python实现两层神经网络识别手写数字体

第一部分是下载数据
第二部分常用函数
第三部分是神经网络类
第四部分主函数

# 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 math
import numpy as np

# 以下部分为下载数据集
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():  # 下载数据集
    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():  # 数据集预处理
    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)
            print("key ")
            print(dataset[key][5][5])
            dataset[key] /= 255.0
            print(dataset[key][5][5])
    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'])

# 以下内容为神经网络


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


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)
    return np.exp(x) / np.sum(np.exp(x))


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 numerical_gradient(f, x):
    h = 1e-4  # 0.0001
    grad = np.zeros_like(x)  # 初始化数组为0用来存放梯度
    # 默认情况下，nditer将视待迭代遍历的数组为只读对象（read-only）
    # 为了在遍历数组的同时，实现对数组元素值得修改，必须指定op_flags=['readwrite']模式。
    # flags=['multi_index']表示对x进行多重索引
    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
    while not it.finished:
        # 把元素的索引（it.multi_index）赋值给idx
        idx = it.multi_index
        # 用来还原值
        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


class TwoLayerNet:
    # 模型初始化
    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        # 初始化权重
        # 第一层的权重
        # 第一层的偏置
        # ##请添加网络第二层的权重和偏置的初始化代码
        # 第2层的权重
        # 第2层的偏置
        self.params = {'W1': weight_init_std * np.random.randn(input_size, hidden_size), 'b1': weight_init_std * np.random.randn(hidden_size),
                       'W2': weight_init_std * np.random.randn(hidden_size, output_size), 'b2': weight_init_std * np.random.randn(output_size)}
    # 模型前向传播过程

    def forward(self, x):
        # ##请从参数字典获取网络参数
        w1 = self.params['W1']
        w2 = self.params['W2']
        b1 = self.params['b1']
        b2 = self.params['b2']
        # 实现第一层的运算
        z1 = np.dot(x, w1) + b1
        h1 = sigmoid(z1)
        # ##请实现第二层的运算
        z2 = np.dot(h1, w2) + b2
        # z2 = sigmoid(z2)
        return z2
    # 定义损失函数

    def loss(self, x, t):  # x:输入数据, t:监督数据
        y = self.forward(x)
        z = softmax(y)
        los = cross_entropy_error(z, t)
        return los
    # ##请补充计算并返回损失函数值的代码
    # 计算预测的准确率

    def accuracy(self, x, t):  # 假定输入的数据x和标签t都是mini-batch形式的
        # ##请补充实现模型前向输出的代码
        y = self.forward(x)
        y = softmax(y)
        y = np.argmax(y, axis=1)
# ##请补充提取模型预测类别和标签真实类别的代码
        if t.ndim != 1: t = np.argmax(t, axis=1)
# ##请补充计算并返回模型类别预测准确率的代码
        acc = np.sum(y == t) / float(x.shape[0])
        print('result:')
        print(t)
        print(y)
        # print(x.shape[0])
        return acc
# 通过数值微分的方式计算模型参数的梯度
    '''def gradient(self, x, t):
        # 定义字典形式的参数梯度
        grads = {}

        # ##请定义需传入numerical_gradient函数的需求梯度的函数
        loss_W = lambda W: self.loss(x, t)
        # ##请补充通过数值微分的方法计算参数W1、W2、b1、b2的梯度的代码
        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'])

        # 返回计算出的梯度
        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 = (1.0 - sigmoid(a1)) * sigmoid(a1) * da1
        grads['W1'] = np.dot(x.T, dz1)
        grads['b1'] = np.sum(dz1, axis=0)

        return grads

    # 主函数


if __name__ == '__main__':
    init_mnist()
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True,normalize=True,one_hot_label=True)
# print(t_train[0])
print(t_test[0])
# ##请补充实例化TwoLayerNet类创建network对象的代码
network = TwoLayerNet(input_size=784, hidden_size=100, output_size=10)  # 在这里调整参数
# 定义训练循环迭代次数
iters_num = 1000
# 获取训练数据规模
train_size = x_train.shape[0]
# 定义训练批次大小
batch_size = 100
# 定义学习率
learning_rate = 0.1

# 创建记录模型训练损失值的列表
train_loss_list = []
# 创建记录模型在训练数据集上预测精度的列表
train_acc_list = []
# 创建记录模型在测试数据集上预测精度的列表
test_acc_list = []

# 计算一个epoch所需的训练迭代次数（一个epoch定义为所有训练数据都遍历过一次所需的迭代次数）
iter_per_epoch = max(train_size / batch_size, 1)
# print(train_size)
# ##请补充创建训练循环的代码
for i in range(int(iters_num)):
    for j in range(int(iter_per_epoch)):
        # 在每次训练迭代内部选择一个批次的数据
        batch_mask = np.random.choice(train_size, batch_size)
        x_batch = x_train[batch_mask]
        t_batch = t_train[batch_mask]

# ##请补充计算梯度的代码
        grad = network.gradient(x_batch, t_batch)
# ##请补充更新模型参数的代码
        for key in ('W1', 'b1', 'W2', 'b2'):  # 梯度更新
            network.params[key] -= learning_rate * grad[key]
# ##请补充向train_loss_list列表添加本轮迭代的模型损失值的代码
        loss = network.loss(x_batch, t_batch)
        train_loss_list.append(loss)

    # ##请补充向train_acc_list列表添加当前模型对于训练集预测精度的代码
    train_acc = network.accuracy(x_train, t_train)
    train_acc_list.append(train_acc)
    # ##请补充向test_acc_list列表添加当前模型对于测试集预测精度的代码
    test_acc = network.accuracy(x_test, t_test)
    test_acc_list.append(test_acc)
    # 输出一个epoch完成后模型分别在训练集和测试集上的预测精度以及损失值
    print("iteration:{} ,train acc:{}, test acc:{} ,loss:{}|".format(i, train_acc, test_acc, loss))