KunpengLi1994 / VSRN

PyTorch code for ICCV'19 paper "Visual Semantic Reasoning for Image-Text Matching"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Do I need train two models for evaluation?

weiyunfei opened this issue · comments

Hi, I'm interested in your work, as well as appreciate for your code.
However, I've not understood why it needs two pretrained models for evaluation.
Should I train another model for evaluation? If so, is there any parameters that should be changed?
I'll appreciate for your reply.

Oops, sorry for this silly question. I found the solution in #5 just now and I will close this issue.