Merge branch 'main' of https://github.com/macster110/PAMGuard

src/rawDeepLearningClassifier/DLControl.java

@@ -228,6 +228,7 @@ public class DLControl extends PamControlledUnit implements PamSettings {
 
 		// classify the raw data segments.
 		addPamProcess(dlClassifyProcess = new DLClassifyProcess(this, segmenterProcess.getSegmenterDataBlock()));
+		dlClassifyProcess.addMultiPlexDataBlock(segmenterProcess.getSegmenteGrouprDataBlock());
 
 		//manages the names assigned to different output classes. 
 		dlClassNameManager = new DLClassNameManager(this);

src/rawDeepLearningClassifier/dataPlotFX/DLPredictionPane.java

@@ -102,6 +102,8 @@ public class DLPredictionPane extends PamBorderPane implements TDSettingsPane {
 			//populate the prediction pane. 
 			DLClassName[] classNames = dlPredictionPlotInfoFX.getDlControl().getDLModel().getClassNames();
 			
+//			System.out.println("MAKE MY CLASS NAMES: " + dlPredictionPlotInfoFX.getDlControl().getDLModel().getClassNames());
+
 			layoutColourPanes(classNames);
 		}
 

src/rawDeepLearningClassifier/dataPlotFX/DLPredictionPlotInfoFX.java

@@ -94,7 +94,7 @@ public class DLPredictionPlotInfoFX extends GenericLinePlotInfo {
 		if (getDlControl().getDLModel()!=null) {
 			DLClassName[] classNames = getDlControl().getDLModel().getClassNames();
 
-//			System.out.println("Class names are: !!! " + (classNames == null ? "null" : classNames.length)); 
+			System.out.println("Class names are: !!! " + (classNames == null ? "null" : classNames.length)); 
 
 			if (classNames!=null) {
 
@@ -105,8 +105,8 @@ public class DLPredictionPlotInfoFX extends GenericLinePlotInfo {
 						dlPredParams.lineInfos[i] = new LineInfo(true, Color.rgb(0, 0, 255%(i*30 + 50)));
 					}
 				}
-
 			}
+			getGraphSettingsPane().setParams();
 		}
 	}
 

src/rawDeepLearningClassifier/dlClassification/DLClassifyProcess.java

@@ -20,6 +20,7 @@ import rawDeepLearningClassifier.logging.DLAnnotation;
 import rawDeepLearningClassifier.logging.DLAnnotationType;
 import rawDeepLearningClassifier.segmenter.GroupedRawData;
 import rawDeepLearningClassifier.segmenter.SegmenterDataBlock;
+import rawDeepLearningClassifier.segmenter.SegmenterDetectionGroup;
 
 /**
  * The deep learning classification process. This takes a segment of raw data from the segmenter. 
@@ -64,15 +65,13 @@ public class DLClassifyProcess extends PamInstantProcess {
 	/**
 	 * The DL buffer
 	 */
-	private ArrayList<GroupedRawData> classificationBuffer; 
-
+	private ArrayList<PamDataUnit> classificationBuffer; 
 
 	/**
 	 * The DL annotation type. 
 	 */
 	private DLAnnotationType dlAnnotationType; 
 
-
 	/**
 	 * The last parent data for grouped data. This is used to ensure that DLDetections 
 	 * correspond to the raw chunk of data from a parent detection e.g. a click detection. 
@@ -117,7 +116,7 @@ public class DLClassifyProcess extends PamInstantProcess {
 		overlayGraphics.setDetectionData(true);
 		dlDetectionDataBlock.setOverlayDraw(overlayGraphics);
 
-		classificationBuffer =  new ArrayList<GroupedRawData>(); 
+		classificationBuffer =  new ArrayList<PamDataUnit>(); 
 
 		//the process name. 
 		setProcessName("Deep Learning Classifier");  
@@ -194,36 +193,72 @@ public class DLClassifyProcess extends PamInstantProcess {
 	 */
 	@Override
 	public void newData(PamObservable obs, PamDataUnit pamRawData) {
+//		System.out.println("NEW SEGMENTER DATA");
 
-		//the raw data units should appear in sequential channel order  
-		GroupedRawData rawDataUnit = (GroupedRawData) pamRawData;
-
-		if (checkGroupData(rawDataUnit)) { 
-			//check whether the classification buffer is full. If it is then run 
-			if (isClassificationBufferFull(classificationBuffer, rawDataUnit)) {
-
-				//first call run model to clear out the classification buffer if needs be
-				runModel(); 
+		if (pamRawData instanceof SegmenterDetectionGroup) {
+			if (classificationBuffer.size()>=1) {
+//				System.out.println("RUN THE MODEL FOR WHISTLES: ");
+				runDetectionGroupModel(); 
 				classificationBuffer.clear(); 
 			}
-
-			classificationBuffer.add(rawDataUnit); 
+			else {
+				classificationBuffer.add(pamRawData);
+			}
 		}
-//				System.out.println("New raw data in: chan: " + PamUtils.getSingleChannel(pamRawData.getChannelBitmap()) + 
-//						" Size: " +  pamRawData.getSampleDuration() + " first sample: " + rawDataUnit.getRawData()[0][0] 
-//								+ "Parent UID: " + rawDataUnit.getParentDataUnit().getUID());
+
+		if (pamRawData instanceof GroupedRawData) {
+			//the raw data units should appear in sequential channel order  
+			GroupedRawData rawDataUnit = (GroupedRawData) pamRawData;
+
+			if (checkGroupData(rawDataUnit)) { 
+				//check whether the classification buffer is full. If it is then run 
+				if (isRawClassificationBufferFull(classificationBuffer, rawDataUnit)) {
+
+					//first call run model to clear out the classification buffer if needs be
+					runRawModel(); 
+					classificationBuffer.clear(); 
+				}
+
+				classificationBuffer.add(rawDataUnit); 
+
+			}
+		}
+		//				System.out.println("New raw data in: chan: " + PamUtils.getSingleChannel(pamRawData.getChannelBitmap()) + 
+		//						" Size: " +  pamRawData.getSampleDuration() + " first sample: " + rawDataUnit.getRawData()[0][0] 
+		//								+ "Parent UID: " + rawDataUnit.getParentDataUnit().getUID());
 	}
 
+
+	/**
+	 * Run a model for which the input is a detection group. 
+	 */
+	private synchronized void runDetectionGroupModel() {
+		if (classificationBuffer.size()<=0) return; 
+		ArrayList<PamDataUnit> classificationBufferTemp = (ArrayList<PamDataUnit>) classificationBuffer.clone(); 
+
+		ArrayList<? extends PredictionResult> modelResults = this.dlControl.getDLModel().runModel(classificationBufferTemp); 
+
+		for (int i=0; i<classificationBufferTemp.size(); i++) {
+			
+			if (modelResults!=null && modelResults.get(i)!=null) {
+				DLDataUnit dlDataUnit =  predictionToDataUnit(classificationBuffer.get(i),  modelResults.get(i));
+				this.dlModelResultDataBlock.addPamData(dlDataUnit); //here
+			}
+		}
+		
+	}
+
+
 	/**
 	 * Run the model if the classification buffer is full. 
 	 */
-	private void runModel() {
+	private void runRawModel() {
 
 		if (classificationBuffer.size()<=0) return; 
 
 		//run the deep learning algorithm 
 		ArrayList<GroupedRawData> classificationBufferTemp = (ArrayList<GroupedRawData>) classificationBuffer.clone(); 
-		ArrayList<? extends PredictionResult> modelResults = this.dlControl.getDLModel().runModel(classificationBuffer); 
+		ArrayList<? extends PredictionResult> modelResults = this.dlControl.getDLModel().runModel(classificationBufferTemp); 
 
 		if (modelResults==null) {
 			return; //there has been a problem
@@ -235,18 +270,18 @@ public class DLClassifyProcess extends PamInstantProcess {
 				//				System.out.println("Compare Times: " + PamCalendar.formatDBDateTime(modelResults.get(i).getTimeMillis(), true)  + 
 				//						"   " + PamCalendar.formatDBDateTime(classificationBufferTemp.get(i).getTimeMilliseconds(), true) + "  " +
 				//						modelResults.get(i).getPrediction()[1]); 
-				newModelResult(modelResults.get(i), classificationBufferTemp.get(i)); 
+				newRawModelResult(modelResults.get(i), classificationBufferTemp.get(i)); 
 			}
 		}
 	}
 
