static Tuple <bool, int, int> predict_color_and_size(Bgr rgb, Size sz)
{
bool retb = false;
int color_id = -1;
int size_id = -1;
try
{
string dir = System.IO.Path.GetDirectoryName(Program.getCurrentExeFilename());
using (SVM model = new SVM())
{
model.Load(System.IO.Path.Combine(dir, "traindata", "iPhone_color.xml"));
Matrix <float> test = new Matrix <float>(1, 3);
test[0, 0] = (float)rgb.Red;
test[0, 1] = (float)rgb.Green;
test[0, 2] = (float)rgb.Blue;
color_id = (int)model.Predict(test);
Program.logIt($"prodict: colorID={color_id}");
}
using (SVM model = new SVM())
{
model.Load(System.IO.Path.Combine(dir, "traindata", "iPhone_size.xml"));
//model.Load(@"traindata/iPhone_size.xml");
Matrix <float> test = new Matrix <float>(1, 2);
test[0, 0] = (float)sz.Width;
test[0, 1] = (float)sz.Height;
size_id = (int)model.Predict(test);
Program.logIt($"prodict: sizeID={size_id}");
}
retb = true;
}
catch (Exception) { }
return(new Tuple <bool, int, int>(retb, color_id, size_id));
}
static void test(string fn)
{
//string fn = @"C:\projects\local\GradeChecker\GradeChecker\bin\Debug\test.json";
try
{
var jss = new System.Web.Script.Serialization.JavaScriptSerializer();
List <Dictionary <string, object> > datas = jss.Deserialize <List <Dictionary <string, object> > >(System.IO.File.ReadAllText(fn));
string[] keys = testMQ.Properties.Resources.keys.Split(new string[] { Environment.NewLine }, StringSplitOptions.RemoveEmptyEntries);
Matrix <float> data;
Matrix <int> response;
load_data(datas.ToArray(), keys, out data, out response);
using (SVM model = new SVM())
{
model.Load("svm.xml");
for (int i = 0; i < data.Rows; i++)
{
float r = model.Predict(data.GetRow(i));
Dictionary <string, object> d = datas[i];
System.Console.WriteLine($"imei={d["imei"]}, VZW={d["VZW"]}, FD={grade_level[(int)r]}");
}
}
}
catch (Exception) { }
}
public void SaveLoadTest()
{
float[,] trainFeaturesData =
{
{ 0, 0 },
{ 0, 100 },
{ 100, 0 },
{ 100, 100 },
};
var trainFeatures = new Mat(4, 2, MatType.CV_32F, trainFeaturesData);
int[] trainLabelsData = { +1, -1, +1, -1 };
var trainLabels = new Mat(4, 1, MatType.CV_32S, trainLabelsData);
const string fileName = "svm.yml";
if (File.Exists(fileName))
{
File.Delete(fileName);
}
using (var model = SVM.Create())
{
model.Type = SVM.Types.CSvc;
model.KernelType = SVM.KernelTypes.Linear;
model.TermCriteria = new TermCriteria(CriteriaTypes.MaxIter, 100, 1e-6);
model.Train(trainFeatures, SampleTypes.RowSample, trainLabels);
model.Save(fileName);
}
Assert.True(File.Exists(fileName));
string content = File.ReadAllText(fileName);
//Console.WriteLine(content);
//Assert.DoesNotThrow
using (var model2 = SVM.Load(fileName))
{
GC.KeepAlive(model2);
}
using (var model2 = SVM.LoadFromString(content))
{
GC.KeepAlive(model2);
}
using (var fs = new FileStorage(fileName, FileStorage.Modes.Read))
using (var model2 = SVM.Create())
{
var node = fs["opencv_ml_svm"];
Assert.NotNull(node);
#pragma warning disable CS8604
model2.Read(node);
#pragma warning restore CS8604
}
}
public FaceEmotionsClassifier(string modelFilepath)
{
classifier = new SVM();
classifier.Load(modelFilepath);
classifier.C = 2.67f;
classifier.Gamma = 5.383f;
classifier.Type = SVM.SvmType.CSvc;
