How to train CNN with an image in the input and an image in the output?
58 views (last 30 days)
Show older comments
Osama Tabbakh
on 26 Apr 2019
Commented: mary john
on 20 May 2022
I have a task to train CNN with an image as input and an image as output. I have tried to do it at the beginning with Matlab tutorial, but matlab has no image as output, but a vector.
any idea how i can do this tutorial again but with image as output?
For example you could insert input as image for number one and the output is also for number one but rotated or deformed.
Please don't send me other people's question, because i have seen all answers about it.
6 Comments
Florent Busnoult
on 25 Aug 2020
Edited: Florent Busnoult
on 25 Aug 2020
There is an example in the 5G toolbox that uses a CNN network with a picture as an input and a picture as an output.
The variable used to store the "labels" or (ouput images) is the following:
trainLabels(:,:,:,i) = est_grid;
It's a 4-D double variable.
And you can look at the different output images used to trian the network by using the command below:
>> imagesc(abs(trainLabels(:,:,:,2))); % output image number 2
>> imagesc(abs(trainLabels(:,:,:,3))); % output image number 3
>> imagesc(abs(trainLabels(:,:,:,25))); % output image number 25
and so on.
Accepted Answer
Vasilis Giannoglou
on 16 Sep 2020
I was also struggling with having an image as an output and I found the solution. Skip the fullyConnectedLayer(n) part, because it causes the network to have an output of either a vector or just a number. However, make sure not to include any Pooling layers if you want your output to be of the same size as your input, because they cause downsampling. Finally, keep in mind that the number of filters of your final conv network is the same number as the 3rd dimension of your output image. For example,
convolution2dLayer(3,1,'Padding','same') gives an output image of (M,N,1), where M,N are the rows and columns of the initial image. The next code runs to me.
layers = [
imageInputLayer([64 64 1]) % My initial image is 64x64
convolution2dLayer(3,8,'Padding','same')
batchNormalizationLayer
reluLayer
% averagePooling2dLayer(2,'Stride',1) % Don't want this
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer
% averagePooling2dLayer(2,'Stride',1) % Don't want this
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
convolution2dLayer(3,1,'Padding','same') % Because my initial image 3rd dimension is one.
batchNormalizationLayer
reluLayer
dropoutLayer(0.2)
% fullyConnectedLayer(10) % Don't want this
regressionLayer];
2 Comments
mary john
on 20 May 2022
I tried to do this and gets an error with the regression layer. It states that the ''output size does not match response size", when I use the deep network designer.
Can you please help me to solve. Thanks in advance![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1005905/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1005905/image.png)
More Answers (1)
Johanna Pingel
on 29 Apr 2019
Try this example: https://www.mathworks.com/help/deeplearning/examples/image-to-image-regression-using-deep-learning.html
Let me know if this doesn't answer your question!
3 Comments
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!