python实现BP神经网络回归预测模型


Posted in Python onAugust 09, 2019

神经网络模型一般用来做分类,回归预测模型不常见,本文基于一个用来分类的BP神经网络,对它进行修改,实现了一个回归模型,用来做室内定位。模型主要变化是去掉了第三层的非线性转换,或者说把非线性激活函数Sigmoid换成f(x)=x函数。这样做的主要原因是Sigmoid函数的输出范围太小,在0-1之间,而回归模型的输出范围较大。模型修改如下:

python实现BP神经网络回归预测模型

python实现BP神经网络回归预测模型

代码如下:

#coding: utf8
''''
author: Huangyuliang
'''
import json
import random
import sys
import numpy as np
 
#### Define the quadratic and cross-entropy cost functions
class CrossEntropyCost(object):
 
  @staticmethod
  def fn(a, y):
    return np.sum(np.nan_to_num(-y*np.log(a)-(1-y)*np.log(1-a)))
 
  @staticmethod
  def delta(z, a, y):
    return (a-y)
 
#### Main Network class
class Network(object):
 
  def __init__(self, sizes, cost=CrossEntropyCost):
 
    self.num_layers = len(sizes)
    self.sizes = sizes
    self.default_weight_initializer()
    self.cost=cost
 
  def default_weight_initializer(self):
 
    self.biases = [np.random.randn(y, 1) for y in self.sizes[1:]]
    self.weights = [np.random.randn(y, x)/np.sqrt(x)
            for x, y in zip(self.sizes[:-1], self.sizes[1:])]
  def large_weight_initializer(self):
 
    self.biases = [np.random.randn(y, 1) for y in self.sizes[1:]]
    self.weights = [np.random.randn(y, x)
            for x, y in zip(self.sizes[:-1], self.sizes[1:])]
  def feedforward(self, a):
    """Return the output of the network if ``a`` is input."""
    for b, w in zip(self.biases[:-1], self.weights[:-1]): # 前n-1层
      a = sigmoid(np.dot(w, a)+b)
 
    b = self.biases[-1]  # 最后一层
    w = self.weights[-1]
    a = np.dot(w, a)+b
    return a
 
  def SGD(self, training_data, epochs, mini_batch_size, eta,
      lmbda = 0.0,
      evaluation_data=None,
      monitor_evaluation_accuracy=False): # 用随机梯度下降算法进行训练
 
    n = len(training_data)
 
    for j in xrange(epochs):
      random.shuffle(training_data)
      mini_batches = [training_data[k:k+mini_batch_size] for k in xrange(0, n, mini_batch_size)]
      
      for mini_batch in mini_batches:
        self.update_mini_batch(mini_batch, eta, lmbda, len(training_data))
      print ("Epoch %s training complete" % j)
      
      if monitor_evaluation_accuracy:
        print ("Accuracy on evaluation data: {} / {}".format(self.accuracy(evaluation_data), j))
     
  def update_mini_batch(self, mini_batch, eta, lmbda, n):
    """Update the network's weights and biases by applying gradient
    descent using backpropagation to a single mini batch. The
    ``mini_batch`` is a list of tuples ``(x, y)``, ``eta`` is the
    learning rate, ``lmbda`` is the regularization parameter, and
    ``n`` is the total size of the training data set.
    """
    nabla_b = [np.zeros(b.shape) for b in self.biases]
    nabla_w = [np.zeros(w.shape) for w in self.weights]
    for x, y in mini_batch:
      delta_nabla_b, delta_nabla_w = self.backprop(x, y)
      nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
      nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
    self.weights = [(1-eta*(lmbda/n))*w-(eta/len(mini_batch))*nw
            for w, nw in zip(self.weights, nabla_w)]
    self.biases = [b-(eta/len(mini_batch))*nb
            for b, nb in zip(self.biases, nabla_b)]
 
  def backprop(self, x, y):
    """Return a tuple ``(nabla_b, nabla_w)`` representing the
    gradient for the cost function C_x. ``nabla_b`` and
    ``nabla_w`` are layer-by-layer lists of numpy arrays, similar
    to ``self.biases`` and ``self.weights``."""
    nabla_b = [np.zeros(b.shape) for b in self.biases]
    nabla_w = [np.zeros(w.shape) for w in self.weights]
    # feedforward
    activation = x
    activations = [x] # list to store all the activations, layer by layer
    zs = [] # list to store all the z vectors, layer by layer
    for b, w in zip(self.biases[:-1], self.weights[:-1]):  # 正向传播 前n-1层
 
      z = np.dot(w, activation)+b
      zs.append(z)
      activation = sigmoid(z)
      activations.append(activation)
# 最后一层,不用非线性
    b = self.biases[-1]
    w = self.weights[-1]
    z = np.dot(w, activation)+b
    zs.append(z)
    activation = z
    activations.append(activation)
    # backward pass 反向传播
    delta = (self.cost).delta(zs[-1], activations[-1], y)  # 误差 Tj - Oj 
    nabla_b[-1] = delta
    nabla_w[-1] = np.dot(delta, activations[-2].transpose()) # (Tj - Oj) * O(j-1)
 
    for l in xrange(2, self.num_layers):
      z = zs[-l]  # w*a + b
      sp = sigmoid_prime(z) # z * (1-z)
      delta = np.dot(self.weights[-l+1].transpose(), delta) * sp # z*(1-z)*(Err*w) 隐藏层误差
      nabla_b[-l] = delta
      nabla_w[-l] = np.dot(delta, activations[-l-1].transpose()) # Errj * Oi
    return (nabla_b, nabla_w)
 
  def accuracy(self, data):
 
    results = [(self.feedforward(x), y) for (x, y) in data] 
    alist=[np.sqrt((x[0][0]-y[0])**2+(x[1][0]-y[1])**2) for (x,y) in results]
 
    return np.mean(alist)
 
  def save(self, filename):
    """Save the neural network to the file ``filename``."""
    data = {"sizes": self.sizes,
        "weights": [w.tolist() for w in self.weights],
        "biases": [b.tolist() for b in self.biases],
        "cost": str(self.cost.__name__)}
    f = open(filename, "w")
    json.dump(data, f)
    f.close()
 
#### Loading a Network
def load(filename):
  """Load a neural network from the file ``filename``. Returns an
  instance of Network.
  """
  f = open(filename, "r")
  data = json.load(f)
  f.close()
  cost = getattr(sys.modules[__name__], data["cost"])
  net = Network(data["sizes"], cost=cost)
  net.weights = [np.array(w) for w in data["weights"]]
  net.biases = [np.array(b) for b in data["biases"]]
  return net
 
def sigmoid(z):
  """The sigmoid function.""" 
  return 1.0/(1.0+np.exp(-z))
 
def sigmoid_prime(z):
  """Derivative of the sigmoid function."""
  return sigmoid(z)*(1-sigmoid(z))

调用神经网络进行训练并保存参数:

#coding: utf8
import my_datas_loader_1
import network_0
 
training_data,test_data = my_datas_loader_1.load_data_wrapper()
#### 训练网络,保存训练好的参数
net = network_0.Network([14,100,2],cost = network_0.CrossEntropyCost)
net.large_weight_initializer()
net.SGD(training_data,1000,316,0.005,lmbda =0.1,evaluation_data=test_data,monitor_evaluation_accuracy=True)
filename=r'C:\Users\hyl\Desktop\Second_158\Regression_Model\parameters.txt'
net.save(filename)

第190-199轮训练结果如下:

python实现BP神经网络回归预测模型

调用保存好的参数,进行定位预测:

#coding: utf8
import my_datas_loader_1
import network_0
import matplotlib.pyplot as plt
 
test_data = my_datas_loader_1.load_test_data()
#### 调用训练好的网络,用来进行预测
filename=r'D:\Workspase\Nerual_networks\parameters.txt'   ## 文件保存训练好的参数
net = network_0.load(filename)                ## 调用参数,形成网络
fig=plt.figure(1)
ax=fig.add_subplot(1,1,1)
ax.axis("equal") 
# plt.grid(color='b' , linewidth='0.5' ,linestyle='-')    # 添加网格
x=[-0.3,-0.3,-17.1,-17.1,-0.3]                ## 这是九楼地形的轮廓
y=[-0.3,26.4,26.4,-0.3,-0.3]
m=[1.5,1.5,-18.9,-18.9,1.5]
n=[-2.1,28.2,28.2,-2.1,-2.1]
ax.plot(x,y,m,n,c='k')
 
for i in range(len(test_data)):  
  pre = net.feedforward(test_data[i][0]) # pre 是预测出的坐标    
  bx=pre[0]
  by=pre[1]          
  ax.scatter(bx,by,s=4,lw=2,marker='.',alpha=1) #散点图  
  plt.pause(0.001)
plt.show()

