Daniel Stoller

Can confirm that with a completely different, self-made Tensorflow implementation that the estimated Wasserstein distances get very very large. Also don't really know what is causing it... Normally values are...

Yes I did not use GP + spectral norm at the same time, rather I used a lot of WGAN-GP, and my experience there was that the estimated Wasserstein distance...

See paper: "We add the log prior p(z) directly into the adversary T(x,z) so that it only has to learn the log density of the inference model q(z|x)". p(z) is...

Looks like an issue with `sacred`, did you make sure you have `sacred==0.7.3` installed as defined in the requirements.txt?

This is hard to debug without having a stack trace, can you print out the full error stack trace you are getting?

Please translate your issue into English to proceed :)

More specifically, why is it ``` return self.residual(x) + self.shortcut(x) ``` in https://github.com/ajbrock/BoilerPlate/blob/master/Models/fixup.py#L45 and not ``` return self.activation(self.residual(x) + self.shortcut(x)) ```

So you are saying everything works well except it generates predictions for the train dataset? I don't know why that would be the case, I set it up to use...

Hey! What do you mean with random images? Also did you use your own custom dataset? How many test samples are in this dataset? At the end of the training...

Hey, parallel GPU usage should be a simple addition by wrapping the generator and discriminator(s) in a ```DataParallel``` module, for example in ```Image2Image.py```. Do you want to make this addition...