Sparkling Water: Spark+H2O #5 – Science To Medicine

前回のH2O DeepLearningモデル構築で最終的にDeepLearning_model.javaが出力される。

/*
  Licensed under the Apache License, Version 2.0
    http://www.apache.org/licenses/LICENSE-2.0.html

  AUTOGENERATED BY H2O at 2018-10-28T16:28:21.908+09:00
  3.10.5.4
  
  Standalone prediction code with sample test data for DeepLearningModel named DeepLearning_model_1540691693623_1

  How to download, compile and execute:
      mkdir tmpdir
      cd tmpdir
      curl http:/macbook-pro-5/***.***.***.***:54321/3/h2o-genmodel.jar > h2o-genmodel.jar
      curl http:/macbook-pro-5/***.***.***.***:54321/3/Models.java/DeepLearning_model_1540691693623_1 > DeepLearning_model_1540691693623_1.java
      javac -cp h2o-genmodel.jar -J-Xmx2g -J-XX:MaxPermSize=128m DeepLearning_model_1540691693623_1.java

     (Note:  Try java argument -XX:+PrintCompilation to show runtime JIT compiler behavior.)
*/
import java.util.Map;
import hex.genmodel.GenModel;
import hex.genmodel.annotations.ModelPojo;

@ModelPojo(name="DeepLearning_model_1540691693623_1", algorithm="deeplearning")
public class DeepLearning_model_1540691693623_1 extends GenModel {
  public hex.ModelCategory getModelCategory() { return hex.ModelCategory.Binomial; }
  public boolean isSupervised() { return true; }
  public int nfeatures() { return 28; }
  public int nclasses() { return 2; }
  // Thread-local storage for input neuron activation values.
  final double[] NUMS = new double[28];
  static class NORMMUL implements java.io.Serializable {
    public static final double[] VALUES = new double[28];
    static {
      NORMMUL_0.fill(VALUES);
    }
    static final class NORMMUL_0 implements java.io.Serializable {
      static final void fill(double[] sa) {
        sa[0] = 1.7687666758901264;
        sa[1] = 0.9913821723096016;
        sa[2] = 0.9936853236221495;
        sa[3] = 1.6666383037503143;
        sa[4] = 0.9937488864153216;
        sa[5] = 2.105437242840467;
        sa[6] = 0.9908361123051243;
        sa[7] = 0.9940879578054577;
        sa[8] = 0.9729178470795813;
        sa[9] = 2.0007082148981183;
        sa[10] = 0.9908480722586916;
        sa[11] = 0.9938660006765665;
        sa[12] = 0.9528949618561464;
        sa[13] = 2.0508575278770245;
        sa[14] = 0.9912345684749029;
        sa[15] = 0.9937069184546701;
        sa[16] = 0.8377686617849256;
        sa[17] = 1.9768892962453906;
        sa[18] = 0.9926596305568416;
        sa[19] = 0.9937642381155177;
        sa[20] = 0.7141691868612743;
        sa[21] = 1.4816770107928496;
        sa[22] = 2.62612559064267;
        sa[23] = 6.074042423656259;
        sa[24] = 2.5162755660661866;
        sa[25] = 1.9042873091548915;
        sa[26] = 2.7391280258211443;
        sa[27] = 3.1929106654741926;
      }
    }
}
  static class NORMSUB implements java.io.Serializable {
    public static final double[] VALUES = new double[28];
    static {
      NORMSUB_0.fill(VALUES);
    }
    static final class NORMSUB_0 implements java.io.Serializable {
      static final void fill(double[] sa) {
        sa[0] = 0.991609543911382;
        sa[1] = -6.172673222856738E-5;
        sa[2] = 2.1854967778855427E-4;
        sa[3] = 0.9984508227147362;
        sa[4] = 2.7703720484945748E-5;
        sa[5] = 0.9908871828929133;
        sa[6] = -8.849292707005366E-5;
        sa[7] = -1.54437948956086E-4;
        sa[8] = 0.9999179533939873;
        sa[9] = 0.9927406409576117;
        sa[10] = -1.6275628806378383E-4;
        sa[11] = 7.234230467006848E-5;
        sa[12] = 1.0002384149332444;
        sa[13] = 0.992170569563542;
        sa[14] = 4.1840079250049434E-5;
        sa[15] = 3.615676062458686E-5;
        sa[16] = 0.999843197801924;
        sa[17] = 0.9861267051297294;
        sa[18] = 3.768967267508312E-5;
        sa[19] = 1.6822728241595495E-4;
        sa[20] = 1.0001443952117024;
        sa[21] = 1.0343311905419041;
        sa[22] = 1.0247880896606023;
        sa[23] = 1.0505599836914452;
        sa[24] = 1.0096686212679917;
        sa[25] = 0.9729231063653536;
        sa[26] = 1.0329730880581618;
        sa[27] = 0.9597638460111044;
      }
    }
}
  // Workspace for categorical offsets.
  public static final int[] CATOFFSETS = {0};
  // Hidden layer dropout ratios.
  public static final double[] HIDDEN_DROPOUT_RATIOS = {0.5,0.5,0.5};
  // Number of neurons for each layer.
  public static final int[] NEURONS = {28,500,500,500,2};
    // Thread-local storage for neuron activation values.
    final double[][] ACTIVATION = new double[][] {
      /* Input */ DeepLearning_model_1540691693623_1_Activation_0.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_1.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_2.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_3.VALUES,
      /* Softmax */ DeepLearning_model_1540691693623_1_Activation_4.VALUES
    };
    // Neuron bias values.
    public static final double[][] BIAS = new double[][] {
      /* Input */ DeepLearning_model_1540691693623_1_Bias_0.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_1.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_2.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_3.VALUES,
      /* Softmax */ DeepLearning_model_1540691693623_1_Bias_4.VALUES
    };
    // Connecting weights between neurons.
    public static final float[][] WEIGHT = new float[][] {
      /* Input */ DeepLearning_model_1540691693623_1_Weight_0.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_1.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_2.VALUES,
      /* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_3.VALUES,
      /* Softmax */ DeepLearning_model_1540691693623_1_Weight_4.VALUES
    };

  // Names of columns used by model.
  public static final String[] NAMES = NamesHolder_DeepLearning_model_1540691693623_1.VALUES;
  // Number of output classes included in training data response column.
  public static final int NCLASSES = 2;

  // Column domains. The last array contains domain of response column.
  public static final String[][] DOMAINS = new String[][] {
    /* features0 */ null,
    /* features1 */ null,
    /* features2 */ null,
    /* features3 */ null,
    /* features4 */ null,
    /* features5 */ null,
    /* features6 */ null,
    /* features7 */ null,
    /* features8 */ null,
    /* features9 */ null,
    /* features10 */ null,
    /* features11 */ null,
    /* features12 */ null,
    /* features13 */ null,
    /* features14 */ null,
    /* features15 */ null,
    /* features16 */ null,
    /* features17 */ null,
    /* features18 */ null,
    /* features19 */ null,
    /* features20 */ null,
    /* features21 */ null,
    /* features22 */ null,
    /* features23 */ null,
    /* features24 */ null,
    /* features25 */ null,
    /* features26 */ null,
    /* features27 */ null,
    /* label */ DeepLearning_model_1540691693623_1_ColInfo_28.VALUES
  };
  // Prior class distribution
  public static final double[] PRIOR_CLASS_DISTRIB = {0.4701428794437793,0.5298571205562207};
  // Class distribution used for model building
  public static final double[] MODEL_CLASS_DISTRIB = null;

  public DeepLearning_model_1540691693623_1() { super(NAMES,DOMAINS); }
  public String getUUID() { return Long.toString(-5314795359721044940L); }

  // Pass in data in a double[], pre-aligned to the Model's requirements.
  // Jam predictions into the preds[] array; preds[0] is reserved for the
  // main prediction (class for classifiers or value for regression),
  // and remaining columns hold a probability distribution for classifiers.
  public final double[] score0( double[] data, double[] preds ) {
    java.util.Arrays.fill(preds,0);
    java.util.Arrays.fill(NUMS,0);
    int i = 0, ncats = 0;
    final int n = data.length;
    for(; i<n; ++i) {
      NUMS[i] = Double.isNaN(data[i]) ? 0 : (data[i] - NORMSUB.VALUES[i])*NORMMUL.VALUES[i];
    }
    java.util.Arrays.fill(ACTIVATION[0],0);
    for (i=0; i<NUMS.length; ++i) {
      ACTIVATION[0][CATOFFSETS[CATOFFSETS.length-1] + i] = Double.isNaN(NUMS[i]) ? 0 : NUMS[i];
    }
    for (i=1; i<ACTIVATION.length; ++i) {
      java.util.Arrays.fill(ACTIVATION[i],0);
      int cols = ACTIVATION[i-1].length;
      int rows = ACTIVATION[i].length;
      int extra=cols-cols%8;
      int multiple = (cols/8)*8-1;
      int idx = 0;
      float[] a = WEIGHT[i];
      double[] x = ACTIVATION[i-1];
      double[] y = BIAS[i];
      double[] res = ACTIVATION[i];
      for (int row=0; row<rows; ++row) {
        double psum0 = 0, psum1 = 0, psum2 = 0, psum3 = 0, psum4 = 0, psum5 = 0, psum6 = 0, psum7 = 0;
        for (int col = 0; col < multiple; col += 8) {
          int off = idx + col;
          psum0 += a[off    ] * x[col    ];
          psum1 += a[off + 1] * x[col + 1];
          psum2 += a[off + 2] * x[col + 2];
          psum3 += a[off + 3] * x[col + 3];
          psum4 += a[off + 4] * x[col + 4];
          psum5 += a[off + 5] * x[col + 5];
          psum6 += a[off + 6] * x[col + 6];
          psum7 += a[off + 7] * x[col + 7];
        }
        res[row] += psum0 + psum1 + psum2 + psum3;
        res[row] += psum4 + psum5 + psum6 + psum7;
        for (int col = extra; col < cols; col++)
          res[row] += a[idx + col] * x[col];
        res[row] += y[row];
        idx += cols;
      }
      if (i<ACTIVATION.length-1) {
        for (int r=0; r<ACTIVATION[i].length; ++r) {
          ACTIVATION[i][r] = Math.max(0, ACTIVATION[i][r]);
          if (i<ACTIVATION.length-1) {
            ACTIVATION[i][r] *= 1 - HIDDEN_DROPOUT_RATIOS[i-1];
          }
        }
      }
      if (i == ACTIVATION.length-1) {
        double max = ACTIVATION[i][0];
        for (int r=1; r<ACTIVATION[i].length; r++) {
          if (ACTIVATION[i][r]>max) max = ACTIVATION[i][r];
        }
        double scale = 0;
        for (int r=0; r<ACTIVATION[i].length; r++) {
          ACTIVATION[i][r] = Math.exp(ACTIVATION[i][r] - max);
          scale += ACTIVATION[i][r];
        }
        for (int r=0; r<ACTIVATION[i].length; r++) {
          if (Double.isNaN(ACTIVATION[i][r]))
            throw new RuntimeException("Numerical instability, predicted NaN.");
          ACTIVATION[i][r] /= scale;
          preds[r+1] = ACTIVATION[i][r];
        }
      }
    }
    preds[0] = hex.genmodel.GenModel.getPrediction(preds, PRIOR_CLASS_DISTRIB, data, 0.44319463906785384);
    return preds;
  }
}
// Neuron activation values for Input layer
class DeepLearning_model_1540691693623_1_Activation_0 implements java.io.Serializable {
  public static final double[] VALUES = new double[28];
  static {
    DeepLearning_model_1540691693623_1_Activation_0_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Activation_0_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.0;
      sa[1] = 0.0;
      sa[2] = 0.0;
      sa[3] = 0.0;
      sa[4] = 0.0;
      sa[5] = 0.0;
      sa[6] = 0.0;
      sa[7] = 0.0;
      sa[8] = 0.0;
      sa[9] = 0.0;
      sa[10] = 0.0;
      sa[11] = 0.0;
      sa[12] = 0.0;
      sa[13] = 0.0;
      sa[14] = 0.0;
      sa[15] = 0.0;
      sa[16] = 0.0;
      sa[17] = 0.0;
      sa[18] = 0.0;
      sa[19] = 0.0;
      sa[20] = 0.0;
      sa[21] = 0.0;
      sa[22] = 0.0;
      sa[23] = 0.0;
      sa[24] = 0.0;
      sa[25] = 0.0;
      sa[26] = 0.0;
      sa[27] = 0.0;
    }
  }
}
// Neuron activation values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Activation_1 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Activation_1_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Activation_1_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.0;
      sa[1] = 0.0;
      sa[2] = 0.0;
      sa[3] = 0.0;
      sa[4] = 0.0;
      sa[5] = 0.0;
......
      sa[499] = 0.0;
    }
  }
}
// Neuron activation values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Activation_2 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Activation_2_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Activation_2_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.0;
      sa[1] = 0.0;
      sa[2] = 0.0;
      sa[3] = 0.0;
      sa[4] = 0.0;
      sa[5] = 0.0;
......
      sa[499] = 0.0;
    }
  }
}
// Neuron activation values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Activation_3 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Activation_3_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Activation_3_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.0;
      sa[1] = 0.0;
      sa[2] = 0.0;
      sa[3] = 0.0;
      sa[4] = 0.0;
      sa[5] = 0.0;
......
      sa[499] = 0.0;
    }
  }
}
// Neuron activation values for Softmax layer
class DeepLearning_model_1540691693623_1_Activation_4 implements java.io.Serializable {
  public static final double[] VALUES = new double[2];
  static {
    DeepLearning_model_1540691693623_1_Activation_4_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Activation_4_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.0;
      sa[1] = 0.0;
    }
  }
}
// Neuron bias values for Input layer
class DeepLearning_model_1540691693623_1_Bias_0 implements java.io.Serializable {
  public static final double[] VALUES = null;
}
// Neuron bias values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Bias_1 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Bias_1_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Bias_1_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = -0.6082208509410506;
      sa[1] = -0.7866761395746675;
      sa[2] = -0.7902771837144533;
      sa[3] = -1.078600190576397;
      sa[4] = -1.1325559100264349;
      sa[5] = -1.3141680956557276;
......
      sa[499] = -1.1605339237438876;
    }
  }
}
// Neuron bias values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Bias_2 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Bias_2_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Bias_2_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = 0.02034537567535967;
      sa[1] = 0.2056398687484795;
      sa[2] = -0.6811208002656562;
      sa[3] = 0.34906780212313926;
      sa[4] = 0.1994718812435918;
      sa[5] = -0.4389162411792007;
......
      sa[499] = -0.19825444966679512;
    }
  }
}
// Neuron bias values for RectifierDropout layer
class DeepLearning_model_1540691693623_1_Bias_3 implements java.io.Serializable {
  public static final double[] VALUES = new double[500];
  static {
    DeepLearning_model_1540691693623_1_Bias_3_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Bias_3_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = -0.37334331766490575;
      sa[1] = -0.2192842820590019;
      sa[2] = -0.48037506449229245;
      sa[3] = -0.27829081354485186;
      sa[4] = -0.5348837641304954;
........
      sa[499] = -0.38094144337852304;
    }
  }
}
// Neuron bias values for Softmax layer
class DeepLearning_model_1540691693623_1_Bias_4 implements java.io.Serializable {
  public static final double[] VALUES = new double[2];
  static {
    DeepLearning_model_1540691693623_1_Bias_4_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Bias_4_0 implements java.io.Serializable {
    static final void fill(double[] sa) {
      sa[0] = -0.11833918432774448;
      sa[1] = 0.08029026554573974;
    }
  }
}
class DeepLearning_model_1540691693623_1_Weight_0 implements java.io.Serializable {
  public static final float[] VALUES = null;
}

