@Namespace(value="torch::nn") @NoOffset @Properties(inherit=torch.class) public class SmoothL1LossImpl extends SmoothL1LossImplCloneable
MSELoss
and in some cases
prevents exploding gradients (e.g. see the paper Fast R-CNN
by Ross
Girshick). See https://pytorch.org/docs/master/nn.html#torch.nn.SmoothL1Loss
to learn about the exact behavior of this module.
See the documentation for torch::nn::SmoothL1LossOptions
class to learn
what constructor arguments are supported for this module.
Example:
SmoothL1Loss model(SmoothL1LossOptions().reduction(torch::kNone).beta(0.5));
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
SmoothL1LossImpl() |
SmoothL1LossImpl(Module pointer)
Downcast constructor.
|
SmoothL1LossImpl(Pointer p)
Pointer cast constructor.
|
SmoothL1LossImpl(SmoothL1LossOptions options) |
Modifier and Type | Method and Description |
---|---|
Tensor |
forward(Tensor input,
Tensor target) |
SmoothL1LossOptions |
options()
The options with which this
Module was constructed. |
SmoothL1LossImpl |
options(SmoothL1LossOptions setter) |
void |
pretty_print(Pointer stream)
Pretty prints the
L1Loss 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 SmoothL1LossImpl(Pointer p)
Pointer(Pointer)
.public SmoothL1LossImpl(Module pointer)
public SmoothL1LossImpl(@ByVal(nullValue="torch::nn::SmoothL1LossOptions{}") SmoothL1LossOptions options)
public SmoothL1LossImpl()
public void reset()
SmoothL1LossImplCloneable
reset()
must perform initialization of all members with reference
semantics, most importantly parameters, buffers and submodules.reset
in class SmoothL1LossImplCloneable
public void pretty_print(@Cast(value="std::ostream*") @ByRef Pointer stream)
L1Loss
module into the given stream
.pretty_print
in class Module
@ByRef public SmoothL1LossOptions options()
Module
was constructed.public SmoothL1LossImpl options(SmoothL1LossOptions setter)
Copyright © 2024. All rights reserved.