@Namespace(value="torch::nn") @NoOffset @Properties(inherit=torch.class) public class TransformerEncoderLayerImpl extends TransformerEncoderLayerImplCloneable
torch::nn::TransformerEncoderLayer class to
learn what constructor arguments are supported for this encoder layer model
Example:
TransformerEncoderLayer encoderLayer(TransformerEncoderLayerOptions(512,
8).dropout(0.1));
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter| Constructor and Description |
|---|
TransformerEncoderLayerImpl(long d_model,
long nhead) |
TransformerEncoderLayerImpl(Module pointer)
Downcast constructor.
|
TransformerEncoderLayerImpl(Pointer p)
Pointer cast constructor.
|
TransformerEncoderLayerImpl(TransformerEncoderLayerOptions options_) |
| Modifier and Type | Method and Description |
|---|---|
Tensor |
forward(Tensor src) |
Tensor |
forward(Tensor src,
Tensor src_mask,
Tensor src_key_padding_mask) |
TransformerEncoderLayerOptions |
options()
options with which this
TransformerEncoderLayer was constructed |
TransformerEncoderLayerImpl |
options(TransformerEncoderLayerOptions setter) |
void |
reset_parameters() |
void |
reset()
reset() must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules. |
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, 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_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 TransformerEncoderLayerImpl(Pointer p)
Pointer(Pointer).public TransformerEncoderLayerImpl(Module pointer)
public TransformerEncoderLayerImpl(@Cast(value="int64_t") long d_model, @Cast(value="int64_t") long nhead)
public TransformerEncoderLayerImpl(@ByVal TransformerEncoderLayerOptions options_)
@ByVal public Tensor forward(@Const @ByRef Tensor src, @Const @ByRef(nullValue="torch::Tensor{}") Tensor src_mask, @Const @ByRef(nullValue="torch::Tensor{}") Tensor src_key_padding_mask)
public void reset()
TransformerEncoderLayerImplCloneablereset() must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules.reset in class TransformerEncoderLayerImplCloneablepublic void reset_parameters()
@ByRef public TransformerEncoderLayerOptions options()
TransformerEncoderLayer was constructedpublic TransformerEncoderLayerImpl options(TransformerEncoderLayerOptions setter)
Copyright © 2024. All rights reserved.