當前位置: 首頁>>代碼示例>>Java>>正文

Java Nd4j.create方法代碼示例

本文整理匯總了Java中org.nd4j.linalg.factory.Nd4j.create方法的典型用法代碼示例。如果您正苦於以下問題：Java Nd4j.create方法的具體用法？Java Nd4j.create怎麽用？Java Nd4j.create使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類org.nd4j.linalg.factory.Nd4j的用法示例。


在下文中一共展示了Nd4j.create方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Java代碼示例。

示例1: fetch

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public void fetch(int numExamples) {
	float[][] featureData = new float[numExamples][0];
	float[][] labelData = new float[numExamples][0];

	int examplesRead = 0;

	for (; examplesRead < numExamples; examplesRead++) {
		if (cursor + examplesRead >= m_allFileNames.size()) {
			break;
		}
		Entry<String, String> entry = m_allFileNames.get(cursor + examplesRead);

		featureData[examplesRead] = imageFileNameToMnsitFormat(entry.getValue());
		labelData[examplesRead] = toLabelArray(entry.getKey());
	}
	cursor += examplesRead;

	INDArray features = Nd4j.create(featureData);
	INDArray labels = Nd4j.create(labelData);
	curr = new DataSet(features, labels);
}
開發者ID:braeunlich，項目名稱:anagnostes，代碼行數:23，代碼來源:NumbersDataFetcher.java

示例2: nd4JExample

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public void nd4JExample() {
    double[] A = {
        0.1950, 0.0311,
        0.3588, 0.2203,
        0.1716, 0.5931,
        0.2105, 0.3242};

    double[] B = {
        0.0502, 0.9823, 0.9472,
        0.5732, 0.2694, 0.916};

    
    INDArray aINDArray = Nd4j.create(A,new int[]{4,2},'c');
    INDArray bINDArray = Nd4j.create(B,new int[]{2,3},'c');
    
    INDArray cINDArray;
    cINDArray = aINDArray.mmul(bINDArray);
    for(int i=0; i<cINDArray.rows(); i++) {
        System.out.println(cINDArray.getRow(i));
    }
}
開發者ID:PacktPublishing，項目名稱:Machine-Learning-End-to-Endguide-for-Java-developers，代碼行數:22，代碼來源:MathExamples.java

示例3: readTestData

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
private static List<TrainingData> readTestData(String fn) {
    int[] shape = { 3, 1 };
    List<TrainingData> trainingDataSet = new ArrayList<>();
    try {
        CSVReader reader = new CSVReader(new FileReader(fn));
        String[] row;
        while ((row = reader.readNext()) != null) {
            int type = Integer.parseInt(row[0]);
            double f1 = Double.parseDouble(row[1]);
            double f2 = Double.parseDouble(row[2]);
            double f3 = Double.parseDouble(row[3]);
            TrainingData trainingData = new TrainingData();
            trainingData.input = Nd4j.create(new double[] { f1, f2, f3 }, shape);
            trainingData.output = Nd4j.zeros(shape);
            trainingData.output.putScalar(type, (double) 1);
            trainingDataSet.add(trainingData);
        }
    } catch (java.io.IOException e) {
    }
    return trainingDataSet;
}
開發者ID:apuder，項目名稱:ActivityMonitor，代碼行數:22，代碼來源:Main.java

示例4: preTrain

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public void preTrain(List<INDArray> X, int minibatchSize, int minibatch_N, int epochs, double learningRate,
                     double corruptionLevel) {
    for (int layer = 0; layer < nLayers; layer++) {
        for (int epoch = 0; epoch < epochs; epoch++) {
            for (int batch = 0; batch < minibatch_N; batch++) {
                INDArray X_ = Nd4j.create(new double[minibatchSize * nIn], new int[] { minibatchSize, nIn });
                INDArray prevLayerX_;
                // Set input data for current layer
                if (layer == 0) {
                    X_ = X.get(batch);
                } else {
                    prevLayerX_ = X_;
                    X_ = hiddenLayers[layer - 1].forward(prevLayerX_);
                }
                daLayers[layer].train(X_, minibatchSize, learningRate, corruptionLevel);
            }
        }
    }
}
開發者ID:IsaacChanghau，項目名稱:NeuralNetworksLite，代碼行數:20，代碼來源:StackedDenoisingAutoencoder.java

