ohadlights

Same here. TF 2.4.1

Yes. I think it doesnt really matter if you dont need to quantize.

In kaffe\graph.py: def load(self): '''Load the layer definitions from the prototxt.''' self.params = get_caffe_resolver().NetParameter() with open(self.def_path, 'rb') as def_file: text_format.Merge(def_file.read(), self.params) change the 'rb' to 'r'. I think it should...