Ismael Fernández
Ismael Fernández
@maxpumperla maybe I'm wrong, but I noticed that layers are recycled, ie, if an evaluation of hyperas has initialized the advanced layer i as SRELU, as a result of choice(),...
I adapted the code to use custom deeplabv3 converted with tfcoreml. You can see https://github.com/ismaeIfm/image-segmenter-ios
@mevinDhun I don't think so, I've tested it on an iPhone XS and it takes a couple of seconds to perform the segmentation on the test image, but I'm not...
Because the Apple coreml model is “compiled” from input to predictions and this code assumes the output of the model is an internal layer (ResizeBilinear), so in order to make...
I also find it easier to read code on the un-styled version in python