Sampling z in VAE

by Edv Beq   Last Updated August 10, 2018 13:19 PM

How many times do we sample from q(z|x) in a Variational Autoencoder?

Let’s say that the autoencoder input (x) is a single image 28x28 pixels - and z is is one dimensional. Then, to reconstruct the output (x_hat) - I read (I could be wrong) that we can sample 10 000 times.

Why do we sample so many? And what do we do to reduce it to 28x28?



Related Questions



Explanation needed for VAE latence space cost term

Updated September 20, 2017 18:19 PM