 	/**
-	 * Check whether the buffer is full and the results should be passed to the classification model. 
+	 * Check whether the buffer is full and the results should be passed to the classification model if we are using GrpoupDataUnits
 	 * @param classificationBuffer2 - the classification buffer. 
 	 * @param rawDataUnit  - the next raw data unit to add to the buffer. 
 	 * @return true if the buffer is full. 
 	 */
-	private boolean isClassificationBufferFull(ArrayList<GroupedRawData> classificationBuffer2, GroupedRawData rawDataUnit) {
+	private boolean isRawClassificationBufferFull(ArrayList<PamDataUnit> classificationBuffer2, GroupedRawData rawDataUnit) {
 
 		if (classificationBuffer2.size()==0) return false; 
 
@@ -254,16 +289,16 @@ public class DLClassifyProcess extends PamInstantProcess {
 		//1) It's over  a max time
 		//2) Contains different parent data units (if not from raw data). 
 
-		GroupedRawData lastUnit = classificationBuffer2.get(classificationBuffer2.size()-1); 
+		GroupedRawData lastUnit = (GroupedRawData) classificationBuffer2.get(classificationBuffer2.size()-1); 
 
 		if (!(lastUnit.getParentDataUnit() instanceof RawDataUnit) && lastUnit.getParentDataUnit()!=rawDataUnit.getParentDataUnit()) {
 			//there is a new parent data unit. 
 			return true; 
 		}
 
-		//get the start time. Use min value instead of first data just in case units ar enot in order. 
+		//get the start time. Use min value instead of first data just in case units are not in order. 
 		long min = Long.MAX_VALUE;
-		for (GroupedRawData groupedRawData:  classificationBuffer2) {
+		for (PamDataUnit groupedRawData:  classificationBuffer2) {
 			if (groupedRawData.getTimeMilliseconds()<min) {
 				min=groupedRawData.getTimeMilliseconds(); 
 			}
@@ -299,18 +334,7 @@ public class DLClassifyProcess extends PamInstantProcess {
 		return true;
 	}
 
-	/**
-	 * Create a data unit form a model result. This is called whenever data passes a prediction threshold.
-	 * 
-	 * @param modelResult - the model result. 
-	 * @param pamRawData - the raw data unit which the model result came from. 
-	 */
-	public void newModelResult(PredictionResult modelResult, GroupedRawData pamRawData) {
-
-		//the model result may be null if the classifier uses a new thread. 
-		
-		//System.out.println("New segment: parent UID: " + pamRawData.getParentDataUnit().getUID() + " Prediciton: " + modelResult.getPrediction()[0]+ "  " + getSourceParams().countChannelGroups());
-
+	private DLDataUnit  predictionToDataUnit(PamDataUnit pamRawData, PredictionResult modelResult) {
 		//create a new data unit - always add to the model result section. 
 		DLDataUnit dlDataUnit = new DLDataUnit(pamRawData.getTimeMilliseconds(), pamRawData.getChannelBitmap(), 
 				pamRawData.getStartSample(), pamRawData.getSampleDuration(), modelResult); 
@@ -319,17 +343,35 @@ public class DLClassifyProcess extends PamInstantProcess {
 		dlDataUnit.setFrequency(new double[] {0, dlControl.getDLClassifyProcess().getSampleRate()/2});
 		dlDataUnit.setDurationInMilliseconds(pamRawData.getDurationInMilliseconds()); 
 
+		return dlDataUnit;
+	}
+
+	/**
+	 * Create a data unit form a model result. This is called whenever data passes a prediction threshold.
+	 * 
+	 * @param modelResult - the model result. 
+	 * @param pamRawData - the raw data unit which the model result came from. 
+	 */
+	public void newRawModelResult(PredictionResult modelResult, GroupedRawData pamRawData) {
+
+		//the model result may be null if the classifier uses a new thread. 
+
+		//System.out.println("New segment: parent UID: " + pamRawData.getParentDataUnit().getUID() + " Prediciton: " + modelResult.getPrediction()[0]+ "  " + getSourceParams().countChannelGroups());
+
+		//create a new data unit - always add to the model result section. 
+		DLDataUnit dlDataUnit =  predictionToDataUnit(pamRawData,  modelResult);
+
 		this.dlModelResultDataBlock.addPamData(dlDataUnit); //here
 
 		//need to implement multiple groups. 
 		for (int i=0; i<getSourceParams().countChannelGroups(); i++) {
 
-//						System.out.println("RawDataIn: chan: " + pamRawData.getChannelBitmap()+ "  " +
-//						PamUtils.hasChannel(getSourceParams().getGroupChannels(i), pamRawData.getChannelBitmap()) + 
-//						" grouped source: " +getSourceParams().getGroupChannels(i) + " Channels OK? " 
-//						+PamUtils.hasChannel(getSourceParams().getGroupChannels(i), PamUtils.getSingleChannel(pamRawData.getChannelBitmap())) 
-//						+ "  groupchan: " + getSourceParams().getGroupChannels(i) + "  " + PamUtils.getLowestChannel(pamRawData.getChannelBitmap())
-//						+ " chan bitmap: " + pamRawData.getChannelBitmap()); 
+			//						System.out.println("RawDataIn: chan: " + pamRawData.getChannelBitmap()+ "  " +
+			//						PamUtils.hasChannel(getSourceParams().getGroupChannels(i), pamRawData.getChannelBitmap()) + 
+			//						" grouped source: " +getSourceParams().getGroupChannels(i) + " Channels OK? " 
+			//						+PamUtils.hasChannel(getSourceParams().getGroupChannels(i), PamUtils.getSingleChannel(pamRawData.getChannelBitmap())) 
+			//						+ "  groupchan: " + getSourceParams().getGroupChannels(i) + "  " + PamUtils.getLowestChannel(pamRawData.getChannelBitmap())
+			//						+ " chan bitmap: " + pamRawData.getChannelBitmap()); 
 
 			if (PamUtils.hasChannel(getSourceParams().getGroupChannels(i), PamUtils.getLowestChannel(pamRawData.getChannelBitmap()))) {
 
@@ -375,7 +417,7 @@ public class DLClassifyProcess extends PamInstantProcess {
 					//Need to go by the parent data unit for merging data not the segments. Note that we may still add multiple
 					//predicitions to a single data unit depending on how many segments it contains. 
 
-				    //System.out.println("New model data " + pamRawData.getParentDataUnit().getUID() + " " + groupDataBuffer[i].size() + " " + modelResultDataBuffer[i].size()); 
+					//System.out.println("New model data " + pamRawData.getParentDataUnit().getUID() + " " + groupDataBuffer[i].size() + " " + modelResultDataBuffer[i].size()); 
 
 					if (pamRawData.getParentDataUnit()!=lastParentDataUnit[i]) {
 						//save any data
@@ -425,22 +467,22 @@ public class DLClassifyProcess extends PamInstantProcess {
 
 
 		//first call run model to clear out the classification buffer if needs be
-		runModel(); 
+		runRawModel(); 
 		classificationBuffer.clear(); 
 
 		//need to implement multiple groups. 
 		for (int i=0; i<getSourceParams().countChannelGroups(); i++) {
 
