-landmark

1M人脸检测模型(含关键点)

Repository: https://github.com/biubug6/Face-Detector-1MB-with-landmark
Canonical: https://ross.abutalabs.com/products/face-detector-1mb-with-landmark
Language: Python
License: MIT
License Family: permissive
Last push: 2022-08-08T03:41:04+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": 2510, "days_push": 1486, "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 1107, forks 275 (observed 2026-08-28T04:03:36.597034+00:00)

## What it is
A PyTorch-based ultra-lightweight face detection library (~1MB models) with 5-point facial landmark detection, offering slim, RFB, and Retinaface-mobile0.25 variants. It includes training, evaluation on WIDER FACE, ONNX export, and ncnn C++ inference for mobile/edge deployment.

## Use cases
- detect faces in images with a tiny model
- find facial landmarks like eyes and nose
- deploy face detection on mobile or embedded devices
- train a lightweight face detector on WIDER FACE
- convert face detection model to onnx or ncnn
- run real-time face detection with low compute

## When to choose
- you need a sub-1MB face detector with landmarks for edge or mobile deployment
- you want ncnn or ONNX inference from a PyTorch-trained model
- you need to train or fine-tune a lightweight detector on WIDER FACE

## When to avoid
- you need full face recognition or identity matching, not just detection
- you need heavy occlusion or extreme pose robustness beyond lightweight model accuracy
- you want a maintained production library with active updates and releases

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, artificial-intelligence
- platform: python, cpp, cross-platform
- tags: face-detection, facial-landmarks, retinaface, ncnn, onnx, pytorch, edge-deployment, mobile-inference, widerface, linux, gpu

## Member repositories
- biubug6/Face-Detector-1MB-with-landmark (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.597034+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 2026-08-30T06:44:01.416078+00:00, confidence not recorded.
  - readme: https://github.com/biubug6/Face-Detector-1MB-with-landmark (fetched 2026-08-28T04:03:36.597034+00:00, sha 89a06cadfd27)
- Data as of 2026-08-30T08:39:29.467469+00:00.