1

I'm trying to use a VAE (CNN-VAE to be exact) to reduce the dimension of some images I have in a dataset.

I successfully trained my VAE, but now I'm not sure of the latent variable to return.

Should I use $\mu$, $\sigma^2$, or $z$ (which is sampled from $\mu$ and $\sigma^2$) ? enter image description here

Thank you in advance for the advice.

Liam

Liam F-A
  • 73
  • 4

1 Answers1

1

The simplest is to use $\mu$ as the output. You could also use $z$ as the output, but that will make your dimension reduction randomized, which in some settings might be undesirable (and others might be desirable).

D.W.
  • 167,959
  • 22
  • 232
  • 500