【问题解决方案】Keras手写数字识别-ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接

参考：台大李宏毅老师视频课程-Keras-Demo

在载入数据阶段报错：

• ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接
  
  

Google之后找到一篇内容相近博文：手写数字识别---demo

问题解决步骤：

1-去官网下载了数据集：

• 数据集网址（宝可梦大师课程里也有提到过）：http://yann.lecun.com/exdb/mnist/
  

2-将下载好的数据集放在一定的位置

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

# 训练集文件
train_images_idx3_ubyte_file = 'C:\\Users\\小辉\\Desktop\\MNIST\\train-images.idx3-ubyte'
# 训练集标签文件
train_labels_idx1_ubyte_file = 'C:\\Users\\小辉\\Desktop\\MNIST\\train-labels.idx1-ubyte'

# 测试集文件
test_images_idx3_ubyte_file = 'C:\\Users\\小辉\\Desktop\\MNIST\\t10k-images.idx3-ubyte'
# 测试集标签文件
test_labels_idx1_ubyte_file = 'C:\\Users\\小辉\\Desktop\\MNIST\\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( train_images_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]
    32 bit integer  0x00000803(2051) magic number
    32 bit integer  60000            number of images
    32 bit integer  28               number of rows
    32 bit integer  28               number of columns
    unsigned byte   ??               pixel
    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]
    32 bit integer  0x00000801(2049) magic number (MSB first)
    32 bit integer  60000            number of items
    unsigned byte   ??               label
    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]
    32 bit integer  0x00000803(2051) magic number
    32 bit integer  10000            number of images
    32 bit integer  28               number of rows
    32 bit integer  28               number of columns
    unsigned byte   ??               pixel
    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]
    32 bit integer  0x00000801(2049) magic number (MSB first)
    32 bit integer  10000            number of items
    unsigned byte   ??               label
    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()

测试用的源码

END