Java MultiLayerNetwork.getParam方法代码示例

本文整理汇总了Java中org.deeplearning4j.nn.multilayer.MultiLayerNetwork.getParam方法的典型用法代码示例。如果您正苦于以下问题：Java MultiLayerNetwork.getParam方法的具体用法？Java MultiLayerNetwork.getParam怎么用？Java MultiLayerNetwork.getParam使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.deeplearning4j.nn.multilayer.MultiLayerNetwork的用法示例。

在下文中一共展示了MultiLayerNetwork.getParam方法的8个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: testRWInit

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testRWInit() {

    for (boolean rwInit : new boolean[]{false, true}) {
        for (int i = 0; i < 3; i++) {

            NeuralNetConfiguration.ListBuilder b = new NeuralNetConfiguration.Builder()
                    .weightInit(new UniformDistribution(0, 1))
                    .list();

            if(rwInit) {
                switch (i) {
                    case 0:
                        b.layer(new LSTM.Builder().nIn(10).nOut(10)
                                .weightInitRecurrent(new UniformDistribution(2, 3))
                                .build());
                        break;
                    case 1:
                        b.layer(new GravesLSTM.Builder().nIn(10).nOut(10)
                                .weightInitRecurrent(new UniformDistribution(2, 3))
                                .build());
                        break;
                    case 2:
                        b.layer(new SimpleRnn.Builder().nIn(10).nOut(10)
                                .weightInitRecurrent(new UniformDistribution(2, 3)).build());
                        break;
                    default:
                        throw new RuntimeException();
                }
            } else {
                switch (i) {
                    case 0:
                        b.layer(new LSTM.Builder().nIn(10).nOut(10).build());
                        break;
                    case 1:
                        b.layer(new GravesLSTM.Builder().nIn(10).nOut(10).build());
                        break;
                    case 2:
                        b.layer(new SimpleRnn.Builder().nIn(10).nOut(10).build());
                        break;
                    default:
                        throw new RuntimeException();
                }
            }

            MultiLayerNetwork net = new MultiLayerNetwork(b.build());
            net.init();

            INDArray rw = net.getParam("0_RW");
            double min = rw.minNumber().doubleValue();
            double max = rw.maxNumber().doubleValue();
            if(rwInit){
                assertTrue(String.valueOf(min), min >= 2.0);
                assertTrue(String.valueOf(max), max <= 3.0);
            } else {
                assertTrue(String.valueOf(min), min >= 0.0);
                assertTrue(String.valueOf(max), max <= 1.0);
            }
        }
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:62，代码来源:TestRecurrentWeightInit.java

示例2: testSimpleRnn

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
    public void testSimpleRnn(){
        Nd4j.getRandom().setSeed(12345);

        int m = 3;
        int nIn = 5;
        int layerSize = 6;
        int tsLength = 7;
        INDArray in = Nd4j.rand(new int[]{m, nIn, tsLength});
//        in.get(all(), all(), interval(1,tsLength)).assign(0);

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new NoOp())
                .weightInit(WeightInit.XAVIER)
                .activation(Activation.TANH)
                .list()
                .layer(new SimpleRnn.Builder().nIn(nIn).nOut(layerSize).build())
                .build();

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

        INDArray out = net.output(in);

        INDArray w = net.getParam("0_W");
        INDArray rw = net.getParam("0_RW");
        INDArray b = net.getParam("0_b");

        INDArray outLast = null;
        for( int i=0; i<tsLength; i++ ){
            INDArray inCurrent = in.get(all(), all(), point(i));

            INDArray outExpCurrent = inCurrent.mmul(w);
            if(outLast != null){
                outExpCurrent.addi(outLast.mmul(rw));
            }

            outExpCurrent.addiRowVector(b);

            Transforms.tanh(outExpCurrent, false);

            INDArray outActCurrent = out.get(all(), all(), point(i));
            assertEquals(String.valueOf(i), outExpCurrent, outActCurrent);

            outLast = outExpCurrent;
        }


        TestUtils.testModelSerialization(net);
    }

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:51，代码来源:TestSimpleRnn.java

示例3: testLayerRecurrentConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testLayerRecurrentConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for (LayerConstraint lc : constraints) {

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 5))
                .list()
                .layer(new LSTM.Builder().nIn(12).nOut(10)
                        .constrainRecurrent(lc).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray RW0 = net.getParam("0_RW");


        if (lc instanceof MaxNormConstraint) {
            assertTrue(RW0.norm2(1).maxNumber().doubleValue() <= 0.5);

        } else if (lc instanceof MinMaxNormConstraint) {
            assertTrue(RW0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(RW0.norm2(1).maxNumber().doubleValue() <= 0.4);
        } else if (lc instanceof NonNegativeConstraint) {
            assertTrue(RW0.minNumber().doubleValue() >= 0.0);
        } else if (lc instanceof UnitNormConstraint) {
            assertEquals(RW0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(RW0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
        }

        TestUtils.testModelSerialization(net);
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:52，代码来源:TestConstraints.java

示例4: testLayerBiasConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testLayerBiasConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for (LayerConstraint lc : constraints) {

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 5))
                .biasInit(10.0)
                .list()
                .layer(new DenseLayer.Builder().nIn(12).nOut(10)
                        .constrainBias(lc).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray b0 = net.getParam("0_b");


        if (lc instanceof MaxNormConstraint) {
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.5);

        } else if (lc instanceof MinMaxNormConstraint) {
            assertTrue(b0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.4);
        } else if (lc instanceof NonNegativeConstraint) {
            assertTrue(b0.minNumber().doubleValue() >= 0.0);
        } else if (lc instanceof UnitNormConstraint) {
            assertEquals(b0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(b0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
        }

        TestUtils.testModelSerialization(net);
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:53，代码来源:TestConstraints.java

示例5: testLayerWeightsConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testLayerWeightsConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for (LayerConstraint lc : constraints) {

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 5))
                .list()
                .layer(new DenseLayer.Builder().nIn(12).nOut(10)
                        .constrainWeights(lc).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray w0 = net.getParam("0_W");


        if (lc instanceof MaxNormConstraint) {
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.5);

        } else if (lc instanceof MinMaxNormConstraint) {
            assertTrue(w0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.4);
        } else if (lc instanceof NonNegativeConstraint) {
            assertTrue(w0.minNumber().doubleValue() >= 0.0);
        } else if (lc instanceof UnitNormConstraint) {
            assertEquals(w0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(w0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
        }

        TestUtils.testModelSerialization(net);
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:52，代码来源:TestConstraints.java

示例6: testLayerWeightsAndBiasConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testLayerWeightsAndBiasConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for (LayerConstraint lc : constraints) {

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 5))
                .biasInit(0.2)
                .list()
                .layer(new DenseLayer.Builder().nIn(12).nOut(10)
                        .constrainAllParameters(lc).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray w0 = net.getParam("0_W");
        INDArray b0 = net.getParam("0_b");


        if (lc instanceof MaxNormConstraint) {
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.5);
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.5);

        } else if (lc instanceof MinMaxNormConstraint) {
            assertTrue(w0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.4);
            assertTrue(b0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.4);
        } else if (lc instanceof NonNegativeConstraint) {
            assertTrue(w0.minNumber().doubleValue() >= 0.0);
            assertTrue(b0.minNumber().doubleValue() >= 0.0);
        } else if (lc instanceof UnitNormConstraint) {
            assertEquals(w0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(w0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(b0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(b0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
        }

        TestUtils.testModelSerialization(net);
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:60，代码来源:TestConstraints.java

示例7: testLayerWeightsAndBiasSeparateConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testLayerWeightsAndBiasSeparateConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for (LayerConstraint lc : constraints) {

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 5))
                .biasInit(0.2)
                .list()
                .layer(new DenseLayer.Builder().nIn(12).nOut(10)
                        .constrainWeights(lc).constrainBias(lc).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray w0 = net.getParam("0_W");
        INDArray b0 = net.getParam("0_b");


        if (lc instanceof MaxNormConstraint) {
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.5);
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.5);

        } else if (lc instanceof MinMaxNormConstraint) {
            assertTrue(w0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.4);
            assertTrue(b0.norm2(1).minNumber().doubleValue() >= 0.3);
            assertTrue(b0.norm2(1).maxNumber().doubleValue() <= 0.4);
        } else if (lc instanceof NonNegativeConstraint) {
            assertTrue(w0.minNumber().doubleValue() >= 0.0);
            assertTrue(b0.minNumber().doubleValue() >= 0.0);
        } else if (lc instanceof UnitNormConstraint) {
            assertEquals(w0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(w0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(b0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6);
            assertEquals(b0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6);
        }

        TestUtils.testModelSerialization(net);
    }
}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:60，代码来源:TestConstraints.java

示例8: testModelConstraints

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void testModelConstraints() throws Exception {

    LayerConstraint[] constraints = new LayerConstraint[]{
            new MaxNormConstraint(0.5, 1),
            new MinMaxNormConstraint(0.3, 0.4, 1.0, 1),
            new NonNegativeConstraint(),
            new UnitNormConstraint(1)
    };

    for(LayerConstraint lc : constraints){

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .constrainWeights(lc)
                .updater(new Sgd(0.0))
                .weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0,5))
                .biasInit(1)
                .list()
                .layer(new DenseLayer.Builder().nIn(12).nOut(10).build())
                .layer(new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(10).nOut(8).build())
                .build();

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

        LayerConstraint exp = lc.clone();
        assertEquals(exp.toString(), net.getLayer(0).conf().getLayer().getConstraints().get(0).toString());
        assertEquals(exp.toString(), net.getLayer(1).conf().getLayer().getConstraints().get(0).toString());

        INDArray input = Nd4j.rand(3, 12);
        INDArray labels = Nd4j.rand(3, 8);

        net.fit(input, labels);

        INDArray w0 = net.getParam("0_W");
        INDArray w1 = net.getParam("1_W");

        if(lc instanceof MaxNormConstraint){
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.5 );
            assertTrue(w1.norm2(1).maxNumber().doubleValue() <= 0.5 );
        } else if(lc instanceof MinMaxNormConstraint){
            assertTrue(w0.norm2(1).minNumber().doubleValue() >= 0.3 );
            assertTrue(w0.norm2(1).maxNumber().doubleValue() <= 0.4 );
            assertTrue(w1.norm2(1).minNumber().doubleValue() >= 0.3 );
            assertTrue(w1.norm2(1).maxNumber().doubleValue() <= 0.4 );
        } else if(lc instanceof NonNegativeConstraint ){
            assertTrue(w0.minNumber().doubleValue() >= 0.0 );
        } else if(lc instanceof UnitNormConstraint ){
            assertEquals(w0.norm2(1).minNumber().doubleValue(), 1.0, 1e-6 );
            assertEquals(w0.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6 );
            assertEquals(w1.norm2(1).minNumber().doubleValue(), 1.0, 1e-6 );
            assertEquals(w1.norm2(1).maxNumber().doubleValue(), 1.0, 1e-6 );
        }


        TestUtils.testModelSerialization(net);
    }

}

开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:60，代码来源:TestConstraints.java

注：本文中的org.deeplearning4j.nn.multilayer.MultiLayerNetwork.getParam方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。