Invalid training data. Predictors and responses must have the same number of observations.

1 次查看（过去 30 天）
tyler seudath
tyler seudath 2021-11-20
评论： Prince Kumar 2021-11-23
Hi Everyone,
I am getting an error Invalid training data Predictors and responses must have the same number of observations in my CNN network.
My training data Tain1_In is a 4D matrix which was initially a 4050 x 400 matrix that i reshaped
My train1_Out data is 4050 x 1
The neural network doesnt run. Could you please help?
The code is attached below
%% SPLITTING MAGNITUDE DATA INTO TRAINING, TESTING AND VALIDATION
%Magnitude data
%Training data
Train_inputX1 =Magnitude_all_data; %5000 segments x 400 samples
Train_outputX1 =Modulation_Schemes ;% 5000 segments x 1
Test_X1 =ceil(0.1 *size(Magnitude_all_data,1)); % 10% is catered for testing
idx1_t= randperm(size(Magnitude_all_data,1),Test_X1);%This will generate the 10% of the random test numbers from 1 to 5000
%
% % Now I'm gonna partition the data accordingly...
testX1_input = Magnitude_all_data(idx1_t',:); %Phase test input
testX1_output = Modulation_Schemes(idx1_t); %Phase test output
Train_inputX1(idx1_t',:) = []; % assigning '[]' to matrix entries deletes them.
Train_outputX1(idx1_t',:) =[]; % Deletes the outputs that was used to test input
%
% %Now we need to repeat to find the validation data
Train1_inputX1 = Train_inputX1; %5000 segments x 400 samples
Train1_outputX1 =Train_outputX1;% 5000 segments x 1
Val_X1 =ceil(0.1 *size(Train_outputX1,1)); % 10% is catered for Validation
idx1_v= randperm(size(Train_outputX1,1),Val_X1);%This will generate the 10% of the random test numbers from 1 to 5000
%
% Now I'm gonna partition the data accordingly...
ValX1_input = Magnitude_all_data(idx1_v',:); %Mag Val input
ValX1_output =Train_outputX1(idx1_v); %Mag Val output
Train1_inputX1(idx1_v',:) = []; % assigning '[]' to matrix entries deletes them.
Train1_outputX1(idx1_v',:) =[]; % Deletes the outputs that was used to test input
%
Train1_In =reshape(num2cell(Train1_inputX1),[400,1,1,4050]);
Train1_Out =categorical(Train1_outputX1);
Val1_In =reshape(num2cell(ValX1_input),[400,1,1,450]);
Val1_Out = categorical(ValX1_output);
%% NETWORK ARCHITECTURE
layers = [imageInputLayer([400 1 1])
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(30)
fullyConnectedLayer(10)
fullyConnectedLayer(2)
softmaxLayer
classificationLayer];
%% Specify training options.
% Note: The code below is an example. use the help for 'trainingOptions
% and change the things in this as needed. Explain all options you set and
% why. Marks are attached.
opts = trainingOptions('sgdm', ...
'MaxEpochs',40, ...
'Shuffle','every-epoch', ...
'Plots','training-progress', ...
'Verbose',false, ...
'ValidationData',{Val1_In,Val1_Out},...
'ValidationPatience',Inf);
%% Train network
% Same comment as in the previous section for training options.
net = trainNetwork(Train1_In,Train1_Out,layers,opts);

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

产品


版本

R2021a

Community Treasure Hunt

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

Start Hunting!

Translated by