TensorFlow学习（二）简单线性模型+梯度下降法优化

import tensorflow as tf
import numpy as ny

#使用numpy生成100个点
x_data=ny.random.rand(100)
y_data=0.1*x_data+0.2

#构造一个线性模型
k=tf.Variable(1.1)
b=tf.Variable(0.5)
y=k*x_data+b

#二次代价函数
loss=tf.reduce_mean(tf.square(y_data-y))
#定义一个梯度下降法来进行训练的优化器
optimizer=tf.train.GradientDescentOptimizer(0.2)
#最小化代价函数
train=optimizer.minimize(loss)

init=tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for step in range(201):
        sess.run(train)
        if step%20==0:
            print(step,sess.run([k,b]))

0 [0.8906657, 0.1687153]
20 [0.4583189, -0.0026669456]
40 [0.309642, 0.08142534]
60 [0.2226555, 0.13062538]
80 [0.17176223, 0.1594109]
100 [0.14198598, 0.1762525]
120 [0.12456478, 0.18610603]
140 [0.11437215, 0.19187103]
160 [0.10840872, 0.19524398]
180 [0.10491971, 0.19721739]
200 [0.10287838, 0.19837198]