org.nd4j.autodiff.samediff.ops

Class SDRandom

java.lang.Object

org.nd4j.autodiff.samediff.ops.SDOps

org.nd4j.autodiff.samediff.ops.SDRandom

public class SDRandom
extends SDOps

Field Summary

Fields inherited from class org.nd4j.autodiff.samediff.ops.SDOps

sd

Constructor Summary

Constructors

Constructor and Description
SDRandom(SameDiff sameDiff)

Method Summary

Modifier and Type	Method and Description
SDVariable	bernoulli(double p, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Bernoulli distribution, with the specified probability.
SDVariable	bernoulli(String name, double p, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Bernoulli distribution, with the specified probability.
SDVariable	binomial(int nTrials, double p, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Binomial distribution, with the specified number of trials and probability.
SDVariable	binomial(String name, int nTrials, double p, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Binomial distribution, with the specified number of trials and probability.
SDVariable	exponential(double lambda, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a exponential distribution: P(x) = lambda * exp(-lambda * x) Inputs must satisfy the following constraints: Must be positive: lambda > 0
SDVariable	exponential(String name, double lambda, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a exponential distribution: P(x) = lambda * exp(-lambda * x) Inputs must satisfy the following constraints: Must be positive: lambda > 0
SDVariable	logNormal(double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Log Normal distribution, i.e., log(x) ~ N(mean, stdev)
SDVariable	logNormal(String name, double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Log Normal distribution, i.e., log(x) ~ N(mean, stdev)
SDVariable	normal(double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution, N(mean, stdev)
SDVariable	normal(String name, double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution, N(mean, stdev)
SDVariable	normalTruncated(double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution, N(mean, stdev).
SDVariable	normalTruncated(String name, double mean, double stddev, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution, N(mean, stdev).
SDVariable	uniform(double min, double max, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a uniform distribution, U(min,max)
SDVariable	uniform(String name, double min, double max, DataType datatype, long... shape) Generate a new random INDArray, where values are randomly sampled according to a uniform distribution, U(min,max)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SDRandom

public SDRandom(SameDiff sameDiff)

Method Detail

bernoulli

public SDVariable bernoulli(double p,
                            DataType datatype,
                            long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Bernoulli distribution,
with the specified probability. Array values will have value 1 with probability P and value 0 with probability
1-P.

Parameters:

p - Probability of value 1

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

bernoulli

public SDVariable bernoulli(String name,
                            double p,
                            DataType datatype,
                            long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Bernoulli distribution,
with the specified probability. Array values will have value 1 with probability P and value 0 with probability
1-P.

Parameters:

name - name May be null. Name for the output variable

p - Probability of value 1

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

binomial

public SDVariable binomial(int nTrials,
                           double p,
                           DataType datatype,
                           long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Binomial distribution,
with the specified number of trials and probability.

Parameters:

nTrials - Number of trials parameter for the binomial distribution

p - Probability of success for each trial

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

binomial

public SDVariable binomial(String name,
                           int nTrials,
                           double p,
                           DataType datatype,
                           long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Binomial distribution,
with the specified number of trials and probability.

Parameters:

name - name May be null. Name for the output variable

nTrials - Number of trials parameter for the binomial distribution

p - Probability of success for each trial

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

exponential

public SDVariable exponential(double lambda,
                              DataType datatype,
                              long... shape)

Generate a new random INDArray, where values are randomly sampled according to a exponential distribution:
P(x) = lambda * exp(-lambda * x)
Inputs must satisfy the following constraints:
Must be positive: lambda > 0

Parameters:

lambda - lambda parameter

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

exponential

public SDVariable exponential(String name,
                              double lambda,
                              DataType datatype,
                              long... shape)

Generate a new random INDArray, where values are randomly sampled according to a exponential distribution:
P(x) = lambda * exp(-lambda * x)
Inputs must satisfy the following constraints:
Must be positive: lambda > 0

Parameters:

name - name May be null. Name for the output variable

lambda - lambda parameter

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

logNormal

public SDVariable logNormal(double mean,
                            double stddev,
                            DataType datatype,
                            long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Log Normal distribution,
i.e., log(x) ~ N(mean, stdev)

Parameters:

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

logNormal

public SDVariable logNormal(String name,
                            double mean,
                            double stddev,
                            DataType datatype,
                            long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Log Normal distribution,
i.e., log(x) ~ N(mean, stdev)

Parameters:

name - name May be null. Name for the output variable

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

normal

public SDVariable normal(double mean,
                         double stddev,
                         DataType datatype,
                         long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution,
N(mean, stdev)

Parameters:

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

normal

public SDVariable normal(String name,
                         double mean,
                         double stddev,
                         DataType datatype,
                         long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution,
N(mean, stdev)

Parameters:

name - name May be null. Name for the output variable

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

normalTruncated

public SDVariable normalTruncated(double mean,
                                  double stddev,
                                  DataType datatype,
                                  long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution,
N(mean, stdev). However, any values more than 1 standard deviation from the mean are dropped and re-sampled

Parameters:

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

normalTruncated

public SDVariable normalTruncated(String name,
                                  double mean,
                                  double stddev,
                                  DataType datatype,
                                  long... shape)

Generate a new random INDArray, where values are randomly sampled according to a Gaussian (normal) distribution,
N(mean, stdev). However, any values more than 1 standard deviation from the mean are dropped and re-sampled

Parameters:

name - name May be null. Name for the output variable

mean - Mean value for the random array

stddev - Standard deviation for the random array

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

uniform

public SDVariable uniform(double min,
                          double max,
                          DataType datatype,
                          long... shape)

Generate a new random INDArray, where values are randomly sampled according to a uniform distribution,
U(min,max)

Parameters:

min - Minimum value

max - Maximum value.

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)

uniform

public SDVariable uniform(String name,
                          double min,
                          double max,
                          DataType datatype,
                          long... shape)

Generate a new random INDArray, where values are randomly sampled according to a uniform distribution,
U(min,max)

Parameters:

name - name May be null. Name for the output variable

min - Minimum value

max - Maximum value.

datatype - Data type of the output variable

shape - Shape of the new random INDArray, as a 1D array (Size: AtLeast(min=0))

Returns:

output Tensor with the given shape where values are randomly sampled according to a %OP_NAME% distribution (NUMERIC type)