org.bytedeco.tensorflowlite

Class InterpreterOptions

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.tensorflowlite.InterpreterOptions

All Implemented Interfaces:

AutoCloseable

@Namespace(value="tflite")
 @Properties(inherit=tensorflowlite.class)
public class InterpreterOptions
extends Pointer

Options class for Interpreter. WARNING: This is an experimental API and subject to change.

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
InterpreterOptions() Default native constructor.
InterpreterOptions(long size) Native array allocator.
InterpreterOptions(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
boolean	GetCacheConstantCastOp()
boolean	GetDisableDelegateClustering()
int	GetDynamicAllocationForLargeTensors() Returns the size (in bytes) threshold for dynamic tensor allocation method.
boolean	GetEnsureDynamicTensorsAreReleased() Returns if the experimental_ensure_dynamic_tensors_are_released_ feature is enabled.
InterpreterOptions	getPointer(long i)
boolean	GetPreserveAllTensors() Returns if the experimental_preserve_all_tensors_ feature is enabled.
void	OptimizeMemoryForLargeTensors()
void	OptimizeMemoryForLargeTensors(int value) Use dynamic tensor allocation and deallocation method for large tensors instead of static memory planner.
InterpreterOptions	position(long position)
void	SetCacheConstantCastOp(boolean value)
void	SetDisableDelegateClustering()
void	SetDisableDelegateClustering(boolean value)
void	SetEnsureDynamicTensorsAreReleased()
void	SetEnsureDynamicTensorsAreReleased(boolean value) Force all intermediate dynamic tensors to be released once they are not used by the model.
void	SetPreserveAllTensors()
void	SetPreserveAllTensors(boolean value) Preserving all intermediates tensors for debugging.

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, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, 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

InterpreterOptions

public InterpreterOptions()

Default native constructor.

InterpreterOptions

public InterpreterOptions(long size)

Native array allocator. Access with Pointer.position(long).

InterpreterOptions

public InterpreterOptions(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

Method Detail

position

public InterpreterOptions position(long position)

Overrides:

position in class Pointer

getPointer

public InterpreterOptions getPointer(long i)

Overrides:

getPointer in class Pointer

SetPreserveAllTensors

public void SetPreserveAllTensors(@Cast(value="bool")
                                  boolean value)

Preserving all intermediates tensors for debugging. WARNING: This is an experimental API and subject to change.

SetPreserveAllTensors

public void SetPreserveAllTensors()

GetPreserveAllTensors

@Cast(value="bool")
public boolean GetPreserveAllTensors()

Returns if the experimental_preserve_all_tensors_ feature is enabled. WARNING: This is an experimental API and subject to change.

SetEnsureDynamicTensorsAreReleased

public void SetEnsureDynamicTensorsAreReleased(@Cast(value="bool")
                                               boolean value)

Force all intermediate dynamic tensors to be released once they are not used by the model. Please use this configuration with caution, since it might reduce the peak memory usage of the model at the cost of a slower inference speed. WARNING: This is an experimental API and subject to change.

SetEnsureDynamicTensorsAreReleased

public void SetEnsureDynamicTensorsAreReleased()

GetEnsureDynamicTensorsAreReleased

@Cast(value="bool")
public boolean GetEnsureDynamicTensorsAreReleased()

Returns if the experimental_ensure_dynamic_tensors_are_released_ feature is enabled. WARNING: This is an experimental API and subject to change.

OptimizeMemoryForLargeTensors

public void OptimizeMemoryForLargeTensors(int value)

Use dynamic tensor allocation and deallocation method for large tensors instead of static memory planner. Dynamic tensors are allocated just before when they're needed and released when they're not needed anymore. It improves peak memory usage but there could be some latency impact. The value (in bytes, and default is 1024 * 1024) is used to determine large tensors. WARNING: This is an experimental API and subject to change.

OptimizeMemoryForLargeTensors

public void OptimizeMemoryForLargeTensors()

GetDynamicAllocationForLargeTensors

public int GetDynamicAllocationForLargeTensors()

Returns the size (in bytes) threshold for dynamic tensor allocation method. It returns zero if the feature is not enabled. WARNING: This is an experimental API and subject to change.

GetDisableDelegateClustering

@Cast(value="bool")
public boolean GetDisableDelegateClustering()

SetDisableDelegateClustering

public void SetDisableDelegateClustering(@Cast(value="bool")
                                         boolean value)

SetDisableDelegateClustering

public void SetDisableDelegateClustering()

SetCacheConstantCastOp

public void SetCacheConstantCastOp(@Cast(value="bool")
                                   boolean value)

GetCacheConstantCastOp

@Cast(value="bool")
public boolean GetCacheConstantCastOp()