@Namespace(value="torch::nn") @NoOffset @Properties(inherit=torch.class) public class EmbeddingImpl extends EmbeddingImplCloneable
torch::nn::EmbeddingOptions class to learn what
constructor arguments are supported for this module.
Example:
Embedding model(EmbeddingOptions(10,
2).padding_idx(3).max_norm(2).norm_type(2.5).scale_grad_by_freq(true).sparse(true));
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter| Constructor and Description |
|---|
EmbeddingImpl(EmbeddingOptions options_) |
EmbeddingImpl(long num_embeddings,
long embedding_dim) |
EmbeddingImpl(Module pointer)
Downcast constructor.
|
EmbeddingImpl(Pointer p)
Pointer cast constructor.
|
| Modifier and Type | Method and Description |
|---|---|
Tensor |
forward(Tensor indices)
Performs a lookup on the embedding table stored in
weight using the
indices supplied and returns the result. |
EmbeddingOptions |
options()
The
Options used to configure this Embedding module. |
EmbeddingImpl |
options(EmbeddingOptions setter) |
void |
pretty_print(Pointer stream)
Pretty prints the
Embedding module into the given stream. |
void |
reset_parameters() |
void |
reset()
reset() must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules. |
Tensor |
weight()
The embedding table.
|
EmbeddingImpl |
weight(Tensor setter) |
asModule, asModule, clone, cloneapply, 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, 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_gradaddress, 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, zeropublic EmbeddingImpl(Pointer p)
Pointer(Pointer).public EmbeddingImpl(Module pointer)
public EmbeddingImpl(@Cast(value="int64_t") long num_embeddings, @Cast(value="int64_t") long embedding_dim)
public EmbeddingImpl(@ByVal EmbeddingOptions options_)
public void reset()
EmbeddingImplCloneablereset() must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules.reset in class EmbeddingImplCloneablepublic void reset_parameters()
public void pretty_print(@Cast(value="std::ostream*") @ByRef Pointer stream)
Embedding module into the given stream.pretty_print in class Module@ByVal public Tensor forward(@Const @ByRef Tensor indices)
weight using the
indices supplied and returns the result.@ByRef public EmbeddingOptions options()
Options used to configure this Embedding module.
Changes to EmbeddingOptions *after construction* have no effect.public EmbeddingImpl options(EmbeddingOptions setter)
public EmbeddingImpl weight(Tensor setter)
Copyright © 2024. All rights reserved.