Module: contrib.distributions.bijectors

Module: tf.contrib.distributions.bijectors

Module tf.contrib.distributions.bijectors

Defined in tensorflow/contrib/distributions/python/ops/bijectors/__init__.py.

Bijector Ops.

Classes

class Affine: Compute Y = g(X; shift, scale) = scale @ X + shift.

class AffineLinearOperator: Compute Y = g(X; shift, scale) = scale @ X + shift.

class Bijector: Interface for invertible transformations of a Distribution sample.

class Chain: Bijector which applies a sequence of bijectors.

class CholeskyOuterProduct: Compute g(X) = X @ X.T; X is lower-triangular, positive-diagonal matrix.

class ConditionalBijector: Conditional Bijector is a Bijector that allows intrinsic conditioning.

class Exp: Compute Y = g(X) = exp(X).

class Identity: Compute Y = g(X) = X.

class Inline: Bijector constructed from custom callables.

class Invert: Bijector which inverts another Bijector.

class PowerTransform: Compute Y = g(X) = (1 + X * c)**(1 / c), X >= -1 / c.

class Sigmoid: Bijector which computes Y = g(X) = 1 / (1 + exp(-X)).

class SigmoidCentered: Bijector which computes Y = g(X) = exp([X 0]) / (1 + exp(-X)).

class SoftmaxCentered: Bijector which computes Y = g(X) = exp([X 0]) / sum(exp([X 0])).

class Softplus: Bijector which computes Y = g(X) = Log[1 + exp(X)].