Classes
class	FloatTensor

interface	NeuralNetwork

class	PlatformValidator

class	SNPE

class	SnpeError

class	Tensor

interface	TensorAttributes

class	TF8UserBufferTensor

class	UserBufferTensor

Functions
boolean	isRuntimeAvailable (final Application application)

String	coreVersion (final Application application)

String	libVersion (final Application application)

boolean	runtimeCheck (final Application application)

Detailed Description

This module defines the SNPE Java APIs

Class Documentation

◆ com::qualcomm::qti::snpe::FloatTensor

class com::qualcomm::qti::snpe::FloatTensor

Tensor class containing float elements.

Public Member Functions
abstract void	write (float[] value, int offset, int length, int... position)

abstract void	write (float value, int... position)

abstract int	read (float[] value, int offset, int length, int... position)

abstract float	read (int... position)

Public Member Functions inherited from Tensor
int []	getShape ()

int	getSize ()

abstract void	release ()

Member Function Documentation

◆ read() [1/2]

abstract int read	(	float []	value,
		int	offset,
		int	length,
		int...	position
	)

abstract

Reads elements from the tensor into the specified array range starting at the specified tensor position.

Parameters

value	array to read values into.
offset	start offset to write into array.
length	number of elements to write into array.
position	the zero indexed position for each of the tensor dimensions to start reading from.

Returns: number of elements read.

◆ read() [2/2]

abstract float read ( int... position )

abstract

Reads a single value from the tensor.

Parameters

position the zero indexed position for each of the tensor dimensions to start reading from.

Returns: the value at the specified position.

◆ write() [1/2]

abstract void write	(	float []	value,
		int	offset,
		int	length,
		int...	position
	)

abstract

Writes the range of the provided input array into the tensor at the specified position.

Parameters

value	float values to write.
offset	start position to read from the input array.
length	number of floats to read from the input array.
position	the zero indexed position for each of the tensor dimensions to start writing to.

◆ write() [2/2]

abstract void write	(	float	value,
		int...	position
	)

abstract

Writes a single float value to the specified position.

Parameters

value	float value.
position	the zero indexed position for each of the tensor dimensions to start writing to.

◆ com::qualcomm::qti::snpe::NeuralNetwork

interface com::qualcomm::qti::snpe::NeuralNetwork

NeuralNetwork helper functions and properties.

Public Member Functions
NeuralNetwork.Runtime	getRuntime ()

Set< String >	getOutputLayers ()

Map< String, FloatTensor >	execute (Map< String, FloatTensor > inputs)

boolean	execute (Map< String, ? extends UserBufferTensor > inputs, Map< String, ? extends UserBufferTensor > outputs)

Map< String, int[]>	getInputTensorsShapes ()

Map< String, int[]>	getOutputTensorsShapes ()

Set< String >	getInputTensorsNames ()

Set< String >	getOutputTensorsNames ()

TensorAttributes	getTensorAttributes (String name)

String	getModelVersion ()

void	release ()

FloatTensor	createFloatTensor (int... shape)

TF8UserBufferTensor	createTF8UserBufferTensor (final int size, final int[] strides, int stepExactly0, float quantizedStepSize, ByteBuffer userBuffer)

Member Function Documentation

◆ createFloatTensor()

FloatTensor createFloatTensor ( int... shape )

Creates a FloatTensor instance with the specified shape.

Parameters

shape tensor shape.

Returns: newly created instance.

◆ createTF8UserBufferTensor()

TF8UserBufferTensor createTF8UserBufferTensor	(	final int	size,
		final int []	strides,
		int	stepExactly0,
		float	quantizedStepSize,
		ByteBuffer	userBuffer
	)

Creates a TF8UserBufferTensor instance to wrap a user buffer.

Parameters

size	total size of the buffer, in bytes
strides	total number of bytes between elements in each dimension
stepExactly0	step value that represents exactly 0.0
quantizedStepSize	step size
userBuffer	byte buffer that contains user data. This buffer must have been allocated using direct allocation and possess native byte ordering.

Returns: newly created instance

◆ execute() [1/2]

Map<String, FloatTensor> execute ( Map< String, FloatTensor > inputs )

Forward propagates the inputs through the neural network.

Parameters

inputs map of input name and tensor.

Returns: a map of output name and tensor.

◆ execute() [2/2]

boolean execute	(	Map< String, ? extends UserBufferTensor >	inputs,
		Map< String, ? extends UserBufferTensor >	outputs
	)

Forward propagates the inputs through the neural network.

Parameters

inputs map of input name and user buffer tensor.

Returns: a map of output name and user buffer tensor.

