torch.distributions.transformed_distribution.TransformedDistribution Class Reference

Inheritance diagram for torch.distributions.transformed_distribution.TransformedDistribution:

Public Member Functions
def	__init__ (self, base_distribution, transforms, validate_args=None)
def	expand (self, batch_shape, _instance=None)
def	support (self)
def	has_rsample (self)
def	sample (self, sample_shape=torch.Size())
def	rsample (self, sample_shape=torch.Size())
def	log_prob (self, value)
def	cdf (self, value)
def	icdf (self, value)
Public Member Functions inherited from torch.distributions.distribution.Distribution
def	__init__ (self, batch_shape=torch.Size(), event_shape=torch.Size(), validate_args=None)
def	expand (self, batch_shape, _instance=None)
def	batch_shape (self)
def	event_shape (self)
def	arg_constraints (self)
def	support (self)
def	mean (self)
def	variance (self)
def	stddev (self)
def	sample (self, sample_shape=torch.Size())
def	rsample (self, sample_shape=torch.Size())
def	sample_n (self, n)
def	log_prob (self, value)
def	cdf (self, value)
def	icdf (self, value)
def	enumerate_support (self, expand=True)
def	entropy (self)
def	perplexity (self)
def	__repr__ (self)

Public Attributes
	base_dist
	transforms

Static Public Attributes
	arg_constraints
Static Public Attributes inherited from torch.distributions.distribution.Distribution
	has_rsample
	has_enumerate_support
	support
	arg_constraints

Additional Inherited Members
Static Public Member Functions inherited from torch.distributions.distribution.Distribution
def	set_default_validate_args (value)

Detailed Description

Definition at line 8 of file transformed_distribution.py.

Member Function Documentation

def torch.distributions.transformed_distribution.TransformedDistribution.cdf	(		self,
			value
	)

Computes the cumulative distribution function by inverting the
transform(s) and computing the score of the base distribution.

Definition at line 132 of file transformed_distribution.py.

def torch.distributions.transformed_distribution.TransformedDistribution.icdf	(		self,
			value
	)

Computes the inverse cumulative distribution function using
transform(s) and computing the score of the base distribution.

Definition at line 145 of file transformed_distribution.py.

def torch.distributions.transformed_distribution.TransformedDistribution.log_prob	(		self,
			value
	)

Scores the sample by inverting the transform(s) and computing the score
using the score of the base distribution and the log abs det jacobian.

Definition at line 102 of file transformed_distribution.py.

def torch.distributions.transformed_distribution.TransformedDistribution.rsample	(		self,
			sample_shape = torch.Size()
	)

Generates a sample_shape shaped reparameterized sample or sample_shape
shaped batch of reparameterized samples if the distribution parameters
are batched. Samples first from base distribution and applies
`transform()` for every transform in the list.

Definition at line 90 of file transformed_distribution.py.

def torch.distributions.transformed_distribution.TransformedDistribution.sample	(		self,
			sample_shape = torch.Size()
	)

Generates a sample_shape shaped sample or sample_shape shaped batch of
samples if the distribution parameters are batched. Samples first from
base distribution and applies `transform()` for every transform in the
list.

Definition at line 77 of file transformed_distribution.py.

---

The documentation for this class was generated from the following file:

• torch/distributions/transformed_distribution.py