tf.contrib.distributions.TransformedDistribution.__init__()

tf.contrib.distributions.TransformedDistribution.__init__(base_dist_cls, transform, inverse, log_det_jacobian, name='TransformedDistribution', **base_dist_args)

Construct a Transformed Distribution.

Args:

• base_dist_cls: the base distribution class to transform. Must be a subclass of Distribution.
• transform: a callable that takes a Tensor sample from base_dist and returns a Tensor of the same shape and type. x => y.
• inverse: a callable that computes the inverse of transform. y => x. If None, users can only call log_pdf on values returned by sample.
• log_det_jacobian: a callable that takes a Tensor sample from base_dist and returns the log of the determinant of the Jacobian of transform.
• name: The name for the distribution.
• **base_dist_args: kwargs to pass on to dist_cls on construction.

Raises:

• TypeError: if base_dist_cls is not a subclass of Distribution.