Two-fold Performance Enhancement by Optimizing Face Extraction Function When align_first == True

serengil / retinaface

RetinaFace: Deep Face Detection Library for Python

https://www.youtube.com/watch?v=Wm1DucuQk70&list=PLsS_1RYmYQQFdWqxQggXHynP1rqaYXv_E&index=3

MIT License

1.15k stars 150 forks source link

Two-fold Performance Enhancement by Optimizing Face Extraction Function When align_first == True #80

Closed UmutDeniz26 closed 7 months ago

UmutDeniz26 commented 7 months ago

Removing the recursive algorithm doubles our performance gains. Also, by recalculating the facial area without reliance on the detect_faces function, we avoid using it twice, resulting in further efficiency.

serengil commented 7 months ago

Linting failed - https://github.com/serengil/retinaface/actions/runs/7857063255/job/21440536002?pr=80

serengil commented 7 months ago

LGTM, thank you for your contribution