tutorial/source/search_inference.py [40:83]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class HashingMarginal(dist.Distribution):
    """
    :param trace_dist: a TracePosterior instance representing a Monte Carlo posterior

    Marginal histogram distribution.
    Turns a TracePosterior object into a Distribution
    over the return values of the TracePosterior's model.
    """
    def __init__(self, trace_dist, sites=None):
        assert isinstance(trace_dist, TracePosterior), \
            "trace_dist must be trace posterior distribution object"

        if sites is None:
            sites = "_RETURN"

        assert isinstance(sites, (str, list)), \
            "sites must be either '_RETURN' or list"

        self.sites = sites
        super().__init__()
        self.trace_dist = trace_dist

    has_enumerate_support = True

    @memoize(maxsize=10)
    def _dist_and_values(self):
        # XXX currently this whole object is very inefficient
        values_map, logits = collections.OrderedDict(), collections.OrderedDict()
        for tr, logit in zip(self.trace_dist.exec_traces,
                             self.trace_dist.log_weights):
            if isinstance(self.sites, str):
                value = tr.nodes[self.sites]["value"]
            else:
                value = {site: tr.nodes[site]["value"] for site in self.sites}
            if not torch.is_tensor(logit):
                logit = torch.tensor(logit)

            if torch.is_tensor(value):
                value_hash = hash(value.cpu().contiguous().numpy().tobytes())
            elif isinstance(value, dict):
                value_hash = hash(self._dict_to_tuple(value))
            else:
                value_hash = hash(value)
            if value_hash in logits:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



examples/rsa/search_inference.py [28:71]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class HashingMarginal(dist.Distribution):
    """
    :param trace_dist: a TracePosterior instance representing a Monte Carlo posterior

    Marginal histogram distribution.
    Turns a TracePosterior object into a Distribution
    over the return values of the TracePosterior's model.
    """
    def __init__(self, trace_dist, sites=None):
        assert isinstance(trace_dist, TracePosterior), \
            "trace_dist must be trace posterior distribution object"

        if sites is None:
            sites = "_RETURN"

        assert isinstance(sites, (str, list)), \
            "sites must be either '_RETURN' or list"

        self.sites = sites
        super().__init__()
        self.trace_dist = trace_dist

    has_enumerate_support = True

    @memoize(maxsize=10)
    def _dist_and_values(self):
        # XXX currently this whole object is very inefficient
        values_map, logits = collections.OrderedDict(), collections.OrderedDict()
        for tr, logit in zip(self.trace_dist.exec_traces,
                             self.trace_dist.log_weights):
            if isinstance(self.sites, str):
                value = tr.nodes[self.sites]["value"]
            else:
                value = {site: tr.nodes[site]["value"] for site in self.sites}
            if not torch.is_tensor(logit):
                logit = torch.tensor(logit)

            if torch.is_tensor(value):
                value_hash = hash(value.cpu().contiguous().numpy().tobytes())
            elif isinstance(value, dict):
                value_hash = hash(self._dict_to_tuple(value))
            else:
                value_hash = hash(value)
            if value_hash in logits:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -