Class VarianceScaling

Initializer capable of adapting its scale to the shape of weights. With distribution = "normal", samples are drawn from a truncated normal distribution centered on zero, with stddev = sqrt(scale / n) where n is: number of input units in the weight tensor, if mode = "fan_in", number of output units, if mode = "fan_out", average of the numbers of input and output units, if mode = "fan_avg", With distribution = "uniform", samples are drawn from a uniform distribution within[-limit, limit], with limit = sqrt(3 * scale / n).

Inheritance

System.Object

Keras

Base

VarianceScaling

Implements

System.IDisposable

Inherited Members

Base.Parameters

Base.None

Base.Init()

Base.ToPython()

Base.InvokeStaticMethod(Object, String, Dictionary<String, Object>)

Base.InvokeMethod(String, Dictionary<String, Object>)

Base.Item[String]

Keras.Instance

Keras.keras

Keras.keras2onnx

Keras.tfjs

Keras.Dispose()

Keras.ToTuple(Array)

Keras.ToList(Array)

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Keras.Initializer

Assembly: Keras.dll

Syntax

public class VarianceScaling : Base, IDisposable

Constructors

VarianceScaling(Single, String, String, Nullable<Int32>)

Initializes a new instance of the VarianceScaling class.

Declaration

public VarianceScaling(float scale = 1F, string mode = "fan_in", string distribution = "normal", int? seed = default(int? ))

Parameters

Type	Name	Description
System.Single	scale	Scaling factor (positive float).
System.String	mode	One of "fan_in", "fan_out", "fan_avg".
System.String	distribution	Random distribution to use. One of "normal", "uniform".
System.Nullable<System.Int32>	seed	The seed number for random generator

Implements

System.IDisposable