how to save and reuse a trained neural network

I just trained a neural network and i will like to test it with new data set that were not included in the training so as to check its performance on new data. This is my code; net = patternnet(30); net = train(net,x,t); save (net); y = net(x); perf = perform(net,t,y) classes = vec2ind(y); where x and t are my input and target respectively. I understand that save net; can be used but my questions are as follows ; 1.At what point in my code will i put save net 2.Using save net;, which location on the system is the trained network saved? 3.How can i load the trained network and supply new data that i want to test it with? Please Note: I want to be able to save the trained neural network such that when i run the code over and over again with the training data set,it gives same output. I have discovered that each time i run my code,it gives a different output which i do not want once i have an acceptable result. Please help

Answer 1

[Greg Heath]

1.At what point in my code will i put save net

 Any time after training it and before deleting it. 
However, give it a unique name so that it is not overwritten 
or used by mistake. 

 gregnet1 = net;
 save gregnet1

2.Using save net;, which location on the system is the trained network saved?

 What ever directory you are in when you save it UNLESS you 
specify another directory.

3.How can i load the trained network and supply new data that i want to test it with?

 load gregnet1
 newoutput = gregnet1(newinput);

Please Note: I want to be able to save the trained neural network such that when i run the code over and over again with the training data set,it gives same output. I have discovered that each time i run my code,it gives a different output which i do not want once i have an acceptable result.

 Then initialize the RNG to the same state before training to 
obtain reproducibility. See any of my training example posts.

Hope this helps.

Thank you for formally accepting my answer

Greg

[Greg Heath]

If you are just loading a trained net and using it on the same data, you should get the same answer.

Somewhere along the line either you net or your data is changing.

Can you tell us which it is?

Greg

[Omotayo Asiru]

Thanks for this explanation. I think my problem has been saving and loading the net because when i use save net,i really can not be sure of the network its loading as i have never used a unique name to save the network. I will work with your explanations above and feed you back on the outcome.

Please, how can i initialize RNG to same state to obtain reproductivity?

[Pierre Pook]

how do you specify a different directory to save the the network in ?

[Abhijit Bhattacharjee]

You can use a different syntax for the SAVE command:

outputDir = "path_to_dir";
outputFile = fullfile(outputDir, "net.mat");
save(outputFile, "net");

In the case above, net is the name of the network in the MATLAB workspace, and we are saving it to the location path_to_dir/net.mat.

Answer 2

[Pranab Das]

Hi ,

When im using save command i'm getting this error.

can you please give reference to debug this error

[Saeed Bello]

Simpply type

save(filename)

Then

load('filename.mat')

Remeber to include the file extension.

Answer 3

[Saeed Bello]

You get error while loading your saved net becuase your filename is not complete (undefined).

Don't forget that on your current folder, the filneame you save your net with has '.mat' file extension.

First save your net as:

save(gregnet1)

The correct way to load it again is

load('gregnet1.mat')

Hope this help.

Answer 4

[Greg Heath]

 save net ...
 ...

 load net

Hope this helps.

Thank you for formally accepting my answer

Greg

[Omotayo Asiru]

Thanks for your response but this has not answered my question.As i said in my question,i know you save net and load net can be used but my questions are: 1.At what point in my code will i put save net 2.Using save net;, which location on the system is the trained network saved? 3.How can i load the trained network and supply new data that i want to test it with? Please Note: I want to be able to save the trained neural network such that when i run the code over and over again with the training data set,it gives same output. I have discovered that each time i run my code,it gives a different output which i do not want once i have an acceptable result.

Answer 5

[Ayesha Zafar]

hello!

I am trying to save and load the net but when i test the net keeping train function in comment.It give error that is "Undefined function or variable 'gregnet1'. " Attached screenshot is explaining the problem

close all, clear all, clc, format compact,
img = imread('nn3.bmp');
% imshow(img);
% imgGray = rgb2gray(img);
% imgCrop = imcrop(imgGray);
% imshow(imgCrop);
% imgLGE=imresize(imgCrop,[7,5 ]);
% imshow(imgLGE);
% imgRTE = imrotate(imgLGE, 35);
% imshow(imgRTE);
% imgBW = im2bw(imgLGE, 0.90455);
% imshow(imgBW);
% imwrite(imgBW,'nine3.bmp');

 input  = imread('nine.bmp'); 
 corresponding target output vector
output=[ -1 -1 -1 -1 -1 -1 -1 -1 -1 1];
net = network( 1,1,0,1,0,1);
net.layers{1}.size = 10;
net.layers{1}.transferFcn = 'tansig';
net = configure(net,input(:),output(:));              
% net = init(net);
view(net);
initial_output = net(input(:))
net.trainFcn = 'traingd';   %the term “backpropagation” is sometimes used to refer specifically to the gradient descent algorithm,
[net,tr]= train(net,input(:),output(:));              %training record= tr
 final_output = net(input(:))
gregnet1 = net;
save gregnet1
%test
% output=sim(net,input(:))
load gregnet1
newoutput = gregnet1(input(:))

[Greg Heath]

1. After you train net, what are the training,validation and test subset error rates ???
2. tr = tr % = ?

Greg

Answer 6

[navid salimpour]

Hi omotayo-asiru, How are you?

did you solve this problem? i have same problem and i dont know how to solve that.

[Soong Yuan See]

i also have the same problem anyone pls help

[Nazila Pourhajy]

Hi everyone

It is better to use the following format to save the trained network:

save('filename.mat','net');

And for load trained network:

load('filename.mat','name of varaible for loading network in it');

for example : load('filename.mat','net1');

and predict with net1 in your program.

[Hargun Kaur]

Thanks, this works very nicely

Answer 7

[The Anh Vuong]

Hi , I would like to share with you this code, it is working in a different working environment.

First in your training program, after trainig save network

...

net1 = net
save ('your_reuse.mat', 'net1')

--.

Than create a new mlx : eg. reuse.mlx with a prediction for testimage.png and a Network with 4 precision-digits

load ('your_reuse.mat', 'net1')
filename = "testimage.png";
im = imread(filename);
I = imresize(im, [224 224]);
[label,scores] = classify(net1,I);
imshow(I)
title(string(filename)+ " typ: " +  string(label) + ", " + num2str(100*max(scores),4) + "%");

l