Class Dropout

Applies Dropout to the input. Dropout consists in randomly setting a fraction rate of input units to 0 at each update during training time, which helps prevent overfitting.

Inheritance
System.Object
BaseLayer
Dropout
Inherited Members
Namespace: SiaNet.Layers
Assembly: SiaNet.dll
Syntax
public class Dropout : BaseLayer

Constructors

| Improve this Doc View Source

Dropout(Single)

Initializes a new instance of the Dropout class.

Declaration
public Dropout(float rate)
Parameters
Type Name Description
System.Single rate

float between 0 and 1. Fraction of the input units to drop..

Properties

| Improve this Doc View Source

Rate

float between 0 and 1. Fraction of the input units to drop.

Declaration
public float Rate { get; set; }
Property Value
Type Description
System.Single

The rate.

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
| 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

See Also