# How can I extract the values of weights and biases after each training epoch?

15 views (last 30 days)

Show older comments

##### 1 Comment

Image Analyst
on 19 Jul 2015

### Answers (3)

Nick Hobbs
on 21 Jul 2015

I am going to assume you are referring to the Neural Network Toolbox due to your reference to weights, biases, and epochs. One way to see the weights after every epoch is to set the network to only train one epoch at a time, and then to use the 'getwb' command. The following code is an example on how to do this with a sample dataset and a feedforward network.

[x,t] = simplefit_dataset;

net = feedforwardnet(20);

net.trainParam.epochs = 1;

weights = []

for i = 1:10

net = train(net,x,t);

weights = [weights getwb(net)]

end

You can also save this matrix instead of printing it out. Do note, however, if you use this method your performance plot, and others, will only appear for the last epoch. So you may need to create your own function to monitor the validation and test data. You will also need to determine when to stop training using a function of your own design.

##### 2 Comments

Greg Heath
on 23 Jul 2015

Another problem is that every time train is called, certain internal parameters (mu?) are reinitialized. Therefore, you will not get the same final set of weights as if you just used one call of train.

I recall saving the aforementioned parameters at the end of every epoch and using them to reinitialize train so that the training was equivalent to not stopping every epoch. Unfortunately I don't remember the name or date of the post.

Salman Habib
on 7 Apr 2017

Hi Greg, I am trying to train a neural network using for loop, 1 epoch at at time, and I want matlab to continue training with the weights and biases from the previous training. Is there any way to save the weights during the current iteration of the loop, and use them to initialize the neural network weights and biases in the next loop iteration ? That is, I want the number of epochs to be the same as the number of iterations of the for loop (say N), and call the training function N times.

Thank you in advance.

Mark Hudson Beale
on 24 Jul 2015

Greg is right, the function to get weights outside of a training function is getwb.

Within a training function it is slightly different. In recent versions of the Neural Network Toolbox, each training function has a trainingIteration helper function. (I.e. edit trainlm for an example.) And within a training function the most reliable way to get weights is calcLib.getwb(calcNet). (Also, see trainlm code for example of this being used.)

So you might insert the following code snippet at the end of trainingIteration in trainlm to get and save a record of the weights in a workspace variable "weightRecord".

try

wr = evalin('base','weightRecord');

catch

wr = {};

end

wr{end+1} = calcLib.getwb(calcNet);

assignin('base','weightRecord',wr);

If you then train with TRAINLM you can get the weight record in the base workspace:

>> [x,t] = house_dataset;

>> net = feedforwardnet(10,'trainlm'); % Has 151 weights and biases

>> net = train(net,x,t);

>> weightRecord

weightRecord =

Columns 1 through 4

[151x1 double] [151x1 double] [151x1 double] ...

##### 1 Comment

Zheng Chai
on 18 Dec 2017

Salma Hassan
on 23 Jan 2018

Edited: Salma Hassan
on 23 Jan 2018

this option 'CheckpointPath' in trainoptions function save the parameters value after each epoch

##### 1 Comment

Andrea Daou
on 18 Aug 2020

Hello,

After using 'CheckpointPath', many .mat files will be saved. How can I visualize the parameters ?

### See Also

### Categories

### Community Treasure Hunt

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

Start Hunting!