手写数字识别的神经网络学习（梯度下降法）

手写数字识别的神经网络学习（梯度下降法）

步骤1（mini-batch）
从训练数据中随机选择一部分数据，称为mini-batch
步骤2（计算梯度）
减少mini-batch的损失函数的值，求各个权重的梯度
步骤3（更新参数）
沿梯度方向进行更新
步骤4（重复，迭代）
重复1，2，3

functions.py代码如下

# coding: utf-8
import numpy as np


def identity_function(x):
    return x


def step_function(x):
    return np.array(x > 0, dtype=np.int)


def sigmoid(x):
    return 1 / (1 + np.exp(-x))    


def sigmoid_grad(x):
    return (1.0 - sigmoid(x)) * sigmoid(x)
    

def relu(x):
    return np.maximum(0, x)


def relu_grad(x):
    grad = np.zeros(x)
    grad[x>=0] = 1
    return grad
    

def softmax(x):
    if x.ndim == 2:
        x = x.T
        x = x - np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T 

    x = x - np.max(x) # 溢出对策
    return np.exp(x) / np.sum(np.exp(x))


def mean_squared_error(y, t):
    return 0.5 * np.sum((y-t)**2)


def cross_entropy_error(y, t):
    if y.ndim == 1:
        t = t.reshape(1, t.size)
        y = y.reshape(1, y.size)
        
    # 监督数据是one-hot-vector的情况下，转换为正确解标签的索引
    if t.size == y.size:
        t = t.argmax(axis=1)
             
    batch_size = y.shape[0]
    return -np.sum(np.log(y[np.arange(batch_size), t] + 1e-7)) / batch_size


def softmax_loss(X, t):
    y = softmax(X)
    return cross_entropy_error(y, t)

gradient.py代码如下

# coding: utf-8
import numpy as np


def _numerical_gradient_1d(f, x):
    h = 1e-4  # 0.0001
    grad = np.zeros_like(x)

    for idx in range(x.size):
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x)  # f(x+h)

        x[idx] = tmp_val - h
        fxh2 = f(x)  # f(x-h)
        grad[idx] = (fxh1 - fxh2) / (2 * h)

        x[idx] = tmp_val  # 还原值

    return grad


def numerical_gradient_2d(f, X):
    if X.ndim == 1:
        return _numerical_gradient_1d(f, X)
    else:
        grad = np.zeros_like(X)

        for idx, x in enumerate(X):
            grad[idx] = _numerical_gradient_1d(f, x)

        return grad


def numerical_gradient(f, x):
    h = 1e-4  # 0.0001
    grad = np.zeros_like(x)

    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
    while not it.finished:
        idx = it.multi_index
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x)  # f(x+h)

        x[idx] = tmp_val - h
        fxh2 = f(x)  # f(x-h)
        grad[idx] = (fxh1 - fxh2) / (2 * h)

        x[idx] = tmp_val  # 还原值
        it.iternext()

    return grad

two_layer_net.py代码如下

# coding: utf-8
import sys, os

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
from functions import *
from gradient import numerical_gradient


class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        # 初始化权重
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)

    def predict(self, x):
        W1, W2 = self.params['W1'], self.params['W2']
        b1, b2 = self.params['b1'], self.params['b2']

        a1 = np.dot(x, W1) + b1
        z1 = sigmoid(a1)
        a2 = np.dot(z1, W2) + b2
        y = softmax(a2)

        return y

    # x:输入数据, t:监督数据
    def loss(self, x, t):
        y = self.predict(x)

        return cross_entropy_error(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)  # axis=1取每行的,最大值的索引
        t = np.argmax(t, axis=1)

        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy

    # x:输入数据, t:监督数据
    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x, t)

        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])

        return grads

    def gradient(self, x, t):
        W1, W2 = self.params['W1'], self.params['W2']
        b1, b2 = self.params['b1'], self.params['b2']
        grads = {}

        batch_num = x.shape[0]

        # forward
        a1 = np.dot(x, W1) + b1
        z1 = sigmoid(a1)
        a2 = np.dot(z1, W2) + b2
        y = softmax(a2)

        # backward
        dy = (y - t) / batch_num
        grads['W2'] = np.dot(z1.T, dy)
        grads['b2'] = np.sum(dy, axis=0)

        da1 = np.dot(dy, W2.T)
        dz1 = sigmoid_grad(a1) * da1
        grads['W1'] = np.dot(x.T, dz1)
        grads['b1'] = np.sum(dz1, axis=0)

        return grads

TwolayerNet类中使用的变量

变量	说明
params	保存神经网络的参数的字典型变量。params[‘W1’]是第1层的权重，params[‘b1’]是第1层的偏置，params[‘W2’]是第2层的权重，params[‘b2’]是第2层的偏置。
grads	保存梯度的字典型变量（numerical_gradient()方法的返回值。grads[‘W1’]是第一层权重的梯度，grads[‘b1’]是第一层偏置的梯度，grads[‘W2’]是第二层权重的梯度，grads[‘b1’]是第二层偏置的梯度。

TwoLayerNet类的方法

方法	说明
init(self , input_size, hidden_size , output_size)	进行初始化，输入层的神经元个数，隐藏层数，输出层数
predict(self , x)	进行识别，x为图像输入数据
loss(self , x, t)	计算损失函数的值。x为输入数据，t为期望数据（正确解标签）
accuracy(self , x, t)	计算识别精度
numerical_gradient(self , x, t)	计算权重的梯度（数值微分）

init(self , input_size, hidden_size , output_size) 方法，类的初始化。手写数字识别时，输入图像的大小是28 X 28 = 784,输出就是0到9,10个数字，所以input_size=784,output_size=10,hidden_size设置一个合适的值，这里我们设置为50。
先用高斯分布的随机数进行权重的初始化，偏置使用0进行初始化。
loss(self , x, t) 计算交叉熵误差
numerical_gradient(self , x, t) 根据数值微分，计算各个参数相对于损失函数的梯度。

