简介

In [1]:

    

import tensorflow as tf
import numpy as np

# 使用numpy生成假数据（phony data)，总共100个点
# 随机输入
x_data = np.float32(np.random.rand(2, 100))
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]


    

    




0 [[ 0.32086498  0.0343847 ]] [ 0.5784325]
20 [[ 0.09581911  0.14217304]] [ 0.33141962]
40 [[ 0.09227795  0.18412542]] [ 0.31230131]
60 [[ 0.0962368   0.19482392]] [ 0.30470738]
80 [[ 0.09846166  0.1981573 ]] [ 0.30178693]
100 [[ 0.0994027   0.19931929]] [ 0.30067635]
120 [[ 0.09977209  0.19974492]] [ 0.30025572]
140 [[ 0.09991359  0.19990391]] [ 0.30009666]
160 [[ 0.09996732  0.19996372]] [ 0.30003652]
180 [[ 0.09998765  0.19998632]] [ 0.30001381]
200 [[ 0.09999532  0.19999483]] [ 0.3000052]