public static MultiRegressionSample <TObj> ClassifiedToRegressionSample <TObj>(ClassifiedSample <TObj> sample)
{
if (sample == null)
{
return(null);
}
var classes = sample.Classes.ToList();
var count = classes.Count;
var marks = new double[count][];
for (int i = 0; i < count; i++)
{
marks[i] = new double[count];
marks[i][i] = 1;
}
var result = new MultiRegressionSample <TObj>();
foreach (var data in sample)
{
var cls = data.Value;
var idx = classes.IndexOf(cls);
var mark = marks[idx];
result.Add(data.Key, mark);
}
return(result);
}
private void loadData(string path, MultiRegressionSample <double[][, ]> sample)
{
sample.Clear();
var dir = new DirectoryInfo(path);
var loaded = 0;
var total = dir.GetFiles().Length;
var marks = new Dictionary <int, double[]>();
var lpath = Path.Combine(path, "labels.csv");
using (var lfile = File.Open(lpath, FileMode.Open, FileAccess.Read))
using (var reader = new StreamReader(lfile))
{
reader.ReadLine(); // header
while (true)
{
var line = reader.ReadLine();
if (string.IsNullOrWhiteSpace(line))
{
break;
}
var segs = line.Split(',');
var id = int.Parse(segs[0]);
var len = segs.Length - 1;
var mark = new double[len];
for (int i = 0; i < len; i++)
{
mark[i] = int.Parse(segs[i + 1]) / 255.0D;
}
marks[id] = mark;
}
}
foreach (var file in dir.EnumerateFiles().Where(f => f.Name.StartsWith(IMG_PREFIX)))
{
var fname = Path.GetFileNameWithoutExtension(file.Name);
var id = int.Parse(fname.Substring(IMG_PREFIX.Length));
var data = loadFile(file.FullName);
Utils.ExportImageData(data, @"F:\Work\science\Machine learning\data\main-colors\train\1.png");
sample.Add(data, marks[id]);
loaded++;
if (loaded % 1000 == 0)
{
Console.Write("\rloaded: {0} of {1} ", loaded, total);
}
}
;
Console.WriteLine("\nLoaded files from: {0}", path);
}
private void loadSample(string ipath, string lpath, MultiRegressionSample <double[][, ]> sample)
{
using (var ifile = File.Open(ipath, FileMode.Open, FileAccess.Read))
using (var lfile = File.Open(lpath, FileMode.Open, FileAccess.Read))
{
var header = ReadInt32BigEndian(ifile);
if (header != 2051)
{
throw new Exception("Incorrect MNIST image datafile");
}
header = ReadInt32BigEndian(lfile);
if (header != 2049)
{
throw new Exception("Incorrect MNIST label datafile");
}
var count = ReadInt32BigEndian(ifile);
var rows = ReadInt32BigEndian(ifile);
var cols = ReadInt32BigEndian(ifile);
ReadInt32BigEndian(lfile);
for (int q = 0; q < count; q++)
{
var data = new double[1][, ] {
new double[rows, cols]
};
for (int i = 0; i < rows; i++)
{
for (int j = 0; j < cols; j++)
{
var shade = ifile.ReadByte(); // do not invert 255-* because we want to keep logical format: 0=white, 255=black - not image color format!
