tf.contrib.distributions.bijectors.ConditionalBijector

Class ConditionalBijector

Inherits From: Bijector

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

Conditional Bijector is a Bijector that allows intrinsic conditioning.

Properties

dtype

dtype of Tensors transformable by this distribution.

event_ndims

Returns then number of event dimensions this bijector operates on.

graph_parents

Returns this Bijector's graph_parents as a Python list.

is_constant_jacobian

Returns true iff the Jacobian is not a function of x.

Note: Jacobian is either constant for both forward and inverse or neither.

Returns:

• is_constant_jacobian: Python bool.

name

Returns the string name of this Bijector.

validate_args

Returns True if Tensor arguments will be validated.

Methods

__init__

__init__(
    event_ndims=None,
    graph_parents=None,
    is_constant_jacobian=False,
    validate_args=False,
    dtype=None,
    name=None
)

Constructs Bijector.

A Bijector transforms random variables into new random variables.

Examples:

# Create the Y = g(X) = X transform which operates on vector events.
identity = Identity(event_ndims=1)

# Create the Y = g(X) = exp(X) transform which operates on matrices.
exp = Exp(event_ndims=2)

See Bijector subclass docstring for more details and specific examples.

Args:

• event_ndims: number of dimensions associated with event coordinates.
• graph_parents: Python list of graph prerequisites of this Bijector.
• is_constant_jacobian: Python bool indicating that the Jacobian is not a function of the input.
• validate_args: Python bool, default False. Whether to validate input with asserts. If validate_args is False, and the inputs are invalid, correct behavior is not guaranteed.
• dtype: tf.dtype supported by this Bijector. None means dtype is not enforced.
• name: The name to give Ops created by the initializer.

Raises:

• ValueError: If a member of graph_parents is not a Tensor.

forward

forward(
    *args,
    **kwargs
)

kwargs:

• **condition_kwargs: Named arguments forwarded to subclass implementation.

forward_event_shape

forward_event_shape(input_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as forward_event_shape_tensor. May be only partially defined.

Args:

• input_shape: TensorShape indicating event-portion shape passed into forward function.

Returns:

• forward_event_shape_tensor: TensorShape indicating event-portion shape after applying forward. Possibly unknown.

forward_event_shape_tensor

forward_event_shape_tensor(
    input_shape,
    name='forward_event_shape_tensor'
)

Shape of a single sample from a single batch as an int32 1D Tensor.

Args:

• input_shape: Tensor, int32 vector indicating event-portion shape passed into forward function.
• name: name to give to the op

Returns:

• forward_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying forward.

forward_log_det_jacobian

forward_log_det_jacobian(
    *args,
    **kwargs
)

kwargs:

• **condition_kwargs: Named arguments forwarded to subclass implementation.

inverse

inverse(
    *args,
    **kwargs
)

kwargs:

• **condition_kwargs: Named arguments forwarded to subclass implementation.

inverse_event_shape

inverse_event_shape(output_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as inverse_event_shape_tensor. May be only partially defined.

Args:

• output_shape: TensorShape indicating event-portion shape passed into inverse function.

Returns:

• inverse_event_shape_tensor: TensorShape indicating event-portion shape after applying inverse. Possibly unknown.

inverse_event_shape_tensor

inverse_event_shape_tensor(
    output_shape,
    name='inverse_event_shape_tensor'
)

Shape of a single sample from a single batch as an int32 1D Tensor.

Args:

• output_shape: Tensor, int32 vector indicating event-portion shape passed into inverse function.
• name: name to give to the op

Returns:

• inverse_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying inverse.

inverse_log_det_jacobian

inverse_log_det_jacobian(
    *args,
    **kwargs
)

kwargs:

• **condition_kwargs: Named arguments forwarded to subclass implementation.