BotKevin

I know this is closed, but when I try to send the model to cuda using ```model.cuda()```, pytorch will throw me ```RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should...

Pretty sure he multiplies the KLD by .1 because that is his KLD weight hyperparameter

Also, while working on a VAE that I wrote based on this, if I change the offending mean to a sum, my recon loss is much higher (2x), while my...

Mean is equivalent to sum, it's just a scalar difference. Normally, using adam, if we don't have a composite loss, this scale doesn't matter, so if I change the sum...

To further explain the we are using logvar is to avoid this problem of negative variance. The output of a NN can be negative, so we use the log of...

I hope the maintainers will add this method or at least make mock.argumentMatcher an exported type. `func MatchedBy(fn interface{}) argumentMatcher` returns an unexported type, which I am pretty sure is...

Yes but it gets really verbose when you have multiple mocks. It would be nice to not have to repeat the code, and it would improve readability.

@manan-sc No. I mean repeating ``` funcMock.On("GetFoo", mock.MatchedBy(func(someIDs []string) bool { return ElementsMatch(someIDs, userIDs) })).Return(fooData, err) ``` instead of a more simple ``` funcMock.On("GetFoo", MockAnyOrder(userIDs)).Return(fooData, err) ``` @brackendawson's idea seems...