tensorflow简单梯度下降

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

points_num = 100
vectors = []

for i in range(points_num):
    x1 = np.random.normal(0.0,0.66)
    y1 = 0.1 * x1 +0.2 + np.random.normal(0.0,0.04)
    vectors.append([x1,y1])
    
x_data = [v[0] for v in vectors]
y_data = [v[1] for v in vectors]

#展示100个随机数据点
plt.plot(x_data,y_data,'r*',label="Original data") 
plt.title("Linear Regression using Gradient Descent")
plt.legend()
plt.show()

#构建线性回归模型
W = tf.Variable(tf.random_uniform([1],-1.0,1.0))#初始化权重
b = tf.Variable(tf.zeros([1])) #初始化Bias
y = W * x_data + b   #模型计算出的y

#定义 loss function
#对tensor的所有维度计算(（y-y_data ^ 2）)之和/N
loss = tf.reduce_mean(tf.square(y-y_data))
#用梯度下降的优化器来优化loss function
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)

#创建会话
sess = tf.Session()
#初始化数据流图的所有变量
init = tf.global_variables_initializer()
sess.run(init)

#训练20步
for step in range(20):
    #优化每一步
    sess.run(train)
    #打印出每一步的损失，权重和偏差
    print(("Step=%d,Loss=%f,[Weight=%f Bias=%f]") \
    %(step,sess.run(loss),sess.run(W),sess.run(b)))
plt.plot(x_data,y_data,'r*',label="Original data") 
plt.title("Linear Regression using Gradient Descent")
plt.plot(x_data,sess.run(W) * x_data + sess.run(b),label="fittes lin")
plt.legend()
plt.xlabel('x')
plt.ylabel('y')
plt.show()

sess.close()