MATLAB Answers

How can I freeze specific weights of Neural network model?

44 views (last 30 days)
Abdelwahab Afifi
Abdelwahab Afifi on 14 Jun 2020
Answered: Utkarsh on 18 Jun 2020
I need to set some specific weights before training, and keep these weights fixed during training

  0 Comments

Sign in to comment.

Accepted Answer

Utkarsh
Utkarsh on 18 Jun 2020
Hi Abdelwahab,
If you wish to assign those weights in the beginning and keep them as constant, you can set the ‘WeightLearnRateFactor’ property as 0 (which defines the learning rate for that layer) for those layers.
For example,
convolution2dLayer(3,1,'Padding',[1 1 1 1],'WeightLearnRateFactor',0);
You may refer to this link to learn more about such properties.
Or if you want to fix certain weights to some layers in a trained network , then directly assign those layers the values after training the network.
net = alexnet; % or your pre-trained network
layer = net.Layers(1) % here 1 can be replaced with the layer number you wish to change
layer.Weights = randn(11,11,3,96); %the weight matrix which you wish to assign

  0 Comments

Sign in to comment.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!