Effacer les filtres
Effacer les filtres

How to match output size in cnn

4 vues (au cours des 30 derniers jours)
Hugo Brandão
Hugo Brandão le 25 Mar 2017
Commenté : Kanushka Gajjar le 24 Juin 2019
I am trying to train a cnn to take as input a grayscale image (25x25) and output also an image (25x25). I have created the training as follows: (I1 is the input and I2 is the response)
[I1, I2] = generateImage();
X(:,:,:,i) = I1;
Y(i,:,:,:) = I2;
The I set the network and try to train it:
%create network layers
layers = [...
imageInputLayer([25 25 1])
convolution2dLayer([4 3],12)
reluLayer
crossChannelNormalizationLayer(4)
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(5,16)
reluLayer
crossChannelNormalizationLayer(4)
maxPooling2dLayer(2,'Stride',2)
fullyConnectedLayer(256)
reluLayer
fullyConnectedLayer(10)
regressionLayer];
%create training option
options = trainingOptions('sgdm','InitialLearnRate',0.001, ...
'MaxEpochs',15);
%create network
net = trainNetwork(X,Y,layers,options)
The message I get is:
Error using trainNetwork (line 92)
The output size [1 1 10] of the last layer doesn't match the response size [1 25 25].
Any ideias on to fix this?
  1 commentaire
Kanushka Gajjar
Kanushka Gajjar le 24 Juin 2019
Hi,
Did you find a solution to this problem?
I am having the same problem.
Thanks,
Kanushka

Connectez-vous pour commenter.

Réponses (1)

Abel Babu
Abel Babu le 28 Mar 2017
This error is due to the ' fullyConnectedLayer'. If you see the following documentation it is clear that the output of this layer is a single dimension vector
The workaround is to unroll your input image matrix to make it single dimension vector and then training it. I have modified your code by taking random matrices as inputs and response.
layers = [...
imageInputLayer([25 25 1])
convolution2dLayer([4 3],12)
reluLayer
crossChannelNormalizationLayer(4)
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(5,16)
reluLayer
crossChannelNormalizationLayer(4)
maxPooling2dLayer(2,'Stride',2)
fullyConnectedLayer(256)
reluLayer
fullyConnectedLayer(25*25)%Change the dimensions to match the outputs.
regressionLayer;
];
%create training option
options = trainingOptions('sgdm','InitialLearnRate',0.001, ...
'MaxEpochs',15);
%create network
X(:,:,:,1) = rand(25);
Y=randn(1,1,25*25,1);
net = trainNetwork(X,Y,layers,options)
I hope the above code will help you.
Regards,
Darshan Bhat
  1 commentaire
Osama Tabbakh
Osama Tabbakh le 11 Avr 2019
Modifié(e) : Osama Tabbakh le 14 Mai 2019
I wounder why u put two fullyConnectedLayers. And can I somehow filter the output also?

Connectez-vous pour commenter.

Produits

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by