/// <summary>Extracts a cross validation set from a given set</summary>
/// <param name="Set">Set to extract cross validation from</param>
/// <param name="CrossValidationSetPercent">Percentage of elements to extract</param>
public static TrainingSet GetCrossValidationSet(TrainingSet Set, float CrossValidationSetPercent)
{
TrainingSet CrossValidationSet = new TrainingSet();
int nCrossSet = (int)(CrossValidationSetPercent * (float)Set.getN);
Random rnd = new Random();
for (int i = 0; i < nCrossSet; i++)
{
int ind = rnd.Next(0, Set.trainingArray.Count - 1);
TrainingUnit u = Set.trainingArray[ind];
Set.trainingArray.Remove(u);
CrossValidationSet.addTrainingUnit(u);
}
return CrossValidationSet;
}
/// <summary>Attempts to pre-calibrate configuration parameters.
/// Finds an alpha that enhances similarities between positive examples
/// and reduces similarities between positive and negative examples.
/// Assumes that decreasing lambda increases kernel match.
/// </summary>
/// <param name="tolPositive">Positive kernels average should be greater than tolPositive</param>
/// <param name="tolNegative">Negative kernels average should be lesser than tolNegative</param>
public void PreCalibrateCfg(float tolPositive, float tolNegative)
{
#region Checks if there are positive and negative examples
bool posSamples = false; bool negSamples = false;
for (int i = 0; i < TrainingSet.trainingArray.Count; i++)
{
if (TrainingSet.trainingArray[i].y > 0) posSamples = true;
if (TrainingSet.trainingArray[i].y < 0) negSamples = true;
if (posSamples && negSamples) i = TrainingSet.trainingArray.Count;
}
if ((!posSamples) || (!negSamples)) throw new Exception("Training set must contain positive and negative samples");
#endregion
Random rnd = new Random();
int nSet = (int)(20 * Math.Log(TrainingSet.getN, 2));
TrainingSet PositiveExamples1 = new TrainingSet();
TrainingSet PositiveExamples2 = new TrainingSet();
TrainingSet NegativeExamples = new TrainingSet();
//Kernel average for positive and negative samples
float positiveAvg = 0, negativeAvg = 0;
float invN = 1 / (float)nSet;
int count = 0;
float bestLambda = ProblemCfg.lambda;
float maxPosNegAvg = -1.0f;
while ((positiveAvg <= tolPositive || negativeAvg >= tolNegative) && count < nSet)
{
//Populates training sets
PositiveExamples1.trainingArray.Clear();
PositiveExamples2.trainingArray.Clear();
NegativeExamples.trainingArray.Clear();
while (PositiveExamples1.getN < nSet || PositiveExamples2.getN < nSet || NegativeExamples.getN < nSet)
{
TrainingUnit tu = TrainingSet.trainingArray[rnd.Next(TrainingSet.trainingArray.Count - 1)];
if (tu.y > 0 && PositiveExamples1.getN < nSet)
PositiveExamples1.addTrainingUnit(tu);
else if (tu.y > 0 && PositiveExamples2.getN < nSet)
PositiveExamples2.addTrainingUnit(tu);
if (tu.y < 0 && NegativeExamples.getN < nSet) NegativeExamples.addTrainingUnit(tu);
}
count++;
positiveAvg = 0;
negativeAvg = 0;
for (int i = 0; i < nSet; i++)
{
positiveAvg += ProblemSolver.calculateSingleKernel(PositiveExamples1.trainingArray[i], PositiveExamples2.trainingArray[i], this);
negativeAvg += ProblemSolver.calculateSingleKernel(PositiveExamples1.trainingArray[i], NegativeExamples.trainingArray[i], this);
}
positiveAvg *= invN;
negativeAvg *= invN;
if (maxPosNegAvg < positiveAvg - negativeAvg)
