python读取MNIST数据集

在学习ufldl课程时需要用到MNIST数据集，主页在这里。但由于该数据集为IDX文件格式，是一种用来存储向量与多维度矩阵的文件格式，不能直接读取。

mnist的结构如下

TRAINING SET LABEL FILE (train-labels-idx1-ubyte):

[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000801(2049) magic number (MSB first) 
0004     32 bit integer  60000            number of items 
0008     unsigned byte   ??               label 
0009     unsigned byte   ??               label 
........ 
xxxx     unsigned byte   ??               label
The labels values are 0 to 9.

TRAINING SET IMAGE FILE (train-images-idx3-ubyte):

[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000803(2051) magic number 
0004     32 bit integer  60000            number of images 
0008     32 bit integer  28               number of rows 
0012     32 bit integer  28               number of columns 
0016     unsigned byte   ??               pixel 
0017     unsigned byte   ??               pixel 
........ 
xxxx     unsigned byte   ??               pixel

Label File

先是一个32位的整形 表示的是Magic Number，这是用来标示文件格式的用的。一般默认不变。2049。第二是图片的的数量。
接下来就是一次排列图片的标示Label

Image File

也是Magic Number。同上。保持不变2051。接下来依次是
图片的数量，图片的高，图片的宽，图片的像素点[灰度 256位]。

---

因此想要读出数据集的图片矩阵和标签的话，需要先读出Magic Number等数据。代码如下：

# encoding: utf-8
"""
对MNIST手写数字数据文件转换为bmp图片文件格式。
数据集下载地址为http://yann.lecun.com/exdb/mnist。
相关格式转换见官网以及代码注释。
"""

import numpy as np
import struct
import matplotlib.pyplot as plt

# 训练集文件
train_images_idx3_ubyte_file = 'E:/important_dataset/train-images.idx3-ubyte'
# 训练集标签文件
train_labels_idx1_ubyte_file = 'E:/important_dataset/train-labels.idx1-ubyte'

# 测试集文件
test_images_idx3_ubyte_file = 'E:/important_dataset/t10k-images.idx3-ubyte'
# 测试集标签文件
test_labels_idx1_ubyte_file = 'E:/important_dataset/t10k-labels.idx1-ubyte'


def decode_idx3_ubyte(idx3_ubyte_file):
    """
    解析idx3文件的通用函数
    :param idx3_ubyte_file: idx3文件路径
    :return: 数据集
    """
    # 读取二进制数据
    bin_data = open(idx3_ubyte_file, 'rb').read()

    # 解析文件头信息，依次为魔数、图片数量、每张图片高、每张图片宽
    offset = 0
    fmt_header = '>iiii'   #'>IIII'是说使用大端法读取4个unsinged int32
    magic_number, num_images, num_rows, num_cols = struct.unpack_from(fmt_header, bin_data, offset)
    print '魔数:%d, 图片数量: %d张, 图片大小: %d*%d' % (magic_number, num_images, num_rows, num_cols)

    # 解析数据集
    image_size = num_rows * num_cols
    offset += struct.calcsize(fmt_header)
    print("offset: ",offset)
    fmt_image = '>' + str(image_size) + 'B'   # '>784B'的意思就是用大端法读取784个unsigned byte
    images = np.empty((num_images, num_rows*num_cols))
    for i in range(num_images):
        if (i + 1) % 10000 == 0:
            print '已解析 %d' % (i + 1) + '张'
        images[i] = np.array(struct.unpack_from(fmt_image, bin_data, offset)).reshape((num_rows*num_cols))
        offset += struct.calcsize(fmt_image)
    return images.T


def decode_idx1_ubyte(idx1_ubyte_file):
    """
    解析idx1文件的通用函数
    :param idx1_ubyte_file: idx1文件路径
    :return: 数据集
    """
    # 读取二进制数据
    bin_data = open(idx1_ubyte_file, 'rb').read()

