参考链接:
http://wiki.jikexueyuan.com/project/tensorflow-zh/get_started/introduction.html
代码:
# -*- coding: utf-8 -*-
"""
Created on Fri Dec 21 14:34:56 2018
@author: Administrator
"""
import tensorflow as tf
import numpy as np
# 使用 NumPy 生成假数据(phony data), 总共 100 个点.
x_data = np.float32(np.random.rand(2, 100)) # 随机输入
y_data = np.dot([0.100, 0.200], x_data) + 0.300
# 构造一个线性模型
#
b = tf.Variable(tf.zeros([1]))
W = tf.Variable(tf.random_uniform([1, 2], -1.0, 1.0))
y = tf.matmul(W, x_data) + b
# 最小化方差
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
# 初始化变量
init = tf.initialize_all_variables()
# 启动图 (graph)
sess = tf.Session()
sess.run(init)
# 拟合平面
for step in range(0, 201):
sess.run(train)
if step % 20 == 0:
print (step, sess.run(W), sess.run(b))
# 得到最佳拟合结果 W: [[0.100 0.200]], b: [0.300]
结果:
0 [[ 0.91210413 -0.04129256]] [ 0.04484042]
20 [[ 0.28546557 0.23647967]] [ 0.19098906]
40 [[ 0.15442868 0.23037918]] [ 0.25790811]
60 [[ 0.11846238 0.21355666]] [ 0.28405273]
80 [[ 0.10667393 0.20536564]] [ 0.29399648]
100 [[ 0.10247139 0.20204933]] [ 0.29774484]
120 [[ 0.10092307 0.20077361]] [ 0.29915351]
140 [[ 0.10034581 0.20029087]] [ 0.29968235]
160 [[ 0.10012968 0.20010923]] [ 0.2998808]
180 [[ 0.10004867 0.200041 ]] [ 0.29995525]
200 [[ 0.10001829 0.20001541]] [ 0.2999832]
说明:
极客学院的代码是python2版的,如果使用python3以上版本,代码会报语法错误:
(1) print 语法错误:把要打印的内容放入()里,即修改为 print()即可;
(2)xrange 未定义:修改为range即可;