Just a reminder:
The current implementation of build_inceptionresnetv1 in dev branch seems problematic, althrough not finished yet, since the input of the FaceVerifier(extractor="facenet", classes=512) is assumed to be an image of 0~255 uint8 values, while all the input images within models.py are preprocessed to be within -1~+1.
The images should be rescaled back to 0~255 similar to the function build_hybrid_ir50s.
Just a reminder: The current implementation of build_inceptionresnetv1 in dev branch seems problematic, althrough not finished yet, since the input of the FaceVerifier(extractor="facenet", classes=512) is assumed to be an image of 0~255 uint8 values, while all the input images within models.py are preprocessed to be within -1~+1. The images should be rescaled back to 0~255 similar to the function build_hybrid_ir50s.