mlpack 3.4.2
|
The empty loss does nothing, letting the user calculate the loss outside the model. More...
#include <empty_loss.hpp>
Public Member Functions | |
EmptyLoss () | |
Create the EmptyLoss object. More... | |
template<typename InputType , typename TargetType , typename OutputType > | |
void | Backward (const InputType &input, const TargetType &target, OutputType &output) |
Ordinary feed backward pass of a neural network. More... | |
template<typename InputType , typename TargetType > | |
double | Forward (const InputType &input, const TargetType &target) |
Computes the Empty loss function. More... | |
The empty loss does nothing, letting the user calculate the loss outside the model.
InputDataType | Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube). |
OutputDataType | Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube). |
Definition at line 35 of file empty_loss.hpp.
void Backward | ( | const InputType & | input, |
const TargetType & | target, | ||
OutputType & | output | ||
) |
Ordinary feed backward pass of a neural network.
input | The propagated input activation. |
target | The target vector. |
output | The calculated error. |
double Forward | ( | const InputType & | input, |
const TargetType & | target | ||
) |
Computes the Empty loss function.
input | Input data used for evaluating the specified function. |
target | The target vector. |