// Neuron weights connecting Input and RectifierDropout layer
class DeepLearning_model_1540691693623_1_Weight_1 implements java.io.Serializable {
  public static final float[] VALUES = new float[14000];
  static {
    DeepLearning_model_1540691693623_1_Weight_1_0.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_1_1.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_1_2.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_1_3.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_1_4.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Weight_1_0 implements java.io.Serializable {
    static final void fill(float[] sa) {
      sa[0] = -0.06823527f;
      sa[1] = 0.01967861f;
      sa[2] = -0.03716086f;
      sa[3] = -0.011376046f;
      sa[4] = -0.019753613f;
      sa[5] = -0.19310619f;
......
      sa[13999] = -0.12823965f;
    }
  }
}
// Neuron weights connecting RectifierDropout and RectifierDropout layer
class DeepLearning_model_1540691693623_1_Weight_2 implements java.io.Serializable {
  public static final float[] VALUES = new float[250000];
  static {
    DeepLearning_model_1540691693623_1_Weight_2_0.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_1.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_2.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_3.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_4.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_5.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_6.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_7.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_8.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_9.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_10.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_11.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_12.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_13.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_14.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_15.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_16.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_17.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_18.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_19.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_20.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_21.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_22.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_23.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_24.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_25.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_26.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_27.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_28.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_29.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_30.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_31.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_32.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_33.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_34.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_35.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_36.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_37.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_38.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_39.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_40.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_41.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_42.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_43.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_44.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_45.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_46.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_47.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_48.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_49.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_50.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_51.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_52.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_53.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_54.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_55.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_56.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_57.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_58.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_59.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_60.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_61.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_62.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_63.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_64.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_65.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_66.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_67.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_68.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_69.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_70.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_71.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_72.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_73.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_74.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_75.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_76.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_77.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_78.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_79.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_80.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_81.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_82.fill(VALUES);
    DeepLearning_model_1540691693623_1_Weight_2_83.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Weight_2_0 implements java.io.Serializable {
    static final void fill(float[] sa) {
      sa[0] = -0.24805546f;
      sa[1] = -0.06499913f;
      sa[2] = -0.14989536f;
      sa[3] = -0.06383444f;
      sa[4] = 0.14076568f;
      sa[5] = -0.16730806f;
......
      sa[249999] = 0.005610808f;
    }
  }
}
// Neuron weights connecting RectifierDropout and Softmax layer
class DeepLearning_model_1540691693623_1_Weight_4 implements java.io.Serializable {
  public static final float[] VALUES = new float[1000];
  static {
    DeepLearning_model_1540691693623_1_Weight_4_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_Weight_4_0 implements java.io.Serializable {
    static final void fill(float[] sa) {
      sa[0] = 0.2789825f;
      sa[1] = 0.4297707f;
      sa[2] = -0.28039044f;
      sa[3] = -0.13956442f;
      sa[4] = -0.07300115f;
      sa[5] = 0.13860723f;
........
      sa[999] = 0.043791886f;
    }
  }
}
// The class representing training column names
class NamesHolder_DeepLearning_model_1540691693623_1 implements java.io.Serializable {
  public static final String[] VALUES = new String[28];
  static {
    NamesHolder_DeepLearning_model_1540691693623_1_0.fill(VALUES);
  }
  static final class NamesHolder_DeepLearning_model_1540691693623_1_0 implements java.io.Serializable {
    static final void fill(String[] sa) {
      sa[0] = "features0";
      sa[1] = "features1";
      sa[2] = "features2";
      sa[3] = "features3";
      sa[4] = "features4";
      sa[5] = "features5";
      sa[6] = "features6";
      sa[7] = "features7";
      sa[8] = "features8";
      sa[9] = "features9";
      sa[10] = "features10";
      sa[11] = "features11";
      sa[12] = "features12";
      sa[13] = "features13";
      sa[14] = "features14";
      sa[15] = "features15";
      sa[16] = "features16";
      sa[17] = "features17";
      sa[18] = "features18";
      sa[19] = "features19";
      sa[20] = "features20";
      sa[21] = "features21";
      sa[22] = "features22";
      sa[23] = "features23";
      sa[24] = "features24";
      sa[25] = "features25";
      sa[26] = "features26";
      sa[27] = "features27";
    }
  }
}
// The class representing column label
class DeepLearning_model_1540691693623_1_ColInfo_28 implements java.io.Serializable {
  public static final String[] VALUES = new String[2];
  static {
    DeepLearning_model_1540691693623_1_ColInfo_28_0.fill(VALUES);
  }
  static final class DeepLearning_model_1540691693623_1_ColInfo_28_0 implements java.io.Serializable {
    static final void fill(String[] sa) {
      sa[0] = "0";
      sa[1] = "1";
    }
  }
}

