Struct CTCLossOptions¶
Defined in File loss.h
Page Contents
Struct Documentation¶
-
struct CTCLossOptions¶
Options for the
CTCLoss
module.Example:
CTCLoss model(CTCLossOptions().blank(42).zero_infinity(false).reduction(torch::kSum));
Public Functions
-
inline auto blank(const int64_t &new_blank) -> decltype(*this)¶
blank label. Default
0
.
-
inline auto blank(int64_t &&new_blank) -> decltype(*this)¶
-
inline const int64_t &blank() const noexcept¶
-
inline int64_t &blank() 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 zero_infinity(const bool &new_zero_infinity) -> decltype(*this)¶
Whether to zero infinite losses and the associated gradients.
Default:
false
. Infinite losses mainly occur when the inputs are too short to be aligned to the targets.
-
inline auto zero_infinity(bool &&new_zero_infinity) -> decltype(*this)¶
-
inline const bool &zero_infinity() const noexcept¶
-
inline bool &zero_infinity() noexcept¶
-
inline auto blank(const int64_t &new_blank) -> decltype(*this)¶