getL2Factor
Get L2 regularization factor of layer learnable parameter
Syntax
Description
returns the L2 regularization factor
of the parameter with the name factor
= getL2Factor(layer
,parameterName
)parameterName
in
layer
.
For built-in layers, you can get the
L2 regularization factor directly
by using the corresponding property. For example, for a
convolution2dLayer
layer, the syntax factor =
getL2Factor(layer,'Weights')
is equivalent to factor =
layer.WeightL2Factor
.
returns the L2 regularization factor
of the parameter specified by the path factor
= getL2Factor(layer
,parameterPath
)parameterPath
. Use
this syntax when the layer is a networkLayer
or when the parameter is in a
dlnetwork
object in a custom layer.
returns the L2 regularization factor
of the parameter with the name factor
= getL2Factor(net
,layerName
,parameterName
)parameterName
in the layer
with name layerName
for the specified
dlnetwork
object.
returns the L2 regularization factor
of the parameter specified by the path factor
= getL2Factor(net
,parameterPath
)parameterPath
. Use
this syntax when the parameter is in a networkLayer
or when the parameter is in a
dlnetwork
object in a custom layer.
Examples
Set and Get Regularization Factor of Learnable Parameter
Set and get the regularization factor of a learnable parameter of a layer.
Create a layer array containing the custom layer sreluLayer
, attached to this example as a supporting file. To access this layer, open this example as a live script.
Create a layer array including a custom layer sreluLayer
.
layers = [ imageInputLayer([28 28 1]) convolution2dLayer(5,20) batchNormalizationLayer sreluLayer fullyConnectedLayer(10) softmaxLayer];
Set the regularization factor of the LeftSlope
learnable parameter of the sreluLayer
to 2.
layers(4) = setL2Factor(layers(4),"LeftSlope",2);
View the updated regularization factor.
factor = getL2Factor(layers(4),"LeftSlope")
factor = 2
Set and Get L2 Regularization Factor of Custom Nested Layer Learnable Parameter
Set and get the L2 regularization factor of a learnable parameter of a custom nested layer defined using network composition.
Create a residual block layer using the custom layer residualBlockLayer
attached to this example as a supporting file. To access this file, open this example as a Live Script.
numFilters = 64; layer = residualBlockLayer(numFilters)
layer = residualBlockLayer with properties: Name: '' Learnable Parameters Network: [1x1 dlnetwork] State Parameters Network: [1x1 dlnetwork] Use properties method to see a list of all properties.
View the layers of the nested network.
layer.Network.Layers
ans = 7x1 Layer array with layers: 1 'conv_1' 2-D Convolution 64 3x3 convolutions with stride [1 1] and padding 'same' 2 'batchnorm_1' Batch Normalization Batch normalization 3 'relu_1' ReLU ReLU 4 'conv_2' 2-D Convolution 64 3x3 convolutions with stride [1 1] and padding 'same' 5 'batchnorm_2' Batch Normalization Batch normalization 6 'add' Addition Element-wise addition of 2 inputs 7 'relu_2' ReLU ReLU
Set the L2 regularization factor of the learnable parameter 'Weights'
of the layer 'conv_1'
to 2 using the setL2Factor
function.
factor = 2;
layer = setL2Factor(layer,'Network/conv_1/Weights',factor);
Get the updated L2 regularization factor using the getL2Factor
function.
factor = getL2Factor(layer,'Network/conv_1/Weights')
factor = 2
Set and Get L2 Regularization Factor of dlnetwork
Learnable Parameter
Set and get the L2 regularization factor of a learnable parameter of a dlnetwork
object.