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

Licensed under the Apache License, Version 2.0

http://www.apache.org/licenses/LICENSE-2.0.html

AUTOGENERATED BY H2O at 2018-10-28T16:28:21.908+09:00

3.10.5.4

Standalone prediction code with sample test data for DeepLearningModel named DeepLearning_model_1540691693623_1

How to download, compile and execute:

mkdir tmpdir

cd tmpdir

curl http:/macbook-pro-5/***.***.***.***:54321/3/h2o-genmodel.jar > h2o-genmodel.jar

curl http:/macbook-pro-5/***.***.***.***:54321/3/Models.java/DeepLearning_model_1540691693623_1 > DeepLearning_model_1540691693623_1.java

javac -cp h2o-genmodel.jar -J-Xmx2g -J-XX:MaxPermSize=128m DeepLearning_model_1540691693623_1.java

(Note: Try java argument -XX:+PrintCompilation to show runtime JIT compiler behavior.)

import java.util.Map;

import hex.genmodel.GenModel;

import hex.genmodel.annotations.ModelPojo;

@ModelPojo(name="DeepLearning_model_1540691693623_1", algorithm="deeplearning")

public class DeepLearning_model_1540691693623_1 extends GenModel {

public hex.ModelCategory getModelCategory() { return hex.ModelCategory.Binomial; }

public boolean isSupervised() { return true; }

public int nfeatures() { return 28; }

public int nclasses() { return 2; }

// Thread-local storage for input neuron activation values.

final double[] NUMS = new double[28];

static class NORMMUL implements java.io.Serializable {

public static final double[] VALUES = new double[28];

static {

NORMMUL_0.fill(VALUES);

}

static final class NORMMUL_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 1.7687666758901264;

sa[1] = 0.9913821723096016;

sa[2] = 0.9936853236221495;

sa[3] = 1.6666383037503143;

sa[4] = 0.9937488864153216;

sa[5] = 2.105437242840467;

sa[6] = 0.9908361123051243;

sa[7] = 0.9940879578054577;

sa[8] = 0.9729178470795813;

sa[9] = 2.0007082148981183;

sa[10] = 0.9908480722586916;

sa[11] = 0.9938660006765665;

sa[12] = 0.9528949618561464;

sa[13] = 2.0508575278770245;

sa[14] = 0.9912345684749029;

sa[15] = 0.9937069184546701;

sa[16] = 0.8377686617849256;

sa[17] = 1.9768892962453906;

sa[18] = 0.9926596305568416;

sa[19] = 0.9937642381155177;

sa[20] = 0.7141691868612743;

sa[21] = 1.4816770107928496;

sa[22] = 2.62612559064267;

sa[23] = 6.074042423656259;

sa[24] = 2.5162755660661866;

sa[25] = 1.9042873091548915;

sa[26] = 2.7391280258211443;

sa[27] = 3.1929106654741926;

}

static class NORMSUB implements java.io.Serializable {

public static final double[] VALUES = new double[28];

static {

NORMSUB_0.fill(VALUES);

}

static final class NORMSUB_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.991609543911382;

sa[1] = -6.172673222856738E-5;

sa[2] = 2.1854967778855427E-4;

sa[3] = 0.9984508227147362;

sa[4] = 2.7703720484945748E-5;

sa[5] = 0.9908871828929133;

sa[6] = -8.849292707005366E-5;

sa[7] = -1.54437948956086E-4;

sa[8] = 0.9999179533939873;

sa[9] = 0.9927406409576117;

sa[10] = -1.6275628806378383E-4;

sa[11] = 7.234230467006848E-5;

sa[12] = 1.0002384149332444;

sa[13] = 0.992170569563542;

sa[14] = 4.1840079250049434E-5;

sa[15] = 3.615676062458686E-5;

sa[16] = 0.999843197801924;

sa[17] = 0.9861267051297294;

sa[18] = 3.768967267508312E-5;

sa[19] = 1.6822728241595495E-4;

sa[20] = 1.0001443952117024;

sa[21] = 1.0343311905419041;

sa[22] = 1.0247880896606023;

sa[23] = 1.0505599836914452;

sa[24] = 1.0096686212679917;

sa[25] = 0.9729231063653536;

sa[26] = 1.0329730880581618;

sa[27] = 0.9597638460111044;

}

// Workspace for categorical offsets.

