详解python实现识别手写MNIST数字集的程序


Posted in Python onAugust 03, 2018

我们需要做的第⼀件事情是获取 MNIST 数据。如果你是⼀个 git ⽤⼾,那么你能够通过克隆这本书的代码仓库获得数据,实现我们的⽹络来分类数字

git clone https://github.com/mnielsen/neural-networks-and-deep-learning.git
class Network(object):
def __init__(self, sizes):
self.num_layers = len(sizes)
self.sizes = sizes
self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
self.weights = [np.random.randn(y, x)
for x, y in zip(sizes[:-1], sizes[1:])]

在这段代码中,列表 sizes 包含各层神经元的数量。例如,如果我们想创建⼀个在第⼀层有2 个神经元,第⼆层有 3 个神经元,最后层有 1 个神经元的 Network 对象,我们应这样写代码:

net = Network([2, 3, 1])

Network 对象中的偏置和权重都是被随机初始化的,使⽤ Numpy 的 np.random.randn 函数来⽣成均值为 0,标准差为 1 的⾼斯分布。这样的随机初始化给了我们的随机梯度下降算法⼀个起点。在后⾯的章节中我们将会发现更好的初始化权重和偏置的⽅法,但是⽬前随机地将其初始化。注意 Network 初始化代码假设第⼀层神经元是⼀个输⼊层,并对这些神经元不设置任何偏置,因为偏置仅在后⾯的层中⽤于计算输出。有了这些,很容易写出从⼀个 Network 实例计算输出的代码。我们从定义 S 型函数开始:

def sigmoid(z):
return 1.0/(1.0+np.exp(-z))

注意,当输⼊ z 是⼀个向量或者 Numpy 数组时,Numpy ⾃动地按元素应⽤ sigmoid 函数,即以向量形式。

我们然后对 Network 类添加⼀个 feedforward ⽅法,对于⽹络给定⼀个输⼊ a,返回对应的输出 6 。这个⽅法所做的是对每⼀层应⽤⽅程 (22):

def feedforward(self, a):
"""Return the output of the network if "a" is input."""
for b, w in zip(self.biases, self.weights):
a = sigmoid(np.dot(w, a)+b)
return a

当然,我们想要 Network 对象做的主要事情是学习。为此我们给它们⼀个实现随即梯度下降算法的 SGD ⽅法。代码如下。其中⼀些地⽅看似有⼀点神秘,我会在代码后⾯逐个分析

def SGD(self, training_data, epochs, mini_batch_size, eta,
test_data=None):
"""Train the neural network using mini-batch stochastic
gradient descent. The "training_data" is a list of tuples
"(x, y)" representing the training inputs and the desired
outputs. The other non-optional parameters are
self-explanatory. If "test_data" is provided then the
network will be evaluated against the test data after each
epoch, and partial progress printed out. This is useful for
tracking progress, but slows things down substantially."""
if test_data: n_test = len(test_data)
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)
if test_data:
print "Epoch {0}: {1} / {2}".format(
j, self.evaluate(test_data), n_test)
else:
print "Epoch {0} complete".format(j)
 

training_data 是⼀个 (x, y) 元组的列表,表⽰训练输⼊和其对应的期望输出。变量 epochs 和mini_batch_size 正如你预料的——迭代期数量,和采样时的⼩批量数据的⼤⼩。 eta 是学习速率,η。如果给出了可选参数 test_data ,那么程序会在每个训练器后评估⽹络,并打印出部分进展。这对于追踪进度很有⽤,但相当拖慢执⾏速度。

在每个迭代期,它⾸先随机地将训练数据打乱,然后将它分成多个适当⼤⼩的⼩批量数据。这是⼀个简单的从训练数据的随机采样⽅法。然后对于每⼀个 mini_batch我们应⽤⼀次梯度下降。这是通过代码 self.update_mini_batch(mini_batch, eta) 完成的,它仅仅使⽤ mini_batch 中的训练数据,根据单次梯度下降的迭代更新⽹络的权重和偏置。这是update_mini_batch ⽅法的代码:

def update_mini_batch(self, mini_batch, eta):
"""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)", and "eta"
is the learning rate."""
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 = [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)]

