tensorflow实现线性方程的参数调整

import tensorflow as tf
import numpy as np
#create data
x_data=np.random.rand(100).astype(np.float32)
y_data=x_data*0.1+0.3 #目标结果

#create tensorflow structure start
Weights=tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases=tf.Variable(tf.zeros([1])) # 权重和偏值从初始值开始不断学习，靠近目标值
y=Weights*x_data+biases
loss=tf.reduce_mean(tf.square(y-y_data))# 均方差
optimizer=tf.train.GradientDescentOptimizer(0.5)
train=optimizer.minimize(loss)

init=tf.initialize_all_variables()
# create tensorflow structure end

sess=tf.Session()
sess.run(init) #指向处理的地方

for step in range(201):
    sess.run(train)
    if step%20==0:
        print(step,sess.run(Weights),sess.run(biases))

实验结果：

如上所示最终实验结果表明Weight接近目标值0.1，biases接近目标值0.3