Package cc.mallet.fst

Examples of cc.mallet.fst.MEMMTrainer.train()

126
127
128
129
130
131
132
133
134
135
136
    MEMM memm = new MEMM (pipe2, null);
    memm.addFullyConnectedStatesForLabels ();
    MEMMTrainer memmt = new MEMMTrainer (memm);
    TransducerEvaluator memmeval = new TokenAccuracyEvaluator (new InstanceList[] {training2, testing2}, new String[] {"Training2", "Testing2"});
    memmt.train (training2, 5);
    memmeval.evaluate(memmt);

    CRFExtractor extor2 = hackCrfExtor (memm);
    Extraction e2 = extor2.extract (new ArrayIterator (data1));
View Full Code Here
122
123
124
125
126
127
128
129
130
131
132
    memm.addStartState();
    memm.setWeightsDimensionAsIn(training);
   
    MEMMTrainer memmt = new MEMMTrainer (memm);
//    memm.gatherTrainingSets (training); // ANNOYING: Need to set up per-instance training sets
    memmt.train (training, 1);  // Set weights dimension, gathers training sets, etc.

//    memm.print();
//    memm.printGradient = true;
//    memm.printInstanceLists();
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
    MEMM memm = new MEMM (p, null);
    memm.addFullyConnectedStatesForLabels ();
    memm.addStartState();
    memm.setWeightsDimensionAsIn(training);
    MEMMTrainer memmt = new MEMMTrainer (memm);
    memmt.train (training, 10);

    MEMM memm2 = (MEMM) TestSerializable.cloneViaSerialization (memm);

    Optimizable.ByGradientValue mcrf1 = memmt.getOptimizableMEMM(training);
    double val1 = mcrf1.getValue ();
View Full Code Here
377
378
379
380
381
382
383
384
385
386
387
      TestOptimizable.testValueAndGradient(minable);
    } else {
      System.out.println("Training Accuracy before training = " + memm.averageTokenAccuracy(lists[0]));
      System.out.println("Testing  Accuracy before training = " + memm.averageTokenAccuracy(lists[1]));
      System.out.println("Training...");
      memmt.train(lists[0], 1);
      System.out.println("Training Accuracy after training = " + memm.averageTokenAccuracy(lists[0]));
      System.out.println("Testing  Accuracy after training = " + memm.averageTokenAccuracy(lists[1]));
      System.out.println("Training results:");
      for (int i = 0; i < lists[0].size(); i++) {
        Instance inst = lists[0].get(i);
View Full Code Here
426
427
428
429
430
431
432
433
434
435
436
    } else {
      System.out.println("Training Accuracy before training = " + crf.averageTokenAccuracy(lists[0]));
      System.out.println("Testing  Accuracy before training = " + crf.averageTokenAccuracy(lists[1]));
      savedCRF = crf;
      System.out.println("Training serialized crf.");
      memmt.train(lists[0], 100);
      double preTrainAcc = crf.averageTokenAccuracy(lists[0]);
      double preTestAcc = crf.averageTokenAccuracy(lists[1]);
      System.out.println("Training Accuracy after training = " + preTrainAcc);
      System.out.println("Testing  Accuracy after training = " + preTestAcc);
      try {
View Full Code Here
508
509
510
511
512
513
514
515
516
517
518
                         null,
                         null,
                         false);
    crf1.setWeightsDimensionAsIn(lists[0]);
    MEMMTrainer memmt1 = new MEMMTrainer (crf1);
    memmt1.train(lists [0]);


    MEMM crf2 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
    crf2.addOrderNStates (lists [0],
                           new int[] { 1, 2, },
View Full Code Here
521
522
523
524
525
526
527
528
529
530
531
                           null,
                           null,
                           false);
    crf2.setWeightsDimensionAsIn(lists[0]);
    MEMMTrainer memmt2 = new MEMMTrainer (crf2);
    memmt2.train(lists [0]);


    MEMM crf3 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
    crf3.addOrderNStates (lists [0],
                         new int[] { 1, 2, },
View Full Code Here
534
535
536
537
538
539
540
541
542
543
544
                         null,
                         null,
                         false);
    crf3.setWeightsDimensionAsIn(lists[0]);
    MEMMTrainer memmt3 = new MEMMTrainer (crf3);
    memmt3.train(lists [0]);

    // Prevent cached values
    double lik1 = getLikelihood (memmt1, lists[0]);
    double lik2 = getLikelihood (memmt2, lists[0]);
    double lik3 = getLikelihood (memmt3, lists[0]);
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.