MedSRGAN icon indicating copy to clipboard operation
MedSRGAN copied to clipboard

Published 20 hours ago • verified publisher icon 04RR

LIPIS-based content loss is missing

Open Kaushalya opened this issue 2 years ago • 2 comments

The paper claims to use a content loss based on a pre-trained VGG-19 model. However, only an L1-loss is used in the training code. How was the performance mentioned in the paper achieved? Is it with L1 loss?

image

Kaushalya avatar May 10 '22 11:05 Kaushalya