public void LoadFeatureTrainData()
{
foreach (SceneFeatureData scenefeatureData in classifier.Values)
{
scenefeatureData.trainData = FeatureDetector.GetAllTrainImageData(path + @"\" + scenefeatureData.feature.name, scenefeatureData.feature.trainFolders);
}
}
private void test1ToolStripMenuItem_Click(object sender, EventArgs e)
{
FeatureDetector f = new FeatureDetector();
f.Init(@"D:\kwang\Csharp\MyAutoIt\MyAutoIt\bin\Debug\Linage2\Main\Features", configure.features["Main"]);
f.LoadFeatureTrainData();
f.Train();
}
private void testWithTestSetToolStripMenuItem_Click(object sender, EventArgs e)
{
ImageTrainDataSet testDataSet = FeatureDetector.GetAllTrainImageData(testDataPath, configure.trainFolders);
testDataSet.flgCache = true;
byte[] hash = imgClassifier.ComputeHash(testDataSet);
logger.logStr(hash.ToHex());
int testErrCount = imgClassifier.Evaluate(testDataSet);
logger.logStr(String.Format("test {0}", testErrCount));
}
private void loadTrainDataToolStripMenuItem_Click_1(object sender, EventArgs e)
{
trainData = FeatureDetector.GetAllTrainImageData(dataPath, configure.trainFolders);
trainData = trainData.BalanceData();
trainData.Shuffle();
testData = trainData.SplitTestData((int)(0.1 * trainData.Count()));
TrainDataInfo[] infos = trainData.GetInfo(configure.trainFolders.Count());
TrainDataInfo[] testinfos = testData.GetInfo(configure.trainFolders.Count());
logger.logStr(Utils.ToJsonString(infos, true));
logger.logStr(Utils.ToJsonString(testinfos, true));
}
public void Init()
{
Accord.Math.Random.Generator.Seed = 0;
logger = new MyLogger(txtDebug);
logger.logStr("Start");
String configFile = configPath + @"\AutoIt.json";
try
{
configure = JsonConvert.DeserializeObject <AutoItConfigure>(File.ReadAllText(configFile));
//configure.features.Add("test",new SceneFeature());
foreach (var s in configure.features.Keys)
{
foreach (var f in configure.features[s])
{
String fname = s + @"\" + f.name;
sceneFeatures.Add(fname, new SceneFeatureData()
{
feature = f,
trainData = FeatureDetector.GetAllTrainImageData(dataPath + @"\" + s + @"\Features\" + f.name, f.trainFolders)
}
);
logger.logStr("add " + fname);
}
}
}
catch (Exception ex)
{
logger.logError("Config not found [" + configFile + "]");
configure = new AutoItConfigure();
}
mask = Utils.CreateMaskBitmap(new Size(1280, 720), configure.areas);
logger.logStr(JsonConvert.SerializeObject(configure, Formatting.Indented));
foreach (String s in configure.trainFolders)
{
cmbFolder.Items.Add(s);
}
Reload();
}
private void trainToolStripMenuItem_Click_1(object sender, EventArgs e)
{
ImageTrainDataSet testDataSet = FeatureDetector.GetAllTrainImageData(testDataPath, configure.trainFolders);
testDataSet.flgCache = true;
int[] labelIndexs = trainData.GetLabelIndexs();
String[] labels = trainData.GetLabels();
var bow = Accord.IO.Serializer.Load <BagOfVisualWords>(dataPath + String.Format(@"\train-{0}.bow", bowSize));
double[][] features = trainData.GetFeature(bow, mask);
int numOutput = trainData.GetNumOutput();
var function = new SigmoidFunction();
logger.logStr("Start Training");
bool flgFound = false;
int count = 0;
while ((flgFound == false) && (count < 100))
{
count++;
var network = new ActivationNetwork(function, bow.NumberOfOutputs, 20, numOutput);
new NguyenWidrow(network).Randomize();
var teacher = new ParallelResilientBackpropagationLearning(network);
BowImageClassifier trainImgClassifier = new BowImageClassifier();
trainImgClassifier.Init(bow, network, mask);
//creat output
double[][] outputs = trainData.GetOutputs(numOutput);
double avgError = 10000.0;
double prevError = avgError;
double bestError = avgError;
int errorCount = 0;
while ((errorCount < 3) && (avgError > 0.00001))
{
//Application.DoEvents();
double[] errors = new double[10];
for (int i = 0; i < 10; i++)
{
errors[i] = teacher.RunEpoch(features, outputs);
}
avgError = errors.Average();
if (prevError > avgError)
{
int trainError = trainImgClassifier.Evaluate(trainData);
int testError = trainImgClassifier.Evaluate(testData);
int testSetError = trainImgClassifier.Evaluate(testDataSet);
logger.logStr(String.Format("{0} {1} {2} {3} {4} #{5}", avgError, prevError, trainError, testError, testSetError, errorCount));
prevError = avgError;
//save best error
if (bestError > avgError)
{
bestError = avgError;
Accord.IO.Serializer.Save(network, dataPath + String.Format(@"\train-{0}.net", bow.NumberOfOutputs));
}
if (trainError + testError + testSetError == 0)
{
flgFound = true;
Accord.IO.Serializer.Save(network, dataPath + String.Format(@"\train-{0}.net", bow.NumberOfOutputs));
break;
}
}
else
{
logger.logStr(String.Format("{0}", avgError));
prevError = 10000.0;
errorCount++;
}
Application.DoEvents();
}
logger.logStr("Done " + bestError + " " + count);
}
}
