Class NativeNetwork¶

Defined in File NativeNetwork.java

Inheritance Relationships¶

Base Type¶

public com.qualcomm.qti.snpe.NeuralNetwork (exhale_interface_interfacecom_1_1qualcomm_1_1qti_1_1snpe_1_1NeuralNetwork)

Class Documentation¶

com::qualcomm::qti::snpe::internal::NativeNetwork : public com.qualcomm.qti.snpe.NeuralNetwork

Public Functions

inline NativeNetwork (final Runtime runtime, final NativeBufferOutputStream modelBuffer, final Set< String > outputLayerNames, final boolean isDebugEnabled, final PerformanceProfile performanceProfile, final ProfilingLevel profileLevel, final ExecutionPriorityHint executionPriorityHint, boolean isCpuFallbackEnabled, boolean unsignedPD, boolean useUserSuppliedBuffers, boolean isInitCacheEnabled, boolean isDlCacheAvailable, boolean cpuFxpMode, final String storageDirectory, final String dspCachePath, final Map< String, int[]> inputDimensions, boolean unconsumedTensorsOutput)

inline NativeNetwork (final Runtime runtime, final File modelFile, final Set< String > outputLayerNames, final boolean isDebugEnabled, final PerformanceProfile performanceProfile, final ProfilingLevel profileLevel, final ExecutionPriorityHint executionPriorityHint, boolean isCpuFallbackEnabled, boolean unsignedPD, boolean useUserSuppliedBuffers, boolean isInitCacheEnabled, boolean isDlCacheAvailable, boolean cpuFxpMode, final String storageDirectory, final String dspCachePath, final Map< String, int[]> inputDimensions, boolean unconsumedTensorsOutput)

inline Map< String, FloatTensor > execute (final 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.

inline 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.

inline FloatTensor createFloatTensor (final int... shape)

Creates a FloatTensor instance with the specified shape.

Parameters: shape – tensor shape.
Returns: newly created instance.

inline 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

inline TF16UserBufferTensor createTF16UserBufferTensor (final int size, final int[] strides, int stepExactly0, float quantizedStepSize, ByteBuffer userBuffer)

Creates a TF16UserBufferTensor 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

inline Map<String, int[]> getInputTensorsShapes()¶

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

inline Map<String, int[]> getOutputTensorsShapes()¶

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

inline Set<String> getInputTensorsNames()¶

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

inline Set<String> getOutputTensorsNames()¶

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

inline TensorAttributes getTensorAttributes(String name)¶

Parameters: name – name of the network tensor.
Returns: object representing the attributes of the tensor.

inline String getModelVersion()¶

Returns: the user defined model version.

inline Runtime getRuntime()¶