# -*- coding: UTF-8 -*-
def trans_to_txt(train_file, txt_file, index):
     
    with open(train_file, 'rb') as sf:
        with open(txt_file, "w") as wf:
            offset = 16 + (28*28*index)
            cur_pos = offset
            count = 28*28
            strlen = 1 
            out_count = 1
            while cur_pos < offset+count:
                sf.seek(cur_pos)
                data = sf.read(strlen)
                res = int(data[0])
        
                #雖然在數據集中像素是1-255表示顏色，這里簡化為Y
                if res > 0 :
                    wf.write(" Y ")
                else:
                    wf.write(" 0 ")

                #由于圖片是28列，因此在此進行換行
                if out_count % 28 == 0 :
                    wf.write("\n")

                cur_pos += strlen
                out_count += 1

trans_to_txt("../data/train-images.idx3-ubyte", "image.txt", 0)

# -*- coding: utf-8 -*-
import os
import struct
import numpy as np

# 讀取數據集，以二維數組的方式返回圖片信息和標簽信息
def load_mnist(path, kind='train'):
   # 從指定目錄加載數據集
    labels_path = os.path.join(path,
                               '%s-labels.idx1-ubyte'
                               % kind)
    images_path = os.path.join(path,
                               '%s-images.idx3-ubyte'
                               % kind)
    with open(labels_path, 'rb') as lbpath:
        magic, n = struct.unpack('>II',
                                 lbpath.read(8))
        labels = np.fromfile(lbpath,
                             dtype=np.uint8)

    with open(images_path, 'rb') as imgpath:
        #解析圖片信息，存儲在images中
        magic, num, rows, cols = struct.unpack('>IIII',
                                               imgpath.read(16))
        images = np.fromfile(imgpath,
                             dtype=np.uint8).reshape(len(labels), 784)

    return images, labels

# 在終端打印某個圖片的數據信息
def print_image(data, index):
    idx = 0;
    count = 0;
    for item in data[index]:
        if count % 28 == 0:
            print("")

        if item > 0:
            print("\033[7;31mY \033[0m", end="")
        else:
            print("0 ", end="")
        
        count += 1

def main():
    cur_path = os.getcwd()
    cur_path = os.path.join(cur_path, "..\data")
    imgs, labels = load_mnist(cur_path)
    print_image(imgs, 0)


if __name__ == "__main__":
    main()

def show_image(data, index):
    fig, ax = plt.subplots(nrows=1, ncols=1, sharex=True, sharey=True, )
        
    img = data[0].reshape(28, 28)
    ax.imshow(img, cmap='Greys', interpolation='nearest')

    ax.set_xticks([])
    ax.set_yticks([])
    plt.tight_layout()
    plt.show()

pip install matplotlib -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com