Module: tf.contrib.distributions

Module tf.contrib.distributions

Classes representing statistical distributions and ops for working with them.

See the Statistical Distributions (contrib) guide.

Members

class Bernoulli: Bernoulli distribution.

class BernoulliWithSigmoidP: Bernoulli with p = sigmoid(p).

class Beta: Beta distribution.

class BetaWithSoftplusAB: Beta with softplus transform on a and b.

class Binomial: Binomial distribution.

class Categorical: Categorical distribution.

class Chi2: The Chi2 distribution with degrees of freedom df.

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

class Dirichlet: Dirichlet distribution.

class DirichletMultinomial: DirichletMultinomial mixture distribution.

class Distribution: A generic probability distribution base class.

class Exponential: The Exponential distribution with rate parameter lam.

class ExponentialWithSoftplusLam: Exponential with softplus transform on lam.

class Gamma: The Gamma distribution with parameter alpha and beta.

class GammaWithSoftplusAlphaBeta: Gamma with softplus transform on alpha and beta.

class InverseGamma: The InverseGamma distribution with parameter alpha and beta.

class InverseGammaWithSoftplusAlphaBeta: Inverse Gamma with softplus applied to alpha and beta.

class Laplace: The Laplace distribution with location and scale > 0 parameters.

class LaplaceWithSoftplusScale: Laplace with softplus applied to scale.

class Mixture: Mixture distribution.

class Multinomial: Multinomial distribution.

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

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

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

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

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

class Normal: The scalar Normal distribution with mean and stddev parameters mu, sigma.

class NormalWithSoftplusSigma: Normal with softplus applied to sigma.

class Poisson: Poisson distribution.

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

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

class StudentT: Student's t distribution with degree-of-freedom parameter df.

class StudentTWithAbsDfSoftplusSigma: StudentT with df = floor(abs(df)) and sigma = softplus(sigma).

class TransformedDistribution: A Transformed Distribution.

class Uniform: Uniform distribution with a and b parameters.

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

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

bijector module: Bijector Ops. See the Random variable transformations (contrib) guide.

kl(...): Get the KL-divergence KL(dist_a || dist_b).

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

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

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

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

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