/// <exception cref="System.IO.IOException"/>
public virtual void Train(IList <Tree> sentences, IdentityHashMap <Tree, byte[]> compressedParses, Treebank testTreebank, string modelPath, string resultsRecordPath)
{
// process:
// we come up with a cost and a derivative for the model
// we always use the gold tree as the example to train towards
// every time through, we will look at the top N trees from
// the LexicalizedParser and pick the best one according to
// our model (at the start, this is essentially random)
// we use QN to minimize the cost function for the model
// to do this minimization, we turn all of the matrices in the
// DVModel into one big Theta, which is the set of variables to
// be optimized by the QN.
Timing timing = new Timing();
long maxTrainTimeMillis = op.trainOptions.maxTrainTimeSeconds * 1000;
int batchCount = 0;
int debugCycle = 0;
double bestLabelF1 = 0.0;
if (op.trainOptions.useContextWords)
{
foreach (Tree tree in sentences)
{
Edu.Stanford.Nlp.Trees.Trees.ConvertToCoreLabels(tree);
tree.SetSpans();
}
}
// for AdaGrad
double[] sumGradSquare = new double[dvModel.TotalParamSize()];
Arrays.Fill(sumGradSquare, 1.0);
int numBatches = sentences.Count / op.trainOptions.batchSize + 1;
log.Info("Training on " + sentences.Count + " trees in " + numBatches + " batches");
log.Info("Times through each training batch: " + op.trainOptions.trainingIterations);
log.Info("QN iterations per batch: " + op.trainOptions.qnIterationsPerBatch);
for (int iter = 0; iter < op.trainOptions.trainingIterations; ++iter)
{
IList <Tree> shuffledSentences = new List <Tree>(sentences);
Java.Util.Collections.Shuffle(shuffledSentences, dvModel.rand);
for (int batch = 0; batch < numBatches; ++batch)
{
++batchCount;
// This did not help performance
//log.info("Setting AdaGrad's sum of squares to 1...");
//Arrays.fill(sumGradSquare, 1.0);
log.Info("======================================");
log.Info("Iteration " + iter + " batch " + batch);
// Each batch will be of the specified batch size, except the
// last batch will include any leftover trees at the end of
// the list
int startTree = batch * op.trainOptions.batchSize;
int endTree = (batch + 1) * op.trainOptions.batchSize;
if (endTree > shuffledSentences.Count)
{
endTree = shuffledSentences.Count;
}
ExecuteOneTrainingBatch(shuffledSentences.SubList(startTree, endTree), compressedParses, sumGradSquare);
long totalElapsed = timing.Report();
log.Info("Finished iteration " + iter + " batch " + batch + "; total training time " + totalElapsed + " ms");
if (maxTrainTimeMillis > 0 && totalElapsed > maxTrainTimeMillis)
{
// no need to debug output, we're done now
break;
}
if (op.trainOptions.debugOutputFrequency > 0 && batchCount % op.trainOptions.debugOutputFrequency == 0)
{
log.Info("Finished " + batchCount + " total batches, running evaluation cycle");
// Time for debugging output!
double tagF1 = 0.0;
double labelF1 = 0.0;
if (testTreebank != null)
{
EvaluateTreebank evaluator = new EvaluateTreebank(AttachModelToLexicalizedParser());
evaluator.TestOnTreebank(testTreebank);
labelF1 = evaluator.GetLBScore();
tagF1 = evaluator.GetTagScore();
if (labelF1 > bestLabelF1)
{
bestLabelF1 = labelF1;
}
log.Info("Best label f1 on dev set so far: " + Nf.Format(bestLabelF1));
}
string tempName = null;
if (modelPath != null)
{
tempName = modelPath;
if (modelPath.EndsWith(".ser.gz"))
{
tempName = Sharpen.Runtime.Substring(modelPath, 0, modelPath.Length - 7) + "-" + Filename.Format(debugCycle) + "-" + Nf.Format(labelF1) + ".ser.gz";
}
SaveModel(tempName);
}
string statusLine = ("CHECKPOINT:" + " iteration " + iter + " batch " + batch + " labelF1 " + Nf.Format(labelF1) + " tagF1 " + Nf.Format(tagF1) + " bestLabelF1 " + Nf.Format(bestLabelF1) + " model " + tempName + op.trainOptions + " word vectors: "
+ op.lexOptions.wordVectorFile + " numHid: " + op.lexOptions.numHid);
log.Info(statusLine);
if (resultsRecordPath != null)
{
FileWriter fout = new FileWriter(resultsRecordPath, true);
// append
fout.Write(statusLine);
fout.Write("\n");
fout.Close();
}
++debugCycle;
}
}
long totalElapsed_1 = timing.Report();
if (maxTrainTimeMillis > 0 && totalElapsed_1 > maxTrainTimeMillis)
{
// no need to debug output, we're done now
log.Info("Max training time exceeded, exiting");
break;
}
}
}
//log.info(Double.toString(score)+" ");
public override int DomainDimension()
{
// TODO: cache this for speed?
return(dvModel.TotalParamSize());
}
