Zach Mueller    @TheZachMueller
TIL einops can be faster than raw PyTorch 🤯 On stream we're reimplementing @fastdotai's AdaptiveConcatPool2d, which just calls Average and Max pooling, and concatentates. We found that doing the same with einops can be a *little* faster!
 Reply      Retweet   25      Like    116   







 







Zach Mueller

Rohan Anil 🏠🤯

OpenAI

Ned Ryun

Aran Komatsuzaki

Dr. Roman Yampolskiy