{
bestLambda = ProblemCfg.lambda;
maxPosNegAvg = positiveAvg - negativeAvg;
}
//Desired: positiveAvg=1, negativeAvg = 0
if (positiveAvg <= tolPositive) this.ProblemCfg.lambda *= 0.15f;
else if (negativeAvg >= tolNegative) this.ProblemCfg.lambda *= 1.2f;
}
ProblemCfg.lambda = bestLambda;
}
/*
/// <summary>
/// Copy all values from another solution
/// </summary>
/// <param name="sourceSolution">The source to copy from</param>
public void Load(SVM sourceSolution)
{
dimension = sourceSolution.dimension;
alphaList = new float[dimension];
for (int i = 0; i < dimension; i++)
{
alphaList[i] = sourceSolution.alphaList[i];
}
b = sourceSolution.b;
}
*/
/// <summary>
/// Copy all values from another solution
/// </summary>
/// <param name="FileName">File containing alpha's data</param>
public void Load(string FileName)
{
DataSet d = new DataSet();
d.ReadXml(FileName);
DataTable t = d.Tables["Solution"];
dimension = t.Rows.Count;
//Configuration
DataTable TblCfg = d.Tables["Config"];
float valC, valTol; int valKernel, valMaxP;
valC = (float)((double)TblCfg.Rows[0]["dblValues"]);
valKernel = (int)((double)TblCfg.Rows[1]["dblValues"]);
valTol = (float)((double)TblCfg.Rows[2]["dblValues"]);
valMaxP = (int)((double)TblCfg.Rows[3]["dblValues"]);
this.b = (float)((double)TblCfg.Rows[4]["dblValues"]);
float Lambda = (float)((double)TblCfg.Rows[5]["dblValues"]);
int xDim = (int)((double)TblCfg.Rows[6]["dblValues"]);
//Reads classifications
DataTable TblClassif = d.Tables["Classifications"];
alphaList = new List<float>();
TrainingSet = new TrainingSet();
for (int i = 0; i < dimension; i++)
{
TrainingSet.addTrainingUnit(new TrainingUnit(new float[xDim], -1));
}
for (int i = 0; i < dimension; i++)
{
alphaList.Add((float)((double)t.Rows[i]["dblValues"]));
TrainingSet.trainingArray[i].y = (float)((double)TblClassif.Rows[i]["dblValues"]) > 0 ? 1 : -1;
}
//Reads training set
//Creates datatables for training examples
DataTable Tbl = d.Tables["Examples"];
for (int i = 0; i < dimension; i ++)
{
for (int j = 0; j < xDim; j++)
{
TrainingSet.trainingArray[i].xVector[j] = (float)((double)Tbl.Rows[j + i*xDim]["dblValues"]);
}
}
this.ProblemCfg = new ProblemConfig(Lambda, valC, valTol, valMaxP, (ProblemConfig.KernelType)valKernel);
if (OpenTKWrapper.CLCalc.CLAcceleration == OpenTKWrapper.CLCalc.CLAccelerationType.UsingCL)
{
this.WriteToDevice();
}
}
/// <summary>Loads and classifies dataset</summary>
private void LoadMITFaceClassifier()
{
/*
CBCL Face Database #1
MIT Center For Biological and Computation Learning
*
*/
string p = System.Windows.Forms.Application.StartupPath;
string fileTrain = p + "\\svm.train.normgrey";
string fileTest = p + "\\svm.test.normgrey";
tSet = new TrainingSet();
//Fills both, we're not testing the results
FillTrainingSet(fileTrain, tSet);
FillTrainingSet(fileTest, tSet);
SVM = new MultiClassSVM(tSet);
}
/// <summary>Adds training units to a set from a file</summary>
/// <param name="filename">File containing features</param>
/// <param name="TrSet">Training set to be populated</param>
private void FillTrainingSet(string filename, TrainingSet TrSet)
{
string sepdec = (1.5).ToString().Substring(1, 1);
using (StreamReader sr = new StreamReader(filename))
{
string line;
line = sr.ReadLine();
int n = int.Parse(line);
