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.
1/ I'm actually thinking of the stuff like self-attention that's in the open source version, and the best practices that are adopted straight from fastai. I keep seeing a strange lack of adoption even though the benefits seem obvious and proven.
-
-
Well, I think self attention has been used enough in computer vision in 2020. I even use it (via the self_attention=true flag) when creating an unet_learner, although I admit I'm not a super expert of attention in any of its forms.
Thanks. 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.