How to test RNN (layrecnet) ?

4 次查看(过去 30 天)
Machine Learning Enthusiast
回答: Jash Kadu 2022-7-13
I have trained my time series data using Recurrent Neural Network (RNN)/ layrecnet function to make predictions.
Now i want to test the trained model with new(test) data.
Can anybody please confirm weather i have implemented the below code correctly?
data=HomeA';
N=50;
XTrain = data(1:end-N);
YTrain = data(1:end-N);
%
XTest=data(end-N+1:end);
YTest = data(end-N+1:end);
X = tonndata(XTrain,true,false);
T = tonndata(YTrain ,true,false);
X2 = tonndata(XTest,true,false);
T2 = tonndata(YTest ,true,false);
%% Build Recurrent neural network
net = layrecnet(1:2,10);
[Xs,Xi,Ai,Ts] = preparets(net,X,T);
net = train(net,Xs,Ts,Xi,Ai);
%view(net)
Y = net(Xs,Xi,Ai);
perf = perform(net,Y,Ts)
%% Test the model on new data
[Xs1,Xio,Aio] = preparets(net,X,T);
[Y1,Xfo,Afo] = net(Xs1,Xio,Aio);
[netc,Xic,Aic] = closeloop(net,Xfo,Afo);
[yPred,Xfc,Afc] = netc(X2,Xic,Aic);
TestPerformance = perform(net,yPred,T2);

回答(1 个)

Jash Kadu
Jash Kadu 2022-7-13
Hi!
Please check out the documentation for Layer recurant neural network : https://www.mathworks.com/help/deeplearning/ref/layrecnet.html.
You can also run the following command;
openExample('nnet/RefLayRecNetExample') in your MATLAB editor to test it.

类别

Help CenterFile Exchange 中查找有关 Sequence and Numeric Feature 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!

Translated by