Number of observations in X and Y disagree. For convolution neural network

clc; clear all; close all;

%Import/Upload data

load generated_data.mat

%transposing glucose data

X1_T = X1';

%transposing insulin data

X2_T = X2';

%Separating data in training, validation and testing data

X1_train = X1_T;

%Partioning data for training

train_X1 = X1_train(1:120,:);

train_Y1 = Y1(1:120);

%DataParts = zeros(size(Train_inputX1,1), size(Train_inputX1,2),1,2); %(4500,400,1,2)

%DataParts(:,:,:,1) = real(cell2mat(Train_inputX1));

%DataParts(:,:,:,2) = imag(cell2mat(Train_inputX1)) ;

XTrain=(reshape(train_X1, [120,1,1,2289])); %Train data

%Separating and partioning for validation data

val_X1 = X1_train(121:150,:);

val_Y1 = Y1(121:150);

XVal=(reshape(val_X1, [30,1,1,2289])); %Train data

%Separating and partioning for test data

test_X1 = X1_train(151:180,:);

test_Y1 = Y1(151:180);

XTest=(reshape(test_X1, [30,1,1,2289])); %Train data

%Xtest=(reshape(test_X1, [120,1,1,2289])); %Train data

%Separating data in training, validation and testing data

%X2_train = X2_T;

%Partioning data for training

%train_X2 = X2_train(1:120,:);

%Separating and partioning for validation data

%val_X2 = X2_train(121:150,:);

%Separating and partioning for test data

%test_X2 = X2_train(151:180,:);

%The number of features chosen to be two representing both glucose and

%insulin

%% NETWORK ARCHITECTURE

layers = [imageInputLayer([120 1 1]) % Creating the image layer

convolution2dLayer([102 1],3,'Stride',1)

maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])

% convolution2dLayer([24 1],10,'Stride',1)

% maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])

% convolution2dLayer([11 1],10,'Stride',1)

% maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])

% convolution2dLayer([9 1],10,'Stride',1)

% maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])

fullyConnectedLayer(6)

%fullyConnectedLayer(6)

%fullyConnectedLayer(6)

softmaxLayer

classificationLayer];

% Specify training options.

opts = trainingOptions('adam', ...

'MaxEpochs',50, ...

'Shuffle','every-epoch', ...

'Plots','training-progress', ...

'Verbose',false, ...

'ValidationData',{XVal,val_Y1},...

'ValidationPatience',Inf);

%% Train network

%net = trainNetwork(XTrain,Trainoutfinal,layers,opts);

net1 = trainNetwork(XTrain,categorical(train_Y1),layers,opts);

%% Compare against testing Data

miniBatchSize =27;

YPred = classify(net1,test_X1, ...

MiniBatchSize=miniBatchSize, ...

SequencePaddingDirection="left");

acc = mean(YPred == categorical(test_Y1));

figure

t = confusionchart(categorical(test_Y1),YPred);

[Rik]

Have a read here and here. It will greatly improve your chances of getting an answer.

Posting duplicates does not help, so please don't.

Answer 1

[yanqi liu]

yes，sir，may be upload generated_data.mat to make some analysis

[Rik]

How exactly does this answer the question?

[yanqi liu]

why? just ask for the data to debug, What's wrong with this? @Rik

[Rik]

There is nothing wrong with asking for data, but it seems like a comment, not an answer. That is all, I was just confused.

[Nathaniel Porter]

Not allowed to upload anyhting for some reason

[Nathaniel Porter]

Any suggestions?

[Rik]

Maybe your mat file is too large. You should get some kind of warning or error message when trying to upload.

Also, were you planning to use the editing tools to format your code as code?

[yanqi liu]

please display the dimension，such as

size(XTrain)

size(categorical(train_Y1))

just from the code, may be the

imageInputLayer([120 1 1])

convolution2dLayer([102 1],3,'Stride',1)

do not match the dimension

[Nathaniel Porter]

clc; clear all; close all;
%Import/Upload data
load generated_data.mat

Error using load
Unable to find file or directory 'generated_data.mat'.

%transposing glucose data
X1_T = X1';
%transposing insulin data
X2_T = X2';
%Separating data in training, validation and testing data
X1_train = X1_T;
%Partioning data for training
train_X1 = X1_train(1:120,:);
train_Y1 = Y1(1:120);
%DataParts = zeros(size(Train_inputX1,1), size(Train_inputX1,2),1,2); %(4500,400,1,2)
%DataParts(:,:,:,1) = real(cell2mat(Train_inputX1));
%DataParts(:,:,:,2) = imag(cell2mat(Train_inputX1)) ;
XTrain=(reshape(train_X1, [120,1,1,2289])); %Train data
%Separating and partioning for validation data
val_X1 = X1_train(121:150,:);
val_Y1 = Y1(121:150);
XVal=(reshape(val_X1, [30,1,1,2289])); %Train data
%Separating and partioning for test data
test_X1 = X1_train(151:180,:);
test_Y1 = Y1(151:180);
XTest=(reshape(test_X1, [30,1,1,2289])); %Train data
%Xtest=(reshape(test_X1, [120,1,1,2289])); %Train data
%Separating data in training, validation and testing data
%X2_train = X2_T;
%Partioning data for training
%train_X2 = X2_train(1:120,:);
%Separating and partioning for validation data
%val_X2 = X2_train(121:150,:);
%Separating and partioning for test data
%test_X2 = X2_train(151:180,:);
%The number of features chosen to be two representing both glucose and
%insulin




