mindspore.nn.probability.distribution.Geometric

class mindspore.nn.probability.distribution.Geometric(probs=None, seed=None, dtype=mstype.int32, name='Geometric')[源代码]

几何分布(Geometric Distribution)。

它代表在第一次成功之前有k次失败,即在第一次成功实现时,总共有k+1个伯努利试验。 离散随机分布,取值范围为正自然数集,概率质量函数为 \(P(X = i) = p(1-p)^{i-1}, i = 1, 2, ...\)

参数:
  • probs (float, list, numpy.ndarray, Tensor) - 成功的概率。默认值: None

  • seed (int) - 采样时使用的种子。如果为None,则使用全局种子。默认值: None

  • dtype (mindspore.dtype) - 事件样例的类型。默认值: mstype.int32

  • name (str) - 分布的名称。默认值: 'Geometric'

说明

probs 必须是合适的概率(0<p<1)。dist_spec_argsprobs

异常:
  • ValueError - probs 中元素小于0或者大于1。

支持平台:

Ascend GPU

样例:

>>> import mindspore
>>> import mindspore.nn as nn
>>> import mindspore.nn.probability.distribution as msd
>>> from mindspore import Tensor
>>> # To initialize a Geometric distribution of the probability 0.5.
>>> g1 = msd.Geometric(0.5, dtype=mindspore.int32)
>>> # A Geometric distribution can be initialized without arguments.
>>> # In this case, `probs` must be passed in through arguments during function calls.
>>> g2 = msd.Geometric(dtype=mindspore.int32)
>>>
>>> # Here are some tensors used below for testing
>>> value = Tensor([1, 0, 1], dtype=mindspore.int32)
>>> probs_a = Tensor([0.6], dtype=mindspore.float32)
>>> probs_b = Tensor([0.2, 0.5, 0.4], 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.
>>> #     probs1 (Tensor): the probability of success of a Bernoulli trial. Default: self.probs.
>>> # Examples of `prob`.
>>> # Similar calls can be made to other probability functions
>>> # by replacing `prob` by the name of the function.
>>> ans = g1.prob(value)
>>> print(ans.shape)
(3,)
>>> # Evaluate with respect to distribution b.
>>> ans = g1.prob(value, probs_b)
>>> print(ans.shape)
(3,)
>>> # `probs` must be passed in during function calls.
>>> ans = g2.prob(value, probs_a)
>>> print(ans.shape)
(3,)
>>> # Functions `mean`, `sd`, `var`, and `entropy` have the same arguments.
>>> # Args:
>>> #     probs1 (Tensor): the probability of success of a Bernoulli trial. Default: self.probs.
>>> # Examples of `mean`. `sd`, `var`, and `entropy` are similar.
>>> ans = g1.mean() # return 1.0
>>> print(ans.shape)
()
>>> ans = g1.mean(probs_b)
>>> print(ans.shape)
(3,)
>>> # Probs must be passed in during function calls
>>> ans = g2.mean(probs_a)
>>> print(ans.shape)
(1,)
>>> # Interfaces of 'kl_loss' and 'cross_entropy' are the same.
>>> # Args:
>>> #     dist (str): the name of the distribution. Only 'Geometric' is supported.
>>> #     probs1_b (Tensor): the probability of success of a Bernoulli trial of distribution b.
>>> #     probs1_a (Tensor): the probability of success of a Bernoulli trial of distribution a.
>>> # Examples of `kl_loss`. `cross_entropy` is similar.
>>> ans = g1.kl_loss('Geometric', probs_b)
>>> print(ans.shape)
(3,)
>>> ans = g1.kl_loss('Geometric', probs_b, probs_a)
>>> print(ans.shape)
(3,)
>>> # An additional `probs` must be passed in.
>>> ans = g2.kl_loss('Geometric', probs_b, probs_a)
>>> print(ans.shape)
(3,)
>>> # Examples of `sample`.
>>> # Args:
>>> #     shape (tuple): the shape of the sample. Default: ()
>>> #     probs1 (Tensor): the probability of success of a Bernoulli trial. Default: self.probs.
>>> ans = g1.sample()
>>> print(ans.shape)
()
>>> ans = g1.sample((2,3))
>>> print(ans.shape)
(2, 3)
>>> ans = g1.sample((2,3), probs_b)
>>> print(ans.shape)
(2, 3, 3)
>>> ans = g2.sample((2,3), probs_a)
>>> print(ans.shape)
(2, 3, 1)
property probs

返回伯努利试验成功的概率。

返回:

Tensor,伯努利试验成功的概率值。

cdf(value, probs)

在给定值下计算累积分布函数(Cumulatuve Distribution Function, CDF)。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,累积分布函数的值。

cross_entropy(dist, probs_b, probs)

计算分布a和b之间的交叉熵。

参数:
  • dist (str) - 分布的类型。

  • probs_b (Tensor) - 对比分布的伯努利实验成功的概率。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,交叉熵的值。

entropy(probs)

计算熵。

参数:
  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,熵的值。

kl_loss(dist, probs_b, probs)

计算KL散度,即KL(a||b)。

参数:
  • dist (str) - 分布的类型。

  • probs_b (Tensor) - 对比分布的伯努利实验成功的概率。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,KL散度。

log_cdf(value, probs)

计算给定值对于的累积分布函数的对数。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,累积分布函数的对数。

log_prob(value, probs)

计算给定值对应的概率的对数。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,累积分布函数的对数。

log_survival(value, probs)

计算给定值对应的生存函数的对数。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,生存函数的对数。

mean(probs)

计算期望。

参数:
  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,概率分布的期望。

mode(probs)

计算众数。

参数:
  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,概率分布的众数。

prob(value, probs)

计算给定值下的概率。对于离散分布是计算概率质量函数(Probability Mass Function)。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,概率值。

sample(shape, probs)

采样函数。

参数:
  • shape (tuple) - 样本的shape。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,根据概率分布采样的样本。

sd(probs)

计算标准差。

参数:
  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,概率分布的标准差。

survival_function(value, probs)

计算给定值对应的生存函数。

参数:
  • value (Tensor) - 要计算的值。

  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,生存函数的值。

var(probs)

计算方差。

参数:
  • probs (Tensor) - 伯努利实验成功的概率。默认值: None

返回:

Tensor,概率分布的方差。