Struct CTCLossImpl¶
Defined in File loss.h
Page Contents
Inheritance Relationships¶
Base Type¶
public torch::nn::Cloneable< CTCLossImpl >
(Template Class Cloneable)
Struct Documentation¶
-
struct CTCLossImpl : public torch::nn::Cloneable<CTCLossImpl>¶
The Connectionist Temporal Classification loss.
See https://pytorch.org/docs/main/nn.html#torch.nn.CTCLoss to learn about the exact behavior of this module.
See the documentation for
torch::nn::CTCLossOptions
class to learn what constructor arguments are supported for this module.Example:
CTCLoss model(CTCLossOptions().blank(42).zero_infinity(false).reduction(torch::kSum));
Public Functions
-
explicit CTCLossImpl(CTCLossOptions options_ = {})¶
-
virtual void reset() override¶
reset()
must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.
-
virtual void pretty_print(std::ostream &stream) const override¶
Pretty prints the
CTCLoss
module into the givenstream
.
-
Tensor forward(const Tensor &log_probs, const Tensor &targets, const Tensor &input_lengths, const Tensor &target_lengths)¶
Public Members
-
CTCLossOptions options¶
The options with which this
Module
was constructed.
-
explicit CTCLossImpl(CTCLossOptions options_ = {})¶