HRNet/HRNet-Facial-Landmark-Detection

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1138 stars · 274 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning artificial-intelligence python hrnet facial-landmark-detection face-alignment pytorch pretrained-models research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="HRNet/HRNet-Facial-Landmark-Detection")