yitu-opensource / T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Transformer block

Summer-sss opened this issue · comments

Hello, may I ask if the parameters are shared between multiple Transformer blocks? If not, how to achieve it? Thank you very much for your reply.

The paramters are not shared by multiple Transformer blocks, which is achieved by generating Transformer block with for-loop.