/// <summary>
/// Creates several splits of the dataset.
/// </summary>
/// <param name="sampleFrequency">How often to sample pixels within the training images.</param>
/// <param name="boxRows">Vertical trim around the edges of images to avoid feature tests beyond the boundary of the image</param>
/// <param name="boxColumns">Vertical trim around the edges of images to avoid feature tests beyond the boundary of the image</param>
/// <param name="numSplits">Number of splits to create</param>
/// <returns>Splits of the data</returns>
public List <ImageDataPoint <T> >[] CreateDataPoints(int sampleFrequency, int boxRows, int boxColumns, int numSplits)
{
List <ImageDataPoint <T> > points = new List <ImageDataPoint <T> >();
foreach (LabeledImage <T> labelledImage in _images)
{
IMultichannelImage <T> image = labelledImage.Image;
LabelImage labels = labelledImage.Labels;
LabelSet set = labels.Labels;
string id = labelledImage.ID;
bool[,] valid = labelledImage.Valid;
int maxRows = image.Rows - boxRows;
int maxColumns = image.Columns - boxColumns;
for (int r = boxRows; r < maxRows; r += sampleFrequency)
{
for (int c = boxColumns; c < maxColumns; c += sampleFrequency)
{
short label = getLabel(labels[r, c], set);
bool sample = valid[r, c];
if (sample && label == LabelImage.BackgroundLabel)
{
switch (_backgroundSampleMode)
{
case BackgroundSampleMode.Ignore:
sample = false;
break;
case BackgroundSampleMode.Half:
sample = ThreadsafeRandom.Test(.5);
break;
}
}
if (sample)
{
points.Add(new ImageDataPoint <T>(image, (short)r, (short)c, label));
}
}
}
}
List <ImageDataPoint <T> >[] splits = new List <ImageDataPoint <T> > [numSplits];
for (int i = 0; i < numSplits; i++)
{
if (_byImage)
{
splits[i] = sampleByImage(points);
}
else
{
splits[i] = sample(points);
}
}
return(splits);
}
private List <ImageDataPoint <T> > sample(List <ImageDataPoint <T> > points)
{
List <ImageDataPoint <T> > result = new List <ImageDataPoint <T> >();
for (int i = 0; i < points.Count; i++)
{
if (ThreadsafeRandom.Test(_dataPercentage))
{
result.Add(points[i]);
}
}
return(result);
}
/// <summary>
/// Computes the inverse label frequency array for the image. This is an array in which each index holds a value equal
/// to the total number of image labels divided by the total number of that particular label.
/// </summary>
/// <param name="numLabels">Total number of labels</param>
/// <returns>Inverse label frequency</returns>
public unsafe float[] ComputeInverseLabelFrequency(int numLabels)
{
int[] counts = new int[numLabels];
foreach (LabeledImage <T> image in _images)
{
LabelImage labels = image.Labels;
LabelSet set = labels.Labels;
fixed(short *labelsSrc = labels.RawArray)
{
int count = labels.Rows * labels.Columns;
short *labelsPtr = labelsSrc;
while (count-- > 0)
{
short index = getLabel(*labelsPtr++, set);
bool sample = true;
if (index == LabelImage.BackgroundLabel)
{
switch (_backgroundSampleMode)
{
case BackgroundSampleMode.Ignore:
sample = false;
break;
case BackgroundSampleMode.Half:
sample = ThreadsafeRandom.Test(.5);
break;
}
}
if (!sample)
{
continue;
}
counts[index]++;
}
}
}
float[] frequency = new float[numLabels];
float sum = 0;
for (short i = 0; i < frequency.Length; i++)
{
frequency[i] = 1 + counts[i];
sum += frequency[i];
}
for (int i = 0; i < frequency.Length; i++)
{
frequency[i] = sum / frequency[i];
}
return(frequency);
}
private List <ImageDataPoint <T> > sampleByImage(List <ImageDataPoint <T> > points)
{
List <ImageDataPoint <T> > result = new List <ImageDataPoint <T> >();
var imageGroups = points.GroupBy(o => o.ImageID);
foreach (var group in imageGroups)
{
if (ThreadsafeRandom.Test(_imagePercentage))
{
result.AddRange(group.Where(o => ThreadsafeRandom.Test(_dataPercentage)));
}
}
return(result);
}
private List <LabelVector> findCenterCandidates(object arg)
{
Job job = arg as Job;
List <LabelVector> result = new List <LabelVector>();
double norm = OversampleRate / _phi;
for (int i = job.StartIndex; i < job.EndIndex; i++)
{
LabelVector x = _data[i];
double sample = x.FeatureValue * norm;
if (ThreadsafeRandom.Test(sample))
{
LabelVector center = x.Clone() as LabelVector;
result.Add(center);
}
}
return(result);
}
private unsafe List <ImageDataPoint <T> > createAllDataPointsLabels(BackgroundSampleMode mode)
{
List <ImageDataPoint <T> > points = new List <ImageDataPoint <T> >();
int rows = _image.Rows;
int columns = _image.Columns;
LabelSet set = _labels.Labels;
fixed(short *labelsSrc = _labels.RawArray)
{
fixed(bool *validSrc = _valid)
{
short *labelsPtr = labelsSrc;
bool * validPtr = validSrc;
for (short r = 0; r < rows; r++)
{
for (short c = 0; c < columns; c++)
{
short label = getLabel(*labelsPtr++, set);
bool sample = *validPtr++;
if (sample && label == LabelImage.BackgroundLabel)
{
switch (mode)
{
case BackgroundSampleMode.Ignore:
sample = false;
break;
case BackgroundSampleMode.Half:
sample = ThreadsafeRandom.Test(.5);
break;
}
}
if (sample)
{
points.Add(new ImageDataPoint <T>(_image, r, c, label));
}
}
}
}
}
return(points);
}