 
-//			System.out.println("Nummber segments " + groupDataBuffer[i].size() + " data unit len: " + dataUnit.getSampleDurationAsInt() + " samples UID: " + dataUnit.getUID()); 
-//						System.out.println("RawDataIn: chan: " + dataUnit.getChannelBitmap()+ "  " +
-//						PamUtils.hasChannel(getSourceParams().getGroupChannels(i), dataUnit.getChannelBitmap()) + 
-//						" grouped source: " +getSourceParams().getGroupChannels(i)); 
+			//			System.out.println("Nummber segments " + groupDataBuffer[i].size() + " data unit len: " + dataUnit.getSampleDurationAsInt() + " samples UID: " + dataUnit.getUID()); 
+			//						System.out.println("RawDataIn: chan: " + dataUnit.getChannelBitmap()+ "  " +
+			//						PamUtils.hasChannel(getSourceParams().getGroupChannels(i), dataUnit.getChannelBitmap()) + 
+			//						" grouped source: " +getSourceParams().getGroupChannels(i)); 
 
 
 			if (PamUtils.hasChannel(getSourceParams().getGroupChannels(i), PamUtils.getSingleChannel(dataUnit.getChannelBitmap()))) {
 				if (groupDataBuffer[i].size()>0) {
-				  //System.out.println("Save click annotation to " + lastParentDataUnit[i].getUID()); 
+					//System.out.println("Save click annotation to " + lastParentDataUnit[i].getUID()); 
 					addDLAnnotation(dataUnit,groupDataBuffer[i],modelResultDataBuffer[i]); 
 					lastParentDataUnit[i]=null;
 					clearBuffer(i); 
@@ -532,14 +574,21 @@ public class DLClassifyProcess extends PamInstantProcess {
 
 	@Override
 	public void pamStart() {
-		// TODO Auto-generated method stub
-		System.out.println("PREP MODEL:");
+//		System.out.println("PREP MODEL:");
 		this.dlControl.getDLModel().prepModel(); 
 	}
 
 	@Override
 	public void pamStop() {
-		runModel(); //make sure to run the last data in the buffer. 
+		//make sure to run the last data in the buffer.
+		if (this.classificationBuffer.size()>0) {
+			if (classificationBuffer.get(0) instanceof GroupedRawData) {
+				runRawModel(); //raw data or raw data units
+			}
+			if (classificationBuffer.get(0) instanceof SegmenterDetectionGroup) {
+				runDetectionGroupModel(); //any other data units. 
+			}
+		}
 
 		//21/11/2022 - it seems like this causes a memory leak when models are reopened and closed every file...
 		//this.dlControl.getDLModel().closeModel(); 

src/rawDeepLearningClassifier/dlClassification/StandardClassifierModel.java

@@ -106,7 +106,7 @@ public abstract class StandardClassifierModel implements DLClassiferModel, PamSe
 	
 	@Override
 	public void prepModel() {
-//		System.out.println("STANDARD CLASSIFIER MODEL PREP MODEL! !!!");
+		System.out.println("STANDARD CLASSIFIER MODEL PREP MODEL! !!!: " +  getDLParams().modelPath);
 //		StandardModelParams oldParams = getDLParams().clone();
 		
 		getDLWorker().prepModel(getDLParams(), dlControl);
@@ -115,6 +115,7 @@ public abstract class StandardClassifierModel implements DLClassiferModel, PamSe
 		if (getDLWorker().isModelNull()) {
 			dlClassifierWarning.setWarningMessage("There is no loaded " + getName() + " classifier model. " + getName() + " disabled.");
 			WarningSystem.getWarningSystem().addWarning(dlClassifierWarning);
+			return;
 		}
 
 
@@ -187,7 +188,7 @@ public abstract class StandardClassifierModel implements DLClassiferModel, PamSe
 	public DLStatus setModel(URI uri) {
 		//will change the params if we do not clone. 
 		StandardModelParams.setModel(uri, this.getDLParams()); 
-		this.prepModel();
+		this.getDLWorker().prepModel(getDLParams(), dlControl);
 		return getModelStatus();
 	}
 	
@@ -271,7 +272,7 @@ public abstract class StandardClassifierModel implements DLClassiferModel, PamSe
 	 */
 	protected void newResult(StandardPrediction modelResult, PamDataUnit groupedRawData) {
 		if (groupedRawData instanceof GroupedRawData) {
-			this.dlControl.getDLClassifyProcess().newModelResult(modelResult, (GroupedRawData) groupedRawData);
+			this.dlControl.getDLClassifyProcess().newRawModelResult(modelResult, (GroupedRawData) groupedRawData);
 		}
 	}
 //	

src/rawDeepLearningClassifier/dlClassification/animalSpot/StandardModelPane.java

@@ -32,6 +32,7 @@ import pamViewFX.fxNodes.PamSpinner;
 import pamViewFX.fxNodes.PamVBox;
 import pamViewFX.validator.PamValidator;
 import rawDeepLearningClassifier.dlClassification.DLClassiferModel;
+import rawDeepLearningClassifier.dlClassification.StandardClassifierModel;
 
 /**
  * Settings pane for SoundSpot
@@ -163,7 +164,7 @@ public abstract class StandardModelPane extends SettingsPane<StandardModelParams
 			defaultSegmentLenChanged(); 
 			//only set the hop if the user physically changes the toggle switch. This is not included in defaultSegmentLenChanged
 			//becuase defaultSegmentLenChanged can be called from elsewhere
-			int defaultsamples =  getDefaultSamples();
+			int defaultsamples =  getDefaultSamples(dlClassifierModel, paramsClone);
 			dlClassifierModel.getDLControl().getSettingsPane().getHopLenSpinner().getValueFactory().setValue((int) defaultsamples/2);
 		});
 		usedefaultSeg.setPadding(new Insets(0,0,0,0));
@@ -269,7 +270,7 @@ public abstract class StandardModelPane extends SettingsPane<StandardModelParams
 
 //			float sR = dlClassifierModel.getDLControl().getSettingsPane().getSelectedParentDataBlock().getSampleRate(); 
 
-			int defaultsamples =  getDefaultSamples();
+			int defaultsamples =  getDefaultSamples(dlClassifierModel, paramsClone);
 
 			//work out the window length in samples
 			dlClassifierModel.getDLControl().getSettingsPane().getSegmentLenSpinner().getValueFactory().setValue(defaultsamples);
@@ -282,7 +283,7 @@ public abstract class StandardModelPane extends SettingsPane<StandardModelParams
 		}
 	}
 	
-	private int getDefaultSamples() {
+	public static int getDefaultSamples(DLClassiferModel dlClassifierModel, StandardModelParams paramsClone) {
 		float sR = dlClassifierModel.getDLControl().getSettingsPane().getSelectedParentDataBlock().getSampleRate(); 
 		int defaultsamples =  (int) (paramsClone.defaultSegmentLen.doubleValue()*sR/1000.0);
 		return defaultsamples;

src/rawDeepLearningClassifier/dlClassification/archiveModel/ArchiveModelWorker.java

@@ -58,10 +58,11 @@ public class ArchiveModelWorker extends GenericModelWorker {
 	}
 
 	/**
-	 * Prepare the model 
+	 * Prepare the model.
+	 * Note it is important to put a synchonized here or the model loading can fail. 
 	 */
 	@Override
-	public void prepModel(StandardModelParams dlParams, DLControl dlControl) {
+	public synchronized void prepModel(StandardModelParams dlParams, DLControl dlControl) {
 		//ClassLoader origCL = Thread.currentThread().getContextClassLoader();
 		try {
 
@@ -198,6 +199,7 @@ public class ArchiveModelWorker extends GenericModelWorker {
 	 * @throws IOException
 	 */
 	public ArchiveModel loadModel(String currentPath2) throws MalformedModelException, IOException {
+	
 		return new SimpleArchiveModel(new File(currentPath2)); 
 	}
 

src/rawDeepLearningClassifier/dlClassification/delphinID/DelphinIDClassifier.java

@@ -8,6 +8,7 @@ import org.jamdev.jdl4pam.transforms.DLTransformsFactory;
 import org.jamdev.jdl4pam.transforms.DLTransfromParams;
 
 import PamController.PamControlledUnitSettings;
+import PamController.PamSettingManager;
 import rawDeepLearningClassifier.DLControl;
 import rawDeepLearningClassifier.dlClassification.DLClassiferModel;
 import rawDeepLearningClassifier.dlClassification.StandardClassifierModel;
@@ -37,6 +38,9 @@ public class DelphinIDClassifier extends StandardClassifierModel {
 
 	public DelphinIDClassifier(DLControl dlControl) {
 		super(dlControl);
+		
+		//load the previous settings
+		PamSettingManager.getInstance().registerSettings(this);
 	}
 
