Layer representing Relu activation function. More...

#include <Relu.hpp>

Inheritance diagram for mlask::Relu:

[legend]

Collaboration diagram for mlask::Relu:

[legend]

Public Member Functions
	Relu (std::size_t in=0)
	Construct a new Relu object.

bool	tryConvertToONNX (onnx::GraphProto *graph, std::string input, std::string output) const override
	Try to convert the layer to ONNX format.

std::string	str () const override
	Returns a string representation of the layer.

Public Member Functions inherited from mlask::ActivationFunction
vectorOut	forward (vectorIn) override
	Defines a way to move forward in a neural network.

vectorIn	backward (vectorOut) override
	Defines a way to backpropagate error in backropagation algorithm.

void	fit (float_t learning_rate) override
	Describes how the layer 'learns', meaning it defines how layer updates itself.

Public Member Functions inherited from mlask::Layer
std::size_t	getIn () const

std::size_t	getOut () const

virtual	~Layer ()=default

Additional Inherited Members
Protected Attributes inherited from mlask::Layer
std::size_t	in_

std::size_t	out_

Detailed Description

Layer representing Relu activation function.

Constructor & Destructor Documentation

mlask::Relu::Relu ( std::size_t in = 0 )

Construct a new Relu object.

Parameters

in	Number of inputs to the layer, default is 0, meaning it can be any size

std::string mlask::Relu::str ( ) const

inlineoverridevirtual

Returns a string representation of the layer.

bool mlask::Relu::tryConvertToONNX	(	onnx::GraphProto *	graph,
		std::string	input,
		std::string	output
	)		const

overridevirtual

Try to convert the layer to ONNX format.

Parameters

graph	ONNX graph to which the layer should be added
input	Name of the input tensor
output	Name of the output tensor

Reimplemented from mlask::Layer.

The documentation for this class was generated from the following files: