Re:Generative Adversarial Networks for Extreme Learned Image...
by make3 on Wednesday April 11, 2018 @11:57PM
(#16817856)
it also means that you could get a meaningful average of two images by averaging their compressed form (aka latent state z), and decoding, just like with the celebrities :)
[ Parent
| on HN ]
There are no comments on this comment yet.