RealSR

RealSR copied to clipboard

Issue in "model/common.py"

2

In the line 213~219 of "model/common.py": gaussian_down = self.Prdown(Gaussian_lists[-1]) Gaussian_lists.append(gaussian_down) size_lists.append(gaussian_down.size()[2:]) Gaussian_lists.append(gaussian_down) Lap = Gaussian_lists[-2]-self.PrUp(Gaussian_lists[-1],size_lists[-2]) Lap = lap.mul(1./255.) Laplacian_lists.append(Lap) I think the 2nd "Gaussian_lists.append(gaussian_down)" need to be commented, and replace...

KaiGuo-Vision

training for x4 super resolution

2

Dear @Alan-xw , thank you for your code. I want to train LP-KPN model for superresolution task in which the input lr images are 4 times smaller than GT. I...

NasrinR791

how about the performance of your implementation? Can it achieve similar performance to the original paper?

jiandandan001

Model parameters

1

Hi, thanks for your codes. However, in origional paper, the model (k = 5) parameters is 5.731M, the model parameters you implemented with pytorch contains only 1545765. I check the...

ZhangDY827

SRFlow

1

Hey, I implement the SRFlow based on the paper with Pytorch. I saw your issue on the official repository. I would be very happy if you could share your code...

Ligerd

Hello, what dataset is used for training？

copy-frogger

calc_psnr()

1

Hi, the author() uses the y channel to calculate psnr. Doesn't your calc_psnr function calculate the y channel?

luyao-cv

Issue in "loss/vgg.py"

2

self.sub_mean = common.MeanShift(rgb_range, vgg_mean, vgg_std) I can't find Where the function "MeanShift" is.

xiaotrong

common.py line 214-220

2

Gaussian_lists.append(gaussian_down) size_lists.append(gaussian_down.size()[2:]) Gaussian_lists.append(gaussian_down) Lap = Gaussian_lists[-2]-self.PrUp(Gaussian_lists[-1],size_lists[-2]) Lap = lap.mul(1./255.) --->why append gaussian_down two times? and Lap = lap.mul the second lap should be Lap?

cnyunchao

Where is meanblur?

1

I have not found **MeanBlur()** in common.py

WenjiaWang0312