◆ getInputTensorsNames()

Set<String> getInputTensorsNames ( )

Returns: a set with the input tensor(s) name(s).

◆ getInputTensorsShapes()

Map<String, int[]> getInputTensorsShapes ( )

Returns: a map of the input tensors(s) shape(s).

◆ getModelVersion()

String getModelVersion ( )

Returns: the user defined model version.

◆ getOutputLayers()

Set<String> getOutputLayers ( )

Returns: The selected output layer(s) name(s).

See also: com.qualcomm.qti.snpe.SNPE.NeuralNetworkBuilder::setOutputLayers(String...)

◆ getOutputTensorsNames()

Set<String> getOutputTensorsNames ( )

Returns: a set with the output tensor(s) name(s).

◆ getOutputTensorsShapes()

Map<String, int[]> getOutputTensorsShapes ( )

Returns: a map of the input tensors(s) shape(s).

◆ getRuntime()

NeuralNetwork.Runtime getRuntime ( )

Returns: The neural network's selected runtime.

See also: com.qualcomm.qti.snpe.SNPE.NeuralNetworkBuilder::setRuntimeOrder(Runtime...)

◆ getTensorAttributes()

TensorAttributes getTensorAttributes ( String name )

Parameters

name	name of the network tensor.

Returns: object representing the attributes of the tensor.

◆ release()

void release ( )

Releases the neural network's resources. After this call you can no longer invoke any methods on this class instance.

◆ com::qualcomm::qti::platformvalidator::PlatformValidator

class com::qualcomm::qti::platformvalidator::PlatformValidator

PlatformValidator class - top level APIs of the SNPE Platform Validator.

Public Member Functions
boolean	isRuntimeAvailable (final Application application)

String	coreVersion (final Application application)

String	libVersion (final Application application)

boolean	runtimeCheck (final Application application)

◆ com::qualcomm::qti::snpe::SNPE

class com::qualcomm::qti::snpe::SNPE

SNPE class - top level APIs of the Snapdragon Neural Network Engine.

Static Public Member Functions
static String	getRuntimeVersion (final Application application)

static boolean	addOpPackage (final Application application, String regLibrary)

Static Public Attributes
static final String	LOG_TAG = "snpe-android"

Member Function Documentation

◆ addOpPackage()

static boolean addOpPackage	(	final Application	application,
		String	regLibrary
	)

inlinestatic

Registers a UDO Package Registration Library

Parameters

application	the application registering the package
regLibraryPath	Path to registration library

Returns: true for successful registration, false for unsuccessful registration

◆ getRuntimeVersion()

static String getRuntimeVersion ( final Application application )

inlinestatic

Returns the version of the Snapdragon Neural Network Engine.

Member Data Documentation

◆ LOG_TAG

final String LOG_TAG = "snpe-android"

static

Log tag used internally by the SDK.

See also: android.util.Log

◆ com::qualcomm::qti::snpe::SnpeError

class com::qualcomm::qti::snpe::SnpeError

SnpeError throws exceptions with code and message

◆ com::qualcomm::qti::snpe::Tensor

class com::qualcomm::qti::snpe::Tensor

Tensor class.

Public Member Functions
int []	getShape ()

int	getSize ()

abstract void	release ()

Member Function Documentation

◆ getShape()

int [] getShape ( )

inline

Returns the shape of the tensor.

Returns: shape array.

◆ getSize()

int getSize ( )

inline

Returns the number of elements in the tensor.

Returns: the size of the tensor.

◆ release()

abstract void release ( )

abstract

Releases the resources used by this tensor. After this call no other methods can be called on this instance!

◆ com::qualcomm::qti::snpe::TensorAttributes

interface com::qualcomm::qti::snpe::TensorAttributes

class representing attributes of a tensor

Public Member Functions
int []	getDims ()

int []	getAlignments ()

int	getElementSize ()

Encoding	getEncoding ()

Member Function Documentation

◆ getAlignments()

int [] getAlignments ( )

Returns the alignment requirements of the tensor

Alignment per each dimension is expressed as an multiple, for example, if one particular dimension can accept multiples of 8, the alignment will be 8.

Returns: alignment in each dimension, in terms of multiple of number of elements

◆ getDims()

int [] getDims ( )

Returns the dimensions attribute

Returns: the dimensions attribute

◆ getElementSize()

int getElementSize ( )

Returns the tensor's element size, in bytes

Returns: element size, in bytes

◆ getEncoding()

Encoding getEncoding ( )

Returns the tensor's encoding type

Returns: the encoding type

◆ com::qualcomm::qti::snpe::TF8UserBufferTensor

class com::qualcomm::qti::snpe::TF8UserBufferTensor

UserBufferTensor class representing TF8 user buffer elements.