public static final int[] CATOFFSETS = {0};

// Hidden layer dropout ratios.

public static final double[] HIDDEN_DROPOUT_RATIOS = {0.5,0.5,0.5};

// Number of neurons for each layer.

public static final int[] NEURONS = {28,500,500,500,2};

// Thread-local storage for neuron activation values.

final double[][] ACTIVATION = new double[][] {

/* Input */ DeepLearning_model_1540691693623_1_Activation_0.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_1.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_2.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Activation_3.VALUES,

/* Softmax */ DeepLearning_model_1540691693623_1_Activation_4.VALUES

};

// Neuron bias values.

public static final double[][] BIAS = new double[][] {

/* Input */ DeepLearning_model_1540691693623_1_Bias_0.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_1.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_2.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Bias_3.VALUES,

/* Softmax */ DeepLearning_model_1540691693623_1_Bias_4.VALUES

};

// Connecting weights between neurons.

public static final float[][] WEIGHT = new float[][] {

/* Input */ DeepLearning_model_1540691693623_1_Weight_0.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_1.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_2.VALUES,

/* RectifierDropout */ DeepLearning_model_1540691693623_1_Weight_3.VALUES,

/* Softmax */ DeepLearning_model_1540691693623_1_Weight_4.VALUES

};

// Names of columns used by model.

public static final String[] NAMES = NamesHolder_DeepLearning_model_1540691693623_1.VALUES;

// Number of output classes included in training data response column.

public static final int NCLASSES = 2;

// Column domains. The last array contains domain of response column.

public static final String[][] DOMAINS = new String[][] {

/* features0 */ null,

/* features1 */ null,

/* features2 */ null,

/* features3 */ null,

/* features4 */ null,

/* features5 */ null,

/* features6 */ null,

/* features7 */ null,

/* features8 */ null,

/* features9 */ null,

/* features10 */ null,

/* features11 */ null,

/* features12 */ null,

/* features13 */ null,

/* features14 */ null,

/* features15 */ null,

/* features16 */ null,

/* features17 */ null,

/* features18 */ null,

/* features19 */ null,

/* features20 */ null,

/* features21 */ null,

/* features22 */ null,

/* features23 */ null,

/* features24 */ null,

/* features25 */ null,

/* features26 */ null,

/* features27 */ null,

/* label */ DeepLearning_model_1540691693623_1_ColInfo_28.VALUES

};

// Prior class distribution

public static final double[] PRIOR_CLASS_DISTRIB = {0.4701428794437793,0.5298571205562207};

// Class distribution used for model building

public static final double[] MODEL_CLASS_DISTRIB = null;

public DeepLearning_model_1540691693623_1() { super(NAMES,DOMAINS); }

public String getUUID() { return Long.toString(-5314795359721044940L); }

// Pass in data in a double[], pre-aligned to the Model's requirements.

// Jam predictions into the preds[] array; preds[0] is reserved for the

// main prediction (class for classifiers or value for regression),

// and remaining columns hold a probability distribution for classifiers.

public final double[] score0( double[] data, double[] preds ) {

java.util.Arrays.fill(preds,0);

java.util.Arrays.fill(NUMS,0);

int i = 0, ncats = 0;

final int n = data.length;

for(; i<n; ++i) {

NUMS[i] = Double.isNaN(data[i]) ? 0 : (data[i] - NORMSUB.VALUES[i])*NORMMUL.VALUES[i];

}

java.util.Arrays.fill(ACTIVATION[0],0);

for (i=0; i<NUMS.length; ++i) {

ACTIVATION[0][CATOFFSETS[CATOFFSETS.length-1] + i] = Double.isNaN(NUMS[i]) ? 0 : NUMS[i];

}

for (i=1; i<ACTIVATION.length; ++i) {

java.util.Arrays.fill(ACTIVATION[i],0);

int cols = ACTIVATION[i-1].length;

int rows = ACTIVATION[i].length;

int extra=cols-cols%8;

int multiple = (cols/8)*8-1;

int idx = 0;

float[] a = WEIGHT[i];

double[] x = ACTIVATION[i-1];

double[] y = BIAS[i];

double[] res = ACTIVATION[i];

for (int row=0; row<rows; ++row) {

double psum0 = 0, psum1 = 0, psum2 = 0, psum3 = 0, psum4 = 0, psum5 = 0, psum6 = 0, psum7 = 0;

for (int col = 0; col < multiple; col += 8) {

int off = idx + col;

psum0 += a[off ] * x[col ];

psum1 += a[off + 1] * x[col + 1];

psum2 += a[off + 2] * x[col + 2];

psum3 += a[off + 3] * x[col + 3];

psum4 += a[off + 4] * x[col + 4];

psum5 += a[off + 5] * x[col + 5];

psum6 += a[off + 6] * x[col + 6];

psum7 += a[off + 7] * x[col + 7];

}

res[row] += psum0 + psum1 + psum2 + psum3;

res[row] += psum4 + psum5 + psum6 + psum7;

for (int col = extra; col < cols; col++)

res[row] += a[idx + col] * x[col];

res[row] += y[row];

idx += cols;

