神经网络代码识别手写字（python3.4.3版本）

神经网络代码如下：

#coding = utf-8"""network.py"""import random   import numpy as np  def sigmoid(z):       return 1.0/(1.0 + np.exp(-z))  def sigmoid_prime(z):      return sigmoid(z)*(1 - sigmoid(z))  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:])]      def feedforward(self, a):           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):          if test_data: n_test = len(test_data)          n = len(training_data)          for j in range(epochs):              random.shuffle(training_data)              mini_batches = [training_data[k:k+mini_batch_size] for k in range(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):           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):          nabla_b = [np.zeros(b.shape) for b in self.biases]          nabla_w = [np.zeros(w.shape) for w in self.weights]           activation = x          activations = [x]          zs = []         for b, w in zip(self.biases, self.weights):              z = np.dot(w, activation)+b              zs.append(z)              activation = sigmoid(z)              activations.append(activation)            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 range(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):            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 (output_activations-y)  

加载数据即代码：

import sysimport importlibimportlib.reload(sys)import pickleimport gzipimport numpy as npdef load_data():    f = gzip.open('/ysk/code/python/neural-networks-and-deep-learning/data/mnist.pkl.gz', 'rb')     #路径填写自己安放数据集的路径    training_data, validation_data, test_data = pickle.load(f, encoding = "iso-8859-1")     f.close()    return (training_data, validation_data, test_data)def load_data_wrapper():    tr_d, va_d, te_d = load_data()    #training_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_data    validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]    validation_data = zip(validation_inputs, va_d[1])    #test_data    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):    e = np.zeros((10, 1))    e[j] = 1.0    return e

终端执行的代码如下：

import mnist_loaderimport network,import randomimport numpy as nptraining_data, valid_data, test_data = mnist_loader.load_data_wrapper()net = network.Network([784, 30, 10])net.SGD(list(training_data), 30, 10, 3, test_data = list(test_data))

相对于最初python2版本的源码，python3代码除了几处模块名之外，数据集使用的时候不能直接使用元组，要利用list函数将元组转化为列表。

这是最初版本的代码，对参数的设置都是使用随机的方式，并且可以看出来，效果并不是太好，因为梯度下降会出现过度的现象．代码使用的代价函数为误差平方，这会导致运行的速度受斜率的影响，后面引入的交叉熵代价函数会改善此现象．总体能达到95%左右的正确率．