org.bytedeco.pytorch

Class TransformerDecoderLayerImpl

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.pytorch.Module

org.bytedeco.pytorch.TransformerDecoderLayerImplCloneable

org.bytedeco.pytorch.TransformerDecoderLayerImpl

All Implemented Interfaces:

AutoCloseable

@Namespace(value="torch::nn")
 @NoOffset
 @Properties(inherit=torch.class)
public class TransformerDecoderLayerImpl
extends TransformerDecoderLayerImplCloneable

TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network. This standard decoder layer is based on the paper "Attention Is All You Need". Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000-6010. Users may modify or implement in a different way during application. See https://pytorch.org/docs/master/nn.html#transformer-layers to learn about the exact behavior of this module. See the documentation for torch::nn::TransformerDecoderLayerOptions class to learn what constructor arguments are supported for this module. Example:

  TransformerDecoderLayer model(TransformerDecoderLayerOptions(512,
  8).dropout(0.2));
  

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
TransformerDecoderLayerImpl(long d_model, long nhead)
TransformerDecoderLayerImpl(Module pointer) Downcast constructor.
TransformerDecoderLayerImpl(Pointer p) Pointer cast constructor.
TransformerDecoderLayerImpl(TransformerDecoderLayerOptions options_)

Method Summary

Modifier and Type	Method and Description
Tensor	forward(Tensor tgt, Tensor memory)
Tensor	forward(Tensor tgt, Tensor memory, Tensor tgt_mask, Tensor memory_mask, Tensor tgt_key_padding_mask, Tensor memory_key_padding_mask) Pass the inputs (and mask) through the decoder layer.
TransformerDecoderLayerOptions	options() The options used to configure this module.
TransformerDecoderLayerImpl	options(TransformerDecoderLayerOptions setter)
void	reset_parameters()
void	reset() reset() must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.

Methods inherited from class org.bytedeco.pytorch.TransformerDecoderLayerImplCloneable

asModule, asModule, clone, clone

Methods inherited from class org.bytedeco.pytorch.Module

apply, apply, apply, apply, apply, apply, apply, apply, buffers, buffers, children, eval, is_serializable, is_training, load, modules, modules, name, named_buffers, named_buffers, named_children, named_modules, named_modules, named_modules, named_parameters, named_parameters, parameters, parameters, pretty_print, register_buffer, register_buffer, register_module, register_module, register_parameter, register_parameter, register_parameter, register_parameter, save, shiftLeft, to, to, to, train, unregister_module, unregister_module, zero_grad

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

TransformerDecoderLayerImpl

public TransformerDecoderLayerImpl(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

TransformerDecoderLayerImpl

public TransformerDecoderLayerImpl(Module pointer)

Downcast constructor.

TransformerDecoderLayerImpl

public TransformerDecoderLayerImpl(@Cast(value="int64_t")
                                   long d_model,
                                   @Cast(value="int64_t")
                                   long nhead)

TransformerDecoderLayerImpl

public TransformerDecoderLayerImpl(@ByVal
                                   TransformerDecoderLayerOptions options_)

Method Detail

reset

public void reset()

Description copied from class: TransformerDecoderLayerImplCloneable

reset() must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.

Overrides:

reset in class TransformerDecoderLayerImplCloneable

reset_parameters

public void reset_parameters()

forward

@ByVal
public Tensor forward(@ByVal
                             Tensor tgt,
                             @Const @ByRef
                             Tensor memory,
                             @Const @ByRef(nullValue="torch::Tensor{}")
                             Tensor tgt_mask,
                             @Const @ByRef(nullValue="torch::Tensor{}")
                             Tensor memory_mask,
                             @Const @ByRef(nullValue="torch::Tensor{}")
                             Tensor tgt_key_padding_mask,
                             @Const @ByRef(nullValue="torch::Tensor{}")
                             Tensor memory_key_padding_mask)

Pass the inputs (and mask) through the decoder layer. 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).

forward

@ByVal
public Tensor forward(@ByVal
                             Tensor tgt,
                             @Const @ByRef
                             Tensor memory)

options

@ByRef
public TransformerDecoderLayerOptions options()

The options used to configure this module.

options

public TransformerDecoderLayerImpl options(TransformerDecoderLayerOptions setter)