MATLAB Answers

how to generate deep dream data from own Images ?

17 views (last 30 days)
Selva Karna
Selva Karna on 9 Sep 2017
Answered: voxey on 4 Apr 2018
how to generate deep dream data from own Images ?

  0 Comments

Sign in to comment.

Accepted Answer

Image Analyst
Image Analyst on 9 Sep 2017
Find an article on it and code it up, because there is no built in function for that.

  1 Comment

Selva Karna
Selva Karna on 11 Sep 2017
any other way to generate deep dream image in our own image?

Sign in to comment.

More Answers (9)

Delprat Sebastien
Delprat Sebastien on 4 Jan 2018
Edited: Star Strider on 4 Jan 2018
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)

  2 Comments

Selva Karna
Selva Karna on 29 Mar 2018
Thanks to Delprat Sebastien, Star Strider
Thanks for spending your Time. and ideas. i will replay you.
Selva Karna
Selva Karna on 29 Mar 2018
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 ????

Sign in to comment.


Selva Karna
Selva Karna on 29 Mar 2018
Edited: Selva Karna on 29 Mar 2018
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.

  6 Comments

Show 3 older comments
Selva Karna
Selva Karna on 30 Mar 2018
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?
Image Analyst
Image Analyst on 31 Mar 2018
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.

Sign in to comment.


Delprat Sebastien
Delprat Sebastien on 1 Apr 2018
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

  0 Comments

Sign in to comment.


Selva Karna
Selva Karna on 2 Apr 2018
Edited: Image Analyst on 2 Apr 2018
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, ...

  2 Comments

Delprat Sebastien
Delprat Sebastien on 2 Apr 2018
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
Selva Karna on 3 Apr 2018
yes i copied deepDreamImageLaplacianNorm as deepDreamImageLaplacianNorm2 in the specified matlab toolbox folder , but i got this error .

Sign in to comment.


Selva Karna
Selva Karna on 3 Apr 2018
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,

  0 Comments

Sign in to comment.


Delprat Sebastien
Delprat Sebastien on 3 Apr 2018
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));

  2 Comments

Selva Karna
Selva Karna on 3 Apr 2018
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
Selva Karna on 3 Apr 2018
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, ...

Sign in to comment.


Selva Karna
Selva Karna on 3 Apr 2018
Can u send code deepDreamImage2 ,.deepDreamImageLaplacianNorm2 ?

  0 Comments

Sign in to comment.


Delprat Sebastien
Delprat Sebastien on 3 Apr 2018
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.

  2 Comments

Selva Karna
Selva Karna on 3 Apr 2018
i have did , but i have error.sir Delprat Sebastien,
Selva Karna
Selva Karna on 3 Apr 2018
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, ...
>> >>

Sign in to comment.


voxey
voxey on 4 Apr 2018
check the image size

  0 Comments

Sign in to comment.

Sign in to answer this question.