Specify the layers of the classification branch and add them to the network.
net = dlnetwork; layers = [ imageInputLayer([28 28 1],'Normalization','none','Name','in') convolution2dLayer(5,20,'Name','conv') batchNormalizationLayer('Name','bn') reluLayer('Name','relu') fullyConnectedLayer(10,'Name','fc') softmaxLayer('Name','sm')]; net = addLayers(net,layers);
Set the L2 regularization factor of the 'Weights'
learnable parameter of the convolution layer to 2 using the setL2Factor
function.
factor = 2; net = setL2Factor(net,'conv','Weights',factor);
Get the updated L2 regularization factor using the getL2Factor
function.
factor = getL2Factor(net,'conv','Weights')
factor = 2
Set and Get L2 Regularization Factor of Nested Layer Learnable Parameter
Create an array of layers containing an lstmLayer
with 100 hidden units and a dropoutLayer
with a dropout probability of 0.2.
layers = [lstmLayer(100,OutputMode="sequence",Name="lstm") dropoutLayer(0.2,Name="dropout")];
Create a network layer containing these layers.
lstmDropoutLayer = networkLayer(layers,Name="lstmDropout");
Use the network layer to build a network.
layers = [sequenceInputLayer(3) lstmDropoutLayer lstmDropoutLayer fullyConnectedLayer(10) softmaxLayer];
Create a dlnetwork
object. You can also create a dlnetwork
object by training the network using the trainnet
function.
net = dlnetwork(layers);
Set the L2 regularization factor of the InputWeights
learnable parameter of the LSTM layer in the first network layer to 2 using the setL2Factor
function.
factor = 2;
net = setL2Factor(net,"lstmDropout_1/lstm/InputWeights",factor);
Get the updated L2 regularization factor using the getL2Factor
function.
factor = getL2Factor(net,"lstmDropout_1/lstm/InputWeights")
factor = 2
Set and Get L2 Regularization Factor of Custom Nested dlnetwork
Learnable Parameter
Set and get the L2 regularization factor of a learnable parameter of a custom nested layer defined using network composition in a dlnetwork
object.
Create a dlnetwork
object containing the custom layer residualBlockLayer
attached to this example as a supporting file. To access this file, open this example as a Live Script.
inputSize = [224 224 3]; numFilters = 32; numClasses = 5; layers = [ imageInputLayer(inputSize,'Normalization','none','Name','in') convolution2dLayer(7,numFilters,'Stride',2,'Padding','same','Name','conv') groupNormalizationLayer('all-channels','Name','gn') reluLayer('Name','relu') maxPooling2dLayer(3,'Stride',2,'Name','max') residualBlockLayer(numFilters,'Name','res1') residualBlockLayer(numFilters,'Name','res2') residualBlockLayer(2*numFilters,'Stride',2,'IncludeSkipConvolution',true,'Name','res3') residualBlockLayer(2*numFilters,'Name','res4') residualBlockLayer(4*numFilters,'Stride',2,'IncludeSkipConvolution',true,'Name','res5') residualBlockLayer(4*numFilters,'Name','res6') globalAveragePooling2dLayer('Name','gap') fullyConnectedLayer(numClasses,'Name','fc') softmaxLayer('Name','sm')]; dlnet = dlnetwork(layers);
The Learnables
property of the dlnetwork
object is a table that contains the learnable parameters of the network. The table includes parameters of nested layers in separate rows. View the learnable parameters of the layer "res1"
.
learnables = dlnet.Learnables;
idx = learnables.Layer == "res1";
learnables(idx,:)
ans=8×3 table
Layer Parameter Value
______ ____________________________ ___________________
"res1" "Network/conv_1/Weights" {3x3x32x32 dlarray}
"res1" "Network/conv_1/Bias" {1x1x32 dlarray}
"res1" "Network/batchnorm_1/Offset" {1x1x32 dlarray}
"res1" "Network/batchnorm_1/Scale" {1x1x32 dlarray}
"res1" "Network/conv_2/Weights" {3x3x32x32 dlarray}
"res1" "Network/conv_2/Bias" {1x1x32 dlarray}
"res1" "Network/batchnorm_2/Offset" {1x1x32 dlarray}
"res1" "Network/batchnorm_2/Scale" {1x1x32 dlarray}
For the layer "res1"
, set the L2 regularization factor of the learnable parameter 'Weights'
of the layer 'conv_1'
to 2 using the setL2Factor
function.