Public Member Functions
Encoding	getEncoding ()

abstract int	getStepExactly0 ()

abstract float	getQuantizedStepSize ()

Public Member Functions inherited from UserBufferTensor
int []	getStrides ()

int	getSize ()

abstract Encoding	getEncoding ()

abstract void	release ()

Member Function Documentation

◆ getEncoding()

Encoding getEncoding ( )

inline

Returns the encoding type of the tensor.

Returns: the encoding type of the tensor

◆ getQuantizedStepSize()

abstract float getQuantizedStepSize ( )

abstract

Returns the step size.

Returns: the step size

◆ getStepExactly0()

abstract int getStepExactly0 ( )

abstract

Returns the step that represents exactly 0.0.

Returns: the step value

◆ com::qualcomm::qti::snpe::UserBufferTensor

class com::qualcomm::qti::snpe::UserBufferTensor

UserBufferTensor class representing user buffer tensors.

Public Member Functions
int []	getStrides ()

int	getSize ()

abstract Encoding	getEncoding ()

abstract void	release ()

Member Function Documentation

◆ getEncoding()

abstract Encoding getEncoding ( )

abstract

Returns the encoding type of the tensor.

Returns: the encoding type of the tensor

◆ getSize()

int getSize ( )

inline

Returns the total size of the tensor.

Returns: the size of the tensor, in bytes.

◆ getStrides()

int [] getStrides ( )

inline

Returns the strides of the tensor.

Returns: shape array.

◆ release()

abstract void release ( )

abstract

Releases the resources used by this tensor. After this call no other methods can be called on this instance!

Function Documentation

◆ coreVersion()

String coreVersion ( final Application application )

inline

Checks core version of the runtime

Parameters

Application context of the caller

Returns: Coreversion string of the runtime

◆ isRuntimeAvailable()

boolean isRuntimeAvailable ( final Application application )

inline

Checks if the runtime associated with the object is available or not

Parameters

Application context of the caller

Returns: True if runtime is available otherwise false

◆ libVersion()

String libVersion ( final Application application )

inline

Checks library version of the runtime

Parameters

Application context of the caller

Returns: library version string of the runtime

◆ runtimeCheck()

boolean runtimeCheck ( final Application application )

inline

Checks SNPE runtime availability

Parameters

Application context of the caller

Returns: True if runtime is available otherwise false

Classes

Functions

Detailed Description

Class Documentation

◆ com::qualcomm::qti::snpe::FloatTensor

Public Member Functions

Member Function Documentation

◆ read() [1/2]

◆ read() [2/2]

◆ write() [1/2]

◆ write() [2/2]

◆ com::qualcomm::qti::snpe::NeuralNetwork

Public Member Functions

Member Function Documentation

◆ createFloatTensor()

◆ createTF8UserBufferTensor()

◆ execute() [1/2]

◆ execute() [2/2]

◆ getInputTensorsNames()

◆ getInputTensorsShapes()

◆ getModelVersion()

◆ getOutputLayers()

◆ getOutputTensorsNames()

◆ getOutputTensorsShapes()

◆ getRuntime()

◆ getTensorAttributes()

◆ release()

◆ com::qualcomm::qti::platformvalidator::PlatformValidator

Public Member Functions

◆ com::qualcomm::qti::snpe::SNPE

Static Public Member Functions

Static Public Attributes

Member Function Documentation

◆ addOpPackage()

◆ getRuntimeVersion()

Member Data Documentation

◆ LOG_TAG

◆ com::qualcomm::qti::snpe::SnpeError

◆ com::qualcomm::qti::snpe::Tensor

Public Member Functions

Member Function Documentation

◆ getShape()

◆ getSize()

◆ release()

◆ com::qualcomm::qti::snpe::TensorAttributes

Public Member Functions

Member Function Documentation

◆ getAlignments()

◆ getDims()

◆ getElementSize()

◆ getEncoding()

◆ com::qualcomm::qti::snpe::TF8UserBufferTensor

Public Member Functions

Member Function Documentation

◆ getEncoding()

◆ getQuantizedStepSize()

◆ getStepExactly0()

◆ com::qualcomm::qti::snpe::UserBufferTensor

Public Member Functions

Member Function Documentation

◆ getEncoding()

◆ getSize()

◆ getStrides()

◆ release()

Function Documentation

◆ coreVersion()

◆ isRuntimeAvailable()

◆ libVersion()

◆ runtimeCheck()