Michael Nielsen神经网络（1）

本例使用了sigmoid函数和二次代价函数，以下是对原代码进行注释。

mnist数据集导入

"""
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

神经网络代码：

# -- coding: utf-8 --
import numpy as np
import random
import mnist_loader


# network类
class Network(object):

    # 初始化
    def __init__(self, sizes):
        self.num_layers = len(sizes)
        self.sizes = sizes
        # 产生符合（0,1）正态分布的随机数，括号里参数为矩阵的维度
        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):
        # 当a为输入时，返回神经网络的输出
        # zip使元素一一对应
        for b, w in zip(self.biases, self.weights):
            a = sigmoid(np.dot(w, a)+b)
        return a

    def stochastic_gradient_descent(self, training_data, epochs, mini_batch_size, eta, test_data=None):
        # training_data是一个(x, y)元组的列表，epochs迭代期数量， mini_batch_size采样时小批量数据的大小，eta学习率
        # 如果给出了可选参数test_data，程序会在每个训练器后评估网络，并打印出部分进展
        if test_data: n_test = len(test_data)
        n = len(training_data)
        # xrange是个迭代器，元素逐个被创建,迭代epochs次
        for j in xrange(epochs):
            # 将元素打乱
            random.shuffle(training_data)
            # 将整个训练集分成适当多个小批量数据集
            mini_batches = [
                training_data[k:k+mini_batch_size]
                for k in xrange(0, n, mini_batch_size)]
            # 每一个小批量数据更新一次参数
            for mini_batch in mini_batches:
                self.update_mini_batch(mini_batch, eta)
            # format字符串格式化{0}，{1}，{2}是后面的索引
            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):
        # 使用反向传播用梯度下降法更新w，b
        # nabla_b，nabla_w即用于存放梯度对参数偏导总的变化值的量
        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:
            # 反向传播
            delta_nabla_b, delta_nabla_w = self.backprop(x, y)
            # 累加各个样本的梯度变化
            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)]
        # 参数更新
        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):

        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        # 前向传播
        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)
        # 反向传播
        delta = self.cost_derivative(activations[-1], y) * sigmoid_prime(zs[-1])
        nabla_b[-1] = delta
        nabla_w[-1] = np.dot(delta, activations[-2].transpose())

        for l in xrange(2, self.num_layers):
            z = zs[-l]
            sp = sigmoid_prime(z)
            # transpose是转置
            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):
        # 返回self.feedforward中最大的结果，即对应的数字
        test_results = [(np.argmax(self.feedforward(x)), y)
                        for (x, y) in test_data]
        # 计算正确输出数目
        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)


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


# sigmoid函数的导数
def sigmoid_prime(z):
    return sigmoid(z) * (1 - sigmoid(z))

# 导入mnist数据，训练集，验证集，测试集
training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
# 初始化神经网络
net = Network([784, 30, 10])
# 迭代次数30次数，小批量数据大小为10，学习率为3
net.stochastic_gradient_descent(training_data, 30, 10, 3.0, test_data=test_data)

输出结果：