MultipleIndependent

MultipleIndependent#

class MultipleIndependent(dists, validate_args=None, arg_constraints=None, device=None)[source]#

Bases: Distribution

Wrap a sequence of PyTorch distributions into a joint PyTorch distribution.

Parameters:

dists (list[Distribution])
validate_args (bool | None)
arg_constraints (Dict[str, Constraint] | None)
device (str | None)

property arg_constraints: Dict[str, Constraint]#: Return argument constraints.

sample(sample_shape=())[source]#

Generates a sample_shape shaped sample or sample_shape shaped batch of samples if the distribution parameters are batched.

Return type:: Tensor

log_prob(value)[source]#

Returns the log of the probability density/mass function evaluated at value.

Parameters:: value (Tensor)
Return type:: Tensor

property mean: Tensor#: Returns the mean of the distribution.

property variance: Tensor#: Returns the variance of the distribution.

property support#: Returns a Constraint object representing this distribution’s support.

to(device)[source]#

Move the distribution to the specified device.

If the distribution has the to method, it is used. Otherwise, the parameters of the distribution are moved to the specified device.

Parameters:: device (str | device) – device to move the distribution to.
Return type:: None

property batch_shape: Size#: Returns the shape over which parameters are batched.

cdf(value)#

Returns the cumulative density/mass function evaluated at value.

Parameters:: value (Tensor)
Return type:: Tensor

entropy()#

Returns entropy of distribution, batched over batch_shape.

Returns:: Tensor of shape batch_shape.
Return type:: Tensor

enumerate_support(expand=True)#

Returns tensor containing all values supported by a discrete distribution. The result will enumerate over dimension 0, so the shape of the result will be (cardinality,) + batch_shape + event_shape (where event_shape = () for univariate distributions).

Note that this enumerates over all batched tensors in lock-step [[0, 0], [1, 1], …]. With expand=False, enumeration happens along dim 0, but with the remaining batch dimensions being singleton dimensions, [[0], [1], ...

To iterate over the full Cartesian product use itertools.product(m.enumerate_support()).

Parameters:: expand (bool) – whether to expand the support over the batch dims to match the distribution’s batch_shape.
Returns:: Tensor iterating over dimension 0.
Return type:: Tensor

property event_shape: Size#: Returns the shape of a single sample (without batching).

expand(batch_shape, _instance=None)#

Returns a new distribution instance (or populates an existing instance provided by a derived class) with batch dimensions expanded to batch_shape. This method calls expand on the distribution’s parameters. As such, this does not allocate new memory for the expanded distribution instance. Additionally, this does not repeat any args checking or parameter broadcasting in __init__.py, when an instance is first created.

Parameters:

batch_shape (torch.Size) – the desired expanded size.
_instance – new instance provided by subclasses that need to override .expand.

Returns:

New distribution instance with batch dimensions expanded to batch_size.

has_enumerate_support = False#

has_rsample = False#

icdf(value)#

Returns the inverse cumulative density/mass function evaluated at value.

Parameters:: value (Tensor)
Return type:: Tensor

property mode: Tensor#: Returns the mode of the distribution.

perplexity()#

Returns perplexity of distribution, batched over batch_shape.

Returns:: Tensor of shape batch_shape.
Return type:: Tensor

rsample(sample_shape=())#

Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched.

Parameters:: sample_shape (Size | list[int] | tuple[int, ...])
Return type:: Tensor

sample_n(n)#

Generates n samples or n batches of samples if the distribution parameters are batched.

Parameters:: n (int)
Return type:: Tensor

static set_default_validate_args(value)#

Sets whether validation is enabled or disabled.

The default behavior mimics Python’s assert statement: validation is on by default, but is disabled if Python is run in optimized mode (via python -O). Validation may be expensive, so you may want to disable it once a model is working.

Parameters:: value (bool) – Whether to enable validation.
Return type:: None

property stddev: Tensor#: Returns the standard deviation of the distribution.

MultipleIndependent

Navigation

MultipleIndependent#