@Namespace(value="torch::nn") @NoOffset @Properties(inherit=torch.class) public class FractionalMaxPool2dImpl extends FractionalMaxPool2dImplCloneable
torch::nn::FractionalMaxPool2dOptions
class to
learn what constructor arguments are supported for this module.
Example:
FractionalMaxPool2d model(FractionalMaxPool2dOptions(5).output_size(1));
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FractionalMaxPool2dImpl(FractionalMaxPool2dOptions options_) |
FractionalMaxPool2dImpl(LongPointer kernel_size) |
FractionalMaxPool2dImpl(Module pointer)
Downcast constructor.
|
FractionalMaxPool2dImpl(Pointer p)
Pointer cast constructor.
|
Modifier and Type | Method and Description |
---|---|
Tensor |
_random_samples() |
FractionalMaxPool2dImpl |
_random_samples(Tensor setter) |
T_TensorTensor_T |
forward_with_indices(Tensor input)
Returns the outputs and the indices of the max values.
|
Tensor |
forward(Tensor input) |
FractionalMaxPool2dOptions |
options()
The options with which this
Module was constructed. |
FractionalMaxPool2dImpl |
options(FractionalMaxPool2dOptions setter) |
void |
pretty_print(Pointer stream)
Pretty prints the
FractionalMaxPool2d module into the given stream . |
void |
reset()
reset() must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules. |
asModule, asModule, clone, clone
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, 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
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
public FractionalMaxPool2dImpl(Pointer p)
Pointer(Pointer)
.public FractionalMaxPool2dImpl(Module pointer)
public FractionalMaxPool2dImpl(@ByVal @Cast(value="torch::ExpandingArray<2>*") LongPointer kernel_size)
public FractionalMaxPool2dImpl(@ByVal FractionalMaxPool2dOptions options_)
public void reset()
FractionalMaxPool2dImplCloneable
reset()
must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules.reset
in class FractionalMaxPool2dImplCloneable
public void pretty_print(@Cast(value="std::ostream*") @ByRef Pointer stream)
FractionalMaxPool2d
module into the given stream
.pretty_print
in class Module
@ByVal public T_TensorTensor_T forward_with_indices(@Const @ByRef Tensor input)
torch::nn::MaxUnpool2d
later.@ByRef public FractionalMaxPool2dOptions options()
Module
was constructed.public FractionalMaxPool2dImpl options(FractionalMaxPool2dOptions setter)
public FractionalMaxPool2dImpl _random_samples(Tensor setter)
Copyright © 2024. All rights reserved.