MATLAB Answers

0

Invalid training data. The output size (5) of the last layer doesn't match the number of classes (5). How to match output size??

Asked by nima aalizade on 16 Dec 2017
Latest activity Edited by nima aalizade on 18 Jul 2018
net=vgg16();
imds = imageDatastore(fullfile('E:\','data','labels'),...
'IncludeSubfolders',true,'FileExtensions','.dcm','LabelSource','foldernames');
labelCount = countEachLabel(imds);
trainingNumFiles = 105;
rng(1) % For reproducibility
[trainData,testData] = splitEachLabel(imds,...
trainingNumFiles,'randomize');
imageSize = [512 512 1];
numClasses = 5;
encoderDepth = 9;
lgraph = segnetLayers(imageSize,numClasses,encoderDepth);
plot(lgraph)
options = trainingOptions('sgdm','InitialLearnRate',1e-3, ...
'MaxEpochs',50,'VerboseFrequency',10);
seg = trainNetwork(imds,lgraph,options)

  0 Comments

Sign in to comment.

2 Answers

Answer by nima aalizade on 16 Feb 2018
Edited by nima aalizade on 16 Feb 2018
 Accepted Answer

hello,
for using SegNet, you most have pixel labeled data with image labeler. you can use this and this example to understand better.

  0 Comments

Sign in to comment.


Answer by abdulkader helwan on 25 Dec 2017

Hello.. i am having the same problem here. could u please tell me how u solved it if u did so. thanks

  3 Comments

hello
for using SegNet, you most have pixel labeled data with image labeler. you can use this and this example to understand better.

Sign in to comment.