org.bytedeco.pytorch

Class AdamW

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.pytorch.Optimizer

org.bytedeco.pytorch.AdamW

All Implemented Interfaces:

AutoCloseable

@Namespace(value="torch::optim")
 @Properties(inherit=torch.class)
public class AdamW
extends Optimizer

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
AdamW(OptimizerParamGroupVector param_groups)
AdamW(OptimizerParamGroupVector param_groups, AdamWOptions defaults)
AdamW(Pointer p) Pointer cast constructor.
AdamW(TensorVector params)
AdamW(TensorVector params, AdamWOptions defaults)

Method Summary

Modifier and Type	Method and Description
void	load(InputArchive archive) Deserializes the optimizer state from the given archive.
void	save(OutputArchive archive) Serializes the optimizer state into the given archive.
Tensor	step()
Tensor	step(LossClosure closure) A loss function closure, which is expected to return the loss value.

Methods inherited from class org.bytedeco.pytorch.Optimizer

add_param_group, add_parameters, defaults, param_groups, parameters, size, zero_grad, 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

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

Constructor Detail

AdamW

public AdamW(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

AdamW

public AdamW(@ByVal
             OptimizerParamGroupVector param_groups,
             @ByVal(nullValue="torch::optim::AdamWOptions{}")
             AdamWOptions defaults)

AdamW

public AdamW(@ByVal
             OptimizerParamGroupVector param_groups)

AdamW

public AdamW(@ByVal
             TensorVector params,
             @ByVal(nullValue="torch::optim::AdamWOptions{}")
             AdamWOptions defaults)

AdamW

public AdamW(@ByVal
             TensorVector params)

Method Detail

step

@ByVal
public Tensor step(@ByVal(nullValue="torch::optim::Optimizer::LossClosure(nullptr)")
                          LossClosure closure)

Description copied from class: Optimizer

A loss function closure, which is expected to return the loss value.

Overrides:

step in class Optimizer

step

@ByVal
public Tensor step()

Overrides:

step in class Optimizer

save

public void save(@ByRef
                 OutputArchive archive)

Description copied from class: Optimizer

Serializes the optimizer state into the given archive.

Overrides:

save in class Optimizer

load

public void load(@ByRef
                 InputArchive archive)

Description copied from class: Optimizer

Deserializes the optimizer state from the given archive.

Overrides:

load in class Optimizer