mindspore.nn.probability.distribution.Cauchy

class mindspore.nn.probability.distribution.Cauchy(loc=None, scale=None, seed=None, dtype=mstype.float32, name='Cauchy')[source]

Cauchy distribution.

Parameters
  • loc (int, float, list, numpy.ndarray, Tensor) – The location of the Cauchy distribution.

  • scale (int, float, list, numpy.ndarray, Tensor) – The scale of the Cauchy distribution.

  • seed (int) – The seed used in sampling. The global seed is used if it is None. Default: None.

  • dtype (mindspore.dtype) – The type of the event samples. Default: mstype.float32.

  • name (str) – The name of the distribution. Default: ‘Cauchy’.

Supported Platforms:

Ascend

Note

scale must be greater than zero. dist_spec_args are loc and scale. dtype must be a float type because Cauchy distributions are continuous. Cauchy distribution is not supported on GPU backend.

Examples

>>> import mindspore
>>> import mindspore.nn as nn
>>> import mindspore.nn.probability.distribution as msd
>>> from mindspore import Tensor
>>> # To initialize a Cauchy distribution of loc 3.0 and scale 4.0.
>>> cauchy1 = msd.Cauchy(3.0, 4.0, dtype=mindspore.float32)
>>> # A Cauchy distribution can be initialized without arguments.
>>> # In this case, 'loc' and `scale` must be passed in through arguments.
>>> cauchy2 = msd.Cauchy(dtype=mindspore.float32)
>>> # Here are some tensors used below for testing
>>> value = Tensor([1.0, 2.0, 3.0], dtype=mindspore.float32)
>>> loc_a = Tensor([2.0], dtype=mindspore.float32)
>>> scale_a = Tensor([2.0, 2.0, 2.0], dtype=mindspore.float32)
>>> loc_b = Tensor([1.0], dtype=mindspore.float32)
>>> scale_b = Tensor([1.0, 1.5, 2.0], dtype=mindspore.float32)
>>> # Private interfaces of probability functions corresponding to public interfaces, including
>>> # `prob`, `log_prob`, `cdf`, `log_cdf`, `survival_function`, and `log_survival`,
>>> # have the same arguments as follows.
>>> # Args:
>>> #     value (Tensor): the value to be evaluated.
>>> #     loc (Tensor): the location of the distribution. Default: self.loc.
>>> #     scale (Tensor): the scale of the distribution. Default: self.scale.
>>> # Examples of `prob`.
>>> # Similar calls can be made to other probability functions
>>> # by replacing 'prob' by the name of the function
>>> ans = cauchy1.prob(value)
>>> print(ans.shape)
(3,)
>>> # Evaluate with respect to distribution b.
>>> ans = cauchy1.prob(value, loc_b, scale_b)
>>> print(ans.shape)
(3,)
>>> # `loc` and `scale` must be passed in during function calls
>>> ans = cauchy2.prob(value, loc_a, scale_a)
>>> print(ans.shape)
(3,)
>>> # Functions `mode` and `entropy` have the same arguments.
>>> # Args:
>>> #     loc (Tensor): the location of the distribution. Default: self.loc.
>>> #     scale (Tensor): the scale of the distribution. Default: self.scale.
>>> # Example of `mode`.
>>> ans = cauchy1.mode() # return 3.0
>>> print(ans.shape)
()
>>> ans = cauchy1.mode(loc_b, scale_b) # return loc_b
>>> print(ans.shape)
(3,)
>>> # `loc` and `scale` must be passed in during function calls.
>>> ans = cauchy2.mode(loc_a, scale_a)
>>> print(ans.shape)
(3,)
>>> # Interfaces of 'kl_loss' and 'cross_entropy' are the same:
>>> # Args:
>>> #     dist (str): the type of the distributions. Only "Cauchy" is supported.
>>> #     loc_b (Tensor): the loc of distribution b.
>>> #     scale_b (Tensor): the scale distribution b.
>>> #     loc (Tensor): the loc of distribution a. Default: self.loc.
>>> #     scale (Tensor): the scale distribution a. Default: self.scale.
>>> # Examples of `kl_loss`. `cross_entropy` is similar.
>>> ans = cauchy1.kl_loss('Cauchy', loc_b, scale_b)
>>> print(ans.shape)
(3,)
>>> ans = cauchy1.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
>>> print(ans.shape)
(3,)
>>> # Additional `loc` and `scale` must be passed in.
>>> ans = cauchy2.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
>>> print(ans.shape)
(3,)
>>> # Examples of `sample`.
>>> # Args:
>>> #     shape (tuple): the shape of the sample. Default: ()
>>> #     loc (Tensor): the location of the distribution. Default: self.loc.
>>> #     scale (Tensor): the scale of the distribution. Default: self.scale.
>>> ans = cauchy1.sample()
>>> print(ans.shape)
()
>>> ans = cauchy1.sample((2,3))
>>> print(ans.shape)
(2, 3)
>>> ans = cauchy1.sample((2,3), loc_b, scale_b)
>>> print(ans.shape)
(2, 3, 3)
>>> ans = cauchy2.sample((2,3), loc_a, scale_a)
>>> print(ans.shape)
(2, 3, 3)
property loc

Return the location of the distribution after casting to dtype.

property scale

Return the scale of the distribution after casting to dtype.