 	@Override
@@ -91,7 +95,7 @@ public class DelphinIDClassifier extends StandardClassifierModel {
 	@Override
 	public boolean isDecision(StandardPrediction modelResult, StandardModelParams modelParmas) {
 		//TODO
-		//DelphinID uses a different decision making process to most of the standard classifiers which just pass a binary threhsoild. 
+		//DelphinID uses a different decision making process to most of the standard classifiers which just pass a binary threshold. 
 		return false;
 	}
 
@@ -105,10 +109,11 @@ public class DelphinIDClassifier extends StandardClassifierModel {
 
 	@Override
 	public boolean restoreSettings(PamControlledUnitSettings pamControlledUnitSettings) {
+
 		DelphinIDParams newParameters = (DelphinIDParams) pamControlledUnitSettings.getSettings();
 		if (newParameters!=null) {
 			delphinIDParams = (DelphinIDParams) newParameters.clone();
-			//System.out.println("SoundSpot have been restored. : " + soundSpotParmas.classNames); 
+//			System.out.println("DELPHINID have been restored. : " + delphinIDParams.modelPath); 
 			if (delphinIDParams.dlTransfromParams!=null) {
 				delphinIDParams.dlTransfroms = DLTransformsFactory.makeDLTransforms((ArrayList<DLTransfromParams>) delphinIDParams.dlTransfromParams); 
 			}

src/rawDeepLearningClassifier/dlClassification/delphinID/DelphinIDPane.java

@@ -1,13 +1,26 @@
 package rawDeepLearningClassifier.dlClassification.delphinID;
 
+
+import java.io.File;
+
 import PamController.SettingsPane;
+import javafx.geometry.Pos;
 import javafx.scene.Node;
+import javafx.scene.control.ContentDisplay;
 import javafx.scene.control.Label;
+import javafx.scene.control.Slider;
+import javafx.scene.control.Spinner;
 import javafx.scene.control.Tooltip;
 import javafx.scene.layout.Pane;
+import javafx.scene.paint.Color;
 import javafx.scene.text.Font;
 import javafx.scene.text.FontWeight;
+import pamViewFX.PamGuiManagerFX;
+import pamViewFX.fxGlyphs.PamGlyphDude;
+import pamViewFX.fxNodes.PamHBox;
+import pamViewFX.fxNodes.PamSpinner;
 import pamViewFX.fxNodes.PamVBox;
+import rawDeepLearningClassifier.dlClassification.animalSpot.StandardModelPane;
 
 /**
  * Settings pane for delphin ID. 
@@ -15,7 +28,7 @@ import pamViewFX.fxNodes.PamVBox;
  * @author Jamie Macaulay
  *
  */
-public class DelphinIDPane  extends SettingsPane<DelphinIDParams> {
+public class DelphinIDPane extends SettingsPane<DelphinIDParams> {
 
 	/**
 	 * The main pane. 
@@ -27,6 +40,14 @@ public class DelphinIDPane  extends SettingsPane<DelphinIDParams> {
 	 */
 	private DelphinIDClassifier delphinUIClassifier;
 
+	private PamSpinner<Double> detectionDensitySpinner;
+
+	private Slider decisionSlider;
+
+	private DelphinIDParams currentParams;
+
+	private File currentSelectedFile;
+
 	public DelphinIDPane(DelphinIDClassifier delphinUIClassifier) {
 		super(null);
 		this.delphinUIClassifier = delphinUIClassifier; 
@@ -35,40 +56,113 @@ public class DelphinIDPane  extends SettingsPane<DelphinIDParams> {
 
 	private Pane createPane() {
 
-
 		//font to use for title labels. 
 		Font font= Font.font(null, FontWeight.BOLD, 11);
 
-		Node classifierIcon;
-		classifierIcon = delphinUIClassifier.getModelUI().getIcon();
+		Label classifierIcon;
+		classifierIcon = new Label("DelphinID");
+		PamGuiManagerFX.titleFont2style(classifierIcon);
+		//todo - will need to figure out colour of icon using CSS. 
+		Node icon = PamGlyphDude.createPamIcon("mdi2r-rss", Color.BLACK, PamGuiManagerFX.iconSize);
+		icon.getStyleClass().add(getName()); 
+		icon.setRotate(45);
+		classifierIcon.setGraphic(icon);
+		classifierIcon.setContentDisplay(ContentDisplay.RIGHT);
 
 
+		//		String settings = currentParams.toString();
+		//		classifierIcon.setTooltip(new Tooltip(settings));
+
 		PamVBox vBox = new PamVBox(); 
 		vBox.setSpacing(5.);
 
+		/**Classification thresholds etc to set.**/
+		Label detectionDensity = new Label("Detection Density"); 
+		detectionDensity.setFont(font);
+		String tooltip = "Set the minimum detection density to attempt to classify.";
+		detectionDensity.setTooltip(new Tooltip(tooltip));
+		detectionDensitySpinner = new PamSpinner<Double>(0.0, 1.0, 0.3, 0.1);
+		detectionDensitySpinner.setPrefWidth(70);
+		detectionDensitySpinner.setEditable(true);
+		detectionDensitySpinner.getStyleClass().add(Spinner.STYLE_CLASS_SPLIT_ARROWS_HORIZONTAL);
+
+		PamHBox minDensityHolder = new PamHBox();
+		minDensityHolder.setAlignment(Pos.CENTER_RIGHT);
+		minDensityHolder.setSpacing(5);
+		Label minDensity = new Label("Min. density");
+		minDensityHolder.getChildren().addAll(minDensity, detectionDensitySpinner);
+
 		/**Classification thresholds etc to set.**/
 		Label classiferInfoLabel2 = new Label("Decision Threshold"); 
 		classiferInfoLabel2.setTooltip(new Tooltip("Set the minimum prediciton value for selected classes. If a prediction exceeds this value "
 				+ "a detection will be saved."));
 		classiferInfoLabel2.setFont(font);
 
+		decisionSlider = new Slider();
+		decisionSlider.setMin(0);
+		decisionSlider.setMax(1);
+		decisionSlider.setMajorTickUnit(0.2);
+		decisionSlider.setMinorTickCount(10);
+		decisionSlider.valueProperty().addListener((obsVal, oldVal, newVal)->{
+			classiferInfoLabel2.setText(String.format("Decision Threshold %.2f", newVal));
+		});
+		decisionSlider.setShowTickMarks(true);
+		decisionSlider.setShowTickLabels(true);
 
-		vBox.getChildren().addAll(classifierIcon, classiferInfoLabel2);
+		vBox.getChildren().addAll(classifierIcon, detectionDensity, minDensityHolder, classiferInfoLabel2, decisionSlider);
 
 		return vBox;
 	}
 
 	@Override
 	public DelphinIDParams getParams(DelphinIDParams currParams) {
-		// TODO Auto-generated method stub
-		return null;
+		currParams.threshold = decisionSlider.getValue();
+		currParams.minDetectionDensity = detectionDensitySpinner.getValue();
+		return currParams;
 	}
 
 	@Override
 	public void setParams(DelphinIDParams input) {
-		// TODO Auto-generated method stub
+		this.currentParams = input;
+		decisionSlider.setValue(input.threshold);
+		detectionDensitySpinner.getValueFactory().setValue(input.minDetectionDensity);
+
+		if (input.modelPath!=null) {
+			//this might 
+			currentSelectedFile = new File(currentParams.modelPath);
+
+			//this might change the paramsClone values if the model contains pamguard compatible metadata
+			newModelSelected(currentSelectedFile); 
+		}
 	}
 
