Class TransformerEncoderImpl¶
Defined in File transformercoder.h
Page Contents
Inheritance Relationships¶
Base Type¶
public torch::nn::Cloneable< TransformerEncoderImpl >
(Template Class Cloneable)
Class Documentation¶
-
class TransformerEncoderImpl : public torch::nn::Cloneable<TransformerEncoderImpl>¶
TransformerEncoder module.
See https://pytorch.org/docs/main/generated/torch.nn.TransformerEncoder.html to learn abouut the exact behavior of this encoder layer module.
See the documentation for
torch::nn::TransformerEncoder
class to learn what constructor arguments are supported for this encoder module.Example:
TransformerEncoderLayer encoderLayer(TransformerEncoderLayerOptions(512, 8).dropout(0.1)); TransformerEncoder encoder(TransformerEncoderOptions(encoderLayer, 6).norm(LayerNorm(LayerNormOptions({2}))));
Public Functions
-
inline TransformerEncoderImpl(TransformerEncoderLayer encoder_layer, int64_t num_layers)¶
-
explicit TransformerEncoderImpl(TransformerEncoderOptions options_)¶
-
Tensor forward(const Tensor &src, const Tensor &src_mask = {}, const Tensor &src_key_padding_mask = {})¶
-
virtual void reset() override¶
reset()
must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.
-
void reset_parameters()¶
Public Members
-
TransformerEncoderOptions options¶
options with which this
TransformerEncoder
was constructed
-
ModuleList layers = nullptr¶
module list that contains all the encoder 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 TransformerEncoderImpl(TransformerEncoderLayer encoder_layer, int64_t num_layers)¶