神经网络之数据拟合（二）

本文在前一章节的基础上做了如下改进：

1、步长与训练次数由定值改为取值范围，即在步长（0.01，1）之间训练次数在（1,100000）之间选取最优结果；

2、增加计时器，关注耗时；

 

import tensorflow as tf
import numpy as np
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import matplotlib.pyplot as plt
import time as t

begin = t.time()
#定义在(-0.5,0.5)之间随机生成50个数,并转换为50*1矩阵
x_data = np.linspace(-0.5,0.5,50)[:,np.newaxis]
#随机生成50个噪音值
noise = np.random.normal(0,0.02,x_data.shape)
#y=x^2+noise
y_data = np.square(x_data) + noise

# x=tf.placeholder(tf.float32,[None,1])
x=tf.compat.v1.placeholder(tf.float32,[None,1])
# y=tf.placeholder(tf.float32,[None,1])
y=tf.compat.v1.placeholder(tf.float32,[None,1])

w_L1=tf.Variable(tf.random.normal([1,10]))
b_L1=tf.Variable(tf.zeros([1,10]))
wx_plut_b_L1=tf.matmul(x,w_L1)+b_L1
L1 = tf.nn.sigmoid(wx_plut_b_L1)

w_L2=tf.Variable(tf.random.normal([10,1]))
b_L2=tf.Variable(tf.zeros([1,1]))
wx_plut_b_L2=tf.matmul(L1,w_L2)+b_L2
prediction= tf.nn.sigmoid(wx_plut_b_L2)

loss = tf.reduce_mean(tf.square(y-prediction))
# train_step=tf.compat.v1.train.ProximalGradientDescentOptimizer(0.8).minimize(loss)

with tf.compat.v1.Session() as sess:
    sess.run(tf.compat.v1.global_variables_initializer())
    list = []
    pre=[]
    j=0.01
    num=100000
    while j< 1:
        train_step = tf.compat.v1.train.ProximalGradientDescentOptimizer(j).minimize(loss)
        for i in range(num):
            sess.run(train_step, feed_dict={x:x_data,y:y_data})
            if i % 100 == 0:
                 print(i,sess.run(loss,feed_dict={x:x_data,y:y_data}))
        prediction_value = sess.run(prediction, feed_dict={x: x_data})
        ss = str(j) + "," + str(i) + "," + str(sess.run(loss, feed_dict={x: x_data, y: y_data}))
        list.append(ss)
        pre.append(prediction_value)
        j+=0.1
        i=1

    error=[]
    for v in list:
        ss=v.strip().split(',')[2]
        error.append(ss)
    value=min(error)#选取最小误差
    index=error.index(value)
    best=list[index]#得到最优解
    predict=pre[index]#得到最优预测值，用于绘制图形
    print(best)
    plt.figure()
    plt.scatter(x_data,y_data)
    end = t.time()
    time_spent = end-begin
    print('time cost :',time_spent,'s')
    plt.plot(x_data,predict,'r-',lw=5)
    plt.show()