org.bytedeco.tensorflowlite

Class TfLiteTensor

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.tensorflowlite.TfLiteTensor

All Implemented Interfaces:

AutoCloseable

@Properties(inherit=tensorflowlite.class)
public class TfLiteTensor
extends Pointer

A tensor in the interpreter system which is a wrapper around a buffer of data including a dimensionality (or NULL if not currently defined).

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

Method Summary

Modifier and Type	Method and Description
int	allocation_type() How memory is mapped kTfLiteMmapRo: Memory mapped read only.
TfLiteTensor	allocation_type(int setter)
Pointer	allocation() An opaque pointer to a tflite::MMapAllocation
TfLiteTensor	allocation(Pointer setter)
int	buffer_handle() An integer buffer handle that can be handled by delegate.
TfLiteTensor	buffer_handle(int setter)
long	bytes() The number of bytes required to store the data of this Tensor.
TfLiteTensor	bytes(long setter)
boolean	data_is_stale() If the delegate uses its own buffer (e.g.
TfLiteTensor	data_is_stale(boolean setter)
TfLitePtrUnion	data() A union of data pointers.
TfLiteTensor	data(TfLitePtrUnion setter)
TfLiteDelegate	delegate() The delegate which knows how to handle buffer_handle.
TfLiteTensor	delegate(TfLiteDelegate setter)
TfLiteIntArray	dims_signature() Optional.
TfLiteTensor	dims_signature(TfLiteIntArray setter)
TfLiteIntArray	dims() A pointer to a structure representing the dimensionality interpretation that the buffer should have.
TfLiteTensor	dims(TfLiteIntArray setter)
TfLiteTensor	getPointer(long i)
boolean	is_variable() True if the tensor is a variable.
TfLiteTensor	is_variable(boolean setter)
BytePointer	name() Null-terminated name of this tensor.
TfLiteTensor	name(BytePointer setter)
TfLiteQuantizationParams	params() Quantization information.
TfLiteTensor	params(TfLiteQuantizationParams setter)
TfLiteTensor	position(long position)
TfLiteQuantization	quantization() Quantization information.
TfLiteTensor	quantization(TfLiteQuantization setter)
TfLiteSparsity	sparsity() Parameters used to encode a sparse tensor.
TfLiteTensor	sparsity(TfLiteSparsity setter)
int	type() The data type specification for data stored in data.
TfLiteTensor	type(int setter)

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

TfLiteTensor

public TfLiteTensor()

Default native constructor.

TfLiteTensor

public TfLiteTensor(long size)

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

TfLiteTensor

public TfLiteTensor(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

Method Detail

position

public TfLiteTensor position(long position)

Overrides:

position in class Pointer

getPointer

public TfLiteTensor getPointer(long i)

Overrides:

getPointer in class Pointer

type

@Cast(value="TfLiteType")
public int type()

The data type specification for data stored in data. This affects what member of data union should be used.

type

public TfLiteTensor type(int setter)

data

@ByRef
public TfLitePtrUnion data()

A union of data pointers. The appropriate type should be used for a typed tensor based on type.

data

public TfLiteTensor data(TfLitePtrUnion setter)

dims

public TfLiteIntArray dims()

A pointer to a structure representing the dimensionality interpretation that the buffer should have. NOTE: the product of elements of dims and the element datatype size should be equal to bytes below.

dims

public TfLiteTensor dims(TfLiteIntArray setter)

params

@ByRef
public TfLiteQuantizationParams params()

Quantization information.

params

public TfLiteTensor params(TfLiteQuantizationParams setter)

allocation_type

@Cast(value="TfLiteAllocationType")
public int allocation_type()

How memory is mapped kTfLiteMmapRo: Memory mapped read only. i.e. weights kTfLiteArenaRw: Arena allocated read write memory (i.e. temporaries, outputs).

allocation_type

public TfLiteTensor allocation_type(int setter)

bytes

@Cast(value="size_t")
public long bytes()

The number of bytes required to store the data of this Tensor. I.e. (bytes of each element) * dims[0] * ... * dims[n-1]. For example, if type is kTfLiteFloat32 and dims = {3, 2} then bytes = sizeof(float) * 3 * 2 = 4 * 3 * 2 = 24.

bytes

public TfLiteTensor bytes(long setter)

allocation

@Const
public Pointer allocation()

An opaque pointer to a tflite::MMapAllocation

allocation

public TfLiteTensor allocation(Pointer setter)

name

@Cast(value="const char*")
public BytePointer name()

Null-terminated name of this tensor.

name

public TfLiteTensor name(BytePointer setter)

delegate

public TfLiteDelegate delegate()

The delegate which knows how to handle buffer_handle. WARNING: This is an experimental interface that is subject to change.

delegate

public TfLiteTensor delegate(TfLiteDelegate setter)

buffer_handle

@Cast(value="TfLiteBufferHandle")
public int buffer_handle()

An integer buffer handle that can be handled by delegate. The value is valid only when delegate is not null. WARNING: This is an experimental interface that is subject to change.

buffer_handle

public TfLiteTensor buffer_handle(int setter)

data_is_stale

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

If the delegate uses its own buffer (e.g. GPU memory), the delegate is responsible to set data_is_stale to true. delegate->CopyFromBufferHandle can be called to copy the data from delegate buffer. WARNING: This is an experimental interface that is subject to change.

data_is_stale

public TfLiteTensor data_is_stale(boolean setter)

is_variable

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

True if the tensor is a variable.

is_variable

public TfLiteTensor is_variable(boolean setter)

quantization

@ByRef
public TfLiteQuantization quantization()

Quantization information. Replaces params field above.

quantization

public TfLiteTensor quantization(TfLiteQuantization setter)

sparsity

public TfLiteSparsity sparsity()

Parameters used to encode a sparse tensor. This is optional. The field is NULL if a tensor is dense. WARNING: This is an experimental interface that is subject to change.

sparsity

public TfLiteTensor sparsity(TfLiteSparsity setter)

dims_signature

@Const
public TfLiteIntArray dims_signature()

Optional. Encodes shapes with unknown dimensions with -1. This field is only populated when unknown dimensions exist in a read-write tensor (i.e. an input or output tensor). (e.g. dims contains [1, 1, 1, 3] and dims_signature contains [1, -1, -1, 3]). If no unknown dimensions exist then dims_signature is either null, or set to an empty array. Note that this field only exists when TF_LITE_STATIC_MEMORY is not defined.

dims_signature

public TfLiteTensor dims_signature(TfLiteIntArray setter)