Class MaxNorm

MaxNorm weight constraint. Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value.

Inheritance

System.Object

BaseConstraint

MaxNorm

Namespace: SiaNet.Constraints

Assembly: SiaNet.dll

Syntax

public class MaxNorm : BaseConstraint

Constructors

MaxNorm(Single, Int32)

Initializes a new instance of the MaxNorm class.

Declaration

public MaxNorm(float maxValue = 2F, int axis = 0)

Parameters

Type	Name	Description
System.Single	maxValue	The maximum norm for the incoming weights.
System.Int32	axis	Integer, axis along which to calculate weight norms.

Properties

Axis

Integer, axis along which to calculate weight norms. For instance, in a Dense layer the weight matrix has shape (input_dim, output_dim), set axis to 0 to constrain each weight vector of length (input_dim,). In a Conv2D layer, the weight tensor has shape (input_depth, output_depth, rows, cols), set axis to [1, 2, 3] to constrain the weights of each filter tensor of size (input_depth, rows, cols).

Declaration

public int Axis { get; set; }

Property Value

Type	Description
System.Int32

MaxValue

The maximum norm for the incoming weights.

Declaration

public float MaxValue { get; set; }

Property Value

Type	Description
System.Single