Borrar filtros
Borrar filtros

How can I freeze specific weights of Neural network model?

44 visualizaciones (últimos 30 días)
Abdelwahab Afifi
Abdelwahab Afifi el 14 de Jun. de 2020
Editada: Ahmad Gad el 25 de Ag. de 2021
I need to set some specific weights before training, and keep these weights fixed during training

Respuesta aceptada

Utkarsh
Utkarsh el 18 de Jun. de 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
  1 comentario
Ahmad Gad
Ahmad Gad el 25 de Ag. de 2021
Editada: Ahmad Gad el 25 de Ag. de 2021
Can I do the same for a shallow network? And using which function?

Iniciar sesión para comentar.

Más respuestas (0)

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Productos

Community Treasure Hunt

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

Start Hunting!

Translated by