}

if (i<ACTIVATION.length-1) {

for (int r=0; r<ACTIVATION[i].length; ++r) {

ACTIVATION[i][r] = Math.max(0, ACTIVATION[i][r]);

if (i<ACTIVATION.length-1) {

ACTIVATION[i][r] *= 1 - HIDDEN_DROPOUT_RATIOS[i-1];

}

if (i == ACTIVATION.length-1) {

double max = ACTIVATION[i][0];

for (int r=1; r<ACTIVATION[i].length; r++) {

if (ACTIVATION[i][r]>max) max = ACTIVATION[i][r];

}

double scale = 0;

for (int r=0; r<ACTIVATION[i].length; r++) {

ACTIVATION[i][r] = Math.exp(ACTIVATION[i][r] - max);

scale += ACTIVATION[i][r];

}

for (int r=0; r<ACTIVATION[i].length; r++) {

if (Double.isNaN(ACTIVATION[i][r]))

throw new RuntimeException("Numerical instability, predicted NaN.");

ACTIVATION[i][r] /= scale;

preds[r+1] = ACTIVATION[i][r];

}

preds[0] = hex.genmodel.GenModel.getPrediction(preds, PRIOR_CLASS_DISTRIB, data, 0.44319463906785384);

return preds;

}

// Neuron activation values for Input layer

class DeepLearning_model_1540691693623_1_Activation_0 implements java.io.Serializable {

public static final double[] VALUES = new double[28];

static {

DeepLearning_model_1540691693623_1_Activation_0_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Activation_0_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.0;

sa[1] = 0.0;

sa[2] = 0.0;

sa[3] = 0.0;

sa[4] = 0.0;

sa[5] = 0.0;

sa[6] = 0.0;

sa[7] = 0.0;

sa[8] = 0.0;

sa[9] = 0.0;

sa[10] = 0.0;

sa[11] = 0.0;

sa[12] = 0.0;

sa[13] = 0.0;

sa[14] = 0.0;

sa[15] = 0.0;

sa[16] = 0.0;

sa[17] = 0.0;

sa[18] = 0.0;

sa[19] = 0.0;

sa[20] = 0.0;

sa[21] = 0.0;

sa[22] = 0.0;

sa[23] = 0.0;

sa[24] = 0.0;

sa[25] = 0.0;

sa[26] = 0.0;

sa[27] = 0.0;

}

// Neuron activation values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Activation_1 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Activation_1_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Activation_1_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.0;

sa[1] = 0.0;

sa[2] = 0.0;

sa[3] = 0.0;

sa[4] = 0.0;

sa[5] = 0.0;

......

sa[499] = 0.0;

}

// Neuron activation values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Activation_2 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Activation_2_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Activation_2_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.0;

sa[1] = 0.0;

sa[2] = 0.0;

sa[3] = 0.0;

sa[4] = 0.0;

sa[5] = 0.0;

......

sa[499] = 0.0;

}

// Neuron activation values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Activation_3 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Activation_3_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Activation_3_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.0;

sa[1] = 0.0;

sa[2] = 0.0;

sa[3] = 0.0;

sa[4] = 0.0;

sa[5] = 0.0;

......

sa[499] = 0.0;

}

// Neuron activation values for Softmax layer

class DeepLearning_model_1540691693623_1_Activation_4 implements java.io.Serializable {

public static final double[] VALUES = new double[2];

static {

DeepLearning_model_1540691693623_1_Activation_4_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Activation_4_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.0;

sa[1] = 0.0;

}

// Neuron bias values for Input layer

class DeepLearning_model_1540691693623_1_Bias_0 implements java.io.Serializable {

public static final double[] VALUES = null;

}

// Neuron bias values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Bias_1 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Bias_1_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Bias_1_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = -0.6082208509410506;

sa[1] = -0.7866761395746675;

sa[2] = -0.7902771837144533;

sa[3] = -1.078600190576397;

sa[4] = -1.1325559100264349;

sa[5] = -1.3141680956557276;

......

sa[499] = -1.1605339237438876;

}

// Neuron bias values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Bias_2 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Bias_2_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Bias_2_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = 0.02034537567535967;

sa[1] = 0.2056398687484795;

sa[2] = -0.6811208002656562;

sa[3] = 0.34906780212313926;

sa[4] = 0.1994718812435918;

sa[5] = -0.4389162411792007;

......

sa[499] = -0.19825444966679512;

}

// Neuron bias values for RectifierDropout layer

class DeepLearning_model_1540691693623_1_Bias_3 implements java.io.Serializable {

public static final double[] VALUES = new double[500];

static {

DeepLearning_model_1540691693623_1_Bias_3_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Bias_3_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = -0.37334331766490575;

sa[1] = -0.2192842820590019;

sa[2] = -0.48037506449229245;

sa[3] = -0.27829081354485186;

sa[4] = -0.5348837641304954;

........

sa[499] = -0.38094144337852304;