+	private void newModelSelected(File currentSelectedFile2) {
+		if (currentParams!=null && currentParams.defaultSegmentLen != null) {
+
+			//System.out.println("Defualt segment length: " + paramsClone.defaultSegmentLen); 
+
+			//cannot use because, if the parent datablock has changed, samplerate will be out of date. 
+			//			int defaultsamples = (int) this.soundSpotClassifier.millis2Samples(paramsClone.defaultSegmentLen); 
+
+
+			//			float sR = dlClassifierModel.getDLControl().getSettingsPane().getSelectedParentDataBlock().getSampleRate(); 
+
+			int defaultsamples =  StandardModelPane.getDefaultSamples(delphinUIClassifier, currentParams);
+
+			//work out the window length in samples
+			delphinUIClassifier.getDLControl().getSettingsPane().getSegmentLenSpinner().getValueFactory().setValue(defaultsamples);
+			//			dlClassifierModel.getDLControl().getSettingsPane().getHopLenSpinner().getValueFactory().setValue((int) defaultsamples/2);
+
+			delphinUIClassifier.getDLControl().getSettingsPane().getSegmentLenSpinner().setDisable(true); 
+		}
+		else {
+			delphinUIClassifier.getDLControl().getSettingsPane().getSegmentLenSpinner().setDisable(false); 
+		}
+
+	}
+
+
+
 	@Override
 	public String getName() {
 		return "delphinIDParams";

src/rawDeepLearningClassifier/dlClassification/delphinID/DelphinIDParams.java

@@ -9,4 +9,10 @@ public class DelphinIDParams extends StandardModelParams {
 	 */
 	private static final long serialVersionUID = 1L;
 	
+	/**
+	 * The minimum detection density. 
+	 */
+	public double minDetectionDensity = 0.3;
+	
+
 }

src/rawDeepLearningClassifier/dlClassification/delphinID/DelphinIDWorker.java

@@ -2,6 +2,7 @@ package rawDeepLearningClassifier.dlClassification.delphinID;
 
 
 import java.io.File;
+import java.io.IOException;
 import java.util.ArrayList;
 
 import org.jamdev.jdl4pam.transforms.DLTransform;
@@ -9,18 +10,23 @@ import org.jamdev.jdl4pam.transforms.DLTransfromParams;
 import org.jamdev.jdl4pam.transforms.FreqTransform;
 import org.jamdev.jdl4pam.transforms.DLTransform.DLTransformType;
 import org.jamdev.jdl4pam.transforms.jsonfile.DLTransformsParser;
+import org.jamdev.jdl4pam.utils.DLMatFile;
 import org.jamdev.jdl4pam.utils.DLUtils;
 import org.json.JSONArray;
 import org.json.JSONObject;
 
+import PamUtils.PamArrayUtils;
 import PamguardMVC.PamDataUnit;
 import ai.djl.Model;
 import rawDeepLearningClassifier.DLControl;
 import rawDeepLearningClassifier.dlClassification.animalSpot.StandardModelParams;
 import rawDeepLearningClassifier.dlClassification.archiveModel.ArchiveModelWorker;
 import rawDeepLearningClassifier.dlClassification.delphinID.Whistles2Image.Whistle2ImageParams;
-import rawDeepLearningClassifier.segmenter.GroupedRawData;
 import rawDeepLearningClassifier.segmenter.SegmenterDetectionGroup;
+import us.hebi.matlab.mat.format.Mat5;
+import us.hebi.matlab.mat.types.MatFile;
+import us.hebi.matlab.mat.types.Matrix;
+import us.hebi.matlab.mat.types.Struct;
 
 /**
  * 
@@ -48,6 +54,11 @@ public class DelphinIDWorker extends  ArchiveModelWorker {
 			System.err.println("Error: could not find whistle2image transform in DelphinID JSON file. Model will not work.");
 			this.setModel(null); // set model to null to make sure nothing works and errors are thrown
 		}
+		
+		dlParams.binaryClassification = new boolean[dlParams.numClasses];
+		for (int i=0; i<dlParams.numClasses; i++) {
+			dlParams.binaryClassification[i]=true;
+		}
 	}
 
 
@@ -81,13 +92,52 @@ public class DelphinIDWorker extends  ArchiveModelWorker {
 
 				return whistle2ImageParmas;
 			}
-
 		}
+		
 		//something has gone wrong if we get here. 
 		return null; 
 	}
 	
 	
+	
+	private Struct imageStruct;
+	int count = 0;
+	/**
+	 * Tets by exporting results to a .mat file. 
+	 * @param data
+	 * @param aSegment
+	 */
+	private void addIMage2MatFile(double[][] data, SegmenterDetectionGroup aSegment) {
+		long dataStartMillis = 1340212413000L;
+
+		if (imageStruct==null) {
+			 imageStruct = Mat5.newStruct(100,1);
+		}
+		Matrix image = DLMatFile.array2Matrix(data);
+		imageStruct.set("image", count, image);
+		imageStruct.set("startmillis", count, Mat5.newScalar(aSegment.getSegmentStartMillis()));
+		imageStruct.set("startseconds", count, Mat5.newScalar((aSegment.getSegmentStartMillis()-dataStartMillis)/1000.));
+
+		count++;
+		
+		System.out.println("SAVED " +count + " TO MAT FILE");
+		
+		if (count==10) {
+			//create MatFile for saving the image data to. 
+			MatFile matFile = Mat5.newMatFile();
+			matFile.addArray("whistle_images", imageStruct);
+			//the path to the model
+			String matImageSave = "C:/Users/Jamie Macaulay/MATLAB Drive/MATLAB/PAMGUARD/deep_learning/delphinID/whistleimages_pg.mat";
+			try {
+				Mat5.writeToFile(matFile,matImageSave);
+			} catch (IOException e) {
+				// TODO Auto-generated catch block
+				e.printStackTrace();
+			}
+		}
+	}
+
+
 	@Override
 	public float[][][] dataUnits2ModelInput(ArrayList<? extends PamDataUnit> dataUnits, float sampleRate, int iChan){
 		//Get a list of of the model transforms. 
@@ -105,6 +155,7 @@ public class DelphinIDWorker extends  ArchiveModelWorker {
 		double[][] transformedData2; //spectrogram data
 		for (int j=0; j<numChunks; j++) {
 
+//			System.out.println("Number of whistle to process: " + whistleGroups.get(j).getStartSecond() + "s  " +  whistleGroups.get(j).getSubDetectionsCount() + "  " + whistleGroups.get(j).getSegmentStartMillis());
 			//create the first transform and set then whistle data. Note that the absolute time limits are
 			//contained within the SegmenterDetectionGroup unit. 
 			Whistles2Image whistles2Image = new Whistles2Image(whistleGroups.get(j), whistleImageParams);
@@ -120,6 +171,14 @@ public class DelphinIDWorker extends  ArchiveModelWorker {
 			
 			transformedData2 = ((FreqTransform) transform).getSpecTransfrom().getTransformedData(); 
 			transformedDataStack[j] = DLUtils.toFloatArray(transformedData2); 
+			
+//			//TEMP
+//			try {
+//				addIMage2MatFile(transformedData2,  whistleGroups.get(j));
+//			}
+//			catch (Exception e) {
+//				e.printStackTrace();
+//			}
 		}
 
 

src/rawDeepLearningClassifier/dlClassification/delphinID/Whistles2Image.java

@@ -1,6 +1,8 @@
 package rawDeepLearningClassifier.dlClassification.delphinID;
 
 import java.awt.Color;
+import java.awt.Graphics2D;
+import java.awt.RenderingHints;
 import java.awt.image.BufferedImage;
 import java.awt.image.Raster;
 import java.util.ArrayList;
@@ -72,7 +74,7 @@ public class Whistles2Image extends FreqTransform {
 		for (int i=0; i<imaged.length; i++) {
 			for (int j=0; j<imaged[0].length; j++) {
 				color = raster.getPixel(i, j, color);
-				imaged[i][j] = color[0]/255.; //normalize
+				imaged[i][j] = (255-color[0])/255.; //normalize
 			}
 		}
 //		
@@ -116,16 +118,19 @@ public class Whistles2Image extends FreqTransform {
 //			}
 //
 //		}
+//		System.out.println("Whistle group: " + segStart);
 
 		for (int i=0; i<whistleGroup.getSubDetectionsCount(); i++) {
 
 			whistleContour = (AbstractWhistleDataUnit) whistleGroup.getSubDetection(i);
-//			System.out.println("Whistle start time: " + (segStart - whistleContour.getTimeMilliseconds())/1000. +  " end: " + (segStart - whistleContour.getTimeMilliseconds() + whistleContour.getDurationInMilliseconds())/1000.);
 			
