Java Code Examples for org.nd4j.common.primitives.Pair#setFirst()

The following examples show how to use org.nd4j.common.primitives.Pair#setFirst() . 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
Source File: CentersHolder.java    From deeplearning4j with Apache License 2.0 6 votes vote down vote up 
public synchronized Pair<Double, Long> getCenterByMinDistance(Point point, Distance distanceFunction) {
    if (distances == null)
        distances = Nd4j.create(centers.dataType(), centers.rows());

    if (argMin == null)
        argMin = Nd4j.createUninitialized(DataType.LONG, new long[0]);

    if (op == null) {
        op = ClusterUtils.createDistanceFunctionOp(distanceFunction, centers, point.getArray(), 1);
        imin = new ArgMin(distances, argMin);
        op.setZ(distances);
    }

    op.setY(point.getArray());

    Nd4j.getExecutioner().exec(op);
    Nd4j.getExecutioner().exec(imin);

    Pair<Double, Long> result = new Pair<>();
    result.setFirst(distances.getDouble(argMin.getLong(0)));
    result.setSecond(argMin.getLong(0));
    return result;
}
Example 2
Source File: TimeDistributedLayer.java    From deeplearning4j with Apache License 2.0 5 votes vote down vote up 
@Override
public Pair<INDArray, MaskState> feedForwardMaskArray(INDArray maskArray, MaskState currentMaskState, int minibatchSize) {
    if(maskArray == null){
        return underlying.feedForwardMaskArray(null, currentMaskState, minibatchSize);
    } else {
        INDArray reshaped = TimeSeriesUtils.reshapeTimeSeriesMaskToVector(maskArray, LayerWorkspaceMgr.noWorkspaces(), ArrayType.ACTIVATIONS);
        Pair<INDArray, MaskState> p = underlying.feedForwardMaskArray(reshaped, currentMaskState, minibatchSize);
        if(p == null || p.getFirst() == null){
            return p;
        }
        INDArray reshaped2 = TimeSeriesUtils.reshapeVectorToTimeSeriesMask(p.getFirst(), (int)maskArray.size(0));
        p.setFirst(reshaped2);
        return p;
    }
}
Example 3
Source File: Convolution1DLayer.java    From deeplearning4j with Apache License 2.0 5 votes vote down vote up 
@Override
protected Pair<INDArray, INDArray> preOutput4d(boolean training, boolean forBackprop, LayerWorkspaceMgr workspaceMgr) {
    Pair<INDArray,INDArray> preOutput = super.preOutput(true, forBackprop, workspaceMgr);
    INDArray p3d = preOutput.getFirst();
    INDArray p = preOutput.getFirst().reshape(p3d.size(0), p3d.size(1), p3d.size(2), 1);
    preOutput.setFirst(p);
    return preOutput;
}
Example 4
Source File: FastText.java    From deeplearning4j with Apache License 2.0 5 votes vote down vote up 
public Pair<String, Float> predictProbability(String text) {

        assertModelLoaded();

        JFastText.ProbLabel predictedProbLabel = fastTextImpl.predictProba(text);

        Pair<String,Float> retVal = new Pair<>();
        retVal.setFirst(predictedProbLabel.label);
        retVal.setSecond(predictedProbLabel.logProb);
        return retVal;
    }
Example 5
Source File: HyperRect.java    From deeplearning4j with Apache License 2.0 5 votes vote down vote up 
public static Pair<float[],float[]> point(INDArray vector) {
    Pair<float[],float[]> ret = new Pair<>();
    float[] curr = new float[(int)vector.length()];
    for (int i = 0; i < vector.length(); i++) {
        curr[i] = vector.getFloat(i);
    }
    ret.setFirst(curr);
    ret.setSecond(curr);
    return ret;
}
Example 6
Source File: SameDiffLoss.java    From deeplearning4j with Apache License 2.0 3 votes vote down vote up 
/**
 * Compute both the score (loss function value) and gradient. This is equivalent to calling {@link #computeScore(INDArray, INDArray, IActivation, INDArray, boolean)}
 * and {@link #computeGradient(INDArray, INDArray, IActivation, INDArray)} individually
 *
 * @param labels       Label/expected output
 * @param preOutput    Output of the model (neural network)
 * @param activationFn Activation function that should be applied to preOutput
 * @param mask         Mask array; may be null
 * @param average      Whether the score should be averaged (divided by number of rows in labels/output) or not
 * @return The score (loss function value) and gradient
 */
@Override
public Pair<Double, INDArray> computeGradientAndScore(INDArray labels, INDArray preOutput, IActivation activationFn,
                                                      INDArray mask, boolean average) {

    Pair<Double, INDArray> GradientAndScore = new Pair<>();
    GradientAndScore.setFirst(this.computeScore(labels, preOutput, activationFn, mask, average));
    GradientAndScore.setSecond(this.computeGradient(labels, preOutput, activationFn, mask));

    return GradientAndScore;
}