classifier.SetKernel(SVM.SvmKernelType.Linear);
}
//加载svm模型,也就是哪个xml文件
public static void Load(string fileName)
{
try
{
svm = SVM.Load(fileName);
IsReady = true;
}
catch (Exception)
{
throw new Exception("ERROR：请检查路径是否正确");
}
}
//加载字符识别库
public static void Load(string fileName)
{
try
{
svm = SVM.Load(fileName);
IsReady = true;
}
catch (Exception)
{
throw new Exception("字符识别库加载异常，请检查存放路路径");
}
}
private static float GetOutline_LoadConfig(Image <Bgr, byte> src)
{
SVM svm = new SVM();
svm.Load("4.xml");
//////////////////////////////////////////////////////////////////参数设定
Rectangle rc = new Rectangle();
rc.Width = 28;
rc.Height = 28;//tuxaing daxiao
Rectangle rc1 = new Rectangle();
rc1.Width = 14;
rc1.Height = 14;//bloke
Rectangle rc2 = new Rectangle();
rc2.Width = 7;
rc2.Height = 7;
Rectangle rc3 = new Rectangle();
rc3.Width = 7;
rc3.Height = 7;
///////////////设置参数//////////////////////////////////////////////
Size r1 = new Size();
r1.Width = 1;
r1.Height = 1;
Size r2 = new Size();
r2.Width = 0;
r2.Height = 0;
HOGDescriptor hog = new HOGDescriptor(rc.Size, rc1.Size, rc2.Size, rc3.Size, 9, 1, -1, 0.2, false);
float[] yy = new float[1000000];
Rectangle bb = new Rectangle();
bb.Width = 28;
bb.Height = 28;
Image <Bgr, byte> yyy = new Image <Bgr, byte>(bb.Size);
CvInvoke.cvResize(src, yyy, INTER.CV_INTER_LINEAR);
yy = hog.Compute(yyy, r1, r2, null);
Matrix <float> match = new Matrix <float>(yy);
float result = svm.Predict(match);
return(result);
}
static void Main(string[] args)
{
//training
Train();
//predict:
Console.WriteLine("Load svm model");
var svm = SVM.Load("SVM_RESULT.xml");
var cnt = 0;
Console.WriteLine("Start prediction process");
var starttime = DateTime.Now;
//predict videos:
//foreach (var i in Directory.GetFiles("Videos", "*.mp4"))
//{
// cnt++;
// var start = DateTime.Now;
// var res = PredictV(svm, i);
// Console.WriteLine($"{Path.GetFileName(i)} - Time cost: {(DateTime.Now - start).TotalMilliseconds} ms");
// Console.WriteLine("Results:");
// for (var j = 1; j < 10; j++)
// {
// Console.WriteLine($"{j} - confidence: {res.Count(k => k == j) * 100f / res.Count} %");
// }
//}
//predict imgs
foreach (var i in Directory.GetFiles("JPEGImages", "*- Copy.jpg")) //test cases
{
cnt++;
var start = DateTime.Now;
Console.WriteLine($"{Path.GetFileName(i)} - Result: {Predict(svm, Cv2.ImRead(i, ImreadModes.GrayScale))}, time cost: {(DateTime.Now - start).TotalMilliseconds} ms");
}
Console.WriteLine($"Average speed: {cnt / (DateTime.Now - starttime).TotalSeconds} per second");
//extract video to images:
//foreach (var i in Directory.GetFiles("Videos"))
//{
// Console.WriteLine($"Processing: {Path.GetFileName(i)}");
// ExportToJpg(i);
//}
Console.WriteLine("Finished");
Console.ReadKey();
return;
}
public static int predict_test(double height, double width)
{
int ret = 0;
using (SVM model = new SVM())
{
model.Load(@"data\iphone_size_svm.xml");
Matrix <float> data = new Matrix <float>(1, 2);
data[0, 0] = (float)height;
data[0, 1] = (float)width;
float r = model.Predict(data);
ret = (int)r;
}
return(ret);
}
public static void Load(string fileName)
{
svm = SVM.Load(fileName);
}
static bool handle_motion_V2(Image <Bgr, Byte> frane, Image <Gray, Byte> bg, int idx)
{
bool device_in_place = false;
