Dropout

@frozen
public struct Dropout<Scalar> : ParameterlessLayer where Scalar : TensorFlowFloatingPoint

A dropout layer.

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


                    
                    
                    probability

@noDerivative
public let probability: Double


                    
                    
                    init(probability:)

Creates a dropout layer.

Precondition

probability must be a value between 0 and 1 (inclusive).

public init(probability: Double)


                                probability

The drop probability.


                    
                    
                    callAsFunction(_:)

Returns the output obtained from applying the layer to the given input.

@differentiable
public func callAsFunction(_ input: Tensor<Scalar>) -> Tensor<Scalar>


                                input

The input to the layer.

The output.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2019-12-09.