+//			System.out.println("Whistle start time: " + (whistleContour.getTimeMilliseconds()-segStart)/1000. +  " end: " + 
+//			(whistleContour.getTimeMilliseconds() - (segStart + whistleContour.getDurationInMilliseconds()))/1000.  
+//			+ "  millis: " + whistleContour.getTimeMilliseconds() +  " first slice: " + whistleContour.getTimesInSeconds()[0]);
 			
 			double[][] contourD = new double[whistleContour.getSliceCount()][2];
 			for (int j=0; j<whistleContour.getSliceCount(); j++) {
-				contourD[j][0] = (whistleContour.getTimeMilliseconds()-segStart)/1000. + whistleContour.getTimesInSeconds()[j];
+				contourD[j][0] = (whistleContour.getTimeMilliseconds()-segStart)/1000. + (whistleContour.getTimesInSeconds()[j]-whistleContour.getTimesInSeconds()[0]);
 				contourD[j][1] = whistleContour.getFreqsHz()[j];
 			}
 			contours.add(contourD);
@@ -173,7 +178,7 @@ public class Whistles2Image extends FreqTransform {
 	 * @param markerSize - the marker size in pixels
 	 * @return an image with y axis as frequency and x axis as time. 
 	 */
-	private BufferedImage makeScatterImage(ArrayList<double[][]> points, double[] size, double[] xlims, double[] ylims, double markerSize) {
+	public static BufferedImage makeScatterImage(ArrayList<double[][]> points, double[] size, double[] xlims, double[] ylims, double markerSize) {
 
 		BufferedImage canvas = new BufferedImage((int) size[0], (int) size[1], BufferedImage.TYPE_INT_RGB);
 
@@ -187,9 +192,13 @@ public class Whistles2Image extends FreqTransform {
 				x = ((points.get(j)[i][0]-xlims[0])/(xlims[1]-xlims[0]))*size[0];
 				y = ((points.get(j)[i][1]-ylims[0])/(ylims[1]-ylims[0]))*size[1];
 				
-//				System.out.println("Fill oval: x" + x + " y: " + y + " time: " + points.get(j)[i][0]);
+//				System.out.println("Fill oval: x " + x + " y: " + y + " time: " + points.get(j)[i][0]);
 				
-				canvas.getGraphics().fillOval((int) (x+markerSize/2),(int) (y-markerSize/2), (int) markerSize,(int) markerSize);
+				Graphics2D g2 = (Graphics2D) canvas.getGraphics();
+
+		        g2.setRenderingHint(RenderingHints.KEY_ANTIALIASING, RenderingHints.VALUE_ANTIALIAS_ON);
+
+		        g2.fillOval((int) (x+markerSize/2),(int) (y-markerSize/2), (int) markerSize,(int) markerSize);
 			}
 		}
 
@@ -209,4 +218,5 @@ public class Whistles2Image extends FreqTransform {
 	
 
 
+
 }

src/rawDeepLearningClassifier/dlClassification/genericModel/GenericDLClassifier.java

@@ -185,7 +185,7 @@ public class GenericDLClassifier extends StandardClassifierModel {
 	 * @param groupedRawData - the grouped raw data. 
 	 */
 	protected void newResult(StandardPrediction modelResult, GroupedRawData groupedRawData) {
-		this.dlControl.getDLClassifyProcess().newModelResult(modelResult, groupedRawData);
+		this.dlControl.getDLClassifyProcess().newRawModelResult(modelResult, groupedRawData);
 	}
 
 

src/rawDeepLearningClassifier/dlClassification/genericModel/GenericModelWorker.java

@@ -9,6 +9,7 @@ import org.jamdev.jdl4pam.transforms.FreqTransform;
 
 import PamModel.PamModel;
 import PamModel.PamModel.PluginClassloader;
+import PamUtils.PamArrayUtils;
 import rawDeepLearningClassifier.DLControl;
 import rawDeepLearningClassifier.dlClassification.animalSpot.StandardModelParams;
 
@@ -32,7 +33,7 @@ public class GenericModelWorker extends DLModelWorker<StandardPrediction> {
 
 	@Override
 	public float[] runModel(float[][][] transformedDataStack) {
-		//System.out.println("RUN GENERIC MODEL: " + transformedDataStack.length +  "  " + transformedDataStack[0].length +  "  " + transformedDataStack[0][0].length);
+//		System.out.println("RUN GENERIC MODEL: " + transformedDataStack.length +  "  " + transformedDataStack[0].length +  "  " + transformedDataStack[0][0].length);
 //		System.out.println("RUN GENERIC MODEL: " + transformedDataStack[0][0][0]);
 		float[]  results; 
 		if (freqTransform)
@@ -47,7 +48,8 @@ public class GenericModelWorker extends DLModelWorker<StandardPrediction> {
 			//System.out.println("RUN GENERIC MODEL WAVE: " + waveStack.length +  "  " + waveStack[0].length +  " " + waveStack[0][0]);
 			results =  getModel().runModel(waveStack);
 		}
-		//System.out.println("GENERIC MODEL RESULTS: " + results== null ? null : results.length);
+//		System.out.println("GENERIC MODEL RESULTS: " + (results== null ? null : results.length));
+//		PamArrayUtils.printArray(results);
 		return results;
 	}
 

src/rawDeepLearningClassifier/segmenter/SegmenterDetectionGroup.java

@@ -21,6 +21,8 @@ public class SegmenterDetectionGroup extends GroupDetection<PamDataUnit> {
 	 */
 	private long segMillis;
 
+	private double timeS;
+
 	/**
 	 * Constructor for a group of detections within a detection. Note that some
 	 * longer detections (e.g. whistles) may have sections outside the segment.
@@ -28,12 +30,12 @@ public class SegmenterDetectionGroup extends GroupDetection<PamDataUnit> {
 	 * @param timeMilliseconds - this is the start of the SEGMENT - Note that the
 	 * @param channelBitmap    - channels of all detections
 	 * @param startSample      - the stratSample of the SEGMENT.
-	 * @param duration         - the duration of the SEGMENT.
+	 * @param duration         - the duration of the SEGMENT in milliseconds.
 	 */
 	public SegmenterDetectionGroup(long timeMilliseconds, int channelBitmap, long startSample, double duration) {
 		super(timeMilliseconds, channelBitmap, startSample, (long) duration);
 		this.setDurationInMilliseconds(duration);
-		this.segMillis =timeMilliseconds;
+		this.segMillis = timeMilliseconds;
 		this.segDuration = duration;
 	}
 	
@@ -52,5 +54,17 @@ public class SegmenterDetectionGroup extends GroupDetection<PamDataUnit> {
 		return segDuration;
 	}
 
+	public long getSegmentEndMillis() {
+		return (long) (segMillis+segDuration);
+	}
+
+	public void setStartSecond(double timeS) {
+		this.timeS = timeS;
+	}
+
+	public double getStartSecond() {
+		return timeS;
+	}
+
 
 }

src/rawDeepLearningClassifier/segmenter/SegmenterGroupDataBlock.java

@@ -12,6 +12,8 @@ public class SegmenterGroupDataBlock extends PamDataBlock<SegmenterDetectionGrou
 
 	public SegmenterGroupDataBlock(String dataName, PamProcess parentProcess, int channelMap) {
 		super(SegmenterDetectionGroup.class, dataName, parentProcess, channelMap);
+		this.setNaturalLifetimeMillis(15000); //do not want to keep the data for very long  - it's raw data segmnents so memory intensive
+
 	}
 	
