Class HardSigmoid

Represents an element-wise HardSigmoid activation layer: f(x) = clamp(alpha * x + beta, 0, 1).

Inheritance

object

Layer

Activation

HardSigmoid

Inherited Members

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

Assembly: solution.dll

Syntax

[Serializable]
public class HardSigmoid : Activation

Constructors

Name	Description
HardSigmoid(string, string, float, float)	Initializes and returns an instance of HardSigmoid activation layer.

Fields

Name	Description
alpha	The alpha value to use for the HardSigmoid activation function.
beta	The beta value to use for the HardSigmoid activation function.

Methods

Name	Description
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.
ToString()	Returns a string that represents the Layer.