示例5: State

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public State(
    final int id,
    final double timestamp,
    final double x,
    final double y,
    final double orientation,
    final TeamColor teamColor
) {
  this(
      id,
      new SimpleDistribution(Nd4j.create(
          new double[]{
              timestamp,
              x,
              y,
              orientation
          },
          new int[]{4, 1}), Nd4j.eye(4)),
      teamColor);
}
開發者ID:delta-leonis，項目名稱:subra，代碼行數:21，代碼來源:Player.java

示例6: predict

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public INDArray predict(INDArray x) {
    INDArray y = output(x); // activate input data through learned networks
    INDArray out = Nd4j.create(new double[x.rows() * nOut], new int[] { x.rows(), nOut });
    for (int i = 0; i < x.rows(); i++) {
        int argmax = -1;
        double max = Double.MIN_VALUE;
        for (int j = 0; j < nOut; j++) {
            if (max < y.getDouble(i, j)) {
                argmax = j;
                max = y.getDouble(i, j);
            }
        }
        out.put(i, argmax, Nd4j.scalar(1.0));
    }
    return out;
}
開發者ID:IsaacChanghau，項目名稱:NeuralNetworksLite，代碼行數:17，代碼來源:OutputLayer.java

示例7: next

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public DataSet next(int num) {
    if (exampleStartOffsets.size() == 0) throw new NoSuchElementException();
    int actualMiniBatchSize = Math.min(num, exampleStartOffsets.size());
    INDArray input = Nd4j.create(new int[] {actualMiniBatchSize, VECTOR_SIZE, exampleLength}, 'f');
    INDArray label;
    if (category.equals(PriceCategory.ALL)) label = Nd4j.create(new int[] {actualMiniBatchSize, VECTOR_SIZE, exampleLength}, 'f');
    else label = Nd4j.create(new int[] {actualMiniBatchSize, predictLength, exampleLength}, 'f');
    for (int index = 0; index < actualMiniBatchSize; index++) {
        int startIdx = exampleStartOffsets.removeFirst();
        int endIdx = startIdx + exampleLength;
        StockData curData = train.get(startIdx);
        StockData nextData;
        for (int i = startIdx; i < endIdx; i++) {
            int c = i - startIdx;
            input.putScalar(new int[] {index, 0, c}, (curData.getOpen() - minArray[0]) / (maxArray[0] - minArray[0]));
            input.putScalar(new int[] {index, 1, c}, (curData.getClose() - minArray[1]) / (maxArray[1] - minArray[1]));
            input.putScalar(new int[] {index, 2, c}, (curData.getLow() - minArray[2]) / (maxArray[2] - minArray[2]));
            input.putScalar(new int[] {index, 3, c}, (curData.getHigh() - minArray[3]) / (maxArray[3] - minArray[3]));
            input.putScalar(new int[] {index, 4, c}, (curData.getVolume() - minArray[4]) / (maxArray[4] - minArray[4]));
            nextData = train.get(i + 1);
            if (category.equals(PriceCategory.ALL)) {
                label.putScalar(new int[] {index, 0, c}, (nextData.getOpen() - minArray[1]) / (maxArray[1] - minArray[1]));
                label.putScalar(new int[] {index, 1, c}, (nextData.getClose() - minArray[1]) / (maxArray[1] - minArray[1]));
                label.putScalar(new int[] {index, 2, c}, (nextData.getLow() - minArray[2]) / (maxArray[2] - minArray[2]));
                label.putScalar(new int[] {index, 3, c}, (nextData.getHigh() - minArray[3]) / (maxArray[3] - minArray[3]));
                label.putScalar(new int[] {index, 4, c}, (nextData.getVolume() - minArray[4]) / (maxArray[4] - minArray[4]));
            } else {
                label.putScalar(new int[]{index, 0, c}, feedLabel(nextData));
            }
            curData = nextData;
        }
        if (exampleStartOffsets.size() == 0) break;
    }
    return new DataSet(input, label);
}
開發者ID:IsaacChanghau，項目名稱:StockPrediction，代碼行數:37，代碼來源:StockDataSetIterator.java

示例8: State

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public State(
    final int id,
    final double timestamp,
    final double x,
    final double y,
    final double orientation,
    final double velocityX,
    final double velocityY,
    final double velocityR,
    final TeamColor teamColor
) {
  this(
      id,
      new SimpleDistribution(Nd4j.create(
          new double[]{
              timestamp,
              x,
              y,
              orientation,
              velocityX,
              velocityY,
              velocityR
          },
          new int[]{7, 1}), Nd4j.eye(7)),
      teamColor);

