clipppy.stochastic.infinite¶
Module Contents¶
- class clipppy.stochastic.infinite.InfiniteUniform(batch_shape=torch.Size(), event_shape=torch.Size(), validate_args=None)¶
A uniform distribution over all real numbers.
Sampling and
log_probalways return zeros.- property arg_constraints(self)¶
Returns a dictionary from argument names to
Constraintobjects that should be satisfied by each argument of this distribution. Args that are not tensors need not appear in this dict.
- log_prob(self, value)¶
Returns the log of the probability density/mass function evaluated at
value.- Args:
value (Tensor):
- rsample(self, sample_shape=torch.Size())¶
Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched.
- support(self)¶
Returns a
Constraintobject representing this distribution’s support.
- class clipppy.stochastic.infinite.SemiInfiniteUniform(batch_shape=torch.Size(), event_shape=torch.Size(), validate_args=None)¶
A uniform distribution over all real numbers.
Sampling and
log_probalways return zeros.- log_prob(self, value)¶
Returns the log of the probability density/mass function evaluated at
value.- Args:
value (Tensor):
- support(self)¶
Returns a
Constraintobject representing this distribution’s support.