⼤部分⼯作由这⾏代码完成:

delta_nabla_b, delta_nabla_w = self.backprop(x, y)

这⾏调⽤了⼀个称为反向传播的算法,⼀种快速计算代价函数的梯度的⽅法。因此update_mini_batch 的⼯作仅仅是对 mini_batch 中的每⼀个训练样本计算梯度,然后适当地更新 self.weights 和 self.biases 。我现在不会列出 self.backprop 的代码。我们将在下章中学习反向传播是怎样⼯作的,包括self.backprop 的代码。现在,就假设它按照我们要求的⼯作,返回与训练样本 x 相关代价的适当梯度

完整的程序

"""
network.py
~~~~~~~~~~
 
A module to implement the stochastic gradient descent learning
algorithm for a feedforward neural network. Gradients are calculated
using backpropagation. Note that I have focused on making the code
simple, easily readable, and easily modifiable. It is not optimized,
and omits many desirable features.
"""
 
#### Libraries
# Standard library
import random
 
# Third-party libraries
import numpy as np
 
class Network(object):
 
 def __init__(self, sizes):
  """The list ``sizes`` contains the number of neurons in the
  respective layers of the network. For example, if the list
  was [2, 3, 1] then it would be a three-layer network, with the
  first layer containing 2 neurons, the second layer 3 neurons,
  and the third layer 1 neuron. The biases and weights for the
  network are initialized randomly, using a Gaussian
  distribution with mean 0, and variance 1. Note that the first
  layer is assumed to be an input layer, and by convention we
  won't set any biases for those neurons, since biases are only
  ever used in computing the outputs from later layers."""
  self.num_layers = len(sizes)
  self.sizes = sizes
  self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
  self.weights = [np.random.randn(y, x)
      for x, y in zip(sizes[:-1], sizes[1:])]
 
 def feedforward(self, a):
  """Return the output of the network if ``a`` is input."""
  for b, w in zip(self.biases, self.weights):
   a = sigmoid(np.dot(w, a)+b)
  return a
 
 def SGD(self, training_data, epochs, mini_batch_size, eta,
   test_data=None):
  """Train the neural network using mini-batch stochastic
  gradient descent. The ``training_data`` is a list of tuples
  ``(x, y)`` representing the training inputs and the desired
  outputs. The other non-optional parameters are
  self-explanatory. If ``test_data`` is provided then the
  network will be evaluated against the test data after each
  epoch, and partial progress printed out. This is useful for
  tracking progress, but slows things down substantially."""
  if test_data: n_test = len(test_data)
  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)
   if test_data:
    print "Epoch {0}: {1} / {2}".format(
     j, self.evaluate(test_data), n_test)
   else:
    print "Epoch {0} complete".format(j)
 
 def update_mini_batch(self, mini_batch, eta):
  """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)``, and ``eta``
  is the learning rate."""
  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 = [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, self.weights):
   z = np.dot(w, activation)+b
   zs.append(z)
   activation = sigmoid(z)
   activations.append(activation)
  # backward pass
  delta = self.cost_derivative(activations[-1], y) * \
   sigmoid_prime(zs[-1])
  nabla_b[-1] = delta
  nabla_w[-1] = np.dot(delta, activations[-2].transpose())
  # Note that the variable l in the loop below is used a little
  # differently to the notation in Chapter 2 of the book. Here,
  # l = 1 means the last layer of neurons, l = 2 is the
  # second-last layer, and so on. It's a renumbering of the
  # scheme in the book, used here to take advantage of the fact
  # that Python can use negative indices in lists.
  for l in xrange(2, self.num_layers):
   z = zs[-l]
   sp = sigmoid_prime(z)
   delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
   nabla_b[-l] = delta
   nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
  return (nabla_b, nabla_w)
 
 def evaluate(self, test_data):
  """Return the number of test inputs for which the neural
  network outputs the correct result. Note that the neural
  network's output is assumed to be the index of whichever
  neuron in the final layer has the highest activation."""
  test_results = [(np.argmax(self.feedforward(x)), y)
      for (x, y) in test_data]
  return sum(int(x == y) for (x, y) in test_results)
 
 def cost_derivative(self, output_activations, y):
  """Return the vector of partial derivatives \partial C_x /
  \partial a for the output activations."""
  return (output_activations-y)
 
#### Miscellaneous functions
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))
"""
mnist_loader
~~~~~~~~~~~~
 
