Trying to create neural network but getting a NaN error from dataset
3 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Nathaniel Porter
le 1 Déc 2021
Commenté : Nathaniel Porter
le 2 Déc 2021
%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,:);
%Separating and partioning for validation data
val_X1 = X1_train(121:150,:);
%Separating and partioning for test data
test_X1 = X1_train(151:180,:);
%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
numFeatures = 2;
% number of hidden units represent the size of the data
numHiddenUnits = 180;
%number of classes represent different patients normal,LIS,type2....
numClasses = 6;
layers = [ ...
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits,'OutputMode','last')
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer];
options = trainingOptions('adam', ...
'MaxEpochs',60, ...
'GradientThreshold',2, ...
'Verbose',0, ...
'Plots','training-progress');
isnan(train_X1)
net = trainNetwork(train_X1,Y1,layers,options);
3 commentaires
KSSV
le 2 Déc 2021
OP commented:
So it is a large set of data can you recommend any ways that I can alter the data to get rid of these Nans?
Réponse acceptée
Walter Roberson
le 2 Déc 2021
net = trainNetwork(train_X1, string(Y1), layers, options);
However:
Error using trainNetwork (line 184)
The training sequences are of feature dimension 120 but the input layer expects sequences of feature dimension 2.
And indeed you coded
numFeatures = 2;
If you are only wanting to pass in two features then you are going to have to extract those two features out of your 120 x 2289 array.
Plus de réponses (2)
yanqi liu
le 2 Déc 2021
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);
%Separating and partioning for validation data
val_X1 = X1_train(121:150,:);
%Separating and partioning for test data
test_X1 = X1_train(151:180,:);
%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
numFeatures = size(X1_T,2);
% number of hidden units represent the size of the data
numHiddenUnits = 180;
%number of classes represent different patients normal,LIS,type2....
numClasses = length(categories(categorical(Y1)));
layers = [ ...
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer];
options = trainingOptions('adam', ...
'MaxEpochs',60, ...
'GradientThreshold',2, ...
'Verbose',0, ...
'Plots','training-progress');
net = trainNetwork(X1_train',categorical(Y1),layers,options);
Voir également
Catégories
En savoir plus sur Deep Learning for Image Processing dans Help Center et File Exchange
Produits
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!