Class RandomNormal

Represents a RandomNormal random layer. This generates an output tensor of a given shape with random values in a normal distribution with given mean and scale, and an optional seed value.

Inheritance

Object

Layer

RandomLayer

RandomNormal

Inherited Members

RandomLayer.hasSeed

RandomLayer.seed

RandomLayer.NextSeed

RandomLayer.ResetSeed()

Layer.inputs

Layer.name

Layer.outputs

Layer.flags

Object.Equals(Object)

Object.Equals(Object, Object)

Object.ReferenceEquals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Namespace: Unity.Sentis.Layers

Syntax

[Serializable]
public class RandomNormal : RandomLayer

Constructors

RandomNormal(String, Int32[], Single, Single, Nullable<Single>)

Initializes and returns an instance of RandomNormal random layer.

Declaration

public RandomNormal(string name, int[] shape, float mean, float scale, float? seed)

Parameters

Type	Name	Description
String	name	The name to use for the output tensor of the layer.
Int32[]	shape	The shape for the output tensor as an array of ints.
Single	mean	The mean of the normal distribution used to generate the output.
Single	scale	The standard deviation of the normal distribution used to generate the output.
Nullable<Single>	seed	The optional seed to use for the random number generation. If this is null the layer generates a seed using System.Random().

Fields

mean

The mean of the normal distribution used to generate the output.

Declaration

public float mean

Field Value

Type	Description
Single

scale

The standard deviation of the normal distribution used to generate the output.

Declaration

public float scale

Field Value

Type	Description
Single

shape

The shape for the output tensor as a TensorShape.

Declaration

public TensorShape shape

Field Value

Type	Description
TensorShape

Methods

Execute(Tensor[], ExecutionContext)

Executes the layer using the operations and variables from the ExecutionContext and returns the output tensor.

If the layer has more than one output, output tensors are saved to variables.

Declaration

public override Tensor Execute(Tensor[] inputTensors, ExecutionContext ctx)

Parameters

Type	Name	Description
Tensor[]	inputTensors
ExecutionContext	ctx

Returns

Type	Description
Tensor

Overrides

Layer.Execute(Tensor[], ExecutionContext)

ToString()

Returns a string that represents the Layer.

Declaration

public override string ToString()

Returns

Type	Description
String

Overrides

Layer.ToString()