How to train CNN with an image in the input and an image in the output?

Question

Osama Tabbakh 2019-4-26

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/458769-how-to-train-cnn-with-an-image-in-the-input-and-an-image-in-the-output

评论： mary john 2022-5-20

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.

https://de.mathworks.com/help/deeplearning/examples/train-a-convolutional-neural-network-for-regression.html

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 个评论
显示 4更早的评论隐藏 4更早的评论

Osama Tabbakh 2020-8-15

Hello Ritesh,

Unfortunately I haven't done it in Python yet. But I wish you all the best with it, good luck.

Florent Busnoult 2020-8-25

编辑：Florent Busnoult 2020-8-25

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.

https://www.mathworks.com/help/5g/examples/deep-learning-data-synthesis-for-5g-channel-estimation.html

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.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Vasilis Giannoglou 2020-9-16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/458769-how-to-train-cnn-with-an-image-in-the-input-and-an-image-in-the-output#answer_495784

在 MATLAB Online 中打开

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 个评论
显示无隐藏无

Osama Tabbakh 2020-9-17

it really worked out, I think this tutorial is the right one:

https://www.mathworks.com/help/5g/examples/deep-learning-data-synthesis-for-5g-channel-estimation.html

Thanks Vasilis Giannoglou Florent Busnoult.

mary john 2022-5-20

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

请先登录，再进行评论。

Answer 2

Johanna Pingel 2019-4-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/458769-how-to-train-cnn-with-an-image-in-the-input-and-an-image-in-the-output#answer_372858

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 个评论
显示 1更早的评论隐藏 1更早的评论

supriya Naik 2020-8-28

Did you get the solution sir?? Actually I am facing same problem now.

Osama Tabbakh 2020-9-17

Yes, please see the accepted answer

请先登录，再进行评论。

How to train CNN with an image in the input and an image in the output?

6 个评论
显示 4更早的评论隐藏 4更早的评论

采纳的回答

2 个评论
显示无隐藏无

更多回答（1 个）

3 个评论
显示 1更早的评论隐藏 1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

How to train CNN with an image in the input and an image in the output?

6 个评论 显示 4更早的评论隐藏 4更早的评论

采纳的回答

2 个评论 显示 无隐藏 无

更多回答（1 个）

3 个评论 显示 1更早的评论隐藏 1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

6 个评论
显示 4更早的评论隐藏 4更早的评论

2 个评论
显示无隐藏无

3 个评论
显示 1更早的评论隐藏 1更早的评论