mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 21:14:14 +08:00
b25ef91bf1
See https://github.com/pytorch/pytorch/pull/129751#issue-2380881501. Most changes are auto-generated by linter. You can review these PRs via: ```bash git diff --ignore-all-space --ignore-blank-lines HEAD~1 ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/129770 Approved by: https://github.com/wconstab
65 lines
1.9 KiB
Python
65 lines
1.9 KiB
Python
# mypy: allow-untyped-defs
|
|
from torch.distributions import constraints
|
|
from torch.distributions.normal import Normal
|
|
from torch.distributions.transformed_distribution import TransformedDistribution
|
|
from torch.distributions.transforms import ExpTransform
|
|
|
|
|
|
__all__ = ["LogNormal"]
|
|
|
|
|
|
class LogNormal(TransformedDistribution):
|
|
r"""
|
|
Creates a log-normal distribution parameterized by
|
|
:attr:`loc` and :attr:`scale` where::
|
|
|
|
X ~ Normal(loc, scale)
|
|
Y = exp(X) ~ LogNormal(loc, scale)
|
|
|
|
Example::
|
|
|
|
>>> # xdoctest: +IGNORE_WANT("non-deterministic")
|
|
>>> m = LogNormal(torch.tensor([0.0]), torch.tensor([1.0]))
|
|
>>> m.sample() # log-normal distributed with mean=0 and stddev=1
|
|
tensor([ 0.1046])
|
|
|
|
Args:
|
|
loc (float or Tensor): mean of log of distribution
|
|
scale (float or Tensor): standard deviation of log of the distribution
|
|
"""
|
|
arg_constraints = {"loc": constraints.real, "scale": constraints.positive}
|
|
support = constraints.positive
|
|
has_rsample = True
|
|
|
|
def __init__(self, loc, scale, validate_args=None):
|
|
base_dist = Normal(loc, scale, validate_args=validate_args)
|
|
super().__init__(base_dist, ExpTransform(), validate_args=validate_args)
|
|
|
|
def expand(self, batch_shape, _instance=None):
|
|
new = self._get_checked_instance(LogNormal, _instance)
|
|
return super().expand(batch_shape, _instance=new)
|
|
|
|
@property
|
|
def loc(self):
|
|
return self.base_dist.loc
|
|
|
|
@property
|
|
def scale(self):
|
|
return self.base_dist.scale
|
|
|
|
@property
|
|
def mean(self):
|
|
return (self.loc + self.scale.pow(2) / 2).exp()
|
|
|
|
@property
|
|
def mode(self):
|
|
return (self.loc - self.scale.square()).exp()
|
|
|
|
@property
|
|
def variance(self):
|
|
scale_sq = self.scale.pow(2)
|
|
return scale_sq.expm1() * (2 * self.loc + scale_sq).exp()
|
|
|
|
def entropy(self):
|
|
return self.base_dist.entropy() + self.loc
|