keras实现手写数字识别第一步:Python3解析MNIST数据集(IDX文件格式)

按李宏毅机器学习课程中所讲

(x_train,y_train),(x_test,y_test)=mnist.load_data()

运行了好久之后报错:

[WinError 10054] 远程主机强迫关闭了一个现有的连接

于是去官网下载数据集,自行解析。http://yann.lecun.com/exdb/mnist/ 该数据下载后得到的是idx格式数据,具体处理方法如下:

1.下载并解压数据集

keras实现手写数字识别第一步:Python3解析MNIST数据集(IDX文件格式)
解压后:
keras实现手写数字识别第一步:Python3解析MNIST数据集(IDX文件格式)

2.数据解析

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

# 训练集文件
train_images_idx3_ubyte_file = 'train-images.idx3-ubyte'
# 训练集标签文件
train_labels_idx1_ubyte_file = 'train-labels.idx1-ubyte'
# 测试集文件
test_images_idx3_ubyte_file = 't10k-images.idx3-ubyte'
# 测试集标签文件
test_labels_idx1_ubyte_file = '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'
    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)
    fmt_image = '>' + str(image_size) + 'B'
    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


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()
    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()

代码原博客地址https://www.jianshu.com/p/84f72791806f

3.解析结果

魔数:2051, 图片数量: 60000张, 图片大小: 28*28
已解析 10000张
已解析 20000张
已解析 30000张
已解析 40000张
已解析 50000张
已解析 60000张
魔数:2049, 图片数量: 60000张
已解析 10000张
已解析 20000张
已解析 30000张
已解析 40000张
已解析 50000张
已解析 60000张
5.0
0.0
4.0
1.0
9.0
2.0
1.0
3.0
1.0
4.0
done
上一篇:linux下几种压缩、解压缩方法


下一篇:linux – 从unix中的.gz日志文件中提取值