Suyuanhang

data generator error when train charnet

10

I'm trying to train the charnet using your code However, keras will throw an error ("tuple expected, but get None") if datagen.flow is fed into model.fit_generator (line 43 in train_charnet.py)...

modified by an inplace operation error at scalar_quantizer.py

2

change levels.unsqueeze_(0) to levels = levels.unsqueeze(0) solve the issue