TensorFlow线性回归

目录

　　数据可视化

　　梯度下降

　　结果可视化

---

 

数据可视化

 

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

# 随机生成1000个点，围绕在y=0.1x+0.3的直线周围
num_points = 1000
vectors_set = []
for i in range(num_points):
    x1 = np.random.normal(0.0, 0.55)
    y1 = x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.03)
    vectors_set.append([x1, y1])

# 生成一些样本
x_data = [v[0] for v in vectors_set]
y_data = [v[1] for v in vectors_set]

plt.scatter(x_data,y_data,c='r')
plt.show()

 

 

 返回目录

 

梯度下降

 

# -*- coding: utf-8 -*-
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

# 随机生成1000个点，围绕在y=0.1x+0.3的直线周围
num_points = 1000
vectors_set = []
for i in range(num_points):
    x1 = np.random.normal(0.0, 0.55)
    y1 = x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.03)
    vectors_set.append([x1, y1])

# 生成一些样本
x_data = [v[0] for v in vectors_set]
y_data = [v[1] for v in vectors_set]

# 生成1维的W矩阵，取值是[-1,1]之间的随机数
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0), name='W')
# 生成1维的b矩阵，初始值是0
b = tf.Variable(tf.zeros([1]), name='b')
# 经过计算得出预估值y
y = W * x_data + b

# 以预估值y和实际值y_data之间的均方误差作为损失
loss = tf.reduce_mean(tf.square(y - y_data), name='loss')
# 采用梯度下降法来优化参数
optimizer = tf.train.GradientDescentOptimizer(0.5) #参数是学习率
# 训练的过程就是最小化这个误差值
train = optimizer.minimize(loss, name='train')

sess = tf.Session()

init = tf.global_variables_initializer()
sess.run(init)

# 初始化的W和b是多少
print ("W =", sess.run(W), "b =", sess.run(b), "loss =", sess.run(loss))
# 执行20次训练
for step in range(20):
    sess.run(train)
    # 输出训练好的W和b
    print ("W =", sess.run(W), "b =", sess.run(b), "loss =", sess.run(loss))
'''
W = [ 0.72134733] b = [ 0.] loss = 0.204532
W = [ 0.54246926] b = [ 0.31014919] loss = 0.0552976
W = [ 0.41924465] b = [ 0.30693138] loss = 0.029155
W = [ 0.33045709] b = [ 0.30471471] loss = 0.0155833
W = [ 0.26648441] b = [ 0.30311754] loss = 0.00853772
W = [ 0.22039121] b = [ 0.30196676] loss = 0.00488007
W = [ 0.18718043] b = [ 0.3011376] loss = 0.00298124
W = [ 0.16325161] b = [ 0.30054021] loss = 0.00199547
W = [ 0.14601055] b = [ 0.30010974] loss = 0.00148373
W = [ 0.13358814] b = [ 0.29979959] loss = 0.00121806
W = [ 0.12463761] b = [ 0.29957613] loss = 0.00108014
W = [ 0.11818863] b = [ 0.29941514] loss = 0.00100854
W = [ 0.11354206] b = [ 0.29929912] loss = 0.000971367
W = [ 0.11019413] b = [ 0.29921553] loss = 0.00095207
W = [ 0.10778191] b = [ 0.29915532] loss = 0.000942053
W = [ 0.10604387] b = [ 0.29911193] loss = 0.000936852
W = [ 0.10479159] b = [ 0.29908064] loss = 0.000934153
W = [ 0.1038893] b = [ 0.29905814] loss = 0.000932751
W = [ 0.10323919] b = [ 0.2990419] loss = 0.000932023
W = [ 0.10277078] b = [ 0.29903021] loss = 0.000931646
W = [ 0.10243329] b = [ 0.29902178] loss = 0.00093145    
'''

 

 

 返回目录

 

结果可视化

　　

 

# -*- coding: utf-8 -*-
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

# 随机生成1000个点，围绕在y=0.1x+0.3的直线周围
num_points = 1000
vectors_set = []
for i in range(num_points):
    x1 = np.random.normal(0.0, 0.55)
    y1 = x1 * 0.1 + 0.3 + np.random.normal(0.0, 0.03)
    vectors_set.append([x1, y1])

# 生成一些样本
x_data = [v[0] for v in vectors_set]
y_data = [v[1] for v in vectors_set]

# 生成1维的W矩阵，取值是[-1,1]之间的随机数
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0), name='W')
# 生成1维的b矩阵，初始值是0
b = tf.Variable(tf.zeros([1]), name='b')
# 经过计算得出预估值y
y = W * x_data + b

# 以预估值y和实际值y_data之间的均方误差作为损失
loss = tf.reduce_mean(tf.square(y - y_data), name='loss')
# 采用梯度下降法来优化参数
optimizer = tf.train.GradientDescentOptimizer(0.5) #参数是学习率
# 训练的过程就是最小化这个误差值
train = optimizer.minimize(loss, name='train')

sess = tf.Session()

init = tf.global_variables_initializer()
sess.run(init)

# 初始化的W和b是多少
print ("W =", sess.run(W), "b =", sess.run(b), "loss =", sess.run(loss))
# 执行20次训练
for step in range(20):
    sess.run(train)
    # 输出训练好的W和b
    print ("W =", sess.run(W), "b =", sess.run(b), "loss =", sess.run(loss))
    
plt.scatter(x_data,y_data,c='r')
plt.plot(x_data,sess.run(W)*x_data+sess.run(b))
plt.show()

 

 

 

 返回目录

转载于:https://www.cnblogs.com/itmorn/p/8158830.html