Java Code Examples for org.deeplearning4j.earlystopping.saver.LocalFileModelSaver

The following examples show how to use org.deeplearning4j.earlystopping.saver.LocalFileModelSaver. These examples are extracted from open source projects. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
public void train() throws IOException {

        MnistDataSetIterator mnistTrain = new MnistDataSetIterator(MINI_BATCH_SIZE, true, 12345);

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .seed(SEED)
                .learningRate(LEARNING_RATE)
                .weightInit(WeightInit.XAVIER)
                .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
                .updater(Updater.NESTEROVS)
                .list()
                .layer(0, new ConvolutionLayer.Builder(5, 5)
                        .nIn(CHANNELS)
                        .stride(1, 1)
                        .nOut(20)
                        .activation(Activation.IDENTITY)
                        .build())
                .layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX)
                        .kernelSize(2, 2)
                        .stride(2, 2)
                        .build())
                .layer(2, new ConvolutionLayer.Builder(5, 5)
                        .nIn(20)
                        .stride(1, 1)
                        .nOut(50)
                        .activation(Activation.IDENTITY)
                        .build())
                .layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX)
                        .kernelSize(2, 2)
                        .stride(2, 2)
                        .build())
                .layer(4, new DenseLayer.Builder().activation(Activation.RELU)
                        .nIn(800)
                        .nOut(128).build())
                .layer(5, new DenseLayer.Builder().activation(Activation.RELU)
                        .nIn(128)
                        .nOut(64).build())
                .layer(6, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
                        .nOut(OUTPUT)
                        .activation(Activation.SOFTMAX)
                        .build())
                .setInputType(InputType.convolutionalFlat(28, 28, 1))
                .backprop(true).pretrain(false).build();

        EarlyStoppingConfiguration earlyStoppingConfiguration = new EarlyStoppingConfiguration.Builder()
                .epochTerminationConditions(new MaxEpochsTerminationCondition(MAX_EPOCHS))
                .scoreCalculator(new AccuracyCalculator(new MnistDataSetIterator(MINI_BATCH_SIZE, false, 12345)))
                .evaluateEveryNEpochs(1)
                .modelSaver(new LocalFileModelSaver(OUT_DIR))
                .build();

        EarlyStoppingTrainer trainer = new EarlyStoppingTrainer(earlyStoppingConfiguration, conf, mnistTrain);

        EarlyStoppingResult<MultiLayerNetwork> result = trainer.fit();

        log.info("Termination reason: " + result.getTerminationReason());
        log.info("Termination details: " + result.getTerminationDetails());
        log.info("Total epochs: " + result.getTotalEpochs());
        log.info("Best epoch number: " + result.getBestModelEpoch());
        log.info("Score at best epoch: " + result.getBestModelScore());
    }
 
Example 2
Source Project: dl4j-quickstart   Source File: Trainer.java    License: Apache License 2.0 4 votes vote down vote up
public static void main(String... args) throws java.io.IOException {
    // create the data iterators for emnist
    DataSetIterator emnistTrain = new EmnistDataSetIterator(emnistSet, batchSize, true);
    DataSetIterator emnistTest = new EmnistDataSetIterator(emnistSet, batchSize, false);

    int outputNum = EmnistDataSetIterator.numLabels(emnistSet);

    // network configuration (not yet initialized)
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
            .seed(rngSeed)
            .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
            .updater(new Adam())
            .l2(1e-4)
            .list()
            .layer(new DenseLayer.Builder()
                    .nIn(numRows * numColumns) // Number of input datapoints.
                    .nOut(1000) // Number of output datapoints.
                    .activation(Activation.RELU) // Activation function.
                    .weightInit(WeightInit.XAVIER) // Weight initialization.
                    .build())
            .layer(new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
                    .nIn(1000)
                    .nOut(outputNum)
                    .activation(Activation.SOFTMAX)
                    .weightInit(WeightInit.XAVIER)
                    .build())
            .pretrain(false).backprop(true)
            .build();

    // create the MLN
    MultiLayerNetwork network = new MultiLayerNetwork(conf);
    network.init();

    // pass a training listener that reports score every N iterations
    network.addListeners(new ScoreIterationListener(reportingInterval));

