public PredictionBreakDownDisplay(PicesDataBase _dbConn,
PicesDataBaseImage _image,
PicesRaster _raster,
TrainingModel2 _trainingModel,
PicesInstrumentData _instrumentData, /*!< Instrument data that goes with image, if null will read from database. */
PicesRunLog _runLog
)
{
if (_runLog == null)
{
runLog = new PicesRunLog();
}
else
{
runLog = _runLog;
}
if (_image == null)
{
return;
}
fileName = _image.ImageFileName;
instrumentData = _instrumentData;
trainingModel = _trainingModel;
PicesRaster raster = _raster;
if (_dbConn != null)
{
if (raster == null)
{
raster = _dbConn.ImageFullSizeFind(fileName);
}
if (instrumentData == null)
{
instrumentData = _dbConn.InstrumentDataGetByScanLine(_image.SipperFileName, _image.TopLeftRow);
}
dbFeatureVector = _dbConn.FeatureDataRecLoad(fileName);
}
if (raster == null)
{
return;
}
//raster = raster.ConnectedComponent ();
featureCalcImages = new PicesRasterList();
featureVector = new PicesFeatureVector(raster, fileName, featureCalcImages, runLog);
if (instrumentData != null)
{
featureVector.AddInstrumentData(instrumentData);
}
InitializeComponent();
}
} /* LoadImageGrid */
private void UpdateDetailProbabilityDisplay(String fileName)
{
if (fileName == null)
{
return;
}
curSelImageFileName = fileName;
String fullFileName = null;
if ((fileName.Length > 1) && (fileName[1] == ':'))
{
fullFileName = fileName;
}
else
{
fullFileName = OSservices.AddSlash(rootDir) + fileName;
}
if (!File.Exists(fullFileName))
{
String fn = OSservices.GetRootName(fileName) + ".bmp";
fullFileName = OSservices.LookForFile(fn, rootDir);
}
Prediction prediction = GetPrediction(fileName);
// We need to call 'PredictProbabilities' twice. Once to get the intermediate images and the
// second time to perform prediction using the FeatureVector that was used in the original
// prediction. It has to be done this way because the version of 'PredictProbabilities' that
// derives the FeatureVector from an image does not always have access of instrumentation data.
PicesRasterList featureCalcImages = new PicesRasterList();
PicesPredictionList guesses2 = prediction.trainModel.PredictProbabilities(fullFileName, featureCalcImages);
// Perform Prediction using original FeatureVector.
PicesPredictionList guesses = prediction.trainModel.PredictProbabilities(prediction.fv);
ImageFileName.Text = fileName;
if (guesses == null)
{
return;
}
ClassificationProbabilities.Rows.Clear();
foreach (PicesPrediction p in guesses)
{
Object[] data = new Object[3];
data[0] = p.ClassName;
data[1] = p.Probability;
data[2] = p.Votes;
ClassificationProbabilities.Rows.Add(data);
}
FeatureCalcImages.Rows.Clear();
if ((featureCalcImages == null) || (featureCalcImages.Count < 1))
{
return;
}
for (int x = 0; x < featureCalcImages.Count; x++)
{
Object[] data = new Object[2];
data[0] = featureCalcImages[x].BuildBitmap();
data[1] = featureCalcImages[x].FileName;
FeatureCalcImages.Rows.Add(data);
}
} /* UpdateDetailProbabilityDisplay */
