How can I freeze specific weights of Neural network model?

Question

Abdelwahab Afifi 2020-6-14

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/548100-how-can-i-freeze-specific-weights-of-neural-network-model

编辑： Ahmad Gad ，2021-8-25

采纳的回答： Utkarsh ，

I need to set some specific weights before training, and keep these weights fixed during training

0 个评论
显示 -1更早的评论隐藏 -1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

Utkarsh 2020-6-18

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/548100-how-can-i-freeze-specific-weights-of-neural-network-model#answer_453111

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 