mjq11302010044 / TATT

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

images_sr = model(images_hr)

chnoguchi opened this issue · comments

At line 1734 in interfaces/super_resolution.py,

images_sr = model(images_hr)

It seems that HR images are input into the model. Is this correct specification?

@chnoguchi Hi, thanks for pointing out that problem, this piece of code is not actually used on our evaluation. Please check eval() function in super_resolution.py. You can directly remove this piece and the project will still perform normally.