cv2.COLOR_BGR2RGB is missing at get_identity_descriptor?

[khlee369]

At get_identity_descriptor.compute_pose_identity_error.py,

if the face detection gets failed, it manually crops and pre-processes the image.
and there is no channel conversion(BGR to RGB)

but if face detection gets succeed, arcface_model.get_input(image) convert image channels.link

i think cv2.cvtColor(image_cropped, cv2.COLOR_BGR2RGB) is needed when image_cropped is None

[shrubb]

Maybe, not sure. Anyway, if a face isn't detected (which already happens quite rarely), then the match score is going to be so large that BGR/RGB won't matter much.
Thanks for the comments.

[khlee369]

Thank you for the reply! :)