search

1adrianb / face-alignment

:fire: 2D and 3D Face alignment library build using pytorch
https://www.adrianbulat.com
BSD 3-Clause "New" or "Revised" License
7.05k stars 1.34k forks source link

bounding box format to be passed #149

Closed reddytocode closed 5 years ago

reddytocode commented 5 years ago

preds = fa.get_landmarks(input_img, detected_faces)[-1] the detected_faces in wich format should be passed?

1adrianb commented 5 years ago

[ [x1, y1, x2, y2], ...] (x1,y1) and (x2,y2) represent the top-left and bottom-right corners of the bbox. If None is passed the code will run one of the included detectors SFD or dlib.

reddytocode commented 5 years ago

Thanks!

mrgloom commented 5 years ago

Also with score? https://github.com/1adrianb/face-alignment/blob/master/face_alignment/detection/sfd/detect.py#L51