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
Keyword here being "controllable", I suppose - this is valid in other DL fields too: generative approaches (in CV, in NLP, etc) are very cool on paper / for academia, but frankly unmanageable when verticalized into industries.
1 reply 1 retweet 23 likes -
Replying to @kairosdojo
I can only imagine! To elaborate on "controllable"- We -just- now got to the point where quality is consistent across rendering with a wide range of resolutions. One of many aspects that matter for production.. That aspect is so hard in practice to engineer for.
1 reply 1 retweet 24 likes -
Replying to @citnaj @kairosdojo
Care to elaborate about the difficulties of wide resolution range? More of an engineering or fundamental problem?
3 replies 0 retweets 0 likes -
I thought that aspect was solved with progressive resizing. At least going down with resolution... going up you need a huge amount of VRAM for your U-Net, a huge amount of VRAM for your perceptual loss ResNet (-34? -50?) >
2 replies 0 retweets 0 likes
Partially solved but not completely :)
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.