data[0][i, j] = shade / 255.0D;
}
}
var label = lfile.ReadByte();
sample.Add(data, m_Marks[label]);
}
Console.WriteLine("Loaded: {0}", ipath);
Console.WriteLine("Loaded: {0}", lpath);
}
}
private void loadSample(string[] fpaths, MultiRegressionSample <double[][, ]> sample)
{
foreach (var fpath in fpaths)
{
using (var file = File.Open(fpath, FileMode.Open, FileAccess.Read))
{
while (true)
{
var label = file.ReadByte();
if (label < 0)
{
break;
}
double[] mark;
if (!m_Marks.TryGetValue(label, out mark))
{
file.Seek(3 * 32 * 32, SeekOrigin.Current);
continue;
}
var data = new double[3][, ];
data[0] = new double[32, 32];
data[1] = new double[32, 32];
data[2] = new double[32, 32];
for (int d = 0; d < 3; d++)
{
for (int y = 0; y < 32; y++)
{
for (int x = 0; x < 32; x++)
{
data[d][y, x] = file.ReadByte() / 255.0D;
}
}
}
sample.Add(data, mark);
}
}
}
}
private void loadSample(string ipath, MultiRegressionSample <double[][, ]> sample)
{
sample.Clear();
using (var ifile = File.Open(ipath, FileMode.Open, FileAccess.Read))
using (var reader = new StreamReader(ifile))
{
var header = reader.ReadLine();
while (true)
{
var str = reader.ReadLine();
if (string.IsNullOrWhiteSpace(str))
{
break;
}
var raw = str.Split(',')
.Select(d => int.Parse(d))
.ToArray();
var label = raw[0];
var data = new double[1][, ] {
new double[IMG_SIZE, IMG_SIZE]
};
for (int i = 1; i <= IMG_SIZE * IMG_SIZE; i++)
{
var shade = raw[i]; // do not invert 255-* because we want to keep logical format: 0=white, 255=black - not image color format!
var x = (i - 1) % IMG_SIZE;
var y = (i - 1) / IMG_SIZE;
data[0][y, x] = shade / 255.0D;
}
sample.Add(data, m_Marks[label]);
}
Console.WriteLine("Loaded: {0}", ipath);
}
}
private void loadTrain(string path, MultiRegressionSample <double[][, ]> sample)
{
sample.Clear();
var dir = new DirectoryInfo(path);
var loaded = 0;
var total = dir.GetFiles().Length;
Parallel.ForEach(dir.EnumerateFiles(), file =>
{
var data = loadFile(file.FullName);
double[] mark;
if (file.Name.StartsWith(CAT_PREFIX))
{
mark = m_Marks[0];
}
else if (file.Name.StartsWith(DOG_PREFIX))
{
mark = m_Marks[1];
}
else
{
throw new MLException("Unknown file");
}
lock (sample)
{
sample.Add(data, mark);
loaded++;
if (loaded % 1000 == 0)
{
Console.Write("\rloaded: {0} of {1} ", loaded, total);
}
}
});
Console.WriteLine("\nLoaded files from: {0}", path);
}
private void loadTrain(string path, string lpath, MultiRegressionSample <double[][, ]> sample)
{
sample.Clear();
using (var lfile = File.Open(lpath, FileMode.Open, FileAccess.Read))
using (var reader = new StreamReader(lfile))
{
reader.ReadLine(); // read label file header
var dir = new DirectoryInfo(path);
foreach (var file in dir.EnumerateFiles())
{
var data = loadFile(file.FullName);
var clsName = reader.ReadLine().Split(',')[1];
var cls = m_Classes.First(c => c.Value.Name.Equals(clsName));
var mark = m_Marks[cls.Key];
sample.Add(data, mark);
}
}
Console.WriteLine("Loaded files from: {0}", path);
}
private void loadData(string path, MultiRegressionSample <double[][, ]> sample)
{
sample.Clear();
var dir = new DirectoryInfo(path);
var loaded = 0;
var total = dir.GetFiles().Length;
foreach (var file in dir.EnumerateFiles())
{
var data = LoadFile(file.FullName);
//Utils.ExportImageData(data, @"F:\Work\science\Machine learning\data\cat-dog\train\"+(c++)+".png");
