org.bytedeco.pytorch

Class SmoothL1LossImpl

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.pytorch.Module

org.bytedeco.pytorch.SmoothL1LossImplCloneable

org.bytedeco.pytorch.SmoothL1LossImpl

All Implemented Interfaces:

AutoCloseable

@Namespace(value="torch::nn")
 @NoOffset
 @Properties(inherit=torch.class)
public class SmoothL1LossImpl
extends SmoothL1LossImplCloneable

Creates a criterion that uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise. It is less sensitive to outliers than the 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));
  

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
SmoothL1LossImpl()
SmoothL1LossImpl(Module pointer) Downcast constructor.
SmoothL1LossImpl(Pointer p) Pointer cast constructor.
SmoothL1LossImpl(SmoothL1LossOptions options)

Method Summary

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.

Methods inherited from class org.bytedeco.pytorch.SmoothL1LossImplCloneable

asModule, asModule, clone, clone

Methods inherited from class org.bytedeco.pytorch.Module

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

Methods inherited from class org.bytedeco.javacpp.Pointer

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

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

SmoothL1LossImpl

public SmoothL1LossImpl(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

SmoothL1LossImpl

public SmoothL1LossImpl(Module pointer)

Downcast constructor.

SmoothL1LossImpl

public SmoothL1LossImpl(@ByVal(nullValue="torch::nn::SmoothL1LossOptions{}")
                        SmoothL1LossOptions options)

SmoothL1LossImpl

public SmoothL1LossImpl()

Method Detail

reset

public void reset()

Description copied from class: SmoothL1LossImplCloneable

reset() must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.

Overrides:

reset in class SmoothL1LossImplCloneable

pretty_print

public void pretty_print(@Cast(value="std::ostream*") @ByRef
                         Pointer stream)

Pretty prints the L1Loss module into the given stream.

Overrides:

pretty_print in class Module

forward

@ByVal
public Tensor forward(@Const @ByRef
                             Tensor input,
                             @Const @ByRef
                             Tensor target)

options

@ByRef
public SmoothL1LossOptions options()

The options with which this Module was constructed.

options

public SmoothL1LossImpl options(SmoothL1LossOptions setter)