line = sr.ReadLine();
int dim = (int)Math.Sqrt(double.Parse(line));
for (int i = 0; i < n; i++)
{
line = sr.ReadLine().Replace(".", sepdec);
string[] s = line.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries);
float[] x = new float[364];
float y;
for (int j = 0; j < s.Length - 1; j++) x[j] = float.Parse(s[j]);
y = float.Parse(s[s.Length - 1]);
TrSet.addTrainingUnit(new TrainingUnit(x, y));
/*
* Features Haar
* [04:05:53] Edmundo ITA05(FOX.Howler): 1,1
[04:05:57] Edmundo ITA05(FOX.Howler): 7,4
[04:06:55] Edmundo ITA05(FOX.Howler): new Rectangle(1, 1, 7, 4)
[04:07:06] Edmundo ITA05(FOX.Howler): 7 x 4
[04:08:15] Edmundo ITA05(FOX.Howler): new Rectangle(11, 4, 7, 4)
[04:08:24] Edmundo ITA05(FOX.Howler): divide por 7*4
[04:09:04] Edmundo ITA05(FOX.Howler): subtrai da área do Rect(8, 1, 3, 4)
[04:09:13] Edmundo ITA05(FOX.Howler): dividido pela 3 *4
*
*
*
* [04:05:53] Edmundo ITA05(FOX.Howler): 1,1
[04:05:57] Edmundo ITA05(FOX.Howler): 7,4
[04:06:55] Edmundo ITA05(FOX.Howler): new Rectangle(1, 1, 7, 4)
[04:07:06] Edmundo ITA05(FOX.Howler): 7 x 4
[04:08:15] Edmundo ITA05(FOX.Howler): new Rectangle(11, 4, 7, 4)
[04:08:24] Edmundo ITA05(FOX.Howler): divide por 7*4
[04:09:04] Edmundo ITA05(FOX.Howler): subtrai da área do Rect(8, 1, 3, 4)
[04:09:13] Edmundo ITA05(FOX.Howler): dividido pela 3 *4
[04:13:38] Edmundo ITA05(FOX.Howler): ((1,6,5,5) + (13,6,5,5)) / 2 - (7,6,5,6)
*
*
* [04:17:15] Edmundo ITA05(FOX.Howler): (1,1,17,5) - (1,6,17,8) dividir pela area
*/
}
}
}
/// <summary>Adds a new self training example</summary>
public void AddSelfTraining(int[] sbFrames, int faceIndex, Bitmap bmp)
{
if (SelfTSet == null) SelfTSet = new TrainingSet();
float[] subF = new float[(sbFrames.Length / 3) * 364];
ExtractFeatures(sbFrames, subF, bmp);
for (int i = 0; i < sbFrames.Length / 3; i++)
{
float[] x = new float[364];
for (int k = 0; k < 364; k++) x[k] = subF[k + i * 364];
TrainingUnit tu = new TrainingUnit(x, i == faceIndex ? 1.0f : -1.0f);
SelfTSet.addTrainingUnit(tu);
}
}
private static void updateSingleError(TrainingSet trainingSet, SVM currentSolution,
float newAlphai, int iIndex)
{
for (int t = 0; t < trainingSet.getN; t++)
{
float variation = 0;
if (trainingSet.trainingArray[iIndex].y > 0)
{
variation += newAlphai * trainingSet.kernels[iIndex][t];
}
else
{
variation -= newAlphai * trainingSet.kernels[iIndex][t];
}
trainingSet.errors[t] += variation;
}
}
/// <summary>Trains current SVM with cross-validation, adjusting kernel parameter lambda and box parameter C.
/// Returns best achieved efficiency.</summary>
/// <param name="CrossValidationSet">Cross validation set</param>
public float TrainWithCrossValidation(TrainingSet CrossValidationSet)
{
Random rnd = new Random();
float[] lambdaSet = new float[12];
//lambdaSet[0] = 3E-9f * ((float)rnd.NextDouble() + 1);
lambdaSet[0] = 3E-3f * ((float)rnd.NextDouble() + 1);
for (int i = 1; i < lambdaSet.Length; i++) lambdaSet[i] = 4.5f * lambdaSet[i - 1];
float[] cSet = new float[13];
cSet[0] = 1E-5f * ((float)rnd.NextDouble() + 1);
for (int i = 1; i < cSet.Length; i++) cSet[i] = 2.0f * cSet[i - 1];
return TrainWithCrossValidation(CrossValidationSet, lambdaSet, cSet);
}
private static void CLupdateErrorsCache(TrainingSet trainingSet, SVM svm,
float oldAlphai, float newAlphai, int iIndex,
