MATLAB Answers

How to make predictions using an already-trained LSTM model?

145 ビュー (過去 30 日間)
Mohamed Nedal
Mohamed Nedal 2020 年 1 月 17 日
編集済み: Mohamed Nedal 2020 年 5 月 9 日
Hello everyone,
I have the attached example LSTM code with the data file (omni.txt: hourly data).
I would like to know how to use the trained LSTM model to make a prediction for new data.
I think the answer lies within the lines starting from line 113, but I'm a novice with LSTM.
----------------------------------------------------------------------------------------------------------------------------------
A side question:
This code is dealing with only one input (feature) to predict its own evolution with time, How can we transform it to deal with several inputs at once?
How can we transform this code to take several inputs and predict the temporal evolution of another output?
For instance, like the feedforward backpropagation network in which it can take several inputs to predict a single output (or several outputs).
I appreciate your help!
Thank you,

  0 件のコメント

サインインしてコメントする。

採用された回答

Hiro
Hiro 2020 年 5 月 7 日
It seems you are predicting the data based on the training data.
That's why the prediction stays unchange after the end of training data.
If you want to make predictions following the test data, you should take either way
  1. feed the test data up to x_{t-1} to predict x_t
  2. feed the predicted test data up to x_{t-1} to predict x_t
you may want to make a referenct to
Good luck!

  3 件のコメント

Mohamed Nedal
Mohamed Nedal 2020 年 5 月 7 日
I already feed the test data up tp X_(t-1) to predict X_(t), then I feed that predicted value to predict the next one, and so on.
%% Forecast Future Time Steps
net = predictAndUpdateState(net, XValidation');
[net, YPred] = predictAndUpdateState(net, YValidation(end));
numTimeStepsTest = numel(XValidation);
for i = 2:numTimeStepsTest
[net, YPred(i)] = predictAndUpdateState(net, YPred(i-1),...
'ExecutionEnvironment','auto');
end
However, I get the same behaviour ..
Hiro
Hiro 2020 年 5 月 8 日
I guess you're doing right.
Why don't you test the model using the training data first to see how good it is.
by the way, I wonder how many pairs of data (x, y) do you have to train the model?
I'll try to take a look at your code when I have free time.
Mohamed Nedal
Mohamed Nedal 2020 年 5 月 9 日
The dataset has 16,071 pairs of (x,y), that means 16,071 days.
Ok great, that would be much appreciated. Thanks!

サインインしてコメントする。

その他の回答 (1 件)

Hiro
Hiro 2020 年 1 月 17 日
I took a look at your script.
in the line 131, you actually update the network together with getting the prediction out of it:
[net,YPred(:,i)] = predictAndUpdateState(net,XTest(:,i),'ExecutionEnvironment','cpu');

  10 件のコメント

表示 7 件の古いコメント
Mohamed Nedal
Mohamed Nedal 2020 年 4 月 9 日
So 'window size' here referes to the batch size, right?
Kindly find the attached code with the data file.
I've used your function also for the testing set at line 53 but, yet I got the following error at line 54 in the code:
Error using
DAGNetwork/predictRNN>iAssertInitialStateIsValidForPredict
(line 72)
Incorrect network state. The network expects
mini-batches size of 31, but was passed a mini-batch of
size 128.
Error in DAGNetwork/predictRNN (line 11)
iAssertInitialStateIsValidForPredict(statefulLayers,
dispatcher.MiniBatchSize)
Error in DAGNetwork/predictAndUpdateState (line 117)
[Y, finalState, predictNetwork] = this.predictRNN(X,
dispatcher, ...
Error in SeriesNetwork/predictAndUpdateState (line 376)
[this.UnderlyingDAGNetwork, Y] =
this.UnderlyingDAGNetwork.predictAndUpdateState(X,
varargin{:});
Excuse me for my silly questions, what should I change to make it works? And what should I change to forecast for any (n) time steps in the future?
Thank you!
Hiro
Hiro 2020 年 4 月 9 日
No, it is a window size with which you chop the signal into peices.
you may want to take a look at this and understand how it works:
Mohamed Nedal
Mohamed Nedal 2020 年 5 月 3 日
Hello Mr. Yoshino, I hope you're fine
I finally managed to make forecasting on new data, but the forecasting of the test data seems very inaccurate.
Kindly find the attached code with the dataset.
Any suggestions to improve the accuracy please?
comparison
prediction
forecast

サインインしてコメントする。

Community Treasure Hunt

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

Start Hunting!

Translated by