Show / Hide Table of Contents

Class Softsign

The softsign activation: x / (abs(x) + 1).

Inheritance
System.Object
BaseLayer
Softsign
Inherited Members
BaseLayer.Params
BaseLayer.Input
BaseLayer.Output
BaseLayer.Name
BaseLayer.SkipPred
BaseLayer.Item[String]
BaseLayer.BuildParam(String, Int64[], DataType, BaseInitializer, BaseConstraint, BaseRegularizer, Boolean)
Namespace: SiaNet.Layers.Activations
Assembly: SiaNet.dll
Syntax
public class Softsign : BaseLayer

Constructors

| Improve this Doc View Source

Softsign()

Initializes a new instance of the Softsign class.

Declaration
public Softsign()

Methods

| Improve this Doc View Source

Backward(Tensor)

Calculate the gradient of this layer function

Declaration
public override void Backward(Tensor outputgrad)
Parameters
Type Name Description
Tensor outputgrad

The calculated output grad from previous layer.

Overrides
BaseLayer.Backward(Tensor)
| Improve this Doc View Source

Forward(Tensor)

Forwards the inputs and compute the output

Declaration
public override void Forward(Tensor x)
Parameters
Type Name Description
Tensor x

The input tensor for this layer.

Overrides
BaseLayer.Forward(Tensor)

See Also

BaseLayer
  • Improve this Doc
  • View Source
Back to top Generated by DocFX