1. MLP-Mixer is a variation on a depthwise separable convnet 2. FNet is similar to Transformer encoder but replaces attention with a Fourier transform 3. gMLP uses a spatial gating unit
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Is there any way to reach you about an example I'd like to add to Keras, if relevant? (Proteins & attention/pretraining + mixed local/global tasks example).https://www.biorxiv.org/content/10.1101/2021.05.24.445464v1 …
-
You can open a PR. The only requirement is that the example should fit in less than 300 lines.
- 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.