Warning: This project is deprecated. Swift for TensorFlow was an experiment in the next-generation platform for machine learning, incorporating the latest research across machine learning, compilers, differentiable programming, systems design, and beyond. It was archived in February 2021.

GaussianNoise

public struct GaussianNoise<Scalar> : ParameterlessLayer where Scalar : TensorFlowFloatingPoint

GaussianNoise adds noise sampled from a normal distribution.

The noise added always has mean zero, but has a configurable standard deviation.


                    
                    
                    TangentVector

Declaration

public typealias TangentVector = EmptyTangentVector


                    
                    
                    standardDeviation

Declaration

@noDerivative
public let standardDeviation: Tensor<Scalar>


                    
                    
                    init(standardDeviation:)

Creates a Gaussian noise layer

Declaration

public init(standardDeviation: Scalar)

Parameters


                                standardDeviation

Standard deviation of the Guassian distribution


                    
                    
                    forward(_:)

Returns a tensor obtained by adding noise to input

Declaration

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