}

// Neuron bias values for Softmax layer

class DeepLearning_model_1540691693623_1_Bias_4 implements java.io.Serializable {

public static final double[] VALUES = new double[2];

static {

DeepLearning_model_1540691693623_1_Bias_4_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Bias_4_0 implements java.io.Serializable {

static final void fill(double[] sa) {

sa[0] = -0.11833918432774448;

sa[1] = 0.08029026554573974;

}

class DeepLearning_model_1540691693623_1_Weight_0 implements java.io.Serializable {

public static final float[] VALUES = null;

}

// Neuron weights connecting Input and RectifierDropout layer

class DeepLearning_model_1540691693623_1_Weight_1 implements java.io.Serializable {

public static final float[] VALUES = new float[14000];

static {

DeepLearning_model_1540691693623_1_Weight_1_0.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_1_1.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_1_2.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_1_3.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_1_4.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Weight_1_0 implements java.io.Serializable {

static final void fill(float[] sa) {

sa[0] = -0.06823527f;

sa[1] = 0.01967861f;

sa[2] = -0.03716086f;

sa[3] = -0.011376046f;

sa[4] = -0.019753613f;

sa[5] = -0.19310619f;

......

sa[13999] = -0.12823965f;

}

// Neuron weights connecting RectifierDropout and RectifierDropout layer

class DeepLearning_model_1540691693623_1_Weight_2 implements java.io.Serializable {

public static final float[] VALUES = new float[250000];

static {

DeepLearning_model_1540691693623_1_Weight_2_0.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_1.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_2.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_3.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_4.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_5.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_6.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_7.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_8.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_9.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_10.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_11.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_12.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_13.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_14.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_15.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_16.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_17.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_18.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_19.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_20.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_21.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_22.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_23.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_24.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_25.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_26.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_27.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_28.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_29.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_30.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_31.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_32.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_33.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_34.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_35.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_36.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_37.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_38.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_39.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_40.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_41.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_42.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_43.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_44.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_45.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_46.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_47.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_48.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_49.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_50.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_51.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_52.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_53.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_54.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_55.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_56.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_57.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_58.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_59.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_60.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_61.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_62.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_63.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_64.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_65.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_66.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_67.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_68.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_69.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_70.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_71.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_72.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_73.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_74.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_75.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_76.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_77.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_78.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_79.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_80.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_81.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_82.fill(VALUES);

DeepLearning_model_1540691693623_1_Weight_2_83.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Weight_2_0 implements java.io.Serializable {

static final void fill(float[] sa) {

sa[0] = -0.24805546f;

sa[1] = -0.06499913f;

sa[2] = -0.14989536f;

sa[3] = -0.06383444f;

sa[4] = 0.14076568f;

sa[5] = -0.16730806f;

......

sa[249999] = 0.005610808f;

}

// Neuron weights connecting RectifierDropout and Softmax layer

class DeepLearning_model_1540691693623_1_Weight_4 implements java.io.Serializable {

public static final float[] VALUES = new float[1000];

static {

DeepLearning_model_1540691693623_1_Weight_4_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_Weight_4_0 implements java.io.Serializable {

static final void fill(float[] sa) {

sa[0] = 0.2789825f;

sa[1] = 0.4297707f;

sa[2] = -0.28039044f;

sa[3] = -0.13956442f;

sa[4] = -0.07300115f;

sa[5] = 0.13860723f;

........

sa[999] = 0.043791886f;

}

// The class representing training column names

class NamesHolder_DeepLearning_model_1540691693623_1 implements java.io.Serializable {

public static final String[] VALUES = new String[28];

static {

NamesHolder_DeepLearning_model_1540691693623_1_0.fill(VALUES);

}

static final class NamesHolder_DeepLearning_model_1540691693623_1_0 implements java.io.Serializable {

static final void fill(String[] sa) {

sa[0] = "features0";

sa[1] = "features1";

sa[2] = "features2";

sa[3] = "features3";

sa[4] = "features4";

sa[5] = "features5";

sa[6] = "features6";

sa[7] = "features7";

sa[8] = "features8";

sa[9] = "features9";

sa[10] = "features10";

sa[11] = "features11";

sa[12] = "features12";

sa[13] = "features13";

sa[14] = "features14";

sa[15] = "features15";

sa[16] = "features16";

sa[17] = "features17";

sa[18] = "features18";

sa[19] = "features19";

sa[20] = "features20";

sa[21] = "features21";

sa[22] = "features22";

sa[23] = "features23";

sa[24] = "features24";

sa[25] = "features25";

sa[26] = "features26";

sa[27] = "features27";

}

// The class representing column label

class DeepLearning_model_1540691693623_1_ColInfo_28 implements java.io.Serializable {

public static final String[] VALUES = new String[2];

static {

DeepLearning_model_1540691693623_1_ColInfo_28_0.fill(VALUES);

}

static final class DeepLearning_model_1540691693623_1_ColInfo_28_0 implements java.io.Serializable {

static final void fill(String[] sa) {

sa[0] = "0";

sa[1] = "1";

}

Science To Medicine

Just My Daily Study Note by ts.anesth.kpum