Java Code Examples for org.deeplearning4j.arbiter.optimize.api.CandidateGenerator#getCandidate()

@Test
public void testSameRanges() {

    ParameterSpace<Double> l1Hyperparam = new ContinuousParameterSpace(0.001, 0.1);
    ParameterSpace<Double> l2Hyperparam = new ContinuousParameterSpace(0.001, 0.1);

    MultiLayerSpace hyperparameterSpace =
                    new MultiLayerSpace.Builder().addLayer(new DenseLayerSpace.Builder().nIn(10).nOut(10).build())
                                    .l1(l1Hyperparam).l2(l2Hyperparam).build();

    CandidateGenerator c = new RandomSearchGenerator(hyperparameterSpace, null);

    Candidate candidate = c.getCandidate();
}
 

@Test
    public void testGridCandidateGenerator(){
        ParameterSpace<Integer> layerSizeParam = new DiscreteParameterSpace<>(32, 48, 64);
        ParameterSpace<Double> learningRateParam = new DiscreteParameterSpace<>(0.005, 0.007, 0.01);

        MultiLayerSpace hyperParamaterSpace = new MultiLayerSpace.Builder()
                .seed(12345)
                .biasInit(1)
                .l2(1e-4)
                .updater(new NesterovsSpace(learningRateParam))
                .addLayer(new DenseLayerSpace.Builder().nIn(10).nOut(layerSizeParam)
                        .weightInit(WeightInit.XAVIER)
                        .activation(Activation.RELU)
                        .build())
                .addLayer(new DenseLayerSpace.Builder().nIn(layerSizeParam).nOut(layerSizeParam)
                        .weightInit(WeightInit.XAVIER)
                        .activation(Activation.RELU)
                        .build())
                .addLayer(new OutputLayerSpace.Builder()
                        .lossFunction(LossFunctions.LossFunction.MSE)
                        .weightInit(WeightInit.XAVIER)
                        .activation(Activation.SOFTMAX)
                        .nIn(layerSizeParam).nOut(10).build())
                .build();

        CandidateGenerator candidateGenerator = new GridSearchCandidateGenerator(hyperParamaterSpace, 30, GridSearchCandidateGenerator.Mode.Sequential, null);
//        CandidateGenerator candidateGenerator = new RandomSearchGenerator(hyperParamaterSpace);

        Set<Pair<Double,Integer>> expCandidates = new HashSet<>();
        for(Double d : new double[]{0.005, 0.007, 0.01}){
            for(int i : new int[]{32, 48, 64}){
                expCandidates.add(new Pair<>(d, i));
            }
        }

        Set<Pair<Double,Integer>> actCandidates = new HashSet<>();
        while(candidateGenerator.hasMoreCandidates()) {
            Candidate<DL4JConfiguration> conf = candidateGenerator.getCandidate();
            MultiLayerConfiguration mlc = conf.getValue().getMultiLayerConfiguration();
            FeedForwardLayer ffl = ((FeedForwardLayer) mlc.getConf(0).getLayer());
//            System.out.println(ffl.getIUpdater() + ", " + ffl.getNOut());
            actCandidates.add(new Pair<>(ffl.getIUpdater().getLearningRate(0,0), (int)ffl.getNOut()));
        }

        assertEquals(expCandidates, actCandidates);
    }
 

@Test
public void testOcnn() {
    Map<String, Object> commands = new HashMap<>();
    commands.put(DataSetIteratorFactoryProvider.FACTORY_KEY, TestDataFactoryProviderMnist.class.getCanonicalName());


    //Define: network config (hyperparameter space)
    MultiLayerSpace mls = new MultiLayerSpace.Builder()
            .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
            .updater(new SgdSpace(new ContinuousParameterSpace(0.0001, 0.1)))
            .l2(new ContinuousParameterSpace(0.0001, 0.01))
            .addLayer(
                    new DenseLayerSpace.Builder().nOut(new IntegerParameterSpace(250, 500))
                            .activation(new DiscreteParameterSpace<>(Activation.RELU,
                                    Activation.TANH))
                            .build(),
                    new IntegerParameterSpace(1, 2)) //1-2 identical layers (except nIn)
            .addLayer(new OCNNLayerSpace.Builder().nu(new ContinuousParameterSpace(0.0001, 0.1))
                    .numHidden(new DiscreteParameterSpace<Integer>(784 / 2,784 / 4))
                    .activation(Activation.HARDSIGMOID)
                    .lossFunction(LossFunctions.LossFunction.MCXENT).build())
            .setInputType(InputType.convolutionalFlat(28,28,1))
            .build();

    //Define configuration:

    CandidateGenerator candidateGenerator = new RandomSearchGenerator(mls, commands);
    DataProvider dataProvider = new DataSetIteratorFactoryProvider();


    String modelSavePath = new File(System.getProperty("java.io.tmpdir"), "ArbiterDL4JTest3\\").getAbsolutePath();

    File f = new File(modelSavePath);
    if (f.exists())
        f.delete();
    f.mkdir();
    f.deleteOnExit();
    if (!f.exists())
        throw new RuntimeException();

    OptimizationConfiguration configuration = new OptimizationConfiguration.Builder()
            .candidateGenerator(candidateGenerator).dataProvider(dataProvider)
            .modelSaver(new FileModelSaver(modelSavePath)).scoreFunction(new TestSetLossScoreFunction())
            .terminationConditions(new MaxTimeCondition(2, TimeUnit.MINUTES),
                    new MaxCandidatesCondition(100))
            .build();


    //candidate generation: uncomment execute if you want to run
    IOptimizationRunner runner = new LocalOptimizationRunner(configuration,
            new MultiLayerNetworkTaskCreator(new ClassificationEvaluator()));

    Candidate candidate = candidateGenerator.getCandidate();

    // runner.execute();
    System.out.println("----- COMPLETE -----");
}