def uniform(self,
name,
minval=0.,
maxval=1.,
n_samples=None,
group_ndims=0,
is_reparameterized=True,
check_numerics=False,
**kwargs):
"""
Add a stochastic node in this :class:`BayesianNet` that follows the
Uniform distribution.
:param name: The name of the stochastic node. Must be unique in a
:class:`BayesianNet`.
See
:class:`~zhusuan.distributions.univariate.Uniform` for more
information about the other arguments.
:return: A :class:`StochasticTensor` instance.
"""
dist = distributions.Uniform(minval,
maxval,
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,
minval=0.,
maxval=1.,
is_reparameterized=True,
check_numerics=False):
"""
Construct the :class:`Uniform`.
Args:
minval: A `float` Tensor. The lower bound on the range of the
uniform distribution. Should be broadcastable to match `maxval`.
maxval: A `float` Tensor. The upper bound on the range of the
uniform distribution. Should be element-wise bigger than
`minval`.
is_reparameterized (bool): Whether or not the gradients can
be propagated through parameters? (default :obj:`True`)
check_numerics (bool): Whether or not to check numeric issues.
"""
super(Uniform, self).__init__(
zd.Uniform(
minval=minval,
maxval=maxval,
is_reparameterized=is_reparameterized,
check_numerics=check_numerics,
))
def __init__(self,
name,
minval=0.,
maxval=1.,
n_samples=None,
group_event_ndims=0,
is_reparameterized=True,
check_numerics=False):
uniform = distributions.Uniform(minval,
maxval,
group_event_ndims=group_event_ndims,
is_reparameterized=is_reparameterized,
check_numerics=check_numerics)
super(Uniform, self).__init__(name, uniform, n_samples)
def __init__(self, minval=0., maxval=1., check_numerics=False):
"""
Construct the :class:`Uniform`.
Args:
minval: A `float` Tensor. The lower bound on the range of the
uniform distribution. Should be broadcastable to match `maxval`.
maxval: A `float` Tensor. The upper bound on the range of the
uniform distribution. Should be element-wise bigger than
`minval`.
check_numerics (bool): Whether or not to check numeric issues.
"""
super(Uniform, self).__init__(
zd.Uniform(
minval=minval, maxval=maxval, check_numerics=check_numerics))
