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

Question

Mohamed Nedal 2020-1-17

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500677-how-to-make-predictions-using-an-already-trained-lstm-model

回答： NGR MNFD 2021-7-2

采纳的回答： Hiro Yoshino

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 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Hiro Yoshino 2020-5-7

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500677-how-to-make-predictions-using-an-already-trained-lstm-model#answer_430908

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

feed the test data up to x_{t-1} to predict x_t
feed the predicted test data up to x_{t-1} to predict x_t

you may want to make a referenct to

https://jp.mathworks.com/help/deeplearning/examples/time-series-forecasting-using-deep-learning.html

Good luck!

3 个评论
显示 1更早的评论隐藏 1更早的评论

Hiro Yoshino 2020-5-8

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 2020-5-9

编辑：Mohamed Nedal 2020-5-9

The dataset has 16,071 pairs of (x,y), that means 16,071 days.

Ok great, that would be much appreciated. Thanks!

请先登录，再进行评论。

Answer 2

Hiro Yoshino 2020-1-17

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500677-how-to-make-predictions-using-an-already-trained-lstm-model#answer_410563

在 MATLAB Online 中打开

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 个评论
显示 8更早的评论隐藏 8更早的评论

Mohamed Nedal 2020-4-9

在 MATLAB Online 中打开

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 Yoshino 2020-4-9

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:

https://jp.mathworks.com/help/deeplearning/examples/time-series-forecasting-using-deep-learning.html

Mohamed Nedal 2020-5-3

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?

请先登录，再进行评论。

Answer 3

NGR MNFD 2021-7-2

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/500677-how-to-make-predictions-using-an-already-trained-lstm-model#answer_738493

ok1.zip

Hello . I hope you have a good day. I sent the article to your service. I implemented the coding part in the MATLAB software, but to implement my network, two lines of setlayers, training MATLAB 2014 give me an error. What other function do you think I should replace? Do you think the codes I wrote are correct?( I used gait-in-neurodegenerative-disease-database in physionet website.) Thanks a lot