How to Solve this, Semantic Segmentation with Dice Loss
5 views (last 30 days)
Show older comments
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]).
4 Comments
Walter Roberson
on 18 Dec 2019
I do not know what the cause of the problem is, but you could try adding a resize layer on the bottom.
Answers (0)
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!