Struct NLLLossOptions

• Defined in File loss.h

Struct Documentation

struct NLLLossOptions

Options for the NLLLoss module.

Example:

NLLLoss model(NLLLossOptions().ignore_index(-100).reduction(torch::kMean));

Public Types

typedef std::variant<enumtype::kNone, enumtype::kMean, enumtype::kSum> reduction_t

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