conv_transpose2d parameter order problem
pierreosselin opened this issue · comments
bayesian-torch/bayesian_torch/layers/variational_layers/conv_variational.py
Lines 784 to 786 in f6f516e
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.
@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) -
closing the issue due to no response from the user.
I am having the same issue and return_kl flag is False
I am having the same Issue, pls suggest what can be wrong