def __init__(self, value, name, log_determinant=None, learnable=False, has_bias=False, is_observed=False, variable_range=geometric_ranges.UnboundedRange(),
is_policy=False, is_reward=False):
self._type = "Deterministic node"
if not isinstance(log_determinant, PartialLink):
if log_determinant is None:
log_determinant = torch.tensor(np.zeros((1, 1))).float().to(device)
var2link(log_determinant)
ranges = {"value": variable_range,
"log_determinant": geometric_ranges.UnboundedRange()}
super().__init__(name, value=value, log_determinant=log_determinant, learnable=learnable, has_bias=has_bias,
ranges=ranges, is_observed=is_observed, is_policy=is_policy, is_reward=is_reward)
self.distribution = distributions.DeterministicDistribution()
def __init__(self,
value,
name,
learnable=False,
is_observed=False,
variable_range=geometric_ranges.UnboundedRange()):
self._type = "Deterministic node"
ranges = {"value": variable_range}
super().__init__(name,
value=value,
learnable=learnable,
ranges=ranges,
is_observed=is_observed)
self.distribution = distributions.DeterministicDistribution()
def __init__(self, data, name, learnable=False, is_observed=False):
self.name = name
self.distribution = distributions.DeterministicDistribution()
self._evaluated = False
self._observed = is_observed
self.parents = set()
self.ancestors = set()
self._type = "Deterministic"
self.learnable = learnable
self.link = None
self._value = coerce_to_dtype(data, is_observed)
if self.learnable:
if not is_discrete(data):
self._value = torch.nn.Parameter(coerce_to_dtype(data, is_observed), requires_grad=True)
self.link = ParameterModule(self._value) # add to optimizer; opt checks links
else:
self.learnable = False
warnings.warn('Currently discrete parameters are not learnable. Learnable set to False')