数字を分類するニューラルネットワークの実装をやってみる2-1


数字を分類するニューラルネットワークの実装をやってみるではWindows + Python 2.xの環境でしたが、ここではubuntu 16.04 LTS + Python 3.xの環境です。

オリジナルコードはPython 2.x用でしたので、Python 3.x用に書き換えて実行してみます。

GitHub

 

ディレクトリー構成はそのまま。

実行コードはmnist_loader.pyとnetwork.py。

2.x->3.xで変更する部分。

 

MNISTをロードするコード(mnist_loader.py)

import pickle as cPickle //変更

 

training_data, validation_data, test_data = cPickle.load(f,encoding=’latin1′) //encodeを追加

 

学習用のコード(network.py)

print関数

if test_data:
print (“Epoch {0}: {1} / {2}”.format(
j, self.evaluate(test_data), n_test)) //変更
else:
print (“Epoch {0} complete”.format(j)) //変更

len関数(zipに対してlenを適用….これでいけると思うんですが)

if test_data:

test_data = list(test_data) //追加
n_test = len(test_data)

training_data = list(training_data)//追加
n = len(training_data)

xrange

xrange -> range //変更

 


入力層784(28×28)・30世代(Epoch)・ミニバッチサイズ10・学習率η=3.0

で学習してみます。

srcディレクトリに入って、Pyhon3のシェルを起動

$python3

>>>import mnist_loader

>>>training_data, validation_data, test_data = mnist_loader.load_data_wrapper()

>>>import network

>>>net = network.Network([784, 30, 10])

>>>net.SGD(training_data, 30, 10, 3.0, test_data=test_data)

 

 

悪くないけど良くもない結果。

 


network.py

import random
import numpy as np

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:
            test_data = list(test_data) 
            n_test = len(test_data)
        training_data = list(training_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)

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

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

mnist_loader.py

import pickle as cPickle

import gzip

import numpy as np



def load_data():

    f = gzip.open('../data/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

 

Be the first to comment

Leave a Reply

Your email address will not be published.


*