This repository has been archived by the owner on Nov 2, 2022. It is now read-only.

AAE with reparameterization trick #1

Open

rdaems opened this issue Sep 12, 2019 · 0 comments

rdaems commented Sep 12, 2019

Hi, thanks for publishing your code!

I have a question about your implementation of the Adversarial AutoEncoder (AAE).
In your code I see you use the reparameterization trick (https://github.com/MaciejZamorski/3d-AAE/blob/master/models/aae.py), like you would if you would train a VAE.

Is there a specific reason to do this? Because I'd think this is not necessary?

Kind regards

Rembert

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.