Class RandomLayer

Represents the abstract base class for layers which generate random values in the output tensor.

Inheritance

Object

Layer

RandomLayer

Bernoulli

Multinomial

RandomNormal

RandomNormalLike

RandomUniform

RandomUniformLike

Inherited Members

Layer.inputs

Layer.name

Layer.outputs

Layer.flags

Layer.Execute(Tensor[], ExecutionContext)

Layer.ToString()

Object.Equals(Object)

Object.Equals(Object, Object)

Object.ReferenceEquals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Namespace: Unity.Sentis.Layers

Syntax

[Serializable]
public abstract class RandomLayer : Layer

Constructors

RandomLayer(Nullable<Single>)

Declaration

protected RandomLayer(float? seed)

Parameters

Type	Name	Description
Nullable<Single>	seed

Fields

hasSeed

Whether the layer has a provided seed value for the random number generator.

Declaration

public bool hasSeed

Field Value

Type	Description
Boolean

seed

The seed value for the random number generator. The layer does not use this value if hasSeed is false.

Declaration

public float seed

Field Value

Type	Description
Single

Properties

NextSeed

Declaration

protected float NextSeed { get; }

Property Value

Type	Description
Single

Methods

ResetSeed()

Resets the state of the random number generator to its initial state.

If hasSeed is false then the random number generator is seeded by System.Random().

Declaration

public void ResetSeed()