geopm::LocalNeuralNet Class Reference

Class to manage data and operations of feed forward neural nets required for neural net inference. More...

#include <LocalNeuralNet.hpp>

Inheritance diagram for geopm::LocalNeuralNet:

Public Member Functions
virtual	~LocalNeuralNet ()=default
virtual TensorOneD	forward (const TensorOneD &inp) const =0
	Perform inference using the instance weights and biases. More...
virtual size_t	get_input_dim () const =0
	Get the dimension required for the input TensorOneD. More...
virtual size_t	get_output_dim () const =0
	Get the dimension of the resulting TensorOneD. More...
TensorOneD	operator() (const TensorOneD &input) const

Static Public Member Functions
static std::unique_ptr< LocalNeuralNet >	make_unique (std::vector< std::shared_ptr< DenseLayer > > layers)
	Returns a unique_ptr to a concrete object constructed using the underlying implementation from a vector of DenseLayers. More...

Detailed Description

Class to manage data and operations of feed forward neural nets required for neural net inference.

Constructor & Destructor Documentation

~LocalNeuralNet()

virtual geopm::LocalNeuralNet::~LocalNeuralNet ( )

virtualdefault

Member Function Documentation

forward()

virtual TensorOneD geopm::LocalNeuralNet::forward ( const TensorOneD &  inp ) const

pure virtual

Perform inference using the instance weights and biases.

Parameters

[in]

TensorOneD

vector of input signals.

Exceptions

geopm::Exception

if input dimension is incompatible with network.

Returns

Returns a TensorOneD vector of output values.

Implemented in geopm::LocalNeuralNetImp.

get_input_dim()

virtual size_t geopm::LocalNeuralNet::get_input_dim ( ) const

pure virtual

Get the dimension required for the input TensorOneD.

Returns

Returns a size_t equal to the number of columns of weights

Implemented in geopm::LocalNeuralNetImp.

get_output_dim()

virtual size_t geopm::LocalNeuralNet::get_output_dim ( ) const

pure virtual

Get the dimension of the resulting TensorOneD.

Returns

Returns a size_t equal to the number of rows of weights

Implemented in geopm::LocalNeuralNetImp.

make_unique()

std::unique_ptr< LocalNeuralNet > geopm::LocalNeuralNet::make_unique ( std::vector< std::shared_ptr< DenseLayer > >  layers )

static

Returns a unique_ptr to a concrete object constructed using the underlying implementation from a vector of DenseLayers.

Parameters

[in]

Vector

of DenseLayers

operator()()

TensorOneD geopm::LocalNeuralNet::operator()

(

const TensorOneD &

input

)

const

---

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

• LocalNeuralNet.hpp
• LocalNeuralNet.cpp