第一个基于 Tensorflow 的简单回归例子

学习自 YouTube 上莫烦的 TensorFlow 的教学视频

# -*- coding: utf-8 -*-
"""
Created on Sun Mar 18 22:53:41 2018

@author: Administrator
"""

import tensorflow as tf
import numpy as np 
import matplotlib.pyplot as plt

#定义隐藏层
def add_layer(inputs,in_size,out_size,activation_function=None):
    W = tf.Variable(tf.random_normal([in_size,out_size]))
    b = tf.Variable(tf.zeros([1,out_size]) + 0.1)
    if activation_function is None:
        ouput = tf.matmul(inputs,W) + b
    else:
        ouput = activation_function(tf.matmul(inputs,W) + b)
    return ouput

#定义数据    
x_data = np.linspace(-1,1,300)[:,np.newaxis]
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

#tf 形式数据
xs = tf.placeholder(np.float32,[None,1])
ys = tf.placeholder(np.float32,[None,1])

#构建结构
l1 = add_layer(xs,1,10,tf.nn.relu)
prediction = add_layer(l1,10,1,None)

#损失函数和优化器
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),reduction_indices=[1]))
train = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

#初始化
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

#画图
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()

for step in range(1000):
    sess.run(train,feed_dict={xs:x_data,ys:y_data})
    if step % 50 == 0:
        #print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction,feed_dict={xs:x_data})
        lines = ax.plot(x_data,prediction_value,'r-',lw=5)

        plt.pause(0.1)

运行结果：