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.

ParameterlessLayer

public protocol ParameterlessLayer : Layer where Self.TangentVector == EmptyTangentVector

A parameterless neural network layer.

The TangentVector of parameterless layers is always EmptyTangentVector.


                    
                    
                    callAsFunction(_:)

Declaration

@differentiable
func callAsFunction(_ input: Input) -> Output


                    
                    
                    move(along:)

Extension method

Declaration

public mutating mutating func move(along direction: EmptyTangentVector)


                    
                    
                    differentiableVectorView

Extension method

Declaration

public var differentiableVectorView: EmptyTangentVector { get }