Class TransformerDecoderImpl¶
Defined in File transformercoder.h
Page Contents
Inheritance Relationships¶
Base Type¶
public torch::nn::Cloneable< TransformerDecoderImpl >
(Template Class Cloneable)
Class Documentation¶
-
class TransformerDecoderImpl : public torch::nn::Cloneable<TransformerDecoderImpl>¶
TransformerDecoder is a stack of N decoder layers.
See https://pytorch.org/docs/main/generated/torch.nn.TransformerDecoder.html to learn abouut the exact behavior of this decoder module
See the documentation for
torch::nn::TransformerDecoderOptions
class to learn what constructor arguments are supported for this decoder moduleExample:
TransformerDecoderLayer decoder_layer(TransformerDecoderLayerOptions(512, 8).dropout(0.1)); TransformerDecoder transformer_decoder(TransformerDecoderOptions(decoder_layer, 6).norm(LayerNorm(LayerNormOptions({2})))); const auto memory = torch::rand({10, 32, 512}); const auto tgt = torch::rand({20, 32, 512}); auto out = transformer_decoder(tgt, memory);
Public Functions
-
inline TransformerDecoderImpl(TransformerDecoderLayer decoder_layer, int64_t num_layers)¶
-
explicit TransformerDecoderImpl(TransformerDecoderOptions options_)¶
-
virtual void reset() override¶
reset()
must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.
-
void reset_parameters()¶
-
Tensor forward(const Tensor &tgt, const Tensor &memory, const Tensor &tgt_mask = {}, const Tensor &memory_mask = {}, const Tensor &tgt_key_padding_mask = {}, const Tensor &memory_key_padding_mask = {})¶
Pass the inputs (and mask) through the decoder layer in turn.
Args: tgt: the sequence to the decoder layer (required). memory: the sequence from the last layer of the encoder (required). tgt_mask: the mask for the tgt sequence (optional). memory_mask: the mask for the memory sequence (optional). tgt_key_padding_mask: the mask for the tgt keys per batch (optional). memory_key_padding_mask: the mask for the memory keys per batch (optional).
Public Members
-
TransformerDecoderOptions options¶
The options used to configure this module.
-
ModuleList layers = {nullptr}¶
Cloned layers of decoder layers.
Protected Functions
-
inline virtual bool _forward_has_default_args() override¶
The following three functions allow a module with default arguments in its forward method to be used in a Sequential module.
You should NEVER override these functions manually. Instead, you should use the
FORWARD_HAS_DEFAULT_ARGS
macro.
-
inline virtual unsigned int _forward_num_required_args() override¶
Friends
- friend struct torch::nn::AnyModuleHolder
-
inline TransformerDecoderImpl(TransformerDecoderLayer decoder_layer, int64_t num_layers)¶