Tensorflow Tutorial 1, Linear regssion

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

# linera regression model

#定义变量
x_data = np.random.rand(100)
y_data = x_data * 0.1 + 0.2
b = tf.Variable(0.)
k = tf.Variable(0.)

y = k*x_data + b

# 二次代价函数
loss = tf.reduce_mean(tf.square(y_data - y))

#定义一个梯度下降算法来进行优化
optimizer = tf.train.GradientDescentOptimizer(0.2)

#最小化代价函数
train = optimizer.minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for step in range(100):
        sess.run(train)
        if step % 20 == 0:
            print(step, sess.run([k, b, loss]))
    predict = sess.run(y)
    plt.figure()
    plt.scatter(x_data, y_data)
    plt.plot(x_data, predict, "r")
    plt.show()