You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
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/
It's been a year since we last used GANs. You may have been lead to believe that GANs are -the- way to get realistic results but believe me, there's actually better ways IMHO. I can't tell you exactly what we're doing now but I can tell you this: 2/
It was a good thing I got past my ego (after some time) and listened to @jeremyphoward and @fastdotai when they said they that they are getting "better than GAN" results using perceptual loss in super resolution :)
3/
I'm trying to straddle the line between maintaining a competitive advantage and giving back to the community that served us so much. It's tough to make the call sometimes. 4/
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.
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.
@citnaj The only thing to do now in my opinion is to just take up predicting color channels in my opinion, but that's just me
Nice trick actually! Maybe in HSV color space?
The good days of GANs are yet to come :) I'working on it Loading...
Don't get me wrong- I love them! I just don't find them practical enough yet. I'm convinced they'll be -the- way to go though eventually. It just makes sense to me- you're essentially learning the loss function itself, which is great.
Very cool update this one. I can just try to guess but I'm betting on bigger ResNets (both for the backbone of the U-Net and in the perceptual loss) and a lot of self attention (maybe SE-ResNet?).
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
