Re:Image-to-Image Translation with Conditional Adversarial Nets
by intoverflow2 on Tuesday November 22, 2016 @10:01AM
(#13014553)
Why are some people better at it than others then if it's purely noise and patterns?
[ Parent
| on HN ]
Re:Image-to-Image Translation with Conditional Adversarial Nets
by MichaelBurge on Tuesday November 22, 2016 @10:55AM
(#13014885)
They do a worse job converting the noise into patterns, relative to some common judge of how good the solution is. See any GAN in its early stages of training for an example.