float oldAlphaj, float newAlphaj, int jIndex,
float oldB, float newB)
{
float alphaiDif = newAlphai - oldAlphai;
float alphajDif = newAlphaj - oldAlphaj;
float BDif = newB - oldB;
if (trainingSet.trainingArray[iIndex].y < 0) alphaiDif = -alphaiDif;
if (trainingSet.trainingArray[jIndex].y < 0) alphajDif = -alphajDif;
lock (CLResource)
{
//Writes kernel values
if (svm.CLKi == null || svm.CLKi.OriginalVarLength != svm.TrainingSet.errors.Length)
{
svm.CLKi = new CLCalc.Program.Variable(svm.TrainingSet.kernels[iIndex]);
svm.CLKj = new CLCalc.Program.Variable(svm.TrainingSet.kernels[jIndex]);
}
else
{
svm.CLKi.WriteToDevice(svm.TrainingSet.kernels[iIndex]);
svm.CLKj.WriteToDevice(svm.TrainingSet.kernels[jIndex]);
}
float[] p = new float[3] { alphaiDif, BDif, alphajDif };
svm.CLUpdtErrParams.WriteToDevice(p);
//Executes update using GPU
kernelUpdateErr.Execute(new CLCalc.Program.Variable[] { svm.CLerr, svm.CLKi, svm.CLKj, svm.CLUpdtErrParams }, svm.TrainingSet.getN);
svm.CLerr.ReadFromDeviceTo(svm.TrainingSet.errors);
}
}
/// <summary>Creates a new multiclass SVM using desired outputs from training set. Classifications -1.0f are negative for all sets</summary>
/// <param name="TSet">Training set</param>
/// <param name="SVMCfg">Configuration parameters</param>
/// <param name="PreCalibrate">Precalibrate RBF parameter lambda? This will ignore the given value</param>
public MultiClassSVM(TrainingSet TSet, ProblemConfig SVMCfg, bool PreCalibrate)
{
initMultiSVM(TSet, SVMCfg, PreCalibrate);
}
/// <summary>Creates a new multiclass SVM using desired outputs from training set. Classifications -1.0f are negative for all sets</summary>
/// <param name="TSet">Training set</param>
public MultiClassSVM(TrainingSet TSet)
{
ProblemConfig cfg = new ProblemConfig(2.529822E-8f * (float)Math.Sqrt(TSet.getN), 127.922182f, 1e-3f, 1, ProblemConfig.KernelType.RBF);
initMultiSVM(TSet, cfg, true);
}
/// <summary>Creates a new multiclass SVM using desired outputs from training set. Classifications -1.0f are negative for all sets</summary>
/// <param name="TSet">Training set</param>
/// <param name="SVMCfg">Configuration parameters</param>
/// <param name="PreCalibrate">Precalibrate RBF parameter lambda? This will ignore the given value</param>
private void initMultiSVM(TrainingSet TSet, ProblemConfig SVMCfg, bool PreCalibrate)
{
//Determines how many different classifications are there
Classifications = new List<float>();
foreach (TrainingUnit tu in TSet.trainingArray)
{
if (Classifications.IndexOf(tu.y) < 0 && tu.y != -1.0f) Classifications.Add(tu.y);
}
//For each different possible classification, create a different SVM
SVMs = new List<SVM>();
foreach (float c in Classifications)
{
SVM svm = new SVM();
svm.TrainingSet = new TrainingSet();
svm.ProblemCfg = SVMCfg.Clone();
SVMs.Add(svm);
foreach (TrainingUnit tu in TSet.trainingArray)
{
TrainingUnit newTu = tu.Clone();
newTu.y = tu.y == c ? 1 : -1;
svm.TrainingSet.addTrainingUnit(newTu);
}
//Train svm
if (PreCalibrate) svm.PreCalibrateCfg(0.8f / (float)Math.Sqrt(svm.TrainingSet.getN), 0.3f / (float)Math.Sqrt(svm.TrainingSet.getN));
svm.Train();
svm.RemoveNonSupportVectors();
}
}
/// <summary>Trains current SVM with cross-validation, adjusting kernel parameter lambda and box parameter C.
