@Namespace(value="torch::nn") @NoOffset @Properties(inherit=torch.class) public class RNNImpl extends RNNImplBase
torch::nn::RNNOptions class to learn what
constructor arguments are supported for this module.
Example:
RNN model(RNNOptions(128,
64).num_layers(3).dropout(0.2).nonlinearity(torch::kTanh));
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter| Constructor and Description |
|---|
RNNImpl(long input_size,
long hidden_size) |
RNNImpl(Module pointer)
Downcast constructor.
|
RNNImpl(Pointer p)
Pointer cast constructor.
|
RNNImpl(RNNOptions options_) |
| Modifier and Type | Method and Description |
|---|---|
T_PackedSequenceTensor_T |
forward_with_packed_input(PackedSequence packed_input) |
T_PackedSequenceTensor_T |
forward_with_packed_input(PackedSequence packed_input,
Tensor hx) |
T_TensorTensor_T |
forward(Tensor input) |
T_TensorTensor_T |
forward(Tensor input,
Tensor hx) |
RNNOptions |
options() |
RNNImpl |
options(RNNOptions setter) |
all_weights, flatten_parameters, options_base, options_base, pretty_print, reset_parameters, reset, to, to, to, to, to, toasModule, 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, 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 RNNImpl(Pointer p)
Pointer(Pointer).public RNNImpl(Module pointer)
public RNNImpl(@Cast(value="int64_t") long input_size, @Cast(value="int64_t") long hidden_size)
public RNNImpl(@Const @ByRef RNNOptions options_)
@ByVal public T_TensorTensor_T forward(@Const @ByRef Tensor input, @ByVal(nullValue="torch::Tensor{}") Tensor hx)
@ByVal public T_TensorTensor_T forward(@Const @ByRef Tensor input)
@ByVal public T_PackedSequenceTensor_T forward_with_packed_input(@Const @ByRef PackedSequence packed_input, @ByVal(nullValue="torch::Tensor{}") Tensor hx)
@ByVal public T_PackedSequenceTensor_T forward_with_packed_input(@Const @ByRef PackedSequence packed_input)
@ByRef public RNNOptions options()
public RNNImpl options(RNNOptions setter)
Copyright © 2024. All rights reserved.