 

src/rawDeepLearningClassifier/segmenter/SegmenterProcess.java

@@ -6,6 +6,7 @@ import java.util.Arrays;
 
 import PamController.PamController;
 import PamDetection.RawDataUnit;
+import PamUtils.PamArrayUtils;
 import PamUtils.PamUtils;
 import PamView.GroupedSourceParameters;
 import PamView.PamDetectionOverlayGraphics;
@@ -62,6 +63,20 @@ public class SegmenterProcess extends PamProcess {
 	 */
 	private SegmenterGroupDataBlock segmenterGroupDataBlock;
 
+	/**
+	 * The first clock update - segments for detection groups (not raw sound data) are referenced from this. 
+	 */
+	private long firstClockUpdate; 
+	
+	/**
+	 * The current segmenter detection group.
+	 */
+	private SegmenterDetectionGroup[] segmenterDetectionGroup = null;
+
+	private long segmentStart=-1;
+
+	private long segmenterEnd=-1; 
+
 
 	public SegmenterProcess(DLControl pamControlledUnit, PamDataBlock parentDataBlock) {
 		super(pamControlledUnit, parentDataBlock);
@@ -101,6 +116,8 @@ public class SegmenterProcess extends PamProcess {
 		setupSegmenter();
 	}
 	
+
+
 	/**
 	 * A list of data block class types which are compatible as parent data blocks
 	 * for the PamProcess. This can return null, e.g. in the case of Acquisition
@@ -111,7 +128,7 @@ public class SegmenterProcess extends PamProcess {
 	 */
 	@Override
 	public ArrayList getCompatibleDataUnits(){
-		return new ArrayList<Class<? extends PamDataUnit>>(Arrays.asList(RawDataUnit.class, ClickDetection.class, ClipDataUnit.class));
+		return new ArrayList<Class<? extends PamDataUnit>>(Arrays.asList(RawDataUnit.class, ClickDetection.class, ClipDataUnit.class, ConnectedRegionDataUnit.class));
 	}
 
 
@@ -149,6 +166,7 @@ public class SegmenterProcess extends PamProcess {
 		if (chanGroups!=null) {
 			currentRawChunks = new GroupedRawData[chanGroups.length]; 
 			nextRawChunks = new GroupedRawData[chanGroups.length][]; 
+			segmenterDetectionGroup = new SegmenterDetectionGroup[chanGroups.length];
 		}
 
 
@@ -178,6 +196,8 @@ public class SegmenterProcess extends PamProcess {
 
 		setParentDataBlock(rawDataBlock);
 		
+		this.firstClockUpdate = -1;
+
 	}
 
 	/*
@@ -203,9 +223,10 @@ public class SegmenterProcess extends PamProcess {
 	 */
 	public void newData(PamDataUnit pamRawData) {
 
+//		System.out.println("New data for segmenter: " + pamRawData); 
+
 		if (!dlControl.getDLParams().useDataSelector || dlControl.getDataSelector().scoreData(pamRawData)>0) {	
 
-			//System.out.println("New data for segmenter: " + pamRawData); 
 			if (pamRawData instanceof RawDataUnit) {
 				newRawDataUnit(pamRawData); 
 			}
@@ -224,19 +245,152 @@ public class SegmenterProcess extends PamProcess {
 
 
 	/**
-	 * A new whistle data unit. 
+	 * A new detection data unit i.e. this is only if we have detection data which is being grouped into segments. 
 	 * @param dataUnit - the whistle data unit. 
 	 */
-	private void newWhistleData(PamDataUnit dataUnit) {
+	private synchronized void newWhistleData(PamDataUnit dataUnit) {
+		
+		
 		ConnectedRegionDataUnit whistle = (ConnectedRegionDataUnit) dataUnit;
 
 		//TODO
 		//this contains no raw data so we are branching off on a completely different processing path here.
-		//Whislte data units are saved to a buffer and then fed to the deep learning algorohtm
+		//Whislte data units are saved to a buffer and then fed to the deep learning algorithms
 		
+		int[] chanGroups = dlControl.getDLParams().groupedSourceParams.getChannelGroups();
+		
+		int index = -1;
+		for (int i=0; i<chanGroups.length; i++) {
+			if (dlControl.getDLParams().groupedSourceParams.getGroupChannels(chanGroups[i])==dataUnit.getChannelBitmap()) {
+				index=i;
+				break;
+			}
+		}
+		
+		//FIXME - TWEMP
+		index =0;
+		
+//		System.out.println("Whistle data: " + ((dataUnit.getTimeMilliseconds()-firstClockUpdate)/1000.) + "s " + chanGroups.length +  "  " +  index + "  " + dataUnit.getChannelBitmap());
+//		PamArrayUtils.printArray(chanGroups);
+		
+		if (index<0) {
+			return;
+		}
+	
+		if (segmenterDetectionGroup[index] == null || !detectionInSegment(dataUnit,  segmenterDetectionGroup[index])) {
+			
+			//System.out.println("Whiste not in segment"); 
+			//iterate until we find the correct time for this detection. This keeps the segments consist no matter 
+			//the data units. What we do not want is the first data unit defining the start of the first segment.
+			if (segmentStart <0) {
+				segmentStart= firstClockUpdate;
+				segmenterEnd = (long) (segmentStart + getSegmentLenMillis());
+			}
+			
+			while(!detectionInSegment(dataUnit,  segmentStart,  segmenterEnd)) {
+				nextGroupSegment( index);
+			}
+		}
+		
+		segmenterDetectionGroup[index].addSubDetection(whistle);
+//		System.out.println("Segment sub detection count: " + 	segmenterDetectionGroup[index].getSubDetectionsCount()); 
 		
 	}
 	
+	/**
+	 * Iterate to the next group segment
+	 * @param index - the group index;
+	 */
+	private void nextGroupSegment(int index) {
+		
+//		System.out.println("----------------------------------");
+
+		segmentStart = (long) (segmentStart+ getSegmentHopMillis());
+		segmenterEnd = (long) (segmentStart + getSegmentLenMillis());
+		
+		int[] chanGroups = dlControl.getDLParams().groupedSourceParams.getChannelGroups();
+
+		long startSample = this.absMillisecondsToSamples(segmentStart);
+
+		//now we need to create a new data unit.
+		SegmenterDetectionGroup aSegment = new SegmenterDetectionGroup(segmentStart, chanGroups[index], startSample,  getSegmentLenMillis());
+		aSegment.setStartSecond((segmentStart-firstClockUpdate)/1000.);
+
+		//save the last segment
+		if (segmenterDetectionGroup[index]!=null) {
+			//add any data units from the previous segment (because segments may overlap);
+			int count =0;
+			for (int i=0; i<segmenterDetectionGroup[index].getSubDetectionsCount() ; i++) {
+				if (detectionInSegment(segmenterDetectionGroup[index].getSubDetection(i), aSegment)){
+					aSegment.addSubDetection(segmenterDetectionGroup[index].getSubDetection(i));
+					count++;
+				}
+			}
+			
+//			System.out.println("SAVE WHISTLE SEGMENT!: " + ((segmenterDetectionGroup[index].getSegmentStartMillis()-firstClockUpdate)/1000.) + "s" + " " + " no. whsitles: " + segmenterDetectionGroup[index].getSubDetectionsCount() + " " + segmenterDetectionGroup[index].getSegmentStartMillis() + "  " + segmenterDetectionGroup[index]);
+			//save the data unit to the data block
+			if (segmenterDetectionGroup[index].getSubDetectionsCount()>0) {
+				this.segmenterGroupDataBlock.addPamData(segmenterDetectionGroup[index]);
+			}
+		}
+		
+		segmenterDetectionGroup[index] = aSegment;
+//		System.out.println("NEW SEGMENT START!: " + (segmentStart-firstClockUpdate)/1000. + "s" + " " + segmenterDetectionGroup[index].getSegmentStartMillis()+ "  " +segmenterDetectionGroup[index]);
+
+	}
+	
+	private boolean detectionInSegment(PamDataUnit dataUnit, SegmenterDetectionGroup segmenterDetectionGroup2) {
+		return detectionInSegment(dataUnit, segmenterDetectionGroup2.getSegmentStartMillis(),
+				(long) (segmenterDetectionGroup2.getSegmentStartMillis()+segmenterDetectionGroup2.getSegmentDuration()));
+	}
+
+
+	private boolean detectionInSegment(PamDataUnit dataUnit, long segStart, long segEnd) {
+		//TODO - this is going to fail for very small segments. 
+		long whistleStart 	= dataUnit.getTimeMilliseconds();
+		long whistleEnd 	= whistleStart + dataUnit.getDurationInMilliseconds().longValue();
+
+		if ((whistleStart>=segStart && whistleStart<segEnd) || ((whistleEnd>=segStart && whistleEnd<segEnd))){
+			//some part of the whistle is in the segment. 
+//			System.out.println("Whsitle in segment: " + whistleStart + "  " + whistleEnd);
+			return true;
+		}
+		return false;
+	}
+	
+	private double getSegmentLenMillis() {
+		double millis = (dlControl.getDLParams().rawSampleSize/this.getSampleRate())*1000.;
+		return millis;
+	}
+	
+	private double getSegmentHopMillis() {
+		double millis = (dlControl.getDLParams().sampleHop/this.getSampleRate())*1000.;
+		return millis;
+	}
+	
+	
+	
+	int count=0;
+	public void masterClockUpdate(long milliSeconds, long sampleNumber) {
+		super.masterClockUpdate(milliSeconds, sampleNumber);
+		if (firstClockUpdate<0) {
+			firstClockUpdate = milliSeconds;
+		}
+		
+		//want to make sure that a segment is saved if we suddenly lose 
+		// a steady stream of data units. This ensure that the segments are saved properly
+		//after the master clock has gone past the end of the current segment. 
+		if (segmenterDetectionGroup!=null && count%20==0) {
+			for (int i=0; i<segmenterDetectionGroup.length; i++) {
+				if (segmenterDetectionGroup[i]!=null && segmenterDetectionGroup[i].getSegmentEndMillis()<milliSeconds) {
+					nextGroupSegment(i);
+				}
+			}
+		}
+		count++;
+	}
+
+
 
