search

yitu-opensource / T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Other
1.15k stars 176 forks source link

Transformer block #58

Open Summer-sss opened 3 years ago

Summer-sss commented 3 years ago

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.

yuanli2333 commented 3 years ago

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