ValueError while calling RetinaFace.detect_faces('img3.jpg') or RetinaFace.build_model()
AjinkyaG opened this issue · 2 comments
AjinkyaG commented
Getting this same error : ValueError: The channel dimension of the inputs should be defined. The input_shape received is (None, None, None, 9), where axis -3 (0-based) is the channel dimension, which found to be None
.
TF version is 2.9.1 , Please let me know if I am missing anything.
serengil commented
Seems this was a channels order issue.
Try to change keras config to channels_last and run
serengil commented
Closed due to inactivity