public static INDArray max(INDArray compute, int dimension) { return compute.max(dimension); }
INDArray maxAlong0 = originalArray.max(0); INDArray sumAlong0 = originalArray.sum(0); INDArray avgAlong0 = originalArray.mean(0);
public static INDArray max(INDArray compute) { return compute.max(Integer.MAX_VALUE); }
throw new IllegalArgumentException("Only supports row wise calculations"); if (x.isMatrix()) { INDArray maxAlongDimension = x.max(dimensions); if (!maxAlongDimension.isVector() && !maxAlongDimension.isScalar()) throw new IllegalStateException("Max along dimension for input must either be a row vector or scalar");
@Override public INDArray exampleMaxs() { return getFeatures().max(1); }
/** * Divides each row by its max * * @param toScale the matrix to divide by its row maxes */ public static void scaleByMax(INDArray toScale) { INDArray scale = toScale.max(1); for (int i = 0; i < toScale.rows(); i++) { double scaleBy = scale.getDouble(i); toScale.putRow(i, toScale.getRow(i).divi(scaleBy)); } }
INDArray batchMax = data.max(0); if (!Arrays.equals(batchMin.shape(), batchMax.shape())) throw new IllegalStateException(
/** * Scales the ndarray columns * to the given min/max values * * @param min the minimum number * @param max the max number */ public static void scaleMinMax(double min, double max, INDArray toScale) { //X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0)) X_scaled = X_std * (max - min) + min INDArray min2 = toScale.min(0); INDArray max2 = toScale.max(0); INDArray std = toScale.subRowVector(min2).diviRowVector(max2.sub(min2)); INDArray scaled = std.mul(max - min).addi(min); toScale.assign(scaled); }
INDArray normalPart = mdc.alpha.div(Transforms.pow(mdc.sigma.mul(SQRT_TWO_PI), mLabelWidth)); INDArray exponent = labelsMinusMuSquared.div(minustwovariance); INDArray exponentMax = exponent.max(1); exponent.subiColumnVector(exponentMax); INDArray pi = Transforms.exp(exponent).muli(normalPart);
@Override public INDArray op(INDArray neighbourhoodFeatures, INDArray nodeFeature) { return neighbourhoodFeatures.max(0); }
public static INDArray max(INDArray compute) { return compute.max(Integer.MAX_VALUE); }
public static INDArray max(INDArray compute, int dimension) { return compute.max(dimension); }
@Override public INDArray exampleMaxs() { return getFeatures().max(1); }
public double getMaxConfidence(INDArray v) { return v.max(0).sumNumber().doubleValue(); }
public double getMaxConfidence(INDArray v) { return v.max(0).sumNumber().doubleValue(); }
public static SummaryStatistics summaryStats(INDArray d) { return new SummaryStatistics(d.mean(Integer.MAX_VALUE), d.sum(Integer.MAX_VALUE), d.min(Integer.MAX_VALUE), d.max(Integer.MAX_VALUE)); }
public static String summaryStatsString(INDArray d) { return new SummaryStatistics(d.mean(Integer.MAX_VALUE), d.sum(Integer.MAX_VALUE), d.min(Integer.MAX_VALUE), d.max(Integer.MAX_VALUE)).toString(); }
/** * Divides each row by its max * * @param toScale the matrix to divide by its row maxes */ public static void scaleByMax(INDArray toScale) { INDArray scale = toScale.max(1); for (int i = 0; i < toScale.rows(); i++) { double scaleBy = scale.getDouble(i); toScale.putRow(i, toScale.getRow(i).divi(scaleBy)); } }
@Override public INDArray ndOp(INDArray features, INDArray adjacencyMatrix) { INDArray[] maxes = new INDArray[features.columns()]; for (int fCol = 0; fCol < features.columns(); fCol++) { INDArray mul = adjacencyMatrix.transpose().mulColumnVector(features.getColumn(fCol)); maxes[fCol] = mul.max(0).transpose(); } return Nd4j.hstack(maxes); }
/** * Scales the ndarray columns * to the given min/max values * * @param min the minimum number * @param max the max number */ public static void scaleMinMax(double min, double max, INDArray toScale) { //X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0)) X_scaled = X_std * (max - min) + min INDArray min2 = toScale.min(0); INDArray max2 = toScale.max(0); INDArray std = toScale.subRowVector(min2).diviRowVector(max2.sub(min2)); INDArray scaled = std.mul(max - min).addi(min); toScale.assign(scaled); }