How to Solve this, Semantic Segmentation with Dice Loss

My images are with 256 X 256 in size

I am doing semantic segmentation with dice loss.

ds = pixelLabelImageDatastore(imdsTrain,pxdsTrain);

layers = [
         imageInputLayer([256 256 1])
         convolution2dLayer(3,32,'Padding',1)
         reluLayer
         maxPooling2dLayer(2,'Stride',2)
         convolution2dLayer(3,32,'Padding',1)
         reluLayer
         transposedConv2dLayer(4,32,'Stride',2,'Cropping',1)
         reluLayer
         transposedConv2dLayer(4,32,'Stride',2,'Cropping',1)
         convolution2dLayer(1,3)
         softmaxLayer
         dicePixelClassificationLayer('dice')
         ]

opts = trainingOptions('sgdm',  'InitialLearnRate',1e-3,  'MaxEpochs',10,  'LearnRateDropFactor',1e-1,  'LearnRateDropPeriod',50,  'LearnRateSchedule','piecewise',  'MiniBatchSize',32);

net = trainNetwork(ds,layers,opts);

Errors are :-

Error using trainNetwork (line 165)

Invalid training data. The output size ([512 512 3]) of the last layer does not match the response size ([256 256 3]).

Error in net_net (line 110)
net = trainNetwork(ds,layers,opts);



The output size ([512 512 3]) of the last layer does not match the response size ([256 256 3]).

[Walter Roberson]

Side note: https://www.mathworks.com/help/vision/ref/nnet.cnn.layer.dicepixelclassificationlayer.html that classification layer does not appear to take a single option such as your 'Dice' . It does appear to permit 'Name', 'Dice' if you want to name the layer.

[Mohammad Bhat]

I think name is optional there, I tried your suggestion but Error is persists

[Walter Roberson]

I do not know what the cause of the problem is, but you could try adding a resize layer on the bottom.

[Mohammad Bhat]

I solved the problem rather error by adding maxpooling layer at the end....

.......................................................................

......................................................................

layers = [
    imageInputLayer([256 256 1])
    convolution2dLayer(3,32,'Padding',1)
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,32,'Padding',1)
    reluLayer
    transposedConv2dLayer(4,32,'Stride',2,'Cropping',1)
    reluLayer
    transposedConv2dLayer(4,32,'Stride',2,'Cropping',1)
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(1,3)
    softmaxLayer
    dicePixelClassificationLayer('dice')
    ]