    # 解析文件头信息，依次为魔数和标签数
    offset = 0
    fmt_header = '>ii'
    magic_number, num_images = struct.unpack_from(fmt_header, bin_data, offset)
    print '魔数:%d, 图片数量: %d张' % (magic_number, num_images)

    # 解析数据集
    offset += struct.calcsize(fmt_header)
    fmt_image = '>B'
    labels = np.empty(num_images)
    for i in range(num_images):
        if (i + 1) % 10000 == 0:
            print '已解析 %d' % (i + 1) + '张'
        labels[i] = struct.unpack_from(fmt_image, bin_data, offset)[0]
        offset += struct.calcsize(fmt_image)
    return labels


def load_train_images(idx_ubyte_file=train_images_idx3_ubyte_file):
    """
    TRAINING SET IMAGE FILE (train-images-idx3-ubyte):
    [offset] [type]          [value]          [description]
    0000     32 bit integer  0x00000803(2051) magic number
    0004     32 bit integer  60000            number of images
    0008     32 bit integer  28               number of rows
    0012     32 bit integer  28               number of columns
    0016     unsigned byte   ??               pixel
    0017     unsigned byte   ??               pixel
    ........
    xxxx     unsigned byte   ??               pixel
    Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).

    :param idx_ubyte_file: idx文件路径
    :return: n*row*col维np.array对象，n为图片数量
    """
    return decode_idx3_ubyte(idx_ubyte_file)


def load_train_labels(idx_ubyte_file=train_labels_idx1_ubyte_file):
    """
    TRAINING SET LABEL FILE (train-labels-idx1-ubyte):
    [offset] [type]          [value]          [description]
    0000     32 bit integer  0x00000801(2049) magic number (MSB first)
    0004     32 bit integer  60000            number of items
    0008     unsigned byte   ??               label
    0009     unsigned byte   ??               label
    ........
    xxxx     unsigned byte   ??               label
    The labels values are 0 to 9.

    :param idx_ubyte_file: idx文件路径
    :return: n*1维np.array对象，n为图片数量
    """
    return decode_idx1_ubyte(idx_ubyte_file)


def load_test_images(idx_ubyte_file=test_images_idx3_ubyte_file):
    """
    TEST SET IMAGE FILE (t10k-images-idx3-ubyte):
    [offset] [type]          [value]          [description]
    0000     32 bit integer  0x00000803(2051) magic number
    0004     32 bit integer  10000            number of images
    0008     32 bit integer  28               number of rows
    0012     32 bit integer  28               number of columns
    0016     unsigned byte   ??               pixel
    0017     unsigned byte   ??               pixel
    ........
    xxxx     unsigned byte   ??               pixel
    Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).

    :param idx_ubyte_file: idx文件路径
    :return: n*row*col维np.array对象，n为图片数量
    """
    return decode_idx3_ubyte(idx_ubyte_file)


def load_test_labels(idx_ubyte_file=test_labels_idx1_ubyte_file):
    """
    TEST SET LABEL FILE (t10k-labels-idx1-ubyte):
    [offset] [type]          [value]          [description]
    0000     32 bit integer  0x00000801(2049) magic number (MSB first)
    0004     32 bit integer  10000            number of items
    0008     unsigned byte   ??               label
    0009     unsigned byte   ??               label
    ........
    xxxx     unsigned byte   ??               label
    The labels values are 0 to 9.

    :param idx_ubyte_file: idx文件路径
    :return: n*1维np.array对象，n为图片数量
    """
    return decode_idx1_ubyte(idx_ubyte_file)




def run():
    train_images = load_train_images() #(num_rows*num_cols,num_images)
    train_labels = load_train_labels()
    # test_images = load_test_images()
    # test_labels = load_test_labels()

    # 查看前十个数据及其标签以读取是否正确
    for i in range(10):
        print train_labels[i]
        #plt.imshow(train_images[i], cmap='gray')
        #plt.show()
    print 'done'

if __name__ == '__main__':
    run()