Help with VDSR example code

Hi,

I'm tring to learn VDSR network through matlab example:

https://www.mathworks.com/help/images/single-image-super-resolution-using-deep-learning.html#VeryDeepSuperResolutionDeepLearningExample-9

I followed step by step the example which use the pre-trained network, but command panel shows me error: Error in test (line 46)

"Iresidual = activations(net,Iy_bicubic,21);

Undefined function 'activations' for input

arguments of type 'struct'.

Error in test (line 46)

Iresidual = activations(net,Iy_bicubic,41);"

can someone help me tell me how to fix the problem? my code is:

clear all;

%% download pretrained VDSR network:

net = load('trainedVDSR-Epoch-100-ScaleFactors-234.mat');

%% create sample low-resolution image:

exts = {'.jpg','.png'};

% fileNames contain 21 images:

fileNames = {'sherlock.jpg','car2.jpg','fabric.png','greens.jpg','hands1.jpg','kobi.png', ...

'lighthouse.png','micromarket.jpg','office_4.jpg','onion.png','pears.png','yellowlily.jpg', ...

'indiancorn.jpg','flamingos.jpg','sevilla.jpg','llama.jpg','parkavenue.jpg', ...

'peacock.jpg','car1.jpg','strawberries.jpg','wagon.jpg'};

%using image processing toolbox:

filePath = [fullfile(matlabroot,'toolbox','images','imdata') filesep];

filePathNames = strcat(filePath,fileNames);

testImages = imageDatastore(filePathNames,'FileExtensions',exts);

% display the testing images as a montage:

montage(testImages);

%% selecting one image to use as the reference image for SR:

% Index of image to read from the test image datastore

close all;

indx = 1;

Ireference = readimage(testImages,indx);

Ireference = im2double(Ireference);

imshow(Ireference);

title('High-Resolution Reference Image');

%% creating low-resolution image by using imresize

close all;

scaleFactor = 0.25;

Ilowres = imresize(Ireference,scaleFactor,'bicubic');

imshow(Ilowres);

title('Low-Resolution Image');

%% improving image resolution using pre-trained VDSR network:

close all;

[nrows,ncols,np] = size(Ireference);

Ibicubic = imresize(Ilowres,[nrows ncols],'bicubic');

% converting low resolution image from rgb2yuv

Iycbcr = rgb2ycbcr(Ilowres);

Iy = Iycbcr(:,:,1);

Icb = Iycbcr(:,:,2);

Icr = Iycbcr(:,:,3);

% up-scaling YUV image by bicubic interpulation:

Iy_bicubic = imresize(Iy,[nrows ncols],'bicubic');

Icb_bicubic = imresize(Icb,[nrows ncols],'bicubic');

Icr_bicubic = imresize(Icr,[nrows ncols],'bicubic');

%% passing the up-scalied images through trained VDSR network:

Iresidual = activations(net,Iy_bicubic,41);

Iresidual = double(Iresidual);

imshow(Iresidual,[]);

title('Residual Image from VDSR');

[adarsh a]

did u find the solution

Answer 1

[Subhadeep Koley]

The function activations was introduced inside Neural Network Toolbox in MATLAB R2016a. You can type the command ver to check whether the Neural Network Toolbox is installed or not.

ver;

Also make sure you are using MATLAB version R2016a or later.

Hope this helps!