public void TestTrainLenetCseg()
{
string bookPath = "data\\0000\\";
string netFileName = "latin-lenet.model";
Linerec.GDef("linerec", "use_reject", 1);
Linerec.GDef("lenet", "junk", 1);
Linerec.GDef("lenet", "epochs", 4);
// create Linerec
Linerec linerec;
if (File.Exists(netFileName))
{
linerec = Linerec.LoadLinerec(netFileName);
}
else
{
linerec = new Linerec("lenet");
LenetClassifier classifier = linerec.GetClassifier() as LenetClassifier;
if (classifier != null)
{
classifier.InitNumSymbLatinAlphabet();
}
}
// temporary disable junk
//linerec.DisableJunk = true;
linerec.StartTraining();
int nepochs = 10;
LineSource lines = new LineSource();
lines.Init(new string[] { "data2" });
//linerec.GetClassifier().Set("epochs", 1);
for (int epoch = 1; epoch <= nepochs; epoch++)
{
linerec.Epoch(epoch);
// load cseg samples
while (!lines.Done())
{
lines.MoveNext();
Intarray cseg = new Intarray();
//Bytearray image = new Bytearray();
string transcript = lines.GetTranscript();
//lines.GetImage(image);
if (!lines.GetCharSegmentation(cseg) && cseg.Length() == 0)
{
Global.Debugf("warn", "skipping book {0} page {1} line {2} (no or bad cseg)",
lines.CurrentBook, lines.CurrentPage, lines.Current);
continue;
}
SegmRoutine.make_line_segmentation_black(cseg);
linerec.AddTrainingLine(cseg, transcript);
}
lines.Reset();
lines.Shuffle();
// do Train and clear Dataset
linerec.FinishTraining();
// do save
if (epoch % 1 == 0)
{
linerec.Save(netFileName);
}
// recognize test line
bool bakDisJunk = linerec.DisableJunk;
linerec.DisableJunk = false;
DoTestLinerecRecognize(linerec, "data2\\", "test1.png");
linerec.DisableJunk = bakDisJunk;
}
// finnaly save
linerec.Save(netFileName);
}