//Rectangle r = new Rectangle(196, 665, 269, 628);
Rectangle r = new Rectangle(334, 774, 452, 1016);
Image <Bgr, Byte> img1 = frane.Copy(r);
Image <Gray, Byte> imgg = frane.Mat.ToImage <Gray, Byte>().Copy(r);
Image <Gray, Byte> imgbg = bg.Copy(r);
imgg = imgg.AbsDiff(imgbg);
Gray g = imgg.GetAverage();
if (g.MCvScalar.V0 > 13)
{
Rectangle sz = detect_size_old(imgg);
Bgr rgb = sample_color(img1);
Program.logIt($"Device arrival. size: {sz.Size}, color: {rgb} ({g.MCvScalar.V0})");
// report
Console.WriteLine($"Raw Data: size={sz.Size}, color={rgb}");
if (sz.Size.Width > 430)
{
// it is plus mode
Console.WriteLine($"sizeID=2");
}
else if (sz.Size.Width < 400)
{
// it is plus mode
Console.WriteLine($"sizeID=1");
}
else
{
// error. unknown size
Console.WriteLine($"sizeID=-1");
}
// for color
string[] color_note = new string[]
{
"NA",
"Blue (iPhone XR)",
"Gray (iPhone 8 Plus)",
"Red (iPhone 8 Plus)",
"Silver (iPhone 8/iPhone 8 Plus)",
};
try
{
Console.WriteLine($"r={rgb.Red}");
Console.WriteLine($"g={rgb.Green}");
Console.WriteLine($"b={rgb.Blue}");
using (SVM model = new SVM())
{
model.Load(@"traindata/iPhone_color.xml");
Matrix <float> test = new Matrix <float>(1, 3);
test[0, 0] = (float)rgb.Red;
test[0, 1] = (float)rgb.Green;
test[0, 2] = (float)rgb.Blue;
int l = (int)model.Predict(test);
Console.WriteLine($"colorID={l}");
if (l >= 0 && l < color_note.Length)
{
Console.WriteLine($"colorNote={color_note[l]}");
}
}
}
catch (Exception) { }
//Console.WriteLine("Enter device model and color:");
//string info = System.Console.ReadLine();
//img1.Save($"temp_{info}_2.jpg");
//imgbg.Save($"temp_{info}_1.jpg");
//imgg.Save($"temp_{info}_3.jpg");
//Console.WriteLine($"{info}: size={sz.Size}, color={rgb}");
//Program.logIt($"{info}: size={sz.Size}, color={rgb}");
device_in_place = true;
}
else
{
Program.logIt($"Device removal. ({g.MCvScalar.V0})");
device_in_place = false;
}
return(device_in_place);
}
private void button3_Click(object sender, EventArgs e)
{
using (SVM model = new SVM())
{
float train_SVM_accuracy = 0;
int train_time = 0;
while (train_SVM_accuracy < 0.98 && train_time < 20)
{
TrainSVM(train_time, ref train_SVM_accuracy);
train_time++;
}
model.Load("SVM_NOTE.txt");
Matrix <float> test = new Matrix <float>(1, featureNum);
float count = 0, count2 = 0;
float[,] AC = new float[10, 10];
for (int i = 0; i < testSampleCount; i++)
{
for (int j = 0; j < featureNum; j++)
{
test.Data[0, j] = sample.Data[i, j];
}
float response = model.Predict(test);
float classSam = sampleClasses[i, 0];
/**********************10x10********************/
AC[(int)classSam - 1, (int)response - 1]++;
richTextBox6.AppendText("(" + i + ")" + "R=" + response + " C=" + classSam + "\n");
if (response == classSam)
{
count2++;
}
if (response == 10)
{
if (classSam == 10)
{
count++;
}
}
else
{
if (classSam != 10)
{
count++;
}
}
}
for (int a = 0; a < 10; a++)
{
for (int b = 0; b < 10; b++)
{
richTextBox7.AppendText(AC[a, b] + "\t");
}
richTextBox7.AppendText("\n");
}
// model.Save("SVM_NOTE.txt");
float accuracy = count / testSampleCount;
float accuracy2 = count2 / testSampleCount;
//richTextBox3.Text = "count=" + count;
richTextBox3.Text = "分兩類準確率=" + accuracy + " 各類別準確率=" + accuracy2;
}
}