Normal¶
正态分布
数学公式:
\[ \begin{align}\begin{aligned}pdf(x; \mu, \sigma) = \frac{1}{Z}e^{\frac {-0.5 (x - \mu)^2} {\sigma^2} }\\Z = (2 \pi \sigma^2)^{0.5}\end{aligned}\end{align} \]
上面的数学公式中:
\(loc = \mu\):平均值。 \(scale = \sigma\):标准差。 \(Z\):正态分布常量。
参数¶
loc (float|list|numpy.ndarray|Variable) - 正态分布平均值。数据类型为float32。
scale (float|list|numpy.ndarray|Variable) - 正态分布标准差。数据类型为float32。
代码示例¶
import numpy as np
from paddle.fluid import layers
from paddle.fluid.layers import Normal
# Define a single scalar Normal distribution.
dist = Normal(loc=0., scale=3.)
# Define a batch of two scalar valued Normals.
# The first has mean 1 and standard deviation 11, the second 2 and 22.
dist = Normal(loc=[1., 2.], scale=[11., 22.])
# Get 3 samples, returning a 3 x 2 tensor.
dist.sample([3])
# Define a batch of two scalar valued Normals.
# Both have mean 1, but different standard deviations.
dist = Normal(loc=1., scale=[11., 22.])
# Complete example
value_npdata = np.array([0.8], dtype="float32")
value_tensor = layers.create_tensor(dtype="float32")
layers.assign(value_npdata, value_tensor)
normal_a = Normal([0.], [1.])
normal_b = Normal([0.5], [2.])
sample = normal_a.sample([2])
# a random tensor created by normal distribution with shape: [2, 1]
entropy = normal_a.entropy()
# [1.4189385] with shape: [1]
lp = normal_a.log_prob(value_tensor)
# [-1.2389386] with shape: [1]
kl = normal_a.kl_divergence(normal_b)
# [0.34939718] with shape: [1]
参数¶
shape (list) - 1维列表,指定生成样本的维度。数据类型为int32。
seed (int) - 长整型数。
返回¶
预先设计好维度的张量,数据类型为float32
返回¶
正态分布的信息熵,数据类型为float32
参数¶
value (Variable) - 输入张量。数据类型为float32或float64。
返回¶
对数概率,数据类型与value相同
参数¶
other (Normal) - Normal的实例。
返回¶
两个正态分布之间的KL散度,数据类型为float32
返回类型¶
Variable