手写数字识别的mini-batch的实现

mnist.py代码如下

# coding: utf-8
try:
    import urllib.request
except ImportError:
    raise ImportError('You should use Python 3.x')
import os.path
import gzip
import pickle
import os
import numpy as np

url_base = 'http://yann.lecun.com/exdb/mnist/'
key_file = {
    'train_img': 'train-images-idx3-ubyte.gz',
    'train_label': 'train-labels-idx1-ubyte.gz',
    'test_img': 't10k-images-idx3-ubyte.gz',
    'test_label': 't10k-labels-idx1-ubyte.gz'
}

dataset_dir = os.path.dirname(os.path.abspath(__file__))
save_file = dataset_dir + "/mnist.pkl"

train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784


def _download(file_name):
    file_path = dataset_dir + "/" + file_name

    if os.path.exists(file_path):
        return

    print("Downloading " + file_name + " ... ")
    urllib.request.urlretrieve(url_base + file_name, file_path)
    print("Done")


def download_mnist():
    for v in key_file.values():
        _download(v)


def _load_label(file_name):
    file_path = dataset_dir + "/" + file_name

    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
        labels = np.frombuffer(f.read(), np.uint8, offset=8)
    print("Done")

    return labels


def _load_img(file_name):
    file_path = dataset_dir + "/" + file_name

    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
        data = np.frombuffer(f.read(), np.uint8, offset=16)
    data = data.reshape(-1, img_size)
    print("Done")

    return data


def _convert_numpy():
    dataset = {}
    dataset['train_img'] = _load_img(key_file['train_img'])
    dataset['train_label'] = _load_label(key_file['train_label'])
    dataset['test_img'] = _load_img(key_file['test_img'])
    dataset['test_label'] = _load_label(key_file['test_label'])

    return dataset


def init_mnist():
    download_mnist()
    dataset = _convert_numpy()
    print("Creating pickle file ...")
    with open(save_file, 'wb') as f:
        pickle.dump(dataset, f, -1)
    print("Done!")


def _change_one_hot_label(X):
    T = np.zeros((X.size, 10))
    for idx, row in enumerate(T):
        row[X[idx]] = 1

    return T


def load_mnist(normalize=True, flatten=True, one_hot_label=False):
    """读入MNIST数据集
    
    Parameters
    ----------
    normalize : 将图像的像素值正规化为0.0~1.0
    one_hot_label : 
        one_hot_label为True的情况下，标签作为one-hot数组返回
        one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
    flatten : 是否将图像展开为一维数组
    
    Returns
    -------
    (训练图像, 训练标签), (测试图像, 测试标签)
    """
    if not os.path.exists(save_file):
        init_mnist()

    with open(save_file, 'rb') as f:
        dataset = pickle.load(f)

    if normalize:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].astype(np.float32)
            dataset[key] /= 255.0

    if one_hot_label:
        dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
        dataset['test_label'] = _change_one_hot_label(dataset['test_label'])

    if not flatten:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].reshape(-1, 1, 28, 28)

    return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label'])


if __name__ == '__main__':
    init_mnist()

train.py代码如下

# coding: utf-8
import sys, os

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
import matplotlib.pyplot as plt
from mnist import load_mnist
from two_layer_net import TwoLayerNet

# 读入数据
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

iters_num = 10000  # 适当设定循环的次数
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1

train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)  # train_size = 60000,batch_size = 100,iter_per_epoch = 600

for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    # 计算梯度
    # grad = network.numerical_gradient(x_batch, t_batch  #  数值微分计算梯度
    grad = network.gradient(x_batch, t_batch)  # 误差反向传播计算梯度

    # 更新参数
    for key in ('W1', 'b1', 'W2', 'b2'):
        network.params[key] -= learning_rate * grad[key]

    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)

    if i % iter_per_epoch == 0:  # 10000/600约等于16次
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)
        print("train acc, test acc | " + str(train_acc) + ", " + str(test_acc))

# 绘制loss函数推移的图像
t1 = np.arange(len(train_loss_list))
plt.plot(t1, train_loss_list)
plt.xlabel("iteration")
plt.ylabel("loss")
plt.ylim(0, 5)
plt.show()

# 绘制识别精度的推移图形
markers = {'train': 'o', 'test': 's'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, label='train acc')
plt.plot(x, test_acc_list, label='test acc', linestyle='--')
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

最后结果为

train acc = 0.9782333333333333 
test acc = 0.9705

mini-batch的大小是100，每次从60000个训练数据中随机取出100个数据（图像数据和正确的标签数据），对这100组数据求梯度，使用随机梯度下降法（SGD）更新参数，梯度法迭代次数是10000次，每更新一次，都对训练数据计算损失函数的值，并把该值放到数据中，然后用图像表示这个损失函数的值的推移，如下

精度的推移图像如下

图中，随着学习的进行，发现训练数据和测试数据的精度都提高了。实线与虚线重合，说明这两个的识别精度基本没有发生变化，所以这次学习没有发生过拟合的现象。

有用请点个赞！！
本站所有文章均为原创，欢迎转载，请注明文章出处：https://blog.csdn.net/weixin_45092662。百度和各类采集站皆不可信，搜索请谨慎鉴别。技术类文章一般都有时效性，本人习惯不定期对自己的博文进行修正和更新，因此请访问出处以查看本文的最新版本。