def bernoulli(self,
name,
logits,
n_samples=None,
group_ndims=0,
dtype=tf.int32,
**kwargs):
"""
Add a stochastic node in this :class:`BayesianNet` that follows the
Bernoulli distribution.
:param name: The name of the stochastic node. Must be unique in a
:class:`BayesianNet`.
See
:class:`~zhusuan.distributions.univariate.Bernoulli` for more
information about the other arguments.
:return: A :class:`StochasticTensor` instance.
"""
dist = distributions.Bernoulli(logits,
group_ndims=group_ndims,
dtype=dtype,
**kwargs)
return self.stochastic(name, dist, n_samples=n_samples, **kwargs)
def __init__(self,
name,
logits,
n_samples=None,
group_ndims=0,
dtype=None,
**kwargs):
bernoulli = distributions.Bernoulli(logits,
group_ndims=group_ndims,
dtype=dtype,
**kwargs)
super(Bernoulli, self).__init__(name, bernoulli, n_samples)
def __init__(self, logits, dtype=tf.int32):
"""
Construct the :class:`Bernoulli`.
Args:
logits: A `float` tensor, log-odds of probabilities of being 1.
:math:`\\mathrm{logits} = \\log \\frac{p}{1 - p}`
dtype: The value type of samples from the distribution.
(default ``tf.int32``)
"""
super(Bernoulli, self).__init__(
zd.Bernoulli(logits=logits, dtype=dtype))