Some questions regarding decoder in vanilla_vae

[ruby-stha]

Hello @AntixK !

Thanks for sharing this helpful repository.

I am a beginner in VAE implementation and hence, had a confusion related to vanilla_vae:

• In the self.final_layer, why is nn.ConvTranspose2d created with both in_channels and out_channels as hidden_dims[-1] i.e. 32 followed later by nn.Conv2d? Can we not have out_channels as 3 directly in nn.ConvTranspose2d and omit nn.Conv2d?

Could you please provide me insight on these?

Thank you, and have a nice day!

[jeetshah-at-X]

I had the same question. Came across this:

Advanced: to avoid checkerboard artifacts, an alternative upsampling method that’s gaining popularity 
is to apply classical upsampling followed by a regular convolution (that preserves the spatial dimensions).

Source: https://medium.com/apache-mxnet/transposed-convolutions-explained-with-ms-excel-52d13030c7e8