I really think it's fruitful to reframe GANs as finding your loss function, as discussed in the article. I've seen that talked about here and there before, but I don't think enough. I think it really is the real reason why GANs are great.
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.