An GAN that just made verbatim copies from the training set would not be able to... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

jaakkol on Oct 28, 2017 | parent | context | favorite | on: Progressive Growing of GANs for Improved Quality, ...

An GAN that just made verbatim copies from the training set would not be able to smoothly interpolate in latent space. Also, see Fig. 10 in the paper at http://research.nvidia.com/publication/2017-10_Progressive-G....

superfx on Oct 28, 2017 [–]

But they seemed to have picked closest neighbors in pixel space instead of z-space, which is not the best idea, no?

Consider applying for YC's Winter 2027 batch! Applications are open till November 2.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact