Examples with BroadcastMulOp org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp used on opensource projects

Example 11 with BroadcastMulOp

use of org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp in project deeplearning4j by deeplearning4j.

the class BatchNormalizationTest method testCnnForwardBackward.

@Test
public void testCnnForwardBackward() {
    double eps = 1e-5;
    int nIn = 4;
    int hw = 3;
    int minibatch = 2;
    Nd4j.getRandom().setSeed(12345);
    INDArray input = Nd4j.rand('c', new int[] { minibatch, nIn, hw, hw });
    //TODO: other values for gamma/beta
    INDArray gamma = Nd4j.ones(1, nIn);
    INDArray beta = Nd4j.zeros(1, nIn);
    Layer l = getLayer(nIn, eps, false, -1, -1);
    INDArray mean = input.mean(0, 2, 3);
    INDArray var = input.var(false, 0, 2, 3);
    INDArray xHat = Nd4j.getExecutioner().execAndReturn(new BroadcastSubOp(input, mean, input.dup(), 1));
    Nd4j.getExecutioner().execAndReturn(new BroadcastDivOp(xHat, Transforms.sqrt(var.add(eps), true), xHat, 1));
    INDArray outExpected = Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(xHat, gamma, xHat.dup(), 1));
    Nd4j.getExecutioner().execAndReturn(new BroadcastAddOp(outExpected, beta, outExpected, 1));
    INDArray out = l.activate(input, true);
    System.out.println(Arrays.toString(outExpected.data().asDouble()));
    System.out.println(Arrays.toString(out.data().asDouble()));
    assertEquals(outExpected, out);
    //-------------------------------------------------------------
    //Check backprop
    //dL/dy
    INDArray epsilon = Nd4j.rand('c', new int[] { minibatch, nIn, hw, hw });
    int effectiveMinibatch = minibatch * hw * hw;
    INDArray dldgammaExp = epsilon.mul(xHat).sum(0, 2, 3);
    INDArray dldbetaExp = epsilon.sum(0, 2, 3);
    //epsilon.mulRowVector(gamma);
    INDArray dldxhat = Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(epsilon, gamma, epsilon.dup(), 1));
    INDArray inputSubMean = Nd4j.getExecutioner().execAndReturn(new BroadcastSubOp(input, mean, input.dup(), 1));
    INDArray dldvar = dldxhat.mul(inputSubMean).mul(-0.5);
    dldvar = Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(dldvar, Transforms.pow(var.add(eps), -3.0 / 2.0, true), dldvar.dup(), 1));
    dldvar = dldvar.sum(0, 2, 3);
    INDArray dldmu = Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(dldxhat, Transforms.pow(var.add(eps), -1.0 / 2.0, true), dldxhat.dup(), 1)).neg().sum(0, 2, 3);
    dldmu = dldmu.add(dldvar.mul(inputSubMean.mul(-2.0).sum(0, 2, 3).div(effectiveMinibatch)));
    INDArray dldinExp = Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(dldxhat, Transforms.pow(var.add(eps), -1.0 / 2.0, true), dldxhat.dup(), 1));
    dldinExp = dldinExp.add(Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(inputSubMean.mul(2.0 / effectiveMinibatch), dldvar, inputSubMean.dup(), 1)));
    dldinExp = Nd4j.getExecutioner().execAndReturn(new BroadcastAddOp(dldinExp, dldmu.mul(1.0 / effectiveMinibatch), dldinExp.dup(), 1));
    Pair<Gradient, INDArray> p = l.backpropGradient(epsilon);
    INDArray dldgamma = p.getFirst().getGradientFor("gamma");
    INDArray dldbeta = p.getFirst().getGradientFor("beta");
    assertEquals(dldgammaExp, dldgamma);
    assertEquals(dldbetaExp, dldbeta);
    //        System.out.println("EPSILONS");
    //        System.out.println(Arrays.toString(dldinExp.data().asDouble()));
    //        System.out.println(Arrays.toString(p.getSecond().dup().data().asDouble()));
    assertEquals(dldinExp, p.getSecond());
}

Example 12 with BroadcastMulOp

use of org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp in project deeplearning4j by deeplearning4j.

the class GlobalPoolingMaskingTests method testMaskingCnnDim3.

@Test
public void testMaskingCnnDim3() {
    //Test masking, where mask is along dimension 3
    int minibatch = 3;
    int depthIn = 3;
    int depthOut = 4;
    int nOut = 5;
    int height = 3;
    int width = 6;
    PoolingType[] poolingTypes = new PoolingType[] { PoolingType.SUM, PoolingType.AVG, PoolingType.MAX, PoolingType.PNORM };
    for (PoolingType pt : poolingTypes) {
        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).convolutionMode(ConvolutionMode.Same).seed(12345L).list().layer(0, new ConvolutionLayer.Builder().nIn(depthIn).nOut(depthOut).kernelSize(height, 2).stride(height, 1).activation(Activation.TANH).build()).layer(1, new org.deeplearning4j.nn.conf.layers.GlobalPoolingLayer.Builder().poolingType(pt).build()).layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).activation(Activation.SOFTMAX).nIn(depthOut).nOut(nOut).build()).pretrain(false).backprop(true).build();
        MultiLayerNetwork net = new MultiLayerNetwork(conf);
        net.init();
        INDArray inToBeMasked = Nd4j.rand(new int[] { minibatch, depthIn, height, width });
        //Shape for mask: [minibatch, width]
        INDArray maskArray = Nd4j.create(new double[][] { { 1, 1, 1, 1, 1, 1 }, { 1, 1, 1, 1, 1, 0 }, { 1, 1, 1, 1, 0, 0 } });
        //Multiply the input by the mask array, to ensure the 0s in the mask correspond to 0s in the input vector
        // as would be the case in practice...
        Nd4j.getExecutioner().exec(new BroadcastMulOp(inToBeMasked, maskArray, inToBeMasked, 0, 3));
        net.setLayerMaskArrays(maskArray, null);
        INDArray outMasked = net.output(inToBeMasked);
        net.clearLayerMaskArrays();
        for (int i = 0; i < minibatch; i++) {
            System.out.println(i);
            int numSteps = width - i;
            INDArray subset = inToBeMasked.get(NDArrayIndex.interval(i, i, true), NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.interval(0, numSteps));
            assertArrayEquals(new int[] { 1, depthIn, height, width - i }, subset.shape());
            INDArray outSubset = net.output(subset);
            INDArray outMaskedSubset = outMasked.getRow(i);
            assertEquals(outSubset, outMaskedSubset);
        }
    }
}

Example 13 with BroadcastMulOp

use of org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp in project deeplearning4j by deeplearning4j.

the class GlobalPoolingMaskingTests method testMaskingCnnDim2.

@Test
public void testMaskingCnnDim2() {
    //Test masking, where mask is along dimension 2
    int minibatch = 3;
    int depthIn = 3;
    int depthOut = 4;
    int nOut = 5;
    int height = 5;
    int width = 4;
    PoolingType[] poolingTypes = new PoolingType[] { PoolingType.SUM, PoolingType.AVG, PoolingType.MAX, PoolingType.PNORM };
    for (PoolingType pt : poolingTypes) {
        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).convolutionMode(ConvolutionMode.Same).seed(12345L).list().layer(0, new ConvolutionLayer.Builder().nIn(depthIn).nOut(depthOut).kernelSize(2, width).stride(1, width).activation(Activation.TANH).build()).layer(1, new org.deeplearning4j.nn.conf.layers.GlobalPoolingLayer.Builder().poolingType(pt).build()).layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).activation(Activation.SOFTMAX).nIn(depthOut).nOut(nOut).build()).pretrain(false).backprop(true).build();
        MultiLayerNetwork net = new MultiLayerNetwork(conf);
        net.init();
        INDArray inToBeMasked = Nd4j.rand(new int[] { minibatch, depthIn, height, width });
        //Shape for mask: [minibatch, width]
        INDArray maskArray = Nd4j.create(new double[][] { { 1, 1, 1, 1, 1 }, { 1, 1, 1, 1, 0 }, { 1, 1, 1, 0, 0 } });
        //Multiply the input by the mask array, to ensure the 0s in the mask correspond to 0s in the input vector
        // as would be the case in practice...
        Nd4j.getExecutioner().exec(new BroadcastMulOp(inToBeMasked, maskArray, inToBeMasked, 0, 2));
        net.setLayerMaskArrays(maskArray, null);
        INDArray outMasked = net.output(inToBeMasked);
        net.clearLayerMaskArrays();
        for (int i = 0; i < minibatch; i++) {
            System.out.println(i);
            int numSteps = height - i;
            INDArray subset = inToBeMasked.get(NDArrayIndex.interval(i, i, true), NDArrayIndex.all(), NDArrayIndex.interval(0, numSteps), NDArrayIndex.all());
            assertArrayEquals(new int[] { 1, depthIn, height - i, width }, subset.shape());
            INDArray outSubset = net.output(subset);
            INDArray outMaskedSubset = outMasked.getRow(i);
            assertEquals(outSubset, outMaskedSubset);
        }
    }
}

Example 14 with BroadcastMulOp

use of org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp in project deeplearning4j by deeplearning4j.

the class L2NormalizeVertex method doBackward.

@Override
public Pair<Gradient, INDArray[]> doBackward(boolean tbptt) {
    if (!canDoBackward())
        throw new IllegalStateException("Cannot do backward pass: errors not set (L2NormalizeVertex " + vertexName + " idx " + vertexIndex + ")");
    INDArray x = inputs[0];
    int[] dimensions = getDimensions(x);
    INDArray norm = x.norm2(dimensions);
    INDArray norm3 = Transforms.pow(norm, 3.0, true);
    // in case of div/0
    Transforms.max(norm, eps, false);
    Transforms.max(norm3, eps, false);
    INDArray dLdx;
    if (x.rank() == 2) {
        // 2D case
        dLdx = epsilon.divColumnVector(norm);
        INDArray xDivNorm3 = x.divColumnVector(norm3);
        dLdx.subi(xDivNorm3.muliColumnVector(epsilon.mul(x).sum(1)));
    } else {
        //RNN and CNN case - Broadcast along dimension 0
        INDArray dx = epsilon.mul(x).sum(dimensions);
        //x / |x|_2^3 * sum_k (dLda*x)
        INDArray xDivNorm3 = Nd4j.createUninitialized(x.shape(), x.ordering());
        Nd4j.getExecutioner().exec(new BroadcastDivOp(x, norm3, xDivNorm3, 0));
        Nd4j.getExecutioner().exec(new BroadcastMulOp(xDivNorm3, dx, xDivNorm3, 0));
        //1/|x|_2 * dLda - above
        dLdx = Nd4j.createUninitialized(epsilon.shape(), epsilon.ordering());
        Nd4j.getExecutioner().exec(new BroadcastDivOp(epsilon, norm, dLdx, 0));
        dLdx.subi(xDivNorm3);
    }
    return new Pair<>(null, new INDArray[] { dLdx });
}

Example 15 with BroadcastMulOp

use of org.nd4j.linalg.api.ops.impl.broadcast.BroadcastMulOp in project deeplearning4j by deeplearning4j.

the class MaskedReductionUtil method maskedPoolingEpsilonTimeSeries.

public static INDArray maskedPoolingEpsilonTimeSeries(PoolingType poolingType, INDArray input, INDArray mask, INDArray epsilon2d, int pnorm) {
    if (input.rank() != 3) {
        throw new IllegalArgumentException("Expect rank 3 input activation array: got " + input.rank());
    }
    if (mask.rank() != 2) {
        throw new IllegalArgumentException("Expect rank 2 array for mask: got " + mask.rank());
    }
    if (epsilon2d.rank() != 2) {
        throw new IllegalArgumentException("Expected rank 2 array for errors: got " + epsilon2d.rank());
    }
    switch(poolingType) {
        case MAX:
            //TODO This is ugly - replace it with something better... Need something like a Broadcast CAS op
            INDArray negInfMask = Transforms.not(mask);
            BooleanIndexing.replaceWhere(negInfMask, Double.NEGATIVE_INFINITY, Conditions.equals(1.0));
            INDArray withInf = Nd4j.createUninitialized(input.shape());
            Nd4j.getExecutioner().exec(new BroadcastAddOp(input, negInfMask, withInf, 0, 2));
            //At this point: all the masked out steps have value -inf, hence can't be the output of the MAX op
            INDArray isMax = Nd4j.getExecutioner().execAndReturn(new IsMax(withInf, 2));
            return Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(isMax, epsilon2d, isMax, 0, 1));
        case AVG:
        case SUM:
            //if out = sum(in,dims) then dL/dIn = dL/dOut -> duplicate to each step and mask
            //if out = avg(in,dims) then dL/dIn = 1/N * dL/dOut
            //With masking: N differs for different time series
            INDArray out = Nd4j.createUninitialized(input.shape(), 'f');
            //Broadcast copy op, then divide and mask to 0 as appropriate
            Nd4j.getExecutioner().exec(new BroadcastCopyOp(out, epsilon2d, out, 0, 1));
            Nd4j.getExecutioner().exec(new BroadcastMulOp(out, mask, out, 0, 2));
            if (poolingType == PoolingType.SUM) {
                return out;
            }
            //[minibatchSize,tsLength] -> [minibatchSize,1]
            INDArray nEachTimeSeries = mask.sum(1);
            Nd4j.getExecutioner().exec(new BroadcastDivOp(out, nEachTimeSeries, out, 0));
            return out;
        case PNORM:
            //Similar to average and sum pooling: there's no N term here, so we can just set the masked values to 0
            INDArray masked2 = Nd4j.createUninitialized(input.shape());
            Nd4j.getExecutioner().exec(new BroadcastMulOp(input, mask, masked2, 0, 2));
            INDArray abs = Transforms.abs(masked2, true);
            Transforms.pow(abs, pnorm, false);
            INDArray pNorm = Transforms.pow(abs.sum(2), 1.0 / pnorm);
            INDArray numerator;
            if (pnorm == 2) {
                numerator = input.dup();
            } else {
                INDArray absp2 = Transforms.pow(Transforms.abs(input, true), pnorm - 2, false);
                numerator = input.mul(absp2);
            }
            INDArray denom = Transforms.pow(pNorm, pnorm - 1, false);
            denom.rdivi(epsilon2d);
            Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(numerator, denom, numerator, 0, 1));
            //Apply mask
            Nd4j.getExecutioner().exec(new BroadcastMulOp(numerator, mask, numerator, 0, 2));
            return numerator;
        case NONE:
            throw new UnsupportedOperationException("NONE pooling type not supported");
        default:
            throw new UnsupportedOperationException("Unknown or not supported pooling type: " + poolingType);
    }
}