Further experimentation done by the @fastdotai community on how to combine the new optimizers that have just come out. This is why I love being a part of it. Sota results on limited epoch Imagewoof training which correlates directly with Imagenet performance. Great work!https://twitter.com/federicolois/status/1166919084052754432 …
-
-
Replying to @Even_Oldridge @fastdotai
Also note they added self-attention and mish (relu replacement) to the mix. Can’t wait to dig into this more tonight. Self-attention in particular to me seems like it really should be given a lot more...ahem...attention.
1 reply 0 retweets 7 likes -
Replying to @citnaj @fastdotai
I've got an architecture that relies on self attention that I've been wanting to try for a while. It's such an interesting method.
1 reply 0 retweets 1 like
Replying to @Even_Oldridge @fastdotai
Yeah it’s hugely powerful in my experience. The only thing you have to be careful about is numerical stability
8:18 PM - 30 Aug 2019
0 replies
0 retweets
0 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.