how to generate deep dream data from own Images ?

how to generate deep dream data from own Images ?

Answer 1

[Image Analyst]

Find an article on it and code it up, because there is no built in function for that.

[Selva Karna]

any other way to generate deep dream image in our own image?

Answer 2

[Delprat Sebastien]

    clear all;
    close all;
    clc;

    % ===============================
    % You will need to download the net using the Matlab app finder tool
    % ===============================
    No=1;
    switch No
        case 1
            net=alexnet;
            netname='AlexNet';
            layer = 23; % Ouput layer before classification
        case 2
            net=vgg16;
            netname='VGG16';
            layer = 39; % Ouput layer before classification
    end
    InputSize=net.Layers(1).InputSize;

    fprintf('==============================\n');
    fprintf('Network layers\n');
    net.Layers

    fprintf('==============================\n');
    fprintf('Network classes\n');
    for i=1:length(net.Layers(end).ClassNames)
        fprintf('%i - %s\n',i,net.Layers(end).ClassNames{i});
    end

    % ==============================================
    % Your image to be used as a starting dream
    % ==============================================
    FileName='Poisson';
    initImg=imread([FileName '.jpg']);
    initImg=imresize(initImg,InputSize(1:2));

    [label,scores] = classify(net,initImg);

    % Display network output, just for info (display the 5 more probable
    % classes)
    [~,idx] = sort(scores,'descend');

    idx = idx(5:-1:1);
    classNames = net.Layers(end).ClassNames;
    classNamesTop = classNames(idx);
    scoreTop = scores(idx);
    fprintf('Most probable classes:\n');
    for i=1:length(idx)
        fprintf('%i - %s - %f\n',i,classNamesTop{i},scoreTop(i));
    end
    % Display initial image
    figure;
    imshow(initImg)

    channels = [208];  % Golden retriever
    channels = 53; % Thunder snake
    channels = 481; % Cash machine
    channels = 158; % Papillon
    channels = 162; % Basset
    channels = 328; % Starfish
    channels = 818; % sports car

    fprintf('Targeted class: %s\n',net.Layers(end).ClassNames{channels});
    levels = 1;       % 1 or 2 is good
    iterations = 20;  % higher better, but also longer
    I = deepDreamImage(net,layer,channels, ...
        'Verbose',true, ...
        'NumIterations',iterations, ...
        'PyramidLevels',levels,...
        'InitialImage',initImg);%    'PyramidScale',1.2,...

    % Save result and built file name using algorithm config
    Classname=net.Layers(end).ClassNames{channels};
    name=sprintf('dreem_%s_%s_chl_%i_iter_%i_lvl_%i_%s',netname,FileName,channels,iterations,levels,Classname);
    imwrite(I,[name '.jpg']);

    % Display result
    figure
    imshow(I)

Original image:

Dreamed image (fish interpreted as a snake)

[Selva Karna]

Thanks to Delprat Sebastien, Star Strider

 Thanks for spending your Time. and ideas. i will replay you.

[Selva Karna]

i did not get result above like this,

My result is , how can i get Good visible result from like above result.. we will change any layer or iteration ????

Answer 3

[Selva Karna]

Why i get the error like this ? how to use directly use image without image resize ?

For an image input layer, the input data for predict must be a single image, a 4D array of images, or an imageDatastore with the correct size.

[Image Analyst]

See attached zoom demo.

[Selva Karna]

if i use this , i got pixel error, so i want change in the in the part of Image input layer like: 227 X 227 X 3 , how can i change ??

[Image Analyst]

I totally don't understand the question. You want to change what?

[Selva Karna]

Image Analyst, actually , i have my image size 512X512X3, in alexnet only able to use 227 X 227 X3 size only, so how to modiyfy Alexnet image input layer size in my own size?

[Selva Karna]

[Image Analyst]

Alexnet is built assuming that size. If you want different size you'd have to use a different network. However, you will probably find it does just fine with resizing your images to that. It will most likely still work with your images.

Answer 4

[Delprat Sebastien]

Please look at the following code https://fr.mathworks.com/matlabcentral/fileexchange/66710-deep-dreaming-animation-for-matlab

There is : 1) a required modification to add clipping to the original matlab code 2) a script that generate an animation from image (with resizing) using recursive deepdream

NB : please read carefully the patch.m file... Enjoy

Answer 5

[Selva Karna]

Delprat Sebastien, it's not working. I got this error below:

Error in deepDreamImage2 (line 186)
X = nnet.internal.cnn.visualize.deepDreamImageLaplacianNorm2(...

Error in check_April2 (line 38)
    Idream = deepDreamImage2(net,layer,channels, ...

[Delprat Sebastien]

If you do not copy the error in detail, I cannot help. Did you copy the deepDreamImageLaplacianNorm as deepDreamImageLaplacianNorm2 in the specified matlab toolbox folder?

[Selva Karna]

yes i copied deepDreamImageLaplacianNorm as deepDreamImageLaplacianNorm2 in the specified matlab toolbox folder , but i got this error .

Answer 6

[Selva Karna]

Error: Frame n°i : 1 / 20 Error using nnet.internal.cnn.visualize.resizeImage (line 11) output size must be [height width]

Error in deepDreamImage2 (line 183) avgI = nnet.internal.cnn.visualize.resizeImage(iVisualNet.Layers{1}.AverageImage, sz(1:3));

Error in check_April2 (line 38) Idream = deepDreamImage2(net,layer,channels, ...

Here i have attached modified code please kindly check the code,

Answer 7

[Delprat Sebastien]

In the deepDreamImageLaplacianNorm2.m you must not comment the gradient ascend % X = X + gradient * stepSize; X=max(XMin2,min(X,XMax2));

=> should be (mind the % removal) X = X + gradient * stepSize; X=max(XMin2,min(X,XMax2));

[Selva Karna]

Again i got this error sir, Frame n°i : 1 / 20 Error using deepDreamImage2 Too many input arguments.

Error in check_April2 (line 90) Idream = deepDreamImage2(net,layer,channels, ...

I have attached my modified files please check this file

[Selva Karna]

I Got this following Erro Frame n°i : 1 / 20 Undefined variable "nnet" or class "nnet.internal.cnn.visualize.deepDreamImageLaplacianNorm2".

Error in deepDreamImage2 (line 186) X = nnet.internal.cnn.visualize.deepDreamImageLaplacianNorm2(...

Error in check_April2 (line 90) Idream = deepDreamImage2(net,layer,channels, ...

Answer 8

[Selva Karna]

Can u send code deepDreamImage2 ,.deepDreamImageLaplacianNorm2 ?

Answer 9

[Delprat Sebastien]

Unfortunately, due to Mathworks copyright, I cannot disclose the source code of their functions. If you follow the steps detailed in the patch. M files, this should be OK.

In your previous code, you did add a comment on the original line x = x + g*stepsize. Remove this comment and it should work.

[Selva Karna]

i have did , but i have error.sir Delprat Sebastien,

[Selva Karna]

 Delprat Sebastien  i got this error following ?

Frame n°i : 1 / 20 Undefined variable "nnet" or class "nnet.internal.cnn.visualize.deepDreamImageLaplacianNorm2".

Error in deepDreamImage2 (line 186) X = nnet.internal.cnn.visualize.deepDreamImageLaplacianNorm2(...

Error in check_April2 (line 90) Idream = deepDreamImage2(net,layer,channels, ...

>> >>

Answer 10

[voxey]

check the image size