Python Read mnist

Python Read mnist

That's actually how Python reads binnary file.

The structure of the mnist is as follows, select Train-images

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

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

That is, we were going to read the 4-bit integer

Tried a lot of ways, feel the most convenient, at least for me or use

Struct.unpack_from ()

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

Read the files in binary mode first

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

Then use the Struc.unpack_from

' >IIII ' is said to use the big-endian method to read 4 unsinged int32

Then read a picture to test whether the read was successful

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()

' >784b ' means reading 784 unsigned byte with the big-endian method.

The complete code is as follows

importnumpy as npimportstructimportmatplotlib.pyplot as pltfilename =‘train-images.idx3-ubyte‘binfile =open(filename , ‘rb‘)buf =binfile.read()index =0magic, numImages , numRows , numColumns =struct.unpack_from(‘>IIII‘, buf , index)index += struct.calcsize(‘>IIII‘)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()

Just to test whether it was successful, so I read only one picture.

Bright should be read right ha ...

Python Read mnist