LostTech.TensorFlow : API Documentation

Type Inline

Namespace tensorflow.contrib.distributions.bijectors

Parent Bijector

Interfaces IInline

Bijector constructed from custom callables.

Example Use: The above example is equivalent to the `Bijector` `Exp()`.
Show Example 
exp = Inline(
              forward_fn=tf.exp,
              inverse_fn=tf.math.log,
              inverse_log_det_jacobian_fn=(
                lambda y: -tf.reduce_sum(tf.math.log(y), axis=-1)),
              name="exp")

Methods

Properties

Public static methods

Inline NewDyn(object forward_fn, object inverse_fn, object inverse_log_det_jacobian_fn, object forward_log_det_jacobian_fn, object forward_event_shape_fn, object forward_event_shape_tensor_fn, object inverse_event_shape_fn, object inverse_event_shape_tensor_fn, ImplicitContainer<T> is_constant_jacobian, ImplicitContainer<T> validate_args, object forward_min_event_ndims, object inverse_min_event_ndims, ImplicitContainer<T> name)

Creates a `Bijector` from callables. (deprecated)

Warning: THIS FUNCTION IS DEPRECATED. It will be removed after 2018-10-01. Instructions for updating: The TensorFlow Distributions library has moved to TensorFlow Probability (https://github.com/tensorflow/probability). You should update all references to use `tfp.distributions` instead of tf.contrib.distributions.
Parameters
object forward_fn
Python callable implementing the forward transformation.
object inverse_fn
Python callable implementing the inverse transformation.
object inverse_log_det_jacobian_fn
Python callable implementing the log o det o jacobian of the inverse transformation.
object forward_log_det_jacobian_fn
Python callable implementing the log o det o jacobian of the forward transformation.
object forward_event_shape_fn
Python callable implementing non-identical static event shape changes. Default: shape is assumed unchanged.
object forward_event_shape_tensor_fn
Python callable implementing non-identical event shape changes. Default: shape is assumed unchanged.
object inverse_event_shape_fn
Python callable implementing non-identical static event shape changes. Default: shape is assumed unchanged.
object inverse_event_shape_tensor_fn
Python callable implementing non-identical event shape changes. Default: shape is assumed unchanged.
ImplicitContainer<T> is_constant_jacobian
Python `bool` indicating that the Jacobian is constant for all input arguments.
ImplicitContainer<T> validate_args
Python `bool` indicating whether arguments should be checked for correctness.
object forward_min_event_ndims
Python `int` indicating the minimal dimensionality this bijector acts on.
object inverse_min_event_ndims
Python `int` indicating the minimal dimensionality this bijector acts on.
ImplicitContainer<T> name
Python `str`, name given to ops managed by this object.

Public properties

object dtype get;

object dtype_dyn get;

object forward_min_event_ndims get;

object forward_min_event_ndims_dyn get;

IList<object> graph_parents get;

object graph_parents_dyn get;

object inverse_min_event_ndims get;

object inverse_min_event_ndims_dyn get;

bool is_constant_jacobian get;

object is_constant_jacobian_dyn get;

object name get;

object name_dyn get;

object PythonObject get;

bool validate_args get;

object validate_args_dyn get;