dl::loss::BCELoss< T > Class Template Reference

Binary Cross Entropy Loss with autograd support. More...

#include <losses.hpp>

Inheritance diagram for dl::loss::BCELoss< T >:

Collaboration diagram for dl::loss::BCELoss< T >:

Public Member Functions
	BCELoss (const std::string &reduction="mean")
	Constructor.
Variable< T >	forward (const Variable< T > &predictions, const Variable< T > &targets) override
	Forward pass: compute binary cross entropy loss.
Public Member Functions inherited from dl::loss::AutogradLoss< T >
virtual	~AutogradLoss ()=default
Variable< T >	operator() (const Variable< T > &predictions, const Variable< T > &targets)
	Convenience operator for computing loss.

Detailed Description

template<typename T>
class dl::loss::BCELoss< T >

Binary Cross Entropy Loss with autograd support.

BCE(y_pred, y_true) = -[y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred)]

Commonly used for binary classification.

Definition at line 121 of file losses.hpp.

Constructor & Destructor Documentation

BCELoss()

template<typename T >

dl::loss::BCELoss< T >::BCELoss ( const std::string &  reduction = "mean" )

inlineexplicit

Constructor.

Parameters

reduction

Type of reduction ('mean', 'sum', 'none')

Definition at line 127 of file losses.hpp.

Member Function Documentation

forward()

template<typename T >

Variable< T > dl::loss::BCELoss< T >::forward ( const Variable< T > &  predictions, const Variable< T > &  targets  )

overridevirtual

Forward pass: compute binary cross entropy loss.

Parameters

predictions	Predicted probabilities (after sigmoid)
targets	Binary target values (0 or 1)

Returns

BCE loss

Implements dl::loss::AutogradLoss< T >.

Definition at line 86 of file losses.cpp.

---

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

• include/loss/losses.hpp
• src/loss/losses.cpp