python构建深度神经网络(DNN)


Posted in Python onMarch 10, 2018

本文学习Neural Networks and Deep Learning 在线免费书籍,用python构建神经网络识别手写体的一个总结。

代码主要包括两三部分:

1)、数据调用和预处理

2)、神经网络类构建和方法建立

3)、代码测试文件

1)数据调用:

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time  : 2017-03-12 15:11 
# @Author : CC 
# @File  : net_load_data.py 
# @Software: PyCharm Community Edition 
 
from numpy import * 
import numpy as np 
import cPickle 
def load_data(): 
  """载入解压后的数据,并读取""" 
  with open('data/mnist_pkl/mnist.pkl','rb') as f: 
    try: 
      train_data,validation_data,test_data = cPickle.load(f) 
      print " the file open sucessfully" 
      # print train_data[0].shape #(50000,784) 
      # print train_data[1].shape  #(50000,) 
      return (train_data,validation_data,test_data) 
    except EOFError: 
      print 'the file open error' 
      return None 
 
def data_transform(): 
  """将数据转化为计算格式""" 
  t_d,va_d,te_d = load_data() 
  # print t_d[0].shape # (50000,784) 
  # print te_d[0].shape # (10000,784) 
  # print va_d[0].shape # (10000,784) 
  # n1 = [np.reshape(x,784,1) for x in t_d[0]] # 将5万个数据分别逐个取出化成(784,1),逐个排列 
  n = [np.reshape(x, (784, 1)) for x in t_d[0]] # 将5万个数据分别逐个取出化成(784,1),逐个排列 
  # print 'n1',n1[0].shape 
  # print 'n',n[0].shape 
  m = [vectors(y) for y in t_d[1]] # 将5万标签(50000,1)化为(10,50000) 
  train_data = zip(n,m) # 将数据与标签打包成元组形式 
  n = [np.reshape(x, (784, 1)) for x in va_d[0]] # 将5万个数据分别逐个取出化成(784,1),排列 
  validation_data = zip(n,va_d[1])  # 没有将标签数据矢量化 
  n = [np.reshape(x, (784, 1)) for x in te_d[0]] # 将5万个数据分别逐个取出化成(784,1),排列 
  test_data = zip(n, te_d[1]) # 没有将标签数据矢量化 
  # print train_data[0][0].shape #(784,) 
  # print "len(train_data[0])",len(train_data[0]) #2 
  # print "len(train_data[100])",len(train_data[100]) #2 
  # print "len(train_data[0][0])", len(train_data[0][0]) #784 
  # print "train_data[0][0].shape", train_data[0][0].shape #(784,1) 
  # print "len(train_data)", len(train_data) #50000 
  # print train_data[0][1].shape #(10,1) 
  # print test_data[0][1] # 7 
  return (train_data,validation_data,test_data) 
def vectors(y): 
  """赋予标签""" 
  label = np.zeros((10,1)) 
  label[y] = 1.0 #浮点计算 
  return label

2)网络构建

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time  : 2017-03-12 16:07 
# @Author : CC 
# @File  : net_network.py 
 
import numpy as np 
import random 
class Network(object):  #默认为基类?用于继承:print isinstance(network,object) 
  def __init__(self,sizes): 
    self.num_layers = len(sizes) 
    self.sizes = sizes 
    # print 'num_layers', self.num_layers 
    self.weight = [np.random.randn(a1, a2) for (a1, a2) in zip(sizes[1:], sizes[:-1])] #产生一个个数组 
    self.bias = [np.random.randn(a3,1) for a3 in sizes[1:]] 
    # print self.weight[0].shape #(20,10) 
 
  def SGD(self,train_data,min_batch_size,epoches,eta,test_data=False): 
    """ 1) 打乱样本,将训练数据划分成小批次 
      2)计算出反向传播梯度 
      3) 获得权重更新""" 
    if test_data: n_test = len(test_data) 
    n = len(train_data)  #50000 
    random.shuffle(train_data) # 打乱 
    min_batches = [train_data[k:k+min_batch_size] for k in xrange(0,n,min_batch_size)] #提取批次数据 
    for k in xrange(0,epoches):  #利用更新后的权值继续更新 
      random.shuffle(train_data) # 打乱 
      for min_batch in min_batches: #逐个传入,效率很低 
        self.updata_parameter(min_batch,eta) 
      if test_data: 
        num = self.evaluate(test_data) 
        print "the {0}th epoches: {1}/{2}".format(k,num,len(test_data)) 
      else: 
        print 'epoches {0} completed'.format(k) 
 