%% NETWORK ARCHITECTURE
layers = [imageInputLayer([120 1 1])  % Creating the image layer
    convolution2dLayer([102 1],3,'Stride',1)
    maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
%     convolution2dLayer([24 1],10,'Stride',1)
%     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
%    convolution2dLayer([11 1],10,'Stride',1)
%     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
%     convolution2dLayer([9 1],10,'Stride',1)
%     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
    fullyConnectedLayer(6)
    fullyConnectedLayer(6)
    fullyConnectedLayer(1)
    softmaxLayer
    classificationLayer];

% Specify training options.  
opts = trainingOptions('adam', ...
    'MaxEpochs',50, ...
    'Shuffle','every-epoch', ...
    'Plots','training-progress', ...
    'Verbose',false, ...
    'ValidationData',{XVal,val_Y1},...
    'ValidationPatience',Inf);

%% Train network
%net = trainNetwork(XTrain,Trainoutfinal,layers,opts);
net1 = trainNetwork(XTrain,categorical(train_Y1),layers,opts);
%% Compare against testing Data

miniBatchSize =27;
YPred = classify(net1,test_X1, ...
    MiniBatchSize=miniBatchSize, ...
    SequencePaddingDirection="left");
acc = mean(YPred == categorical(test_Y1));


figure
t = confusionchart(categorical(test_Y1),YPred);

Okay a bit unsure of the questions being asked but here is my code with the dataset hoping I can get a better idea as to where im going wrong or where exactly I may need to fix

[yanqi liu]

clc; clear all; close all;

%Import/Upload data
load generated_data.mat
%transposing glucose data
X1_T = X1';
%transposing insulin data
X2_T = X2';
ind = randperm(size(X1_T, 1));
X1_T = X1_T(ind, :);
Y1 = Y1(ind);
%Separating data in training, validation and testing data
X1_train = X1_T;
%Partioning data for training
train_X1 = X1_train(1:120,:);
train_Y1 = Y1(1:120);
%DataParts = zeros(size(Train_inputX1,1), size(Train_inputX1,2),1,2); %(4500,400,1,2)
%DataParts(:,:,:,1) = real(cell2mat(Train_inputX1));
%DataParts(:,:,:,2) = imag(cell2mat(Train_inputX1)) ;
XTrain=(reshape(train_X1', [2289,1,1,120])); %Train data
%Separating and partioning for validation data
val_X1 = X1_train(121:150,:);
val_Y1 = Y1(121:150);
XVal=(reshape(val_X1', [2289,1,1,30])); %Train data
%Separating and partioning for test data
test_X1 = X1_train(151:180,:);
test_Y1 = Y1(151:180);
XTest=(reshape(test_X1', [2289,1,1,30])); %Train data
%Xtest=(reshape(test_X1, [120,1,1,2289])); %Train data
%Separating data in training, validation and testing data
%X2_train = X2_T;
%Partioning data for training
%train_X2 = X2_train(1:120,:);
%Separating and partioning for validation data
%val_X2 = X2_train(121:150,:);
%Separating and partioning for test data
%test_X2 = X2_train(151:180,:);
%The number of features chosen to be two representing both glucose and
%insulin




%% NETWORK ARCHITECTURE
layers = [imageInputLayer([2289 1 1])  % Creating the image layer
    convolution2dLayer([102 1],3,'Stride',1)
    maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
    %     convolution2dLayer([24 1],10,'Stride',1)
    %     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
    %    convolution2dLayer([11 1],10,'Stride',1)
    %     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
    %     convolution2dLayer([9 1],10,'Stride',1)
    %     maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
    %fullyConnectedLayer(6)
    %fullyConnectedLayer(6)
    fullyConnectedLayer(6)
    softmaxLayer
    classificationLayer];

% Specify training options.
opts = trainingOptions('adam', ...
    'MaxEpochs',50, ...
    'Shuffle','every-epoch', ...
    'Plots','training-progress', ...
    'Verbose',false, ...
    'ValidationData',{XVal,categorical(val_Y1)},...
    'ExecutionEnvironment', 'cpu', ...
    'ValidationPatience',Inf);

%% Train network
%net = trainNetwork(XTrain,Trainoutfinal,layers,opts);
yc = categorical(train_Y1);
net1 = trainNetwork(XTrain,yc,layers,opts);
%% Compare against testing Data

miniBatchSize =27;
YPred = classify(net1,XTest, ...
    'MiniBatchSize',miniBatchSize,...
    'ExecutionEnvironment', 'cpu');
acc = mean(YPred(:) == categorical(test_Y1(:)))


figure
t = confusionchart(categorical(test_Y1(:)),YPred(:));

acc =

0.9000

[Nathaniel Porter]

Thank you. I realized you got an acc = 0.900 but when I ran the code I got 0.677 any reasons as to the change?

[yanqi liu]

yes，sir，i think

ind = randperm(size(X1_T, 1));

may be get different train、test、val

so，i think the data split should make prepare，and use the 6 classies data