I am trying to build a Variational Autoencoder from Scratch and stuck at a problem with dimensions.
Below Architecture:
Variational Autoencoder Class:
Issue:
I am not sure why decoder is expecting (64, 64, 3, 3) ?
Help me out
I am trying to build a Variational Autoencoder from Scratch and stuck at a problem with dimensions.
Below Architecture:
Variational Autoencoder Class:
Issue:
I am not sure why decoder is expecting (64, 64, 3, 3) ?
Help me out
Can you try reshaping with batch size = 1? Like
x = x.reshape((1,64,7,7))
It worked. Thank you.