  def forward(self,x): 
    """获得各层激活值""" 
    for w,b in zip(self.weight,self.bias): 
      x = sigmoid(np.dot(w, x)+b) 
    return x 
 
  def updata_parameter(self,min_batch,eta): 
    """1) 反向传播计算每个样本梯度值 
      2) 累加每个批次样本的梯度值 
      3) 权值更新""" 
    ndeltab = [np.zeros(b.shape) for b in self.bias] 
    ndeltaw = [np.zeros(w.shape) for w in self.weight] 
    for x,y in min_batch: 
      deltab,deltaw = self.backprop(x,y) 
      ndeltab = [nb +db for nb,db in zip(ndeltab,deltab)] 
      ndeltaw = [nw + dw for nw,dw in zip(ndeltaw,deltaw)] 
    self.bias = [b - eta * ndb/len(min_batch) for ndb,b in zip(ndeltab,self.bias)] 
    self.weight = [w - eta * ndw/len(min_batch) for ndw,w in zip(ndeltaw,self.weight)] 
 
 
  def backprop(self,x,y): 
    """执行前向计算,再进行反向传播,返回deltaw,deltab""" 
    # [w for w in self.weight] 
    # print 'len',len(w) 
    # print "self.weight",self.weight[0].shape 
    # print w[0].shape 
    # print w[1].shape 
    # print w.shape 
    activation = x 
    activations = [x] 
    zs = [] 
    # feedforward 
    for w, b in zip(self.weight, self.bias): 
      # print w.shape,activation.shape,b.shape 
      z = np.dot(w, activation) +b 
      zs.append(z)  #用于计算f(z)导数 
      activation = sigmoid(z) 
      # print 'activation',activation.shape 
      activations.append(activation) # 每层的输出结果 
    delta = self.top_subtract(activations[-1],y) * dsigmoid(zs[-1]) #最后一层的delta,np.array乘,相同维度乘 
    deltaw = [np.zeros(w1.shape) for w1 in self.weight] #每一次将获得的值作为列表形式赋给deltaw 
    deltab = [np.zeros(b1.shape) for b1 in self.bias] 
    # print 'deltab[0]',deltab[-1].shape 
    deltab[-1] = delta 
    deltaw[-1] = np.dot(delta,activations[-2].transpose()) 
    for k in xrange(2,self.num_layers): 
      delta = np.dot(self.weight[-k+1].transpose(),delta) * dsigmoid(zs[-k]) 
      deltab[-k] = delta 
      deltaw[-k] = np.dot(delta,activations[-k-1].transpose()) 
    return (deltab,deltaw) 
 
  def evaluate(self,test_data): 
    """评估验证集和测试集的精度,标签直接一个数作为比较""" 
    z = [(np.argmax(self.forward(x)),y) for x,y in test_data] 
    zs = np.sum(int(a == b) for a,b in z) 
    # zk = sum(int(a == b) for a,b in z) 
    # print "zs/zk:",zs,zk 
    return zs 
 
  def top_subtract(self,x,y): 
    return (x - y) 
 
def sigmoid(x): 
  return 1.0/(1.0+np.exp(-x)) 
 
def dsigmoid(x): 
  z = sigmoid(x) 
  return z*(1-z)

3)网络测试

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time  : 2017-03-12 15:24 
# @Author : CC 
# @File  : net_test.py 
 
import net_load_data 
# net_load_data.load_data() 
train_data,validation_data,test_data = net_load_data.data_transform() 
 
import net_network as net 
net1 = net.Network([784,30,10]) 
min_batch_size = 10 
eta = 3.0 
epoches = 30 
net1.SGD(train_data,min_batch_size,epoches,eta,test_data) 
print "complete"

4)结果

the 9th epoches: 9405/10000 
the 10th epoches: 9420/10000 
the 11th epoches: 9385/10000 
the 12th epoches: 9404/10000 
the 13th epoches: 9398/10000 
the 14th epoches: 9406/10000 
the 15th epoches: 9396/10000 
the 16th epoches: 9413/10000 
the 17th epoches: 9405/10000 
the 18th epoches: 9425/10000 
the 19th epoches: 9420/10000

