conv_transpose2d parameter order problem

[pierreosselin]

bayesian-torch/bayesian_torch/layers/variational_layers/conv_variational.py

Lines 784 to 786 in f6f516e

 out = F.conv_transpose2d(input, weight, bias, self.stride, 
                          self.padding, self.output_padding, 
                          self.dilation, self.groups) 

When I try to convert a deterministic autoencoder into a bayesian one with a ConvTranspose2d layer I get the error "Exception has occurred: TypeError
conv_transpose2d(): argument 'groups' (position 7) must be int, not tuple" which I suspect comes from self.dilation and self.group which are swaped.

[Ranganath Krishnan]

@pierreosselin can you check how you are getting model output in your code? If return_kl flag is True (by default), the forward function returns a tuple (output and kl) -

bayesian-torch/bayesian_torch/layers/variational_layers/conv_variational.py

Line 793 in f6f516e

 return out, kl 

[Ranganath Krishnan]

closing the issue due to no response from the user.

[SoyedTuhinAhmed]

I am having the same issue and return_kl flag is False

[Rameesha]

I am having the same Issue, pls suggest what can be wrong