}
開發者ID:delta-leonis，項目名稱:subra，代碼行數:28，代碼來源:MovingPlayer.java

示例9: ax

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public double[] ax(double[] x, double[] y) {
    // Nd4j.getBlasWrapper().level2().gemv() crashes.
    // Use gemm for now.
    int m = nrows();
    int n = ncols();
    INDArray ndx = Nd4j.create(x, new int[]{n, 1});
    INDArray ndy = Nd4j.gemm(A, ndx, false, false);
    for (int i = 0; i < m; i++) {
        y[i] = ndy.getDouble(i);
    }

    return y;
}
開發者ID:takun2s，項目名稱:smile_1.5.0_java7，代碼行數:15，代碼來源:NDMatrix.java

示例10: axpy

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public double[] axpy(double[] x, double[] y) {
    // Nd4j.getBlasWrapper().level2().gemv() crashes.
    // Use gemm for now.
    int m = nrows();
    int n = ncols();
    INDArray ndx = Nd4j.create(x, new int[]{n, 1});
    INDArray ndy = Nd4j.gemm(A, ndx, false, false);
    for (int i = 0; i < m; i++) {
        y[i] += ndy.getDouble(i);
    }

    return y;
}
開發者ID:takun2s，項目名稱:smile_1.5.0_java7，代碼行數:15，代碼來源:NDMatrix.java

示例11: binomial

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
private INDArray binomial(INDArray x, Random rng) {
    INDArray y = Nd4j.create(new double[x.rows() * x.columns()], new int[] { x.rows(), x.columns() });
    for (int i = 0; i < x.rows(); i++) {
        for (int j = 0; j < x.columns(); j++) { y.put(i, j, RandomGenerator.binomial(1, x.getDouble(i, j), rng)); }
    }
    return y;
}
開發者ID:IsaacChanghau，項目名稱:NeuralNetworksLite，代碼行數:8，代碼來源:RestrictedBoltzmannMachine.java

示例12: atx

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public double[] atx(double[] x, double[] y) {
    // Nd4j.getBlasWrapper().level2().gemv() crashes.
    // Use gemm for now.
    int m = nrows();
    int n = ncols();
    INDArray ndx = Nd4j.create(x, new int[]{m, 1});
    INDArray ndy = Nd4j.gemm(A, ndx, true, false);
    for (int i = 0; i < n; i++) {
        y[i] = ndy.getDouble(i);
    }

    return y;
}
開發者ID:takun2s，項目名稱:smile_1.5.0_java7，代碼行數:15，代碼來源:NDMatrix.java

示例13: State

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public State(
    final double timestamp,
    final double x,
    final double y,
    final double z
) {
  this(new SimpleDistribution(Nd4j.create(
      new double[]{
          timestamp,
          x,
          y,
          z
      },
      new int[]{4, 1}), Nd4j.eye(4)));
}
開發者ID:delta-leonis，項目名稱:subra，代碼行數:16，代碼來源:Ball.java

示例14: atxpy

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
@Override
public double[] atxpy(double[] x, double[] y, double b) {
    // Nd4j.getBlasWrapper().level2().gemv() crashes.
    // Use gemm for now.
    int m = nrows();
    int n = ncols();
    INDArray ndx = Nd4j.create(x, new int[]{m, 1});
    INDArray ndy = Nd4j.gemm(A, ndx, true, false);
    for (int i = 0; i < n; i++) {
        y[i] = b * y[i] + ndy.getDouble(i);
    }

    return y;
}
開發者ID:takun2s，項目名稱:smile_1.5.0_java7，代碼行數:15，代碼來源:NDMatrix.java

示例15: outputBinomial

import org.nd4j.linalg.factory.Nd4j; //導入方法依賴的package包/類
public INDArray outputBinomial (INDArray X) {
    INDArray out = output(X);
    INDArray y = Nd4j.create(new double[out.rows() * out.columns()], new int[] { out.rows(), out.columns() });
    for (int i = 0; i < out.rows(); i++) {
        for (int j = 0; j < out.columns(); j++) {
            double value = RandomGenerator.binomial(1, out.getDouble(i, j), rng);
            y.put(i, j, Nd4j.scalar(value));
        }
    }
    return y;
}
開發者ID:IsaacChanghau，項目名稱:NeuralNetworksLite，代碼行數:12，代碼來源:DenseLayer.java


注：本文中的org.nd4j.linalg.factory.Nd4j.create方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。