Here's something a lot of people still don't know: The latest DeOldify doesn't use GANs anymore. And I'm not being cute with terminology- NoGAN isn't used either. We needed something more production worthy and controllable and it just wasn't cutting it. 1/
-
Show this thread
-
Replying to @citnaj @math_rachel
How much did operational issues like GAN size/difficulty hosting the model play in?
2 replies 0 retweets 1 like
Replying to @DrElleOBrien @math_rachel
1/ Well I can tell you GANs are more difficult in that regard as none of the usual tricks work easily out of the box: Distributed training, FP16, etc. But that would have just been an inconvenience and if I really thought they were the way to go those wouldn't have stopped me.
12:03 PM - 16 Jun 2020
0 replies
0 retweets
3 likes
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.