Layer defines the layout of a layer.
Layer defines the layout of a specific layer in the DNN Objects of this class don't hold the layer data itself (see class "LayerData")
Definition at line 672 of file NeuralNet.h.
Public Member Functions | |
Layer (size_t numNodes, EnumFunction activationFunction, ModeOutputValues eModeOutputValues=ModeOutputValues::DIRECT) | |
c'tor for defining a Layer | |
std::shared_ptr< std::function< double(double)> > | activationFunction () const |
fetch the activation function for this layer | |
EnumFunction | activationFunctionType () const |
get the activation function type for this layer | |
std::shared_ptr< std::function< double(double)> > | inverseActivationFunction () const |
fetch the inverse activation function for this layer | |
ModeOutputValues | modeOutputValues () const |
get the mode-output-value (direct, probabilities) | |
void | modeOutputValues (ModeOutputValues eModeOutputValues) |
set the mode-output-value | |
size_t | numNodes () const |
return the number of nodes of this layer | |
size_t | numWeights (size_t numInputNodes) const |
return the number of weights for this layer (fully connected) | |
Private Attributes | |
std::shared_ptr< std::function< double(double)> > | m_activationFunction |
stores the activation function | |
EnumFunction | m_activationFunctionType |
ModeOutputValues | m_eModeOutputValues |
do the output values of this layer have to be transformed somehow (e.g. to probabilities) or returned as such | |
std::shared_ptr< std::function< double(double)> > | m_inverseActivationFunction |
stores the inverse activation function | |
size_t | m_numNodes |
Friends | |
class | Net |
#include <TMVA/NeuralNet.h>
TMVA::DNN::Layer::Layer | ( | size_t | numNodes, |
EnumFunction | activationFunction, | ||
ModeOutputValues | eModeOutputValues = ModeOutputValues::DIRECT ) |
c'tor for defining a Layer
Definition at line 166 of file NeuralNet.cxx.
|
inline |
fetch the activation function for this layer
Definition at line 688 of file NeuralNet.h.
|
inline |
get the activation function type for this layer
Definition at line 691 of file NeuralNet.h.
|
inline |
fetch the inverse activation function for this layer
Definition at line 689 of file NeuralNet.h.
|
inline |
get the mode-output-value (direct, probabilities)
Definition at line 682 of file NeuralNet.h.
|
inline |
set the mode-output-value
Definition at line 683 of file NeuralNet.h.
|
inline |
return the number of nodes of this layer
Definition at line 685 of file NeuralNet.h.
|
inline |
return the number of weights for this layer (fully connected)
Definition at line 686 of file NeuralNet.h.
Definition at line 705 of file NeuralNet.h.
stores the activation function
Definition at line 696 of file NeuralNet.h.
|
private |
Definition at line 703 of file NeuralNet.h.
|
private |
do the output values of this layer have to be transformed somehow (e.g. to probabilities) or returned as such
Definition at line 702 of file NeuralNet.h.
|
private |
stores the inverse activation function
Definition at line 697 of file NeuralNet.h.
|
private |
Definition at line 700 of file NeuralNet.h.