public void Process(RNN <T> rnn, DataSet <T> trainingSet, RunningMode runningMode, int totalSequenceNum)
{
//Shffle training corpus
trainingSet.Shuffle();
for (var i = 0; i < trainingSet.SequenceList.Count; i++)
{
var pSequence = trainingSet.SequenceList[i];
int wordCnt = 0;
if (pSequence is Sequence)
{
wordCnt = (pSequence as Sequence).States.Length;
}
else
{
SequencePair sp = pSequence as SequencePair;
if (sp.srcSentence.TokensList.Count > rnn.MaxSeqLength)
{
continue;
}
wordCnt = sp.tgtSequence.States.Length;
}
if (wordCnt > rnn.MaxSeqLength)
{
continue;
}
Interlocked.Add(ref processedWordCnt, wordCnt);
int[] predicted;
if (IsCRFTraining)
{
predicted = rnn.ProcessSequenceCRF(pSequence as Sequence, runningMode);
}
else
{
Matrix <float> m;
predicted = rnn.ProcessSequence(pSequence, runningMode, false, out m);
}
int newTknErrCnt;
if (pSequence is Sequence)
{
newTknErrCnt = GetErrorTokenNum(pSequence as Sequence, predicted);
}
else
{
newTknErrCnt = GetErrorTokenNum((pSequence as SequencePair).tgtSequence, predicted);
}
Interlocked.Add(ref tknErrCnt, newTknErrCnt);
if (newTknErrCnt > 0)
{
Interlocked.Increment(ref sentErrCnt);
}
Interlocked.Increment(ref processedSequence);
if (processedSequence % 1000 == 0)
{
Logger.WriteLine("Progress = {0} ", processedSequence / 1000 + "K/" + totalSequenceNum / 1000.0 + "K");
Logger.WriteLine(" Error token ratio = {0}%", (double)tknErrCnt / (double)processedWordCnt * 100.0);
Logger.WriteLine(" Error sentence ratio = {0}%", (double)sentErrCnt / (double)processedSequence * 100.0);
}
if (ModelSettings.SaveStep > 0 && processedSequence % ModelSettings.SaveStep == 0)
{
//After processed every m_SaveStep sentences, save current model into a temporary file
Logger.WriteLine("Saving temporary model into file...");
rnn.SaveModel("model.tmp");
}
}
}
