How to save network obtained from a loop to use it for prediction?

13 次查看(过去 30 天)
Dear MATLAB users,
I trained my data in a loop (N=10), and I found that network{2} provides the best results. How do I save this specific network so that I can use it for prediction later with test data.
Thank you

回答(1 个)

VINAYAK LUHA
VINAYAK LUHA 2024-1-4
编辑:VINAYAK LUHA 2024-1-4
Hello Nurliana,
I understand that you're training a series of neural networks within MATLAB and you wish to preserve one particular network—namely network{2}—for subsequent predictions using test data.
Here is the step by step explanation to achieve the above objective -
1.To store network{2}, you can apply the MATLAB "save" function in the following manner:
bestNetwork = network{2};
save('DestinationFolderPath\bestNetwork.mat', 'bestNetwork');
2.To retrieve the saved network back into your workspace, use the MATLAB "load" function:
load('bestNetwork.mat', 'bestNetwork');
3. For making predictions with your test data - testX , the syntax would be
testY = bestNetwork(testX');
You can refer to the following documentation for more details about the MATLAB "save" and "load" functions-
Hope this helps you to understand how to save and reuse trained neural network in MATLAB.
Regards,
Vinayak Luha

类别

Help CenterFile Exchange 中查找有关 Deep Learning Toolbox 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