Package rawDeepLearningClassifier.dlClassification

Interface DLClassiferModel

All Known Implementing Classes:

ArchiveModelClassifier, DelphinIDClassifier, DummyClassifier, GenericDLClassifier, KetosClassifier, KetosClassifier2, KooguClassifier, OrcaSpotClassifier, PamZipModelClassifier, SoundSpotClassifier, StandardClassifierModel

public interface DLClassiferModel

The classifier model. Each classifier must satisfy this interface.

Author:

Jamie Macaulay

Method Summary

Modifier and Type	Method	Description
void	closeModel()	Called whenever PAMGuard stops.
ArrayList<Class>	getAllowedDataTypes()	Get the allowed data types for the model.The can be null in which case only data units with raw data are allowed.
DLClassName[]	getClassNames()	Get the number of output classes.
DLControl	getDLControl()	Reference to the dlControl
Serializable	getDLModelSettings()	A settings object that can be saved.
static ArrayList<org.jamdev.jdl4pam.transforms.DLTransfromParams>	getDLTransformParams(ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> dlTransfroms)	Get the parameters which can be serialized from transforms.
DLStatus	getModelStatus()	Check whether a model has been selected and can be loaded successfully.
DLCLassiferModelUI	getModelUI()	Get any UI components for the model.
String	getName()	Get the name of the model.
int	getNumClasses()	Get the number of output classes.
boolean	isModelType(URI model)	Check whether a URI is compatible with a classification framework
void	prepModel()	Prepare the model.
ArrayList<? extends PredictionResult>	runModel(ArrayList<? extends PamDataUnit> rawDataUnit)	Run the deep learning model on a list of grouped raw data units and return a corresponding list of model results.
DLStatus	setModel(URI model)	Set and load the model.

Method Details

runModel

ArrayList<? extends PredictionResult> runModel(ArrayList<? extends PamDataUnit> rawDataUnit)

Run the deep learning model on a list of grouped raw data units and return a corresponding list of model results.

Note the reason we use list is that often it is more efficient to get a model to predict a stacked group of inputs rather than one at a time.

Returns:

the deep learning model.

prepModel

void prepModel()

Prepare the model. This is called on PAMGuard start up and before processing in viewer mode.

setModel

DLStatus setModel(URI model)

Set and load the model.

Returns:

the status of the model e.g. if there has been an error loading

isModelType

boolean isModelType(URI model)

Check whether a URI is compatible with a classification framework

Parameters:

model - - the URI to the model

Returns:

true if the model is compatible.

closeModel

void closeModel()

Called whenever PAMGuard stops.

getName

String getName()

Get the name of the model.

Returns:

the name of the model.

getModelUI

DLCLassiferModelUI getModelUI()

Get any UI components for the model. Can be null.

Returns:

UI components for the model.

getDLModelSettings

Serializable getDLModelSettings()

A settings object that can be saved.

Returns:

the settings object.

getNumClasses

int getNumClasses()

Get the number of output classes.

Returns:

the number of output classes.

getClassNames

DLClassName[] getClassNames()

Get the number of output classes.

Returns:

the number of output classes.

getDLControl

DLControl getDLControl()

Reference to the dlControl

Returns:

reference to the DL control.

getAllowedDataTypes

ArrayList<Class> getAllowedDataTypes()

Get the allowed data types for the model.The can be null in which case only data units with raw data are allowed.

Returns:

a list of the allowed data types.

getModelStatus

DLStatus getModelStatus()

Check whether a model has been selected and can be loaded successfully.

getDLTransformParams

static ArrayList<org.jamdev.jdl4pam.transforms.DLTransfromParams> getDLTransformParams(ArrayList<org.jamdev.jdl4pam.transforms.DLTransform> dlTransfroms)

Get the parameters which can be serialized from transforms.

Parameters:

dlTransfroms - - the DL transforms.