public boolean train (ACRF acrf, InstanceList trainingList, InstanceList validationList, InstanceList testSet, ACRFEvaluator eval, int numIter) { Optimizable.ByGradientValue macrf = createOptimizable (acrf, trainingList); return train (acrf, trainingList, validationList, testSet, eval, numIter, macrf); }
public boolean incrementalTrain (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return incrementalTrain (acrf, training, validation, testing, new LogEvaluator (), numIter); }
public void test (ACRF acrf, InstanceList testing, ACRFEvaluator eval) { test (acrf, testing, new ACRFEvaluator[]{eval}); }
public boolean train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return train (acrf, training, validation, testing, new LogEvaluator (), numIter); }
private static ACRFTrainer createTrainer () { if (usePiecewiseTraining.value) { return new PiecewiseACRFTrainer(); } else if (usePwplTraining.value) { return new PwplACRFTrainer(); } else if (usePlTraining.value) { return new PseudolikelihoodACRFTrainer (); } else { return new DefaultAcrfTrainer (); } }
Optimizable.ByGradientValue macrf) Optimizer maximizer = createMaxer (macrf); converged |= callEvaluator (acrf, trainingList, validationList, testSet, iter, eval);
public boolean train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return train (acrf, training, validation, testing, new LogEvaluator (), numIter); }
private static ACRFTrainer createTrainer () { if (usePiecewiseTraining.value) { return new PiecewiseACRFTrainer(); } else if (usePwplTraining.value) { return new PwplACRFTrainer(); } else if (usePlTraining.value) { return new PseudolikelihoodACRFTrainer (); } else { return new DefaultAcrfTrainer (); } }
Optimizable.ByGradientValue macrf) Optimizer maximizer = createMaxer (macrf); converged |= callEvaluator (acrf, trainingList, validationList, testSet, iter, eval);
public boolean train (ACRF acrf, InstanceList trainingList, InstanceList validationList, InstanceList testSet, ACRFEvaluator eval, int numIter) { Optimizable.ByGradientValue macrf = createOptimizable (acrf, trainingList); return train (acrf, trainingList, validationList, testSet, eval, numIter, macrf); }
public boolean train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return train (acrf, training, validation, testing, new LogEvaluator (), numIter); }
private static ACRFTrainer createTrainer () { if (usePiecewiseTraining.value) { return new PiecewiseACRFTrainer(); } else if (usePwplTraining.value) { return new PwplACRFTrainer(); } else if (usePlTraining.value) { return new PseudolikelihoodACRFTrainer (); } else { return new DefaultAcrfTrainer (); } }
Optimizable.ByGradientValue macrf) Optimizer maximizer = createMaxer (macrf); converged |= callEvaluator (acrf, trainingList, validationList, testSet, iter, eval);
public boolean incrementalTrain (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return incrementalTrain (acrf, training, validation, testing, new LogEvaluator (), numIter); }
public void test (ACRF acrf, InstanceList testing, ACRFEvaluator eval) { test (acrf, testing, new ACRFEvaluator[]{eval}); }
public boolean train (ACRF acrf, InstanceList trainingList, InstanceList validationList, InstanceList testSet, ACRFEvaluator eval, int numIter) { Optimizable.ByGradientValue macrf = createOptimizable (acrf, trainingList); return train (acrf, trainingList, validationList, testSet, eval, numIter, macrf); }
public void train (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, ACRFEvaluator eval, double[] proportions, int iterPerProportion) { for (int i = 0; i < proportions.length; i++) { double proportion = proportions[i]; InstanceList[] lists = training.split (r, new double[]{proportion, 1.0}); logger.info ("ACRF trainer: Round " + i + ", training proportion = " + proportion); train (acrf, lists[0], validation, testing, eval, iterPerProportion); } logger.info ("ACRF trainer: Training on full data"); train (acrf, training, validation, testing, eval, 99999); }
ACRFTrainer trainer = new DefaultAcrfTrainer (); trainer.train (acrf, training, null, testing, 99999);
public boolean incrementalTrain (ACRF acrf, InstanceList training, InstanceList validation, InstanceList testing, int numIter) { return incrementalTrain (acrf, training, validation, testing, new LogEvaluator (), numIter); }
public void test (ACRF acrf, InstanceList testing, ACRFEvaluator eval) { test (acrf, testing, new ACRFEvaluator[]{eval}); }