# HRNet/HRNet-Facial-Landmark-Detection

This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

Repository: https://github.com/HRNet/HRNet-Facial-Landmark-Detection
Canonical: https://ross.abutalabs.com/products/hrnet-facial-landmark-detection
Language: Python
License: MIT
License Family: permissive
Topics: hrnets, facial-landmarks, deep-high-resolution-net, face-alignment, facealignment
Last push: 2022-08-12T08:03:02+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": 2703, "days_push": 1482, "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 1138, forks 274 (observed 2026-08-28T04:03:44.075420+00:00)

## What it is
Official PyTorch implementation of HRNet-based facial landmark detection from the TPAMI paper 'Deep High-Resolution Representation Learning for Visual Recognition'. It provides training and evaluation code plus pretrained models for the COFW, AFLW, WFLW, and 300W datasets.

## Use cases
- detect facial landmarks in images
- align faces with a deep learning model
- train a face landmark model on WFLW or 300W
- evaluate face alignment accuracy with NME metrics
- use HRNet pretrained weights for face keypoint tasks
- reproduce TPAMI facial landmark detection results

## When to choose
- you need state-of-the-art facial landmark detection with pretrained HRNet models
- you want to reproduce or build on published face alignment research
- you work in PyTorch and need benchmark code for COFW, AFLW, WFLW, or 300W

## When to avoid
- you need a production-ready face alignment service with easy APIs
- you require recent maintenance or support for new PyTorch versions
- you need lightweight CPU-only inference without GPU setup

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence
- platform: python
- tags: hrnet, facial-landmark-detection, face-alignment, pytorch, pretrained-models, research-code, linux, gpu

## Member repositories
- HRNet/HRNet-Facial-Landmark-Detection (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.075420+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 2026-08-30T06:36:07.107813+00:00, confidence not recorded.
  - readme: https://github.com/HRNet/HRNet-Facial-Landmark-Detection (fetched 2026-08-28T04:03:44.075420+00:00, sha c5be8dbf7754)
- Data as of 2026-08-30T08:39:29.467469+00:00.