Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
IemProg opened this issue 3 years ago · comments
Thanks for sharing the ViT implementation, wonderful work.
I'm wondering why you are not using the Softmax() function after head component -from features to classes-, as you did in the Jupyter notebook example?
Thanks