Number of observations in X and Y disagree.
2 次查看(过去 30 天)
显示 更早的评论
clc; clear all; close all;
%Import/Upload data
load Projectdata.mat
% change to label vector
CS = categories(categorical(GR_output));
CS1 = categories(categorical(INS_output));
Z1 = []; Z2 = [];
for i = 1 : length(GR_output)
Z1(i,1) = find(GR_output(i)==CS);
end
for i = 1 : length(INS_output)
Z2(i,1) = find(INS_output(i)==CS1);
end
Yo1 = GR_output;
Yo2 = INS_output;
GR_output= Z1;
INS_output = Z2;
%transposing glucose data
GlucoseReadings_T = GlucoseReadings';
%transposing insulin data
InsulinReadings_T = InsulinReadings';
%Shuffling data to take randomly
rand('seed', 0)
ind = randperm(size(GlucoseReadings_T, 1));
GlucoseReadings_T = GlucoseReadings_T(ind, :);
GR_output = GR_output(ind);
ind = randperm(size(InsulinReadings_T, 1));
InsulinReadings_T = InsulinReadings_T(ind, :);
INS_output = INS_output(ind);
%Separating data in training, validation and testing data
GlucoseReadings_train = GlucoseReadings_T;
InsulinReadings_train = InsulinReadings_T;
%Partioning data for training 70%
train_GlucoseReadings = GlucoseReadings_train(1:84,:);
train_InsulinReadings = InsulinReadings_train(1:84,:);
%Corresponding X(input) data to Y(output) data
train_GR_output = GR_output(1:17);
train_INS_output = INS_output(1:84);
%reshaping data into 4D array
GlucoseReadingsTrain=(reshape(train_GlucoseReadings', [1749,1,1,84]));
InsulinReadingsTrain=(reshape(train_InsulinReadings',[1758,1,1,84]));
%Separating and partioning for validation data 15%
val_GlucoseReadings = GlucoseReadings_train(85:102,:);
val_InsulinReadings = InsulinReadings_train(85:102,:);
%Corresponding X(input) data to Y(output) data
val_GR_output = GR_output(85:102);
val_INS_output = INS_output(85:102);
%reshaping data into 4D array
whos
GlucoseReadingsVal=(reshape(val_GlucoseReadings', [1749,1,1,18]));
InsulinReadingsVal=(reshape(val_InsulinReadings', [1758,1,1,18]));
%Separating and partioning for test data 15%
test_GlucoseReadings = GlucoseReadings_train(103:120,:);
test_InsulinReadings = InsulinReadings_train(103:120,:);
%Corresponding X(input) data to Y(output) data
test_GR_output = GR_output(103:120);
test_INS_output = INS_output(103:120);
%reshaping data into 4D array
GlucoseReadingsTest=(reshape(test_GlucoseReadings', [1749,1,1,18]));
InsulinReadingsTest=(reshape(test_InsulinReadings', [1758,1,1,18]));
%% NETWORK ARCHITECTURE
layers = [imageInputLayer([1758 1 1]) % Creating the image layer
convolution2dLayer([102 1],3,'Stride',1)
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2,'Padding',[0 0 0 1])
dropoutLayer
fullyConnectedLayer(1)
regressionLayer];
% Specify training options.
opts = trainingOptions('sgdm', ...
'MaxEpochs',1000, ...
'Shuffle','every-epoch', ...
'Plots','training-progress', ...
'Verbose',false, ...
'ValidationData',{GlucoseReadingsVal,val_GR_output,},...
'ValidationData',{InsulinReadingsVal,val_INS_output,},...
'LearnRateDropFactor',0.2,...
'LearnRateDropPeriod',5,...
'ExecutionEnvironment', 'cpu', ...
'ValidationPatience',Inf);
%% Train network
%net = trainNetwork(XTrain,Trainoutfinal,layers,opts);
yc = train_GR_output(:);
yc1 = train_INS_output(:);
net1 = trainNetwork(GlucoseReadingsTrain,yc,layers,opts);
net2 = trainNetwork(InsulinReadingsTrain,yc1,layers,opts);
%% Compare against testing Data
GR_outputpredicted = predict(net1, GlucoseReadingsTest)
INS_outputpredicted = predict(net1, InsulinReadingsTest)
predictionError = test_GR_output - GR_outputpredicted;
predictionError1 = test_INS_output - INS_outputpredicted;
squares = predictionError.^2;
rmse = sqrt(mean(squares))
figure
scatter(GR_outputpredicted, test_GR_output,'+')
title ('True value vs Predicted Value')
xlabel ("Predicted Value")
ylabel ("True Value")
hold on
plot([-3 3], [-7 7], 'b--')
scatter(INS_outputpredicted, test_INS_output,'+')
title ('True value vs Predicted Value')
xlabel ("Predicted Value")
ylabel ("True Value")
hold on
plot([-3 3], [-7 7], 'b--')
0 个评论
采纳的回答
KSSV
2022-3-4
编辑:KSSV
2022-3-4
Your yc i.e. target for the respective input in the line:
net1 = trainNetwork(GlucoseReadingsTrain,yc,layers,opts);
is of dimension 17x1. Where as input is 1749x1x1x84. So there is a miss match and you got error. Where as the variables yc1 is of dimension 84x1 and this should work. This line should not through any error:
net2 = trainNetwork(InsulinReadingsTrain,yc1,layers,opts);
So you have to use net2. You may delete the line net1.
5 个评论
KSSV
2022-3-4
Now you messed up with the input: GlucoseReadingsTrain
It should be 1758x1x1x84, but it is 1749x1x1x84.
更多回答(1 个)
Walter Roberson
2022-3-4
编辑:Walter Roberson
2022-3-4
net2 = trainNetwork(train_GlucoseReadings,yc1,layers1,opts);
Your code uses a series of variables that are not well distinguished from each other in meaning, so it is easy to get wrong which ones you are talking about.
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!