/// <summary>
/// SVM
/// </summary>
/// <param name="dataFilename"></param>
/// <param name="filenameToSave"></param>
/// <param name="filenameToLoad"></param>
private void BuildSvmClassifier(string dataFilename, string filenameToSave, string filenameToLoad)
{
//C_SVCのパラメータ
const float SvmC = 1000;
//RBFカーネルのパラメータ
const float SvmGamma = 0.1f;
CvMat data = null;
CvMat responses = null;
CvMat sampleIdx = null;
int nsamplesAll = 0, ntrainSamples = 0;
double trainHr = 0, testHr = 0;
CvSVM svm = new CvSVM();
CvTermCriteria criteria = new CvTermCriteria(100, 0.001);
try
{
ReadNumClassData(dataFilename, 16, out data, out responses);
}
catch
{
Console.WriteLine("Could not read the database {0}", dataFilename);
return;
}
Console.WriteLine("The database {0} is loaded.", dataFilename);
nsamplesAll = data.Rows;
ntrainSamples = (int)(nsamplesAll * 0.2);
// Create or load Random Trees classifier
if (filenameToLoad != null)
{
// load classifier from the specified file
svm.Load(filenameToLoad);
ntrainSamples = 0;
if (svm.GetSupportVectorCount() == 0)
{
Console.WriteLine("Could not read the classifier {0}", filenameToLoad);
return;
}
Console.WriteLine("The classifier {0} is loaded.", filenameToLoad);
}
else
{
// create classifier by using <data> and <responses>
Console.Write("Training the classifier ...");
// 2. create sample_idx
sampleIdx = new CvMat(1, nsamplesAll, MatrixType.U8C1);
{
CvMat mat;
Cv.GetCols(sampleIdx, out mat, 0, ntrainSamples);
mat.Set(CvScalar.RealScalar(1));
Cv.GetCols(sampleIdx, out mat, ntrainSamples, nsamplesAll);
mat.SetZero();
}
// 3. train classifier
// 方法、カーネルにより使わないパラメータは0で良く、
// 重みについてもNULLで良い
svm.Train(data, responses, null, sampleIdx, new CvSVMParams(CvSVM.C_SVC, CvSVM.RBF, 0, SvmGamma, 0, SvmC, 0, 0, null, criteria));
Console.WriteLine();
}
// compute prediction error on train and test data
for (int i = 0; i < nsamplesAll; i++)
{
double r;
CvMat sample;
Cv.GetRow(data, out sample, i);
r = svm.Predict(sample);
// compare results
Console.WriteLine(
"predict: {0}, responses: {1}, {2}",
(char)r,
(char)responses.DataArraySingle[i],
Math.Abs((double)r - responses.DataArraySingle[i]) <= float.Epsilon ? "Good!" : "Bad!"
);
r = Math.Abs((double)r - responses.DataArraySingle[i]) <= float.Epsilon ? 1 : 0;
if (i < ntrainSamples)
trainHr += r;
else
testHr += r;
}
testHr /= (double)(nsamplesAll - ntrainSamples);
trainHr /= (double)ntrainSamples;
Console.WriteLine("Gamma={0:F5}, C={1:F5}", SvmGamma, SvmC);
if (filenameToLoad != null)
{
Console.WriteLine("Recognition rate: test = {0:F1}%", testHr * 100.0);
}
else
{
Console.WriteLine("Recognition rate: train = {0:F1}%, test = {1:F1}%", trainHr * 100.0, testHr * 100.0);
}
Console.WriteLine("Number of Support Vector: {0}", svm.GetSupportVectorCount());
// Save SVM classifier to file if needed
if (filenameToSave != null)
{
svm.Save(filenameToSave);
}
Console.Read();
if (sampleIdx != null) sampleIdx.Dispose();
data.Dispose();
responses.Dispose();
svm.Dispose();
}
public void Run()
{
// Training data
var points = new CvPoint2D32f[500];
var responses = new int[points.Length];
var rand = new Random();
for (int i = 0; i < responses.Length; i++)
{
double x = rand.Next(0, 300);
double y = rand.Next(0, 300);
points[i] = new CvPoint2D32f(x, y);
responses[i] = (y > f(x)) ? 1 : 2;
}
// Show training data and f(x)
using (Mat pointsPlot = Mat.Zeros(300, 300, MatType.CV_8UC3))
{
for (int i = 0; i < points.Length; i++)
{
int x = (int)points[i].X;
int y = (int)(300 - points[i].Y);
int res = responses[i];
Scalar color = (res == 1) ? Scalar.Red : Scalar.GreenYellow;
pointsPlot.Circle(x, y, 2, color, -1);
}
// f(x)
for (int x = 1; x < 300; x++)
{
int y1 = (int)(300 - f(x - 1));
int y2 = (int)(300 - f(x));
pointsPlot.Line(x - 1, y1, x, y2, Scalar.LightBlue, 1);
}
Window.ShowImages(pointsPlot);
}
// Train
var dataMat = new Mat(points.Length, 2, MatType.CV_32FC1, points);
var resMat = new Mat(responses.Length, 1, MatType.CV_32SC1, responses);
using (var svm = new CvSVM())
{
// normalize data
dataMat /= 300.0;
var criteria = TermCriteria.Both(1000, 0.000001);
var param = new CvSVMParams(
SVMType.CSvc,
SVMKernelType.Rbf,
100.0, // degree
100.0, // gamma
1.0, // coeff0
1.0, // c
0.5, // nu
0.1, // p
null,
criteria);
svm.Train(dataMat, resMat, null, null, param);
// Predict for each 300x300 pixel
using (Mat retPlot = Mat.Zeros(300, 300, MatType.CV_8UC3))
{
for (int x = 0; x < 300; x++)
{
for (int y = 0; y < 300; y++)
{
float[] sample = {x / 300f, y / 300f};
var sampleMat = new CvMat(1, 2, MatrixType.F32C1, sample);
int ret = (int)svm.Predict(sampleMat);
var plotRect = new CvRect(x, 300 - y, 1, 1);
if (ret == 1)
retPlot.Rectangle(plotRect, Scalar.Red);
else if (ret == 2)
retPlot.Rectangle(plotRect, Scalar.GreenYellow);
}
}
Window.ShowImages(retPlot);
}
}
}