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

7 ビュー (過去 30 日間)
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)

採用された回答

nima aalizade
nima aalizade 2018 年 2 月 16 日
編集済み: nima aalizade 2018 年 2 月 16 日
hello,
for using SegNet, you most have pixel labeled data with image labeler. you can use this and this example to understand better.

その他の回答 (1 件)

abdulkader helwan
abdulkader helwan 2017 年 12 月 25 日
Hello.. i am having the same problem here. could u please tell me how u solved it if u did so. thanks
  4 件のコメント
nima aalizade
nima aalizade 2018 年 2 月 16 日
編集済み: nima aalizade 2018 年 2 月 16 日
hello
for using SegNet, you most have pixel labeled data with image labeler. you can use this and this example to understand better.
Mihai Mihaela
Mihai Mihaela 2019 年 12 月 8 日
Same issue here. The attached link doesn't work.

サインインしてコメントする。

カテゴリ

Help Center および File ExchangeConvert Image Type についてさらに検索

Community Treasure Hunt

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

Start Hunting!

Translated by