training data 數據結構：

[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

將整個文件讀入：

filename = ‘train-images.idx3-ubyte‘
binfile = open(filename , ‘rb‘)
buf = binfile.read()

讀取頭四個32bit的interger:

index = 0
magic, numImages , numRows , numColumns = struct.unpack_from(‘>IIII‘ , buf , index)
index += struct.calcsize(‘>IIII‘)

讀取一個圖片，784=28*28 ：

im = struct.unpack_from(‘>784B‘ ,buf, index)
index += struct.calcsize(‘>784B‘)

im = np.array(im)
im = im.reshape(28,28)

fig = plt.figure()
plotwindow = fig.add_subplot(111)
plt.imshow(im , cmap=‘gray‘)
plt.show()

python讀取二進制mnist