We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
@csjcai @TZYSJTU Hi, I encounter the same problem. How to reproduce the Bicubic results reported in the paper?
I use the modified test code to evaluate the Version 1 dataset.
clear; clc; close all; warning off; addpath(genpath('./.')); count = 1; folder2 = ['./Test/2']; filepathsHR = []; filepathsHR = cat(1,filepathsHR, dir(fullfile(folder2, 'HR', '*.png'))); filepathsLR = []; filepathsLR = cat(1,filepathsLR, dir(fullfile(folder2, 'LR', '*.png'))); for i = 1 : 1: length(filepathsHR) disp(filepathsHR(i).name) disp(filepathsLR(i).name) HR = imread(fullfile(folder2,'HR',filepathsHR(i).name)); HR_Ycbcr = im2double(rgb2ycbcr(HR)); HR_Y = im2single(HR_Ycbcr(:, :, 1)); LR = imread(fullfile(folder2,'LR',filepathsLR(i).name)); LR_Ycbcr = im2double(rgb2ycbcr(LR)); LR_Y = im2single(LR_Ycbcr(:, :, 1)); [PSNRCur, SSIMCur] = Cal_PSNRSSIM(im2uint8(HR_Y),im2uint8(LR_Y), 0, 0); PSNRs(count) = PSNRCur; SSIMs(count) = SSIMCur; count = count + 1; end length(PSNRs) mean(PSNRs) mean(SSIMs)
I have reorganized Test folder as follow:
Test
./Test/2/HR/Canon_XXX_HR.png ./Test/2/LR/Canon_XXX_LR2.png ./Test/3/HR/Canon_XXX_HR.png ./Test/3/LR/Canon_XXX_LR3.png ./Test/4/HR/Canon_XXX_HR.png ./Test/4/LR/Canon_XXX_LR4.png
Thanks in advance!
Originally posted by @HolmesShuan in #23 (comment)
The text was updated successfully, but these errors were encountered:
No branches or pull requests
@csjcai @TZYSJTU Hi, I encounter the same problem. How to reproduce the Bicubic results reported in the paper?
I use the modified test code to evaluate the Version 1 dataset.
I have reorganized
Test
folder as follow:Thanks in advance!
Originally posted by @HolmesShuan in #23 (comment)
The text was updated successfully, but these errors were encountered: