zoukankan      html  css  js  c++  java
  • tensorflow非线性回归

    该程序有输入层,中间层和输出层

    运行环境:ubuntun

    (menpo) queen@queen-X550LD:~/Downloads/py $ python nonliner_regression.py

    # -*- coding: UTF-8 -*-
    #定义一个神经网络:输入层一个元素,中间层10个神经元,输出层1个元素
    import numpy as np
    import matplotlib.pyplot as plt
    import tensorflow as tf
    
    #使用numpy生成200个随机点
    x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
    noise = np.random.normal(0,0.02,x_data.shape)
    y_data = np.square(x_data)+noise
    
    #定义两个placeholder
    x = tf.placeholder(tf.float32,[None,1])
    y = tf.placeholder(tf.float32,[None,1])
    
    #定义神经网络中间层
    Weights_L1 = tf.Variable(tf.random_normal([1,10])) #输入层1个元素,中间层10个神经元
    biases_L1 = tf.Variable(tf.zeros([1,10]))
    Wx_plus_b_L1 = tf.matmul(x,Weights_L1) + biases_L1
    L1 = tf.tanh(Wx_plus_b_L1)
    
    #定义神经网络输出层
    Weights_L2 = tf.Variable(tf.random_normal([10,1])) #中间层10个神经元,输出层1个元素
    biases_L2 = tf.Variable(tf.zeros([1,1]))
    Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
    prediction = tf.tanh(Wx_plus_b_L2)
    
    #二次代价函数
    loss = tf.reduce_mean(tf.square(y-prediction))
    
    #使用梯度下降法
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
    
    with tf.Session() as sess:
        #变量初始化
        sess.run(tf.global_variables_initializer())
        for _ in range(2000):
            sess.run(train_step,feed_dict={x:x_data,y:y_data})
    
        #获取预测值
        prediction_value = sess.run(prediction,feed_dict={x:x_data})
        #画图
        plt.figure()
        plt.scatter(x_data,y_data)
        plt.plot(x_data,prediction_value,'r-',lw=5)
        plt.show()

    运行结果图

  • 相关阅读:
    DB2 for Z/os Statement prepare
    Foreign key (referential) constraints on DB2 LUW v105
    复制Informational constraints on LUW DB2 v105
    DB2 SQL Mixed data in character strings
    DB2 create partitioned table
    MVC中使用EF的技巧集(一)
    Asp.Net MVC 开发技巧(二)
    Linq使用技巧及查询示例(一)
    Asp.Net MVC 开发技巧(一)
    Asp.Net MVC Identity 2.2.1 使用技巧(八)
  • 原文地址:https://www.cnblogs.com/spore/p/12732114.html
Copyright © 2011-2022 走看看