So... What are the key insights? I can't remember having seen low hanging fruits in the source code. But it is pretty likely I just missed them!
It's interesting to observe how the spread of ideas actually works in practice. I've seen DeOldify cited many places, yet the key insights that to me seem like low hanging fruit don't actually get traction. I suppose not having a paper might be part of it but it's still odd.
-
-
-
I think he's talking about the n optimizations he did since he released the open source version. Yep, the problem is that those optimizations are just "hints" spread across many tweets, releasing a full paper with all the list and all the experiments would be a great thing.
- Show replies
New conversation -
-
-
NoGAN was inspirational, but alas GAN’s have been disavowed.
-
I'd like to see more work done in that direction but I actually am less enthused about that part, funnily enough.
End of conversation
New conversation -
-
-
I am always amused to see papers in 2020 that have very basic training loops that take forever to converge. What is your exp with self attention?
-
1/ Well I can tell you this much: I've had several instances where I've accidentally disabled self attention, and I'm alerted to it because it makes such a visual difference. Namely- large details lose consistency (like stretches of forest or skin) and small details are missed.
- Show replies
New conversation -
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.