 	/**
 	 * A new raw data unit. 
@@ -347,7 +501,7 @@ public class SegmenterProcess extends PamProcess {
 
 	/**
 	 * Take a raw sound chunk of data and segment into discrete groups. This handles
-	 * much situations e.g. where the segment is much larger than the raw data or
+	 * many situations e.g. where the segment is much larger than the raw data or
 	 * where the segment is much small than each rawDataChunk returning multiple
 	 * segments.
 	 * 
@@ -363,7 +517,7 @@ public class SegmenterProcess extends PamProcess {
 
 	/**
 	 * Take a raw sound chunk of data and segment into discrete groups. This handles
-	 * much situations e.g. where the segment is much larger than the raw data or
+	 * many situations e.g. where the segment is much larger than the raw data or
 	 * where the segment is much small than each rawDataChunk returning multiple
 	 * segments.
 	 * 
@@ -595,7 +749,7 @@ public class SegmenterProcess extends PamProcess {
 		//Need to copy a section of the old data into the new 
 		if (nextRawChunks[i]!=null) {
 			/**
-			 * It's very important to clone this as otherwise some very weird things happnen as the units are
+			 * It's very important to clone this as otherwise some very weird things happen as the units are
 			 * passed to downstream processes. 
 			 */
 			currentRawChunks[i] = nextRawChunks[i][nextRawChunks[i].length-1].clone(); //in an unlikely situation this could be null should be picked up by the first null check. 
@@ -692,4 +846,9 @@ public class SegmenterProcess extends PamProcess {
 		return segmenterDataBlock;
 	}
 
+
+	public SegmenterGroupDataBlock getSegmenteGrouprDataBlock() {
+		return this.segmenterGroupDataBlock;
+	}
+
 } 

src/test/rawDeepLearningClassifier/DelphinIDTest.java

@@ -0,0 +1,113 @@
+package test.rawDeepLearningClassifier;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+import java.awt.image.BufferedImage;
+import java.awt.image.Raster;
+import java.io.IOException;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+
+import org.jamdev.jdl4pam.transforms.DLTransform;
+import org.jamdev.jdl4pam.transforms.FreqTransform;
+import org.jamdev.jdl4pam.transforms.DLTransform.DLTransformType;
+import org.jamdev.jdl4pam.utils.DLMatFile;
+import org.jamdev.jdl4pam.utils.DLUtils;
+import org.junit.jupiter.api.Test;
+
+import rawDeepLearningClassifier.dlClassification.delphinID.Whistles2Image;
+import us.hebi.matlab.mat.format.Mat5;
+import us.hebi.matlab.mat.types.MatFile;
+import us.hebi.matlab.mat.types.Matrix;
+
+public class DelphinIDTest { 
+	
+	
+	@Test
+	public void whistle2ImageTest() {
+	
+		System.out.println("Whislte2Image test started");
+
+		/**
+		 * Test whether the Whistles2Image transform works properly
+		 */
+		String relMatPath  =	"./src/test/resources/rawDeepLearningClassifier/DelphinID/whistle_image_example.mat";
+
+		Path path = Paths.get(relMatPath);
+	
+		// Create MAT file with a scalar in a nested struct
+		try {
+			MatFile matFile = Mat5.readFromFile(path.toString());
+			Matrix array = matFile.getArray("tfvalues");
+			
+			//the values for the whistle detector.
+			double[][] whistleValues = DLMatFile.matrix2array(array);
+			
+			//the image after compression 
+			array = matFile.getArray("image1compressedgrayscale");
+			double[][] compressedWhistleImage = DLMatFile.matrix2array(array);
+
+			//the whistle2Image transform image
+			array = matFile.getArray("image1originalgrayscalenorm");
+			double[][] whislteImage = DLMatFile.matrix2array(array);
+			
+			//now perform the image transform in Java 
+			double[] freqLimits = new double[] {0., 20000.};
+			double[] size = new double[] {680., 480.};
+			
+			ArrayList<double[][]> whistleImageArr = new ArrayList<double[][]>();
+			whistleImageArr.add(whistleValues);
+			
+			BufferedImage canvas = Whistles2Image.makeScatterImage(whistleImageArr, size, new double[]{48, 48. + 4.}, freqLimits,  5.);
+
+			double[][] imaged = new double[(int) size[0]][(int) size[1]];
+
+			float[] color = new float[3];
+			Raster raster = canvas.getData();
+			for (int i=0; i<imaged.length; i++) {
+				for (int j=0; j<imaged[0].length; j++) {
+					color = raster.getPixel(i, j, color);
+					imaged[i][j] = (255-color[0])/255.; //normalize
+				}
+			}
+			
+			ArrayList<DLTransform> transforms = new ArrayList<DLTransform>();
+			transforms.add(new FreqTransform(DLTransformType.SPECRESIZE, new Number[] {Integer.valueOf(64), Integer.valueOf(48)}));
+			
+//			
+//			//set the spec transform
+//			((FreqTransform) transforms.get(0)).setSpecTransfrom(whistles2Image.getSpecTransfrom());
+//
+//			//process all the transforms. 
+//			DLTransform transform = modelTransforms.get(0); 
+//			for (int i =0; i<modelTransforms.size(); i++) {
+//				transform = modelTransforms.get(i).transformData(transform); 
+//			}
+//			
+//			transformedData2 = ((FreqTransform) transform).getSpecTransfrom().getTransformedData(); 
+//			transformedDataStack[j] = DLUtils.toFloatArray(transformedData2); 
+//			
+			
+			
+			//now save this image to a MATFILE
+			// Create MAT file with a scalar in a nested struct
+			MatFile matFileWrite = Mat5.newMatFile()
+			    .addArray("image1originalgrayscalenorm",DLMatFile.array2Matrix(imaged));
+			// Serialize to disk using default configurations
+			Mat5.writeToFile(matFileWrite, "C:\\Users\\Jamie Macaulay\\MATLAB Drive\\MATLAB\\PAMGUARD\\deep_learning\\delphinID\\whistle_image_example_java.mat");
+			
+			System.out.println("Whislte2Image test finished");
+			
+		} catch (IOException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+			assertEquals(false, false);
+		}
+		
+		
+		
+		
+	}
+
+}