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

Question

Nathaniel Porter 2021-12-5

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1603220-number-of-observations-in-x-and-y-disagree-for-convolution-neural-network

评论： yanqi liu 2021-12-13

采纳的回答： 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';

%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)

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);

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Rik 2021-12-8

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.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

yanqi liu 2021-12-9

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1603220-number-of-observations-in-x-and-y-disagree-for-convolution-neural-network#answer_851045

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

11 个评论
显示 9更早的评论隐藏 9更早的评论

Nathaniel Porter 2021-12-13

在 MATLAB Online 中打开

generated_data.mat

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 2021-12-13

在 MATLAB Online 中打开

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(:));