mxfusion.components.distributions.normal¶
Members¶
-
class
mxfusion.components.distributions.normal.Normal(mean, variance, rand_gen=None, dtype=None, ctx=None)¶ Bases:
mxfusion.components.distributions.univariate.UnivariateDistributionThe one-dimensional normal distribution. The normal distribution can be defined over a scalar random variable or an array of random variables. In case of an array of random variables, the mean and variance are broadcasted to the shape of the output random variable (array).
Parameters: - mean (Variable) – Mean of the normal distribution.
- variance (Variable) – Variance of the normal distribution.
- rand_gen (RandomGenerator) – the random generator (default: MXNetRandomGenerator).
- dtype (numpy.float32 or numpy.float64) – the data type for float point numbers.
- ctx (None or mxnet.cpu or mxnet.gpu) – the mxnet context (default: None/current context).
-
log_pdf(F, variables)¶ Computes the logrithm of the probability density/mass function (PDF/PMF) of the distribution. The inputs and outputs variables are fetched from the variables argument according to their UUIDs.
Parameters: - F (mxnet.symbol or mxnet.ndarray) – the MXNet computation mode
- variables – the set of MXNet arrays that holds the values of
variables at runtime. :type variables: {str(UUID): MXNet NDArray or MXNet Symbol} :returns: log pdf of the distribution :rtypes: MXNet NDArray or MXNet Symbol
-
draw_samples(F, variables, num_samples=1, always_return_tuple=False)¶ Draw a set of samples from the distribution. The inputs variables are fetched from the variables argument according to their UUIDs.
Parameters: - F (mxnet.symbol or mxnet.ndarray) – the MXNet computation mode
- variables – the set of MXNet arrays that holds the values of
variables at runtime. :type variables: {str(UUID): MXNet NDArray or MXNet Symbol} :param num_samples: the number of drawn samples (default: one) :int num_samples: int :param always_return_tuple: Whether return a tuple even if there is only one variables in outputs. :type always_return_tuple: boolean :returns: a set samples of the distribution :rtypes: MXNet NDArray or MXNet Symbol or [MXNet NDArray or MXNet Symbol]
-
static
define_variable(mean=0.0, variance=1.0, shape=None, rand_gen=None, dtype=None, ctx=None)¶ Creates and returns a random variable drawn from a normal distribution.
Parameters: - mean – Mean of the distribution.
- variance – Variance of the distribution.
- shape (tuple or [tuple]) – the shape of the random variable(s).
- rand_gen (RandomGenerator) – the random generator (default: MXNetRandomGenerator).
- dtype (numpy.float32 or numpy.float64) – the data type for float point numbers.
- ctx (None or mxnet.cpu or mxnet.gpu) – the mxnet context (default: None/current context).
Returns: the random variables drawn from the normal distribution.
Rtypes: Variable
-
class
mxfusion.components.distributions.normal.MultivariateNormalLogPDFDecorator¶ Bases:
mxfusion.components.distributions.distribution.LogPDFDecorator
-
class
mxfusion.components.distributions.normal.MultivariateNormalDrawSamplesDecorator¶ Bases:
mxfusion.components.distributions.distribution.DrawSamplesDecorator
-
class
mxfusion.components.distributions.normal.MultivariateNormal(mean, covariance, rand_gen=None, minibatch_ratio=1.0, dtype=None, ctx=None)¶ Bases:
mxfusion.components.distributions.distribution.DistributionThe multi-dimensional normal distribution.
Parameters: - mean (Variable) – Mean of the normal distribution.
- covariance (Variable) – Covariance matrix of the distribution.
- rand_gen (RandomGenerator) – the random generator (default: MXNetRandomGenerator).
- dtype (numpy.float32 or numpy.float64) – the data type for float point numbers.
- ctx (None or mxnet.cpu or mxnet.gpu) – the mxnet context (default: None/current context).
-
replicate_self(attribute_map=None)¶ Replicates this Factor, using new inputs, outputs, and a new uuid. Used during model replication to functionally replicate a factor into a new graph.
Parameters:
-
log_pdf(F, variables)¶ Computes the logrithm of the probability density/mass function (PDF/PMF) of the distribution. The inputs and outputs variables are fetched from the variables argument according to their UUIDs.
Parameters: - F (mxnet.symbol or mxnet.ndarray) – the MXNet computation mode
- variables – the set of MXNet arrays that holds the values of
variables at runtime. :type variables: {str(UUID): MXNet NDArray or MXNet Symbol} :returns: log pdf of the distribution :rtypes: MXNet NDArray or MXNet Symbol
-
draw_samples(F, variables, num_samples=1, always_return_tuple=False)¶ Draw a set of samples from the distribution. The inputs variables are fetched from the variables argument according to their UUIDs.
Parameters: - F (mxnet.symbol or mxnet.ndarray) – the MXNet computation mode
- variables – the set of MXNet arrays that holds the values of
variables at runtime. :type variables: {str(UUID): MXNet NDArray or MXNet Symbol} :param num_samples: the number of drawn samples (default: one) :int num_samples: int :param always_return_tuple: Whether return a tuple even if there is only one variables in outputs. :type always_return_tuple: boolean :returns: a set samples of the distribution :rtypes: MXNet NDArray or MXNet Symbol or [MXNet NDArray or MXNet Symbol]
-
static
define_variable(shape, mean=0.0, covariance=None, rand_gen=None, minibatch_ratio=1.0, dtype=None, ctx=None)¶ Creates and returns a random variable drawn from a normal distribution.
Parameters: - mean – Mean of the distribution.
- covariance – Variance of the distribution.
- shape (tuple or [tuple]) – the shape of the random variable(s).
- rand_gen (RandomGenerator) – the random generator (default: MXNetRandomGenerator).
- dtype (numpy.float32 or numpy.float64) – the data type for float point numbers.
- ctx (None or mxnet.cpu or mxnet.gpu) – the mxnet context (default: None/current context).
Returns: the random variables drawn from the normal distribution.
Rtypes: Variable