Package com.github.neuralnetworks.calculation

Examples of com.github.neuralnetworks.calculation.OutputError

66
67
68
69
70
71
72
73
74
75
76
77
      StringBuilder sb = new StringBuilder();
      sb.append(((finishTime - startTime) / 1000f) + " s  total time" + s);
      sb.append((miniBatchTotalTime / (miniBatches * 1000f)) + " s  per minibatch of " + miniBatches + " mini batches" + s);
      if (event instanceof TestingFinishedEvent) {
    Trainer<?> t = (Trainer<?>) event.getSource();
    OutputError oe = t.getOutputError();
    sb.append(oe.getTotalErrorSamples() + "/" + oe.getTotalInputSize() + " samples (" + oe.getTotalNetworkError() + ", " + (oe.getTotalNetworkError() * 100) + "%) error" + s + s);
      }

      System.out.print(sb.toString());
  } else if (event instanceof MiniBatchFinishedEvent) {
      miniBatches++;
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
    NeuralNetwork n = t.getNeuralNetwork();

    if (n.getLayerCalculator() != null) {
        Set<Layer> calculatedLayers = new UniqueList<>();
        TrainingInputData input = null;
        OutputError outputError = t.getOutputError();
        outputError.reset();
        inputProvider.reset();

        while ((input = inputProvider.getNextInput()) != null) {
      calculatedLayers.clear();
      calculatedLayers.add(n.getInputLayer());
      ValuesProvider vp = mbe.getResults();
      if (vp == null) {
          vp = new ValuesProvider();
      }

      vp.addValues(n.getInputLayer(), input.getInput());
      n.getLayerCalculator().calculate(n, n.getOutputLayer(), calculatedLayers, vp);

      outputError.addItem(vp.getValues(n.getOutputLayer()), input.getTarget());
        }

        float e = outputError.getTotalNetworkError();
        if (e <= acceptanceError) {
      System.out.println("Stopping at error " + e + " (" + (e * 100) + "%) for " + mbe.getBatchCount() + " minibatches");
      t.stopTraining();
        }
    }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
  NeuralNetworkImpl mlp = NNFactory.mlpSigmoid(new int[] { 4, 2, 3 }, true);

  // training and testing data providers
  IrisInputProvider trainInputProvider = new IrisInputProvider(150, 300000, new IrisTargetMultiNeuronOutputConverter(), false, true, false);
  IrisInputProvider testInputProvider = new IrisInputProvider(1, 150, new IrisTargetMultiNeuronOutputConverter(), false, true, false);
  OutputError outputError = new MultipleNeuronsOutputError();

  // trainer
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, outputError, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f);

  // log data
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
  // training and testing data providers
  IrisInputProvider trainInputProvider = new IrisInputProvider(new IrisTargetMultiNeuronOutputConverter(), false);
  trainInputProvider.addInputModifier(new ScalingInputFunction(trainInputProvider));
  IrisInputProvider testInputProvider = new IrisInputProvider(new IrisTargetMultiNeuronOutputConverter(), false);
  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));
  OutputError outputError = new MultipleNeuronsOutputError();

  // trainer
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, outputError, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f, 0f, 150, 1, 2000);

  // log data
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
  trainInputProvider.addInputModifier(new ScalingInputFunction(trainInputProvider));

  TrainingInputProviderImpl testInputProvider = new CSVInputProvider(new File(inputPath), new File(targetPath));
  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));

  OutputError outputError = new MultipleNeuronsOutputError();

  // trainer
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, outputError, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f, 0f, 150, 1, 2000);

  // log data
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
      triggerEvent(new TestingStartedEvent(this));

      Set<Layer> calculatedLayers = new UniqueList<>();
      ValuesProvider results = TensorFactory.tensorProvider(n, getTestBatchSize(), Environment.getInstance().getUseDataSharedMemory());

      OutputError oe = getOutputError();
      if (oe != null) {
    oe.reset();
    results.add(oe, results.get(n.getOutputLayer()).getDimensions());
      }

      TrainingInputData input = new TrainingInputDataImpl(results.get(n.getInputLayer()), results.get(oe));
      for (int i = 0; i < ip.getInputSize(); i += getTestBatchSize()) {
    ip.populateNext(input);
    calculatedLayers.clear();
    calculatedLayers.add(n.getInputLayer());
    n.getLayerCalculator().calculate(n, n.getOutputLayer(), calculatedLayers, results);
   
    if (oe != null) {
        oe.addItem(results.get(n.getOutputLayer()), input.getTarget());
    }
   
    triggerEvent(new MiniBatchFinishedEvent(this, input, results, null));
      }
     
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
      StringBuilder sb = new StringBuilder();
      sb.append(((finishTime - startTime) / 1000f) + " s  total time" + s);
      sb.append((miniBatchTotalTime / (miniBatches * 1000f)) + " s  per minibatch of " + miniBatches + " batches" + s);
      if (event instanceof TestingFinishedEvent) {
    Trainer<?> t = (Trainer<?>) event.getSource();
    OutputError oe = t.getOutputError();
    sb.append(oe.getTotalErrorSamples() + "/" + oe.getTotalInputSize() + " samples (" + oe.getTotalNetworkError() + ", " + (oe.getTotalNetworkError() * 100) + "%) error" + s + s);
      }

      System.out.print(sb.toString());
  } else if (event instanceof MiniBatchFinishedEvent) {
      miniBatches++;
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
      if (mbe.getBatchCount() % validationFrequency == 0) {
    OneStepTrainer<?> t = (OneStepTrainer<?>) event.getSource();
    NeuralNetwork n = t.getNeuralNetwork();

    if (n.getLayerCalculator() != null) {
        OutputError outputError = t.getOutputError();
        outputError.reset();
        inputProvider.reset();

        ValuesProvider vp = mbe.getResults();
        if (vp == null) {
      vp = TensorFactory.tensorProvider(n, 1, Environment.getInstance().getUseDataSharedMemory());
        }
        if (vp.get(outputError) == null) {
      vp.add(outputError, vp.get(n.getOutputLayer()).getDimensions());
        }
        TrainingInputData input = new TrainingInputDataImpl(vp.get(n.getInputLayer()), vp.get(outputError));

        Set<Layer> calculatedLayers = new UniqueList<>();
        for (int i = 0; i < inputProvider.getInputSize(); i++) {
      inputProvider.populateNext(input);
      calculatedLayers.clear();
      calculatedLayers.add(n.getInputLayer());

      n.getLayerCalculator().calculate(n, n.getOutputLayer(), calculatedLayers, vp);

      outputError.addItem(vp.get(n.getOutputLayer()), input.getTarget());
        }

        float e = outputError.getTotalNetworkError();
        if (e <= acceptanceError) {
      System.out.println("Stopping at error " + e + " (" + (e * 100) + "%) for " + mbe.getBatchCount() + " minibatches");
      t.stopTraining();
        }
    }
View Full Code Here
TOP

Related Classes of com.github.neuralnetworks.calculation.OutputError

  • com.github.neuralnetworks.samples.test.IrisTest
  • com.github.neuralnetworks.training.events.EarlyStoppingListener
  • com.github.neuralnetworks.training.events.LogTrainingListener
  • com.github.neuralnetworks.training.Trainer
    • Copyright © 2018 www.massapicom. 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.