ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
mmobai opened this issue 3 years ago · comments
your work is very good, I want to know the FPS of the models, can you tell me?
Hi, testing on 3090Ti, the steptime of T2T-ViT-19 is around 159ms.