A library to load the MNIST image data. For details of the data
structures that are returned, see the doc strings for ``load_data``
and ``load_data_wrapper``. In practice, ``load_data_wrapper`` is the
function usually called by our neural network code.
"""
 
#### Libraries
# Standard library
import cPickle
import gzip
 
# Third-party libraries
import numpy as np
 
def load_data():
 """Return the MNIST data as a tuple containing the training data,
 the validation data, and the test data.
 
 The ``training_data`` is returned as a tuple with two entries.
 The first entry contains the actual training images. This is a
 numpy ndarray with 50,000 entries. Each entry is, in turn, a
 numpy ndarray with 784 values, representing the 28 * 28 = 784
 pixels in a single MNIST image.
 
 The second entry in the ``training_data`` tuple is a numpy ndarray
 containing 50,000 entries. Those entries are just the digit
 values (0...9) for the corresponding images contained in the first
 entry of the tuple.
 
 The ``validation_data`` and ``test_data`` are similar, except
 each contains only 10,000 images.
 
 This is a nice data format, but for use in neural networks it's
 helpful to modify the format of the ``training_data`` a little.
 That's done in the wrapper function ``load_data_wrapper()``, see
 below.
 """
 f = gzip.open('../data/mnist.pkl.gz', 'rb')
 training_data, validation_data, test_data = cPickle.load(f)
 f.close()
 return (training_data, validation_data, test_data)
 
def load_data_wrapper():
 """Return a tuple containing ``(training_data, validation_data,
 test_data)``. Based on ``load_data``, but the format is more
 convenient for use in our implementation of neural networks.
 
 In particular, ``training_data`` is a list containing 50,000
 2-tuples ``(x, y)``. ``x`` is a 784-dimensional numpy.ndarray
 containing the input image. ``y`` is a 10-dimensional
 numpy.ndarray representing the unit vector corresponding to the
 correct digit for ``x``.
 
 ``validation_data`` and ``test_data`` are lists containing 10,000
 2-tuples ``(x, y)``. In each case, ``x`` is a 784-dimensional
 numpy.ndarry containing the input image, and ``y`` is the
 corresponding classification, i.e., the digit values (integers)
 corresponding to ``x``.
 
 Obviously, this means we're using slightly different formats for
 the training data and the validation / test data. These formats
 turn out to be the most convenient for use in our neural network
 code."""
 tr_d, va_d, te_d = load_data()
 training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
 training_results = [vectorized_result(y) for y in tr_d[1]]
 training_data = zip(training_inputs, training_results)
 validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
 validation_data = zip(validation_inputs, va_d[1])
 test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
 test_data = zip(test_inputs, te_d[1])
 return (training_data, validation_data, test_data)
 
def vectorized_result(j):
 """Return a 10-dimensional unit vector with a 1.0 in the jth
 position and zeroes elsewhere. This is used to convert a digit
 (0...9) into a corresponding desired output from the neural
 network."""
 e = np.zeros((10, 1))
 e[j] = 1.0
 return e
# test network.py "cost function square func"
import mnist_loader
training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
import network
net = network.Network([784, 10])
net.SGD(training_data, 5, 10, 5.0, test_data=test_data)

