Module: contrib.distributions

Module: tf.contrib.distributions

Module tf.contrib.distributions

Defined in tensorflow/contrib/distributions/__init__.py.

Classes representing statistical distributions and ops for working with them.

See the Statistical Distributions (contrib) guide.

Modules

bijectors module: Bijector Ops.

Classes

class Bernoulli: Bernoulli distribution.

class BernoulliWithSigmoidProbs: Bernoulli with probs = nn.sigmoid(logits).

class Beta: Beta distribution.

class BetaWithSoftplusConcentration: Beta with softplus transform of concentration1 and concentration0.

class Binomial: Binomial distribution.

class Categorical: Categorical distribution.

class Chi2: Chi2 distribution.

class Chi2WithAbsDf: Chi2 with parameter transform df = floor(abs(df)).

class ConditionalDistribution: Distribution that supports intrinsic parameters (local latents).

class ConditionalTransformedDistribution: A TransformedDistribution that allows intrinsic conditioning.

class Deterministic: Scalar Deterministic distribution on the real line.

class Dirichlet: Dirichlet distribution.

class DirichletMultinomial: Dirichlet-Multinomial compound distribution.

class Distribution: A generic probability distribution base class.

class ExpRelaxedOneHotCategorical: ExpRelaxedOneHotCategorical distribution with temperature and logits.

class Exponential: Exponential distribution.

class ExponentialWithSoftplusRate: Exponential with softplus transform on rate.

class Gamma: Gamma distribution.

class GammaWithSoftplusConcentrationRate: Gamma with softplus of concentration and rate.

class Geometric: Geometric distribution.

class InverseGamma: InverseGamma distribution.

class InverseGammaWithSoftplusConcentrationRate: InverseGamma with softplus of concentration and rate.

class Laplace: The Laplace distribution with location loc and scale parameters.

class LaplaceWithSoftplusScale: Laplace with softplus applied to scale.

class Logistic: The Logistic distribution with location loc and scale parameters.

class Mixture: Mixture distribution.

class Multinomial: Multinomial distribution.

class MultivariateNormalDiag: The multivariate normal distribution on R^k.

class MultivariateNormalDiagPlusLowRank: The multivariate normal distribution on R^k.

class MultivariateNormalDiagWithSoftplusScale: MultivariateNormalDiag with diag_stddev = softplus(diag_stddev).

class MultivariateNormalFullCovariance: The multivariate normal distribution on R^k.

class MultivariateNormalTriL: The multivariate normal distribution on R^k.

class NegativeBinomial: NegativeBinomial distribution.

class Normal: The Normal distribution with location loc and scale parameters.

class NormalWithSoftplusScale: Normal with softplus applied to scale.

class OneHotCategorical: OneHotCategorical distribution.

class Poisson: Poisson distribution.

class QuantizedDistribution: Distribution representing the quantization Y = ceiling(X).

class RegisterKL: Decorator to register a KL divergence implementation function.

class RelaxedBernoulli: RelaxedBernoulli distribution with temperature and logits parameters.

class RelaxedOneHotCategorical: RelaxedOneHotCategorical distribution with temperature and logits.

class ReparameterizationType: Instances of this class represent how sampling is reparameterized.

class StudentT: Student's t-distribution.

class StudentTWithAbsDfSoftplusScale: StudentT with df = floor(abs(df)) and scale = softplus(scale).

class TransformedDistribution: A Transformed Distribution.

class Uniform: Uniform distribution with low and high parameters.

class VectorDeterministic: Vector Deterministic distribution on R^k.

class VectorLaplaceDiag: The vectorization of the Laplace distribution on R^k.

class WishartCholesky: The matrix Wishart distribution on positive definite matrices.

class WishartFull: The matrix Wishart distribution on positive definite matrices.

Functions

kl_divergence(...): Get the KL-divergence KL(distribution_a || distribution_b).

matrix_diag_transform(...): Transform diagonal of [batch-]matrix, leave rest of matrix unchanged.

normal_conjugates_known_scale_posterior(...): Posterior Normal distribution with conjugate prior on the mean.

normal_conjugates_known_scale_predictive(...): Posterior predictive Normal distribution w. conjugate prior on the mean.

percentile(...): Compute the q-th percentile of x.

softplus_inverse(...): Computes the inverse softplus, i.e., x = softplus_inverse(softplus(x)).

Other Members

FULLY_REPARAMETERIZED

NOT_REPARAMETERIZED