使用前馈神经网络对mnist数据进行学习-基于深入浅出深度学习中的例子

基于深入浅出深度学习中的例子，将书上代码改为python3实现，并提高了一些效率（可能）

首先加载数据，数据来源于书本github

import pickle as cPickle 
import gzip 


import numpy as np 
def load_data(): 
    f = gzip.open('mnist.pkl.gz', 'rb') 
    training_data, validation_data, test_data = cPickle.load(f,encoding='latin1') 
    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) 
    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): 
    e = np.zeros((10, 1)) 
    e[j] = 1.0 
    return e 

前馈神经网络

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_n_backprop(self,x,y=None,isforwardonly=True):
        a=x
        if isforwardonly:
            for w,b in zip(self.weights,self.biases):
                a=sigmoid(np.dot(w,a)+b)
            return a
        else:
            activations=[a]
            zs=[]
            for w,b in zip(self.weights,self.biases):
                a=np.dot(w,a)+b
                zs.append(a)
                a=sigmoid(a)
                activations.append(a)
            delta=((activations[-1]-y))*sigmoid_prime(zs[-1])
            nabla_b=[np.zeros_like(b) for b in self.biases]
            nabla_w=[np.zeros_like(w) for w in self.weights]
            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 SGD(self, training_data, epochs, mini_batch_size, eta,
            test_data=None):
        if test_data:
            test_data=list(test_data)
            n_test = len(test_data)
            print(n_test)
        traindata=list(training_data)
        n=len(traindata)
        for j in range(epochs):
            mini_batches = [
                traindata[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_like(b) for b in self.biases]
        nabla_w = [np.zeros_like(w) for w in self.weights]
        for x, y in mini_batch:
            delta_nabla_b, delta_nabla_w = self.feedforward_n_backprop(x, y,False)
            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 evaluate(self, test_data):
        test_results = [(np.argmax(self.feedforward_n_backprop(x)),y) for (x, y) in test_data]
        return sum(int(x == y) for (x, y) in test_results)
        
          
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))

实例：

train_data,validate_data,test_data = load_data_wrapper()
net=Network([784,30,10])
net.SGD(train_data, 30, 10, 3.0, test_data=test_data)

运行结果：

10000 Epoch 0: 9079 / 10000 Epoch 1: 9277 / 10000 Epoch 2: 9316 / 10000 Epoch 3: 9340 / 10000 Epoch 4: 9367 / 10000 Epoch 5: 9384 / 10000 Epoch 6: 9382 / 10000 Epoch 7: 9421 / 10000 Epoch 8: 9437 / 10000 Epoch 9: 9441 / 10000