/// Returns best achieved efficiency.</summary>
/// <param name="CrossValidationSet">Cross validation set</param>
/// <param name="LambdaSet">Lambda set</param>
/// <param name="CSet">C values set</param>
public float TrainWithCrossValidation(TrainingSet CrossValidationSet, float[] LambdaSet, float[] CSet)
{
foreach (float _lambda in LambdaSet)
{
for (int i = 0; i < SVMs.Count; i++) SVMs[i].ProblemCfg.lambda = _lambda;
foreach (float _c in CSet)
{
for (int i = 0; i < SVMs.Count; i++)
{
SVMs[i].ProblemCfg.c = _c;
SVMs[i].Train();
}
float performance = this.GetHitRate(CrossValidationSet);
if (CrossValParams == null) CrossValParams = new float[3];
if (performance > CrossValParams[0])
{
CrossValParams[0] = performance;
CrossValParams[1] = _lambda;
CrossValParams[2] = _c;
}
}
}
//Train with best parameters
for (int i = 0; i < SVMs.Count; i++)
{
SVMs[i].ProblemCfg.lambda = CrossValParams[1];
SVMs[i].ProblemCfg.c = CrossValParams[2];
SVMs[i].Train();
}
return CrossValParams[0];
}
/// <summary>Trains current SVM with cross-validation, adjusting kernel parameter lambda and box parameter C. Returns best performance so far</summary>
/// <param name="CrossValidationSetPercent">Percentage of training examples that should be used as cross validation set</param>
/// <param name="lambdaSet">Values of lambda to try</param>
/// <param name="CSet">Values of c to try</param>
public float TrainWithCrossValidation(float CrossValidationSetPercent, float[] lambdaSet, float[] CSet)
{
if (alphaList == null || alphaList.Count != TrainingSet.getN)
{
//Problem changed, previous values dont make sense
initializeWithZeros();
CrossValParams = null;
}
#region Constructs cross validation set
TrainingSet CrossValidationSet = new TrainingSet();
int nCrossSet = (int)(CrossValidationSetPercent * (float)this.TrainingSet.getN);
Random rnd = new Random();
for (int i = 0; i < nCrossSet; i++)
{
int ind = rnd.Next(0, this.TrainingSet.trainingArray.Count - 1);
TrainingUnit u = this.TrainingSet.trainingArray[ind];
this.TrainingSet.trainingArray.Remove(u);
CrossValidationSet.addTrainingUnit(u);
}
#endregion
#region Loops through lambdas and Cs and finds maximum crossvalidation
foreach (float _lambda in lambdaSet)
{
this.ProblemCfg.lambda = _lambda;
this.initializeWithZeros();
PreComputeKernels();
foreach (float _c in CSet)
{
this.ProblemCfg.c = _c;
//ProblemSolver.solveSMOStartingFromPreviousSolution(this);
ProblemSolver.solveSMOStartingFromZero(this);
float performance = this.GetHitRate(CrossValidationSet);
if (CrossValParams == null) CrossValParams = new float[3];
if (performance > CrossValParams[0])
{
CrossValParams[0] = performance;
CrossValParams[1] = _lambda;
CrossValParams[2] = _c;
}
}
}
#endregion
#region Trains with best parameters so far
this.ProblemCfg.lambda = CrossValParams[1];
this.ProblemCfg.c = CrossValParams[2];
this.Train();
#endregion
return CrossValParams[0];
}
private static void updateErrorsCache(TrainingSet trainingSet, SVM currentSolution,
float oldAlphai, float newAlphai, int iIndex,
float oldAlphaj, float newAlphaj, int jIndex,
float oldB, float newB)
{
float alphaiDif = newAlphai - oldAlphai;
float alphajDif = newAlphaj - oldAlphaj;
float BDif = newB - oldB;
if (trainingSet.trainingArray[iIndex].y < 0) alphaiDif = -alphaiDif;
if (trainingSet.trainingArray[jIndex].y < 0) alphajDif = -alphajDif;
for (int t = 0; t < trainingSet.getN; t++)
{
float variation = alphaiDif * trainingSet.kernels[iIndex][t];
variation += alphajDif * trainingSet.kernels[jIndex][t];
variation += BDif;
trainingSet.errors[t] += variation;
}
}
/// <summary>Computes hit rates for a given test set</summary>
/// <param name="samples">Test set to be used</param>
public float GetHitRate(TrainingSet samples)
{
float rate = 0;
foreach (TrainingUnit tu in samples.trainingArray)
{
bool c = Classify(tu);
if ((c && tu.y == 1) || ((!c) && tu.y == -1)) rate++;
}
return rate / (float)samples.getN;
}
/// <summary>Gets SVM hit rate</summary>
/// <param name="TestSet">Test set</param>
public float GetHitRate(TrainingSet TestSet)
{
float rate = 0, val;
foreach (TrainingUnit tu in TestSet.trainingArray)
{
float resp = Classify(tu, out val);
if (resp == tu.y) rate++;
}
return rate / (float)TestSet.trainingArray.Count;
}
