mlask::SoftMax Class Reference

class reprsenting Soft Max activation function, since the definition is to complex for activation function it derives from Layer More...

#include <SoftMax.hpp>

Inheritance diagram for mlask::SoftMax:

Collaboration diagram for mlask::SoftMax:

Public Member Functions
	SoftMax (std::size_t in=0)
	Construct a new SoftMax object.
vectorOut	forward (vectorIn) override
	softmax definition
vectorIn	backward (vectorOut) override
	derived version of softmax
void	fit (float_t learning_rate) override
	This does nothing, since softmax doesnt change.
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.

Detailed Description

class reprsenting Soft Max activation function, since the definition is to complex for activation function it derives from Layer

Constructor & Destructor Documentation

SoftMax()

mlask::SoftMax::SoftMax

(

std::size_t

in = 0

)

Construct a new SoftMax object.

Parameters

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

Member Function Documentation

backward()

vectorIn mlask::SoftMax::backward ( vectorOut  error )

overridevirtual

derived version of softmax

Implements mlask::Layer.

fit()

void mlask::SoftMax::fit ( float_t  learning_rate )

inlineoverridevirtual

This does nothing, since softmax doesnt change.

Implements mlask::Layer.

forward()

vectorOut mlask::SoftMax::forward ( vectorIn  input )

overridevirtual

softmax definition

Implements mlask::Layer.

str()

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

inlineoverridevirtual

Returns a string representation of the layer.

Reimplemented from mlask::Layer.

tryConvertToONNX()

bool mlask::SoftMax::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

Returns

True if the conversion was successful, false otherwise

Reimplemented from mlask::Layer.

---

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

• include/activation_functions/SoftMax.hpp
• src/activation_functions/SoftMax.cpp