def fold_normal(self,
name,
mean=0.,
_sentinel=None,
std=None,
logstd=None,
n_samples=None,
group_ndims=0,
is_reparameterized=True,
check_numerics=False,
**kwargs):
"""
Add a stochastic node in this :class:`BayesianNet` that follows the
FoldNormal distribution.
:param name: The name of the stochastic node. Must be unique in a
:class:`BayesianNet`.
See
:class:`~zhusuan.distributions.univariate.FoldNormal` for more
information about the other arguments.
:return: A :class:`StochasticTensor` instance.
"""
dist = distributions.FoldNormal(mean,
_sentinel=_sentinel,
std=std,
logstd=logstd,
group_ndims=group_ndims,
is_reparameterized=is_reparameterized,
check_numerics=check_numerics,
**kwargs)
return self.stochastic(name, dist, n_samples=n_samples, **kwargs)
def __init__(self,
name,
mean=0.,
logstd=None,
std=None,
n_samples=None,
group_ndims=0,
is_reparameterized=True,
check_numerics=False,
**kwargs):
norm = distributions.FoldNormal(mean,
logstd=logstd,
std=std,
group_ndims=group_ndims,
is_reparameterized=is_reparameterized,
check_numerics=check_numerics,
**kwargs)
super(FoldNormal, self).__init__(name, norm, n_samples)