convolutional neural network for medical segmentation code

Question

Mohamed Nasr 2020-4-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/521219-convolutional-neural-network-for-medical-segmentation-code

回答： vaibhav mishra 2020-6-30

在 MATLAB Online 中打开

please this is my code and error is

labelCount =

2×2 table

Label Count

_____ _____

no 91

yes 154

Error using trainNetwork (line 170)

The validation images are of size 248x208x3 but the input layer expects images of size 201x173x3.

Error in ccn (line 51)

net = trainNetwork(imdsTrain,layers,options);

>> (what I do ?!)

clear all;
clc;
close all;
imds = imageDatastore('D:\matlab aml\dataset1','FileExtensions',{'.jpg'},'IncludeSubfolders',true,'LabelSource','foldernames');
imgs = readall(imds);
figure;
perm = randperm(200,20);%Display some of the images in the datastore.
for i = 1:20
    subplot(4,5,i);
    imshow(imds.Files{perm(i)});
end
img = readimage(imds,1); %Check the size of the first image in digitData. Each image is 201-by-173-by-3 pixels.
size(img)
%Specify Training and Validation Sets
labelCount = countEachLabel(imds) %Calculate the number of images in each category
numTrainFiles = 90;
[imdsTrain,imdsValidation] = splitEachLabel(imds,numTrainFiles,'randomize');
%Define the convolutional neural network architecture.
layers = [
    imageInputLayer([201 173 3])
    convolution2dLayer(3,8,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    fullyConnectedLayer(2)
    softmaxLayer
    classificationLayer];
%Specify Training Options
options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',10, ...
    'Verbose',false, ...
    'Plots','training-progress');
%Train Network Using Training Data
net = trainNetwork(imdsTrain,layers,options);
YPred = classify(net,imdsValidation);
YValidation = imdsValidation.Labels;
accuracy = sum(YPred == YValidation)/numel(YValidation)