首页 > 其他 > 详细

TensorFlow1.0 线性回归

时间:2020-03-15 00:29:59      阅读:75      评论:0      收藏:0      [点我收藏+]
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

Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases = tf.Variable(tf.zeros([1]))

y = Weights*x_data+biases
loss = tf.reduce_mean(tf.square(y-y_data))

optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
init = tf.initialize_all_variables()

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

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


0 [0.7417692] [-0.07732911]
20 [0.30772722] [0.18689097]
40 [0.16603212] [0.26404503]
60 [0.12099022] [0.28857067]
80 [0.10667235] [0.29636687]
100 [0.10212099] [0.2988451]
120 [0.10067423] [0.29963288]
140 [0.10021434] [0.2998833]
160 [0.10006816] [0.2999629]
180 [0.10002167] [0.2999882]
200 [0.10000689] [0.29999626]

  

TensorFlow1.0 线性回归

原文:https://www.cnblogs.com/LiuXinyu12378/p/12495344.html

(0)
(0)
   
举报
评论 一句话评论(0
关于我们 - 联系我们 - 留言反馈 - 联系我们:wmxa8@hotmail.com
© 2014 bubuko.com 版权所有
打开技术之扣,分享程序人生!