Zhenliang He
Zhenliang He
 @hardikbansal I think it's not suitable to invert the attribute label for training the encoder. It should be more a sensible way, but I can't find it in the...
@hardikbansal Sorry, I haven't find out any solution yet.
I met the similar problem. Using spyder:  Using sublime with jedi:  slim.conv2d is under decorated.
A python IDE. It seems that spyder uses jedi but I am not sure.
@GilbertTam What modification did you made?
@GilbertTam Do the images in the output folder make sense? I just rerun the code but haven't got any error.
@millionsofluo I am still confused by this problem. Is there any good results in the `output` folder.
I met the same problem.
I think it's for the non-negative loss function
@zhangqianhui Thanks for the suggestion! Should we include all below? Or which one is the most important for that wgan works with spectral norm? (1) D network, using spectral norm,...