Struct TripletMarginLossOptions¶
Defined in File loss.h
Page Contents
Struct Documentation¶
-
struct TripletMarginLossOptions¶
Options for the
TripletMarginLoss
module.Example:
TripletMarginLoss model(TripletMarginLossOptions().margin(3).p(2).eps(1e-06).swap(false));
Public Functions
-
inline auto margin(const double &new_margin) -> decltype(*this)¶
Specifies the threshold for which the distance of a negative sample must reach in order to incur zero loss.
Default: 1
-
inline auto margin(double &&new_margin) -> decltype(*this)¶
-
inline const double &margin() const noexcept¶
-
inline double &margin() noexcept¶
-
inline auto p(const double &new_p) -> decltype(*this)¶
Specifies the norm degree for pairwise distance. Default: 2.
-
inline auto p(double &&new_p) -> decltype(*this)¶
-
inline const double &p() const noexcept¶
-
inline double &p() noexcept¶
-
inline auto eps(const double &new_eps) -> decltype(*this)¶
-
inline auto eps(double &&new_eps) -> decltype(*this)¶
-
inline const double &eps() const noexcept¶
-
inline double &eps() noexcept¶
-
inline auto swap(const bool &new_swap) -> decltype(*this)¶
The distance swap is described in detail in the paper Learning shallow convolutional feature descriptors with triplet losses by V.
Balntas, E. Riba et al. Default: False
-
inline auto swap(bool &&new_swap) -> decltype(*this)¶
-
inline const bool &swap() const noexcept¶
-
inline bool &swap() noexcept¶
-
inline auto reduction(const reduction_t &new_reduction) -> decltype(*this)¶
Specifies the reduction to apply to the output. Default: Mean.
-
inline auto reduction(reduction_t &&new_reduction) -> decltype(*this)¶
-
inline const reduction_t &reduction() const noexcept¶
-
inline reduction_t &reduction() noexcept¶
-
inline auto margin(const double &new_margin) -> decltype(*this)¶