下载mnist数据集的正确姿势

目录树结构：

.
├── dataset
│   └── mnist.py
└── main.py

 

dataset中包含了下载mnist数据的代码，下载的mnist数据以及缓存也会保存在这个文件中。

# 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()

 

main.py 中保存了实际使用的代码，第一次调用时会下载mnist数据。

from dataset.mnist import load_mnist

(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False)

print('训练集数据:', x_train.shape)     # 训练集数据 (6000, 784)
print('训练集标签:', t_train.shape)     # 训练集标签 (6000,)
print('测试集数据:', x_test.shape)      # 测试集数据 (1000, 784) 
print('测试集标签:', t_test.shape)      # 测试集标签 (1000,)


img = x_train[0]
label = t_train[0]
print('第一张图片的标签:', label)  # 5

 

提一个和MNIST识别相关的问题。直接使用该数据集做全连接识别，容易出现准确率一直是0.098的问题。

网上说有两种可能，

一种是需要对MNIST数据做正则化，也就是像素值除以255，

在代码中的体现就是：

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

另一种可能是softmax函数出现了0，导致交叉熵中 0*log(0) 梯度下降失效。

解决办法是： tf.clip_by_value(v, min, max)， 将v限制在min和max之间，一旦超出直接截断。

也就是：

在代码中：

y = tf.nn.softmax(tf.matmul(x, w) + b)
y = tf.clip_by_value(y, 1e-10, 1.0)
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))