double[] mark;
if (file.Name.StartsWith(CAT_PREFIX))
{
mark = m_Marks[0];
}
else if (file.Name.StartsWith(DOG_PREFIX))
{
mark = m_Marks[1];
}
else
{
throw new MLException("Unknown file");
}
sample.Add(data, mark);
loaded++;
if (loaded % 1000 == 0)
{
Console.Write("\rloaded: {0} of {1} ", loaded, total);
}
}
;
Console.WriteLine("\nLoaded files from: {0}", path);
}
private void loadSample(string[] fpaths, MultiRegressionSample <double[][, ]> sample)
{
foreach (var fpath in fpaths)
{
using (var file = File.Open(fpath, FileMode.Open, FileAccess.Read))
{
while (true)
{
var label = file.ReadByte();
if (label < 0)
{
break;
}
var cls = m_Marks[label];
var data = new double[3][, ];
data[0] = new double[32, 32];
data[1] = new double[32, 32];
data[2] = new double[32, 32];
for (int d = 0; d < 3; d++)
{
for (int y = 0; y < 32; y++)
{
for (int x = 0; x < 32; x++)
{
data[d][y, x] = file.ReadByte() / 255.0D;
}
}
}
sample.Add(data, cls);
}
}
}
}
private void onTestButtonClick(object sender, RoutedEventArgs e)
{
var path = @"F:\Work\science\Machine learning\data\cat-dog\train\kaggle";
var errors1 = 0;
var errors1C = 0;
var errors1D = 0;
var errors2 = 0;
var errors2C = 0;
var errors2D = 0;
var errorsC1 = 0;
var errorsC2 = 0;
var errorsR = 0;
var pct1 = 0;
var pct1C = 0;
var pct1D = 0;
var pct2 = 0;
var pct2C = 0;
var pct2D = 0;
var pctC = 0;
var pctC1 = 0;
var pctC2 = 0;
var pctR = 0;
var alp1 = 0.95D;
var alp2 = 0.05D;
var dir = new DirectoryInfo(path);
var total = dir.GetFiles().Length;
var sample = new MultiRegressionSample <double[][, ]>();
var cat = new double[] { 1.0D, 0.0D };
var dog = new double[] { 0.0D, 1.0D };
int cnt = 0;
foreach (var file in dir.EnumerateFiles().Shuffle(0).Skip(10000).Take(500))
{
var fname = Path.GetFileNameWithoutExtension(file.Name);
var expected = fname.StartsWith("cat.") ? 0 : 1;
var data1 = getNetData(file.FullName);
double[][,] data2;
using (var image = (Bitmap)System.Drawing.Image.FromFile(file.FullName))
data2 = getNetFData(image);
sample.Add(data2, expected == 0 ? cat : dog);
var result1 = m_Network.Calculate(data1).Select(d => d[0, 0]).ToArray();
var actual1 = ML.Core.Mathematics.MathUtils.ArgMax(result1);
if (expected != actual1)
{
if (expected == 0)
{
errors1C++;
}
else
{
errors1D++;
}
errors1++;
}
var result2 = m_NetworkF.Calculate(data2).Select(d => d[0, 0]).ToArray();
var actual2 = ML.Core.Mathematics.MathUtils.ArgMax(result2);
if (expected != actual2)
{
if (expected == 0)
{
errors2C++;
}
else
{
errors2D++;
}
errors2++;
}
var resultR = new double[result1.Length];
resultR[0] = alp1 * result1[0] + (1 - alp1) * result2[0];
resultR[1] = alp2 * result1[1] + (1 - alp2) * result2[1];
var actualR = ML.Core.Mathematics.MathUtils.ArgMax(resultR);
if (expected != actualR)
{
errorsR++;
}
if ((expected != actual1) && (expected != actual2))
{
if (expected == 0)
{
errorsC1++;
}
else
{
errorsC2++;
}
}
cnt++;
pct1 = errors1 * 100 / cnt;
pct2 = errors2 * 100 / cnt;
pctC1 = errorsC1 * 100 / cnt;
pctC2 = errorsC2 * 100 / cnt;
pctC = (errorsC1 + errorsC2) * 100 / cnt;
pctR = errorsR * 100 / cnt;
}
var alg = new BackpropAlgorithm(m_NetworkF);
var err = alg.GetErrors(sample, 0, true);
var message = "Errors1: {0}%, Errors2: {1}%, ErrorsC: {2}%, ErrorR: {3}%";
MessageBox.Show(string.Format(message, pct1, pct2, pctC, pctR));
}