factor = 2;
dlnet = setL2Factor(dlnet,'res1/Network/conv_1/Weights',factor);
Get the updated L2 regularization factor using the getL2Factor
function.
factor = getL2Factor(dlnet,'res1/Network/conv_1/Weights')
factor = 2
Input Arguments
layer
— Input layer
scalar Layer
object
Input layer, specified as a scalar Layer
object.
parameterName
— Parameter name
character vector | string scalar
Parameter name, specified as a character vector or a string scalar.
parameterPath
— Path to parameter in nested layer
string scalar | character vector
Path to parameter in nested layer, specified as a string scalar or a character vector.
A nested layer can be a layer within a networkLayer
or a custom layer that itself defines a neural network as a learnable parameter.
If the input to getL2Factor
is a layer, then:
If the nested layer is in a network layer, the parameter path has the form
"nestedLayerName/parameterName"
wherenestedlayerName
is the name of the nested layer inside the network layer, andparameterName
is the name of the parameter. If there are multiple levels of nested layers, then specify the path using the formnestedLayerName1/.../nestedLayerNameN/parameterName
.If the nested layer is a custom layer that itself defines a neural network as a learnable parameter, the parameter path has the form
"propertyName/layerName/parameterName"
wherepropertyName
is the name of the property containing adlnetwork
object,layerName
is the name of the layer in thedlnetwork
object, andparameterName
is the name of the parameter. If there are multiple levels of nested layers, then specify the path using the form"propertyName1/layerName1/.../propertyNameN/layerNameN/parameterName"
.
If the input to getL2Factor
is a dlnetwork
object and the desired parameter is in a nested layer, then:
If the nested layer is in a network layer, the parameter path has the form
"networkLayerName/nestedLayerName/parameterName"
wherenetworkLayerName
is the name of the network layer,nestedlayerName
is the name of the nested layer inside the network layer, andparameterName
is the name of the parameter. If there are multiple levels of nested layers, then specify the path using the form"networkLayerName1/.../networkLayerNameN/nestedLayerName/parameterName"
.If the nested layer is a custom layer that itself defines a neural network as a learnable parameter, the parameter path has the form
"customLayerName1/propertyName/layerName/parameterName"
, wherelayerName1
is the name of the layer in the inputdlnetwork
object,propertyName
is the name of the property of the layer containing adlnetwork
object,layerName
is the name of the layer in thedlnetwork
object, andparameterName
is the name of the parameter. If there are multiple levels of nested layers, then specify the path using the form"customLayerName1/propertyName1/.../customLayerNameN/propertyNameN/layerName/parameterName"
.
Data Types: char
| string
net
— Neural network
dlnetwork
object
Neural network, specified as a dlnetwork
object.
layerName
— Layer name
string scalar | character vector
Layer name, specified as a string scalar or a character vector.
Data Types: char
| string
Output Arguments
factor
— L2 regularization
factor
nonnegative scalar
L2 regularization factor for the parameter, returned as a nonnegative scalar.
The software multiplies this factor by the global
L2 regularization factor
to determine the L2 regularization
for the specified parameter. For example, if factor
is
2
, then the
L2 regularization for the
specified parameter is twice the current global
L2 regularization. The
software determines the global L2
regularization based on the settings specified with the trainingOptions
function.
Version History
Introduced in R2017bR2024a: Specify Path to Parameter in Network Layer
Specify the path to a parameter in a networkLayer
using the parameterPath
argument.
Commande MATLAB
Vous avez cliqué sur un lien qui correspond à cette commande MATLAB :
Pour exécuter la commande, saisissez-la dans la fenêtre de commande de MATLAB. Les navigateurs web ne supportent pas les commandes MATLAB.
Select a Web Site
Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .
You can also select a web site from the following list:
How to Get Best Site Performance
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.
Americas
- América Latina (Español)
- Canada (English)
- United States (English)
Europe
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)