定位精度达到了1.5米左右。定位效果如下图所示:

python实现BP神经网络回归预测模型

真实路径为行人从原点绕环形走廊一圈。

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持三水点靠木。

Python 相关文章推荐
Python实现批量把SVG格式转成png、pdf格式的代码分享
Aug 21 Python
python 把数据 json格式输出的实例代码
Oct 31 Python
Python实现将数据库一键导出为Excel表格的实例
Dec 30 Python
python字典DICT类型合并详解
Aug 17 Python
Python多进程并发与多线程并发编程实例总结
Feb 08 Python
Python闭包执行时值的传递方式实例分析
Jun 04 Python
python采集微信公众号文章
Dec 20 Python
pytorch中如何使用DataLoader对数据集进行批处理的方法
Aug 06 Python
浅析pandas 数据结构中的DataFrame
Oct 12 Python
pytorch中的卷积和池化计算方式详解
Jan 03 Python
pandas中read_csv、rolling、expanding用法详解
Apr 21 Python
Python的logging模块基本用法
Dec 24 Python
Django ORM 聚合查询和分组查询实现详解
Aug 09 #Python
解决Django后台ManyToManyField显示成Object的问题
Aug 09 #Python
详解Python中的正斜杠与反斜杠
Aug 09 #Python
图文详解Django使用Pycharm连接MySQL数据库
Aug 09 #Python
Django ORM多对多查询方法(自定义第三张表&ManyToManyField)
Aug 09 #Python
Django使用Jinja2模板引擎的示例代码
Aug 09 #Python
在Django admin中编辑ManyToManyField的实现方法
Aug 09 #Python
You might like
PHP 读取和编写 XML
2014/11/19 PHP
ioncube_loader_win_5.2.dll的错误解决方法
2015/01/04 PHP
php中的动态调用实例分析
2015/01/07 PHP
ThinkPHP中数据操作案例分析
2015/09/27 PHP
PHP YII框架开发小技巧之模型(models)中rules自定义验证规则
2015/11/16 PHP
php微信公众平台交互与接口详解
2016/11/28 PHP
Yii框架分页实现方法详解
2017/05/20 PHP
PHP面向对象程序设计(OOP)之方法重写(override)操作示例
2018/12/21 PHP
用javascript实现点击链接弹出"图片另存为"而不是直接打开
2007/08/15 Javascript
JavaScript高级程序设计(第3版)学习笔记 概述
2012/10/11 Javascript
javascript显示用户停留时间的简单实例
2013/08/05 Javascript
jquery中加载图片自适应大小主要实现代码
2013/08/23 Javascript
jquery 添加节点的几种方法介绍
2013/09/04 Javascript
javascript移出节点removeChild()使用介绍
2014/04/03 Javascript
jQuery height()、innerHeight()、outerHeight()函数的区别详解
2016/05/23 Javascript
JavaScript简单获取页面图片原始尺寸的方法
2016/06/21 Javascript
jQuery实现鼠标经过像翻页和描点链接效果
2016/08/08 Javascript
JavaScript SHA512加密算法详细代码
2016/10/06 Javascript
javascript如何用递归写一个简单的树形结构示例
2017/09/06 Javascript
基于Particles.js制作超炫粒子动态背景效果(仿知乎)
2017/09/13 Javascript
详解nodejs通过代理(proxy)发送http请求(request)
2017/09/22 NodeJs
小程序点击图片实现png转jpg
2019/10/22 Javascript
[04:42]2015国际邀请赛CDEC战队晋级之路
2015/08/13 DOTA
Python中的字典遍历备忘
2015/01/17 Python
使用python实现省市三级菜单效果
2016/01/20 Python
Python利用Django如何写restful api接口详解
2018/06/08 Python
python模块导入的细节详解
2018/12/10 Python
对Tensorflow中Device实例的生成和管理详解
2020/02/04 Python
python实现吃苹果小游戏
2020/03/21 Python
python如何求100以内的素数
2020/05/27 Python
Python使用pickle进行序列化和反序列化的示例代码
2020/09/22 Python
总经理助理的职责
2014/03/14 职场文书
教师业务培训方案
2014/05/01 职场文书
先进学校事迹材料
2014/12/30 职场文书
python如何进行基准测试
2021/04/26 Python
一篇文章弄懂Python关键字、标识符和变量
2021/07/15 Python