org.bytedeco.depthai

Class NeuralNetwork

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.depthai.Node

org.bytedeco.depthai.NeuralNetwork

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

DetectionNetwork

@Namespace(value="dai::node")
 @NoOffset
 @Properties(inherit=depthai.class)
public class NeuralNetwork
extends Node

\brief NeuralNetwork node. Runs a neural inference on input data.

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.depthai.Node

Node.Connection, Node.DatatypeHierarchy, Node.Input, Node.Output

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
NeuralNetwork(PipelineImpl par, long nodeId)
NeuralNetwork(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
BytePointer	getName() Retrieves nodes name
int	getNumInferenceThreads() How many inference threads will be used to run the network
Node.Input	input() Input message with data to be infered upon Default queue is blocking with size 5
Node.Output	out() Outputs NNData message that carries inference results
Node.Output	passthrough() Passthrough message on which the inference was performed.
void	setBlobPath(BytePointer path) Load network blob into assets and use once pipeline is started.
void	setBlobPath(String path)
void	setNumInferenceThreads(int numThreads) How many threads should the node use to run the network.
void	setNumNCEPerInferenceThread(int numNCEPerThread) How many Neural Compute Engines should a single thread use for inference
void	setNumPoolFrames(int numFrames) Specifies how many frames will be avilable in the pool

Methods inherited from class org.bytedeco.depthai.Node

assetManager, clone, getAssets, getInputRefs, getInputs, getOutputRefs, getOutputs, getParentPipeline, getProperties, getRequiredOpenVINOVersion, id, inputs, outputs

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, getPointer, getPointer, getPointer, getPointer, hashCode, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralNetwork

public NeuralNetwork(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

NeuralNetwork

public NeuralNetwork(@SharedPtr
                     PipelineImpl par,
                     @Cast(value="int64_t")
                     long nodeId)

Method Detail

getName

@StdString
public BytePointer getName()

Description copied from class: Node

Retrieves nodes name

Overrides:

getName in class Node

input

@MemberGetter
 @ByRef
public Node.Input input()

Input message with data to be infered upon Default queue is blocking with size 5

out

@MemberGetter
 @ByRef
public Node.Output out()

Outputs NNData message that carries inference results

passthrough

@MemberGetter
 @ByRef
public Node.Output passthrough()

Passthrough message on which the inference was performed. Suitable for when input queue is set to non-blocking behavior.

setBlobPath

public void setBlobPath(@StdString
                        BytePointer path)

Load network blob into assets and use once pipeline is started. Throws if file doesn't exist or isn't a valid network blob.

Parameters:

path - Path to network blob

setBlobPath

public void setBlobPath(@StdString
                        String path)

setNumPoolFrames

public void setNumPoolFrames(int numFrames)

Specifies how many frames will be avilable in the pool

Parameters:

numFrames - How many frames will pool have

setNumInferenceThreads

public void setNumInferenceThreads(int numThreads)

How many threads should the node use to run the network.

Parameters:

numThreads - Number of threads to dedicate to this node

setNumNCEPerInferenceThread

public void setNumNCEPerInferenceThread(int numNCEPerThread)

How many Neural Compute Engines should a single thread use for inference

Parameters:

numNCEPerThread - Number of NCE per thread

getNumInferenceThreads

public int getNumInferenceThreads()

How many inference threads will be used to run the network

Returns:

Number of threads, 0, 1 or 2. Zero means AUTO