BP神经网络识别手写字体

摘自于《神经网络与深度学习》

mnist_loader.py

#coding:utf-8
import cPickle
import gzip
import numpy as np

def load_data():
    f = gzip.open("F:/neuralnetwork/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():
    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)
    vadiation_inputs = [np.reshape(x, (784,1)) for x in va_d[0]]
    validation_data = zip(vadiation_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):
    e = np.zeros((10, 1))
    e[j] = 1.0
    return e

neuralnetwork_sample1.py

#coding:utf-8
'''
    神经网络识别手写字体
'''
import random
import numpy as np

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

def sigmoid_prime(z):
    return sigmoid(z)*(1-sigmoid(z))

class Network(object):
    '''
        神经网络
    '''
    
    def __init__(self, sizes):
        self.num_layers = len(sizes)
        self.sizes = sizes
        self.bias = [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.bias, 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 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):
        nabla_b = [np.zeros(b.shape) for b in self.bias]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        for x,y in mini_batch:
            delta_nabla_b,delta_nabla_w = self.backdrop(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.bias = [
            b - (eta/len(mini_batch))*nb
            for b,nb in zip(self.bias, nabla_b)
            ]

    def backdrop(self, x, y):
        nabla_b = [np.zeros(b.shape) for b in self.bias]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        activation = x 
        activations = [x]
        zs = []
        for b,w in zip(self.bias, 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 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):
        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)

if __name__ == '__main__':
    network = Network([2, 3, 1])
    

执行效果如下：

即10000个测试数据，识别准确的大概第五轮迭代时就超过90%的准确率了。

使用的数据集为MNIST手写字体数据集，下载地址为：mnist数据集