Struct NLLLossOptions¶
Defined in File loss.h
Page Contents
Struct Documentation¶
-
struct NLLLossOptions¶
Options for the
NLLLoss
module.Example:
NLLLoss model(NLLLossOptions().ignore_index(-100).reduction(torch::kMean));
Public Functions
-
inline auto weight(const Tensor &new_weight) -> decltype(*this)¶
A manual rescaling weight given to each class.
If given, it has to be a Tensor of size
C
. Otherwise, it is treated as if having all ones.
-
inline auto weight(Tensor &&new_weight) -> decltype(*this)¶
-
inline const Tensor &weight() const noexcept¶
-
inline Tensor &weight() noexcept¶
-
inline auto ignore_index(const int64_t &new_ignore_index) -> decltype(*this)¶
Specifies a target value that is ignored and does not contribute to the input gradient.
-
inline auto ignore_index(int64_t &&new_ignore_index) -> decltype(*this)¶
-
inline const int64_t &ignore_index() const noexcept¶
-
inline int64_t &ignore_index() 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 weight(const Tensor &new_weight) -> decltype(*this)¶