原英文查看:http://neuralnetworksanddeeplearning.com/chap1.html

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进阶教程之循环相关函数range、enumerate、zip
Aug 30 Python
python获取元素在数组中索引号的方法
Jul 15 Python
用Python将IP地址在整型和字符串之间轻松转换
Mar 22 Python
详解appium+python 启动一个app步骤
Dec 20 Python
Java与Python两大幸存者谁更胜一筹呢
Apr 12 Python
pyqt5让图片自适应QLabel大小上以及移除已显示的图片方法
Jun 21 Python
python中pygame安装过程(超级详细)
Aug 04 Python
python实现拼接图片
Mar 23 Python
基于python实现把json数据转换成Excel表格
May 07 Python
Python实现简单猜数字游戏
Feb 03 Python
PyCharm配置KBEngine快速处理代码提示冲突、配置命令问题
Apr 03 Python
Python如何使用循环结构和分支结构
Apr 13 Python
opencv python 基于KNN的手写体识别的实例
Aug 03 #Python
Flask实现图片的上传、下载及展示示例代码
Aug 03 #Python
python使用opencv驱动摄像头的方法
Aug 03 #Python
python 简单照相机调用系统摄像头实现方法 pygame
Aug 03 #Python
Python判断字符串是否为字母或者数字(浮点数)的多种方法
Aug 03 #Python
OpenCV2从摄像头获取帧并写入视频文件的方法
Aug 03 #Python
python中copy()与deepcopy()的区别小结
Aug 03 #Python
You might like
优化php效率,提高php性能的一些方法
2011/03/24 PHP
PHP图片验证码制作实现分享(全)
2012/05/10 PHP
PHP扩展框架之Yaf框架的安装与使用
2016/05/18 PHP
CentOS系统中PHP安装扩展的方式汇总
2017/04/09 PHP
PHP children()函数讲解
2019/02/03 PHP
php中的依赖注入实例详解
2019/08/14 PHP
JAVASCRIPT IE 与 FF中兼容问题小结
2009/02/18 Javascript
JavaScript 密码强度判断代码
2009/09/05 Javascript
JavaScript聚焦于第一个字段的代码
2010/10/15 Javascript
jquery使用append(content)方法注意事项分享
2014/01/06 Javascript
jQuery实现点击小图显示大图代码分享
2015/08/25 Javascript
JS实现双击内容变为可编辑状态
2017/03/03 Javascript
微信小程序 实现动态显示和隐藏某个控件
2017/04/27 Javascript
浅析Vue.js中v-bind v-model的使用和区别
2018/12/04 Javascript
JS实现的小火箭发射动画效果示例
2018/12/08 Javascript
tweenjs缓动算法的使用实例分析
2019/08/26 Javascript
Vue使用自定义指令实现拖拽行为实例分析
2020/06/06 Javascript
详谈Vue.js框架下main.js,App.vue,page/index.vue之间的区别
2020/08/12 Javascript
基于原生JS封装的Modal对话框插件的示例代码
2020/09/09 Javascript
Vue封装Axios请求和拦截器的步骤
2020/09/16 Javascript
vuex页面刷新导致数据丢失的解决方案
2020/12/10 Vue.js
Pythont特殊语法filter,map,reduce,apply使用方法
2016/02/27 Python
Python解惑之整数比较详解
2017/04/24 Python
Python urls.py的三种配置写法实例详解
2017/04/28 Python
Python使用win32com实现的模拟浏览器功能示例
2017/07/13 Python
pytorch中获取模型input/output shape实例
2019/12/30 Python
Python属性和内建属性实例解析
2020/01/14 Python
python+opencv3.4.0 实现HOG+SVM行人检测的示例代码
2021/01/28 Python
科沃斯机器人官网商城:Ecovacs
2016/08/29 全球购物
Java程序员面试题
2016/09/27 面试题
中式婚礼主持词
2014/03/13 职场文书
中国入世承诺
2014/04/01 职场文书
2014年技术员工作总结
2014/11/18 职场文书
我们的节日元宵节活动总结
2015/02/06 职场文书
elementui的el-popover修改样式不生效的解决
2021/06/30 Javascript
Python可视化学习之seaborn绘制矩阵图详解
2022/02/24 Python