Trying to understand the training on LSUN dataset with multi-class labels

[prash030]

Hi @ptrblck ,
Thanks for this implementation!

I have a question, and I was wondering if I can get your thoughts: The paper mentions that their training is unsupervised - meaning that it was not label-conditioned. Then how come they were able to generate label-specific images for LSUN dataset? Did they train separate networks for each label or is their network a multi-class generator?

Thanks in advance!

[ptrblck]

Hi @cardyfib,

as far as I know, they used label-specific images and trained separate models for each label.
You can find some of the LSUN classes in Tero Karras' Google Drive.

Best,
ptrblck

[prash030]

Thank you!