Variational-Autoencoder-PyTorch icon indicating copy to clipboard operation
Variational-Autoencoder-PyTorch copied to clipboard

Variational Autoencoder implemented with PyTorch, Trained over CelebA Dataset

Results 4 Variational-Autoencoder-PyTorch issues
Sort by recently updated
recently updated
newest added

Hi, I tried running your code but even after 40 to 50 epochs my reconstructions are like below. Can you help? ![Epoch_29_recon](https://user-images.githubusercontent.com/21245519/108228902-4751f880-710d-11eb-941c-fb56bafca7e0.jpg)

ValueError: invalid literal for int() with base 10: 'Epoch'. Shows this error when we run the script.

Why you reshape input before passing to encoder? ``` def forward(self, x): mu, logvar = self.encode(x.view(-1, self.nc, self.ndf, self.ngf)) ``` line 149 self.ndf, self.ngf - are numbers of filters(channels). Am...

https://github.com/bhpfelix/Variational-Autoencoder-PyTorch/blob/135ad8cfff8f5d01a5bfd44fbfc53066150fa8e5/src/vanila_vae.py#L125 Is there a particular reason why the method ".exp_()" has been preferred to ".exp()" ?