    // here we set up an early stopping trainer
    // early stopping is useful when your trainer runs for
    // a long time or you need to programmatically stop training
    EarlyStoppingConfiguration esConf = new EarlyStoppingConfiguration.Builder()
            .epochTerminationConditions(new MaxEpochsTerminationCondition(5))
            .iterationTerminationConditions(new MaxTimeIterationTerminationCondition(20, TimeUnit.MINUTES))
            .scoreCalculator(new DataSetLossCalculator(emnistTest, true))
            .evaluateEveryNEpochs(1)
            .modelSaver(new LocalFileModelSaver(System.getProperty("user.dir")))
            .build();

    // training
    EarlyStoppingTrainer trainer = new EarlyStoppingTrainer(esConf, network, emnistTrain);
    EarlyStoppingResult result = trainer.fit();

    // print out early stopping results
    System.out.println("Termination reason: " + result.getTerminationReason());
    System.out.println("Termination details: " + result.getTerminationDetails());
    System.out.println("Total epochs: " + result.getTotalEpochs());
    System.out.println("Best epoch number: " + result.getBestModelEpoch());
    System.out.println("Score at best epoch: " + result.getBestModelScore());

    // evaluate basic performance
    Evaluation eval = network.evaluate(emnistTest);
    System.out.println(eval.accuracy());
    System.out.println(eval.precision());
    System.out.println(eval.recall());

    // evaluate ROC and calculate the Area Under Curve
    ROCMultiClass roc = network.evaluateROCMultiClass(emnistTest);
    System.out.println(roc.calculateAverageAUC());

    // calculate AUC for a single class
    int classIndex = 0;
    System.out.println(roc.calculateAUC(classIndex));

    // optionally, you can print all stats from the evaluations
    System.out.println(eval.stats());
    System.out.println(roc.stats());
}
 
Example 3
Source Project: deeplearning4j   Source File: TestEarlyStopping.java    License: Apache License 2.0 4 votes vote down vote up
@Test
public void testEarlyStoppingMaximizeScore() throws Exception {
    Nd4j.getRandom().setSeed(12345);

    int outputs = 2;

    DataSet ds = new DataSet(
            Nd4j.rand(new int[]{3, 10, 50}),
            TestUtils.randomOneHotTimeSeries(3, outputs, 50, 12345));
    DataSetIterator train = new ExistingDataSetIterator(
            Arrays.asList(ds, ds, ds, ds, ds, ds, ds, ds, ds, ds));
    DataSetIterator test = new SingletonDataSetIterator(ds);


    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
            .seed(123)
            .weightInit(WeightInit.XAVIER)
            .updater(new Adam(0.1))
            .activation(Activation.ELU)
            .l2(1e-5)
            .gradientNormalization(GradientNormalization
                    .ClipElementWiseAbsoluteValue)
            .gradientNormalizationThreshold(1.0)
            .list()
            .layer(0, new LSTM.Builder()
                    .nIn(10)
                    .nOut(10)
                    .activation(Activation.TANH)
                    .gateActivationFunction(Activation.SIGMOID)
                    .dropOut(0.5)
                    .build())
            .layer(1, new RnnOutputLayer.Builder()
                    .nIn(10)
                    .nOut(outputs)
                    .activation(Activation.SOFTMAX)
                    .lossFunction(LossFunctions.LossFunction.MCXENT)
                    .build())
            .build();

    File f = testDir.newFolder();
    EarlyStoppingModelSaver<MultiLayerNetwork> saver = new LocalFileModelSaver(f.getAbsolutePath());
    EarlyStoppingConfiguration<MultiLayerNetwork> esConf =
            new EarlyStoppingConfiguration.Builder<MultiLayerNetwork>()
                    .epochTerminationConditions(
                            new MaxEpochsTerminationCondition(10),
                            new ScoreImprovementEpochTerminationCondition(1))
                    .iterationTerminationConditions(
                            new MaxTimeIterationTerminationCondition(10, TimeUnit.MINUTES))
                    .scoreCalculator(new ClassificationScoreCalculator(Evaluation.Metric.F1, test))
                    .modelSaver(saver)
                    .saveLastModel(true)
                    .build();

    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();

    EarlyStoppingTrainer t = new EarlyStoppingTrainer(esConf, net, train);
    EarlyStoppingResult<MultiLayerNetwork> result = t.fit();

    Map<Integer,Double> map = result.getScoreVsEpoch();
    for( int i=1; i<map.size(); i++ ){
        if(i == map.size() - 1){
            assertTrue(map.get(i) <+ map.get(i-1));
        } else {
            assertTrue(map.get(i) > map.get(i-1));
        }
    }
}