Python tf.compat.v1.distributions.Normal用法及代码示例

具有位置 loc 和 scale 参数的正态分布。

继承自：Distribution

用法

tf.compat.v1.distributions.Normal(
    loc, scale, validate_args=False, allow_nan_stats=True, name='Normal'
)

数学细节

概率密度函数 (pdf) 是，

pdf(x; mu, sigma) = exp(-0.5 (x - mu)**2 / sigma**2) / Z
Z = (2 pi sigma**2)**0.5

其中loc = mu 是平均值，scale = sigma 是标准差。偏差，并且，Z 是归一化常数。

正态分布是 location-scale 系列的成员，即，它可以构造为，

X ~ Normal(loc=0, scale=1)
Y = loc + scale * X

例子

一个或一批分布的初始化示例。

import tensorflow_probability as tfp
tfd = tfp.distributions

# Define a single scalar Normal distribution.
dist = tfd.Normal(loc=0., scale=3.)

# Evaluate the cdf at 1, returning a scalar.
dist.cdf(1.)

# Define a batch of two scalar valued Normals.
# The first has mean 1 and standard deviation 11, the second 2 and 22.
dist = tfd.Normal(loc=[1, 2.], scale=[11, 22.])

# Evaluate the pdf of the first distribution on 0, and the second on 1.5,
# returning a length two tensor.
dist.prob([0, 1.5])

# Get 3 samples, returning a 3 x 2 tensor.
dist.sample([3])

尽可能广播参数。

# Define a batch of two scalar valued Normals.
# Both have mean 1, but different standard deviations.
dist = tfd.Normal(loc=1., scale=[11, 22.])

# Evaluate the pdf of both distributions on the same point, 3.0,
# returning a length 2 tensor.
dist.prob(3.0)