TensorFlow的初次使⽤+Python画3D图和计算KL散度ython计算KL散度
import numpy as np
import scipy.stats
x = [np.random.randint(1,11) for i in range(10)]
print(x)
print(np.sum(x))
px = x/np.sum(x)#归⼀化
print(px)
y = [np.random.randint(1, 11) for i in range(10)]
print(y)
print(np.sum(y))
py = y / np.sum(y)#归⼀化
print(py)
## scipy计算函数可以处理⾮归⼀化情况，因此这⾥使⽤# py(x, y)或py(px, py)均可
KL = py(x, y)
print(KL)
#⾃⼰编程实现
kl= 0.0
for i in range(10):
kl += px[i] * np.log(px[i]/py[i])
print(kl)
#TensorFlow的神经⽹络
import sys;
sys.path.append("/home/hxj/anaconda3/lib/python3.6/site-packages")
import tensorflow as tf
import numpy as np
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1+0.3
print(x_data)
print(y_data)
Weights = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
biases = tf.s([1]))
y = Weights*x_data + biases
print(y)
loss = tf.reduce_mean(tf.square(y-y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
upperstrain = optimizer.minimize(loss)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for step in range(201):
sess.run(train)
if step % 20 == 0:
print(step, sess.run(Weights), sess.run(biases))
#Python画2D图
from functools import partial
import numpy
from matplotlib import pyplot
# Define a PDF
x_samples = numpy.arange(-3, 3.01, 0.01)
PDF = pty(x_samples.shape)
PDF[x_samples < 0] = und(x_samples[x_samples < 0] + 3.5) / 3
PDF[x_samples >= 0] = 0.5 * s(numpy.pi * x_samples[x_samples >= 0]) + 0.5
PDF /= numpy.sum(PDF)
# Calculate approximated CDF
CDF = pty(PDF.shape)
cumulated = 0
for i in range(CDF.shape[0]):
cumulated += PDF[i]
CDF[i] = cumulated
# Generate samples
generate = partial(numpy.interp, xp=CDF, fp=x_samples)
u_rv = numpy.random.random(10000)
x = generate(u_rv)
# Visualization
fig, (ax0, ax1) = pyplot.subplots(ncols=2, figsize=(9, 4))
ax0.plot(x_samples, PDF)
ax0.axis([-3.5, 3.5, 0, numpy.max(PDF)*1.1])
ax1.hist(x, 100)
pyplot.show()
#Python画3D图
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
np.random.seed(42)
# 采样个数500
n_samples = 500
dim = 3
# 先⽣成⼀组3维正态分布数据，数据⽅向完全随机
samples = np.random.multivariate_normal(
<(dim),
n_samples
)
# 通过把每个样本到原点距离和均匀分布吻合得到球体内均匀分布的样本for i in range(samples.shape[0]):
r = np.power(np.random.random(), 1.0/3.0)
samples[i] *= r / (samples[i])
upper_samples = []
lower_samples = []
for x, y, z in samples:
# 3x+2y-z=1作为判别平⾯
if z > 3*x + 2*y - 1:
upper_samples.append((x, y, z))
else:
lower_samples.append((x, y, z))
fig = plt.figure('3D scatter plot')
ax = fig.add_subplot(111, projection='3d')
uppers = np.array(upper_samples)
lowers = np.array(lower_samples)
# ⽤不同颜⾊不同形状的图标表⽰平⾯上下的样本
# 判别平⾯上半部分为红⾊圆点，下半部分为绿⾊三⾓
ax.scatter(uppers[:, 0], uppers[:, 1], uppers[:, 2], c='r', marker='o') ax.scatter(lowers[:, 0], lowers[:, 1], lowers[:, 2], c='g', marker='^') plt.show()

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。