lucidrains / vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Attention maps rectangular input

lucaswannen opened this issue · comments

Hi,

How to get the attention map with rectangle images? It seems that in any case, the output for the attention is a square dimension