guoqiangqi/PFLD

Implementation of PFLD A Practical Facial Landmark Detector , reference to https://arxiv.org/pdf/1902.10859.pdf

38
/ 100
Emerging

Built with TensorFlow, this implementation trains on the WFLW dataset (10,000 faces with 98 manually-annotated landmarks) to detect facial keypoints across unconstrained poses and lighting conditions. The architecture includes auxiliary supervision for head pose (Euler angles) prediction, with optimizations to precompute pose ground-truth during preprocessing rather than on-CPU during training.

641 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 1 / 25
Community 25 / 25

How are scores calculated?

Stars

641

Forks

165

Language

Python

License

Last pushed

May 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/guoqiangqi/PFLD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.