ESRGAN icon indicating copy to clipboard operation
ESRGAN copied to clipboard

Published 20 hours ago • verified publisher icon xinntao

issue with esrgan implementation

Open vibss2397 opened this issue 5 years ago • 3 comments

hi, i was making my own implementation of esrgan, except i made 2 changes, the number of rrdb blocks is 8 and i haven't included L1 loss in the perceptual loss function. The data is cell microscopy data and after 100 epochs i have been still getting output like the ones attatched in images( the generated is the 3rd image, ground truth is 4th, 1st and 2nd are bicubic and nearest neighbor). does my network need more epochs to train or is there something wrong.

P.S. i am asking this because these color losses in a normal srgan start to disappear after 10-20 epochs only.

generated_image_105 generated_image_90

vibss2397 avatar Jul 13 '19 17:07 vibss2397

Hey, I am facing something similar too, did you find a solution to your problem?

HarshPathakhp avatar Oct 03 '19 02:10 HarshPathakhp

hey @HarshPathakhp, I'm sorry it didn't work i had to switch my strategy

vibss2397 avatar Oct 16 '19 23:10 vibss2397

L1 loss should not deprecated in loss function

XiaotianM avatar Oct 18 '19 09:10 XiaotianM