总体来说这本书的实例,用来熟悉python和神经网络非常好。

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 Deque 模块使用详解
Jul 04 Python
Python检测网站链接是否已存在
Apr 07 Python
对python中for、if、while的区别与比较方法
Jun 25 Python
python3使用flask编写注册post接口的方法
Dec 28 Python
Python3.5模块的定义、导入、优化操作图文详解
Apr 27 Python
Django保护敏感信息的方法示例
May 09 Python
ZABBIX3.2使用python脚本实现监控报表的方法
Jul 02 Python
python单例模式原理与创建方法实例分析
Oct 26 Python
Python搭建代理IP池实现存储IP的方法
Oct 27 Python
Anaconda3中的Jupyter notebook添加目录插件的实现
May 18 Python
Python Flask异步发送邮件实现方法解析
Aug 01 Python
Django框架模板用法详解
Jun 10 Python
Python使用numpy实现BP神经网络
Mar 10 #Python
python实现日常记账本小程序
Mar 10 #Python
python实现简单神经网络算法
Mar 10 #Python
TensorFlow saver指定变量的存取
Mar 10 #Python
TensorFLow用Saver保存和恢复变量
Mar 10 #Python
tensorflow创建变量以及根据名称查找变量
Mar 10 #Python
Python2中文处理纪要的实现方法
Mar 10 #Python
You might like
php 修改zen-cart下单和付款流程以防止漏单
2010/03/08 PHP
php计算几分钟前、几小时前、几天前的几个函数、类分享
2014/04/09 PHP
php实现的SESSION类
2014/12/02 PHP
ThinkPHP通过AJAX返回JSON的两种实现方法
2014/12/18 PHP
excel操作之Add Data to a Spreadsheet Cell
2007/06/12 Javascript
js刷新框架子页面的七种方法代码
2008/11/20 Javascript
JavaScript 类的定义和引用 JavaScript高级培训 自定义对象
2010/04/27 Javascript
zeroclipboard复制到剪切板的flash
2010/08/04 Javascript
多种方法判断Javascript对象是否存在
2013/09/22 Javascript
jQuery学习笔记之jQuery.extend(),jQuery.fn.extend()分析
2014/06/09 Javascript
jQuery实现自动滚动到页面顶端的方法
2015/05/22 Javascript
JavaScript判断FileUpload控件上传文件类型
2015/09/28 Javascript
Javascript基础教程之比较null和undefined值
2016/05/16 Javascript
Node.js配合node-http-proxy解决本地开发ajax跨域问题
2016/08/31 Javascript
详解JS几种变量交换方式以及性能分析对比
2016/11/25 Javascript
js for循环倒序输出数组元素的实例
2017/03/01 Javascript
angular.js4使用 RxJS 处理多个 Http 请求
2017/09/23 Javascript
nodejs读取本地中文json文件出现乱码解决方法
2018/10/10 NodeJs
layer.prompt输入层的例子
2019/09/24 Javascript
微信小程序实现点赞业务
2021/02/10 Javascript
python实现自动更换ip的方法
2015/05/05 Python
python操作ie登陆土豆网的方法
2015/05/09 Python
使用Python脚本将文字转换为图片的实例分享
2015/08/29 Python
Python列表切片用法示例
2017/04/19 Python
python利用sklearn包编写决策树源代码
2017/12/21 Python
基于CSS3制作立体效果导航菜单
2016/01/12 HTML / CSS
DOUGLAS荷兰:购买香水和化妆品
2020/10/24 全球购物
如何进行Linux分区优化
2013/02/12 面试题
求职信模板标准格式范文
2014/02/23 职场文书
向国旗敬礼活动小结
2014/09/27 职场文书
党员自评材料范文
2014/12/17 职场文书
导盲犬小Q观后感
2015/06/11 职场文书
幼儿园教师教学反思
2016/03/02 职场文书
Java反应式框架Reactor中的Mono和Flux
2021/07/25 Java/Android
sql server偶发出现死锁的解决方法
2022/04/10 SQL Server
vue使用localStorage持久性存储实现评论列表
2022/04/14 Vue.js