Package rawDeepLearningClassifier.dlClassification.genericModel

Class DLModelWorker<T>

java.lang.Object

rawDeepLearningClassifier.dlClassification.genericModel.DLModelWorker<T>

Direct Known Subclasses:

GenericModelWorker, KetosWorker, SoundSpotWorker

public abstract class DLModelWorker<T>
extends Object

Runs the deep learning model and performs feature extraction.

Author:

Jamie Macaulay

Field Summary

Fields

Modifier and Type	Field	Description
static final int	MAX_QUEUE_SIZE	The maximum allowed queue size;

Constructor Summary

Constructors

Constructor	Description
DLModelWorker()

Method Summary

Modifier and Type	Method	Description
abstract void	closeModel()	Destroy the model.
float[][][]	dataUnits2ModelInput(ArrayList<? extends PamDataUnit> dataUnits, float sampleRate, int iChan)	Convert a list of data units to a stack if images.
ArrayList<org.jamdev.jdl4pam.transforms.DLTransform>	getModelTransforms()
boolean	isEnableSoftMax()	Check whether the results are normalised with a softmax function.
abstract boolean	isModelNull()	Check whether a model is null or not.
abstract T	makeModelResult(float[] prob, double time)
ArrayList<org.jamdev.jdl4pam.transforms.DLTransform>	model2DLTransforms(org.jamdev.jdl4pam.animalSpot.AnimalSpotParams dlParams)	Convert the parameters saved in the sound spot model to DLtransform parameters.
abstract void	prepModel(StandardModelParams soundSpotParams, DLControl dlControl)
abstract float[]	runModel(float[][][] transformedDataStack)
ArrayList<T>	runModel(ArrayList<? extends PamDataUnit> dataUnits, float sampleRate, int iChan)	Run the initial data feature extraction and the model
void	setEnableSoftMax(boolean enableSoftMax)	Set whether the results are normalised with a softmax function.
void	setModelTransforms(ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> modelTransforms)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

MAX_QUEUE_SIZE

public static final int MAX_QUEUE_SIZE

The maximum allowed queue size;

See Also:

• Constant Field Values

Constructor Details

DLModelWorker

public DLModelWorker()

Method Details

dataUnits2ModelInput

public float[][][] dataUnits2ModelInput(ArrayList<? extends PamDataUnit> dataUnits,
 float sampleRate,
 int iChan)

Convert a list of data units to a stack if images.

Parameters:

dataUnits - - the data units.

sampleRate - - the sample rate

iChan - - the channels

Returns:

a stack of images for input into a deep learning model.

runModel

public ArrayList<T> runModel(ArrayList<? extends PamDataUnit> dataUnits,
 float sampleRate,
 int iChan)

Run the initial data feature extraction and the model

Parameters:

iChan - - the channel to run the data on.

rawDataUnit - - the raw data unit. This is a stack of data units to be classified either together or seperately.

Returns:

the model to run.

runModel

public abstract float[] runModel(float[][][] transformedDataStack)

isModelNull

public abstract boolean isModelNull()

Check whether a model is null or not.

Returns:

true of the model is null.

makeModelResult

public abstract T makeModelResult(float[] prob,
 double time)

prepModel

public abstract void prepModel(StandardModelParams soundSpotParams,
 DLControl dlControl)

closeModel

public abstract void closeModel()

Destroy the model.

getModelTransforms

public ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> getModelTransforms()

setModelTransforms

public void setModelTransforms(ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> modelTransforms)

model2DLTransforms

public ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> model2DLTransforms(org.jamdev.jdl4pam.animalSpot.AnimalSpotParams dlParams)

Convert the parameters saved in the sound spot model to DLtransform parameters.

Returns:

the DLTransform parameters.

isEnableSoftMax

public boolean isEnableSoftMax()

Check whether the results are normalised with a softmax function.

Returns:

true if results are normalised using a softmax function

setEnableSoftMax

public void setEnableSoftMax(boolean enableSoftMax)

Set whether the results are normalised with a softmax function.

Parameters:

set - to true if results are normalised using a softmax function