Spaces:
Sleeping
Sleeping
File size: 1,600 Bytes
5d923de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
import numpy as np
import cv2
import os
import struct
def trans(image, label, save):
if 'train' in os.path.basename(image):
prefix = 'train'
else:
prefix = 'test'
labelIndex = 0
imageIndex = 0
i = 0
lbdata = open(label, 'rb').read()
magic, nums = struct.unpack_from(">II", lbdata, labelIndex)
labelIndex += struct.calcsize('>II')
imgdata = open(image, "rb").read()
magic, nums, numRows, numColumns = struct.unpack_from('>IIII', imgdata, imageIndex)
imageIndex += struct.calcsize('>IIII')
for i in range(nums):
label = struct.unpack_from('>B', lbdata, labelIndex)[0]
labelIndex += struct.calcsize('>B')
im = struct.unpack_from('>784B', imgdata, imageIndex)
imageIndex += struct.calcsize('>784B')
im = np.array(im, dtype='uint8')
img = im.reshape(28, 28)
save_name = os.path.join(save, '{}_{}_{}.jpg'.format(prefix, i, label))
cv2.imwrite(save_name, img)
if __name__ == '__main__':
path = './origin_data'
train_images = f'{path}/train-images-idx3-ubyte'
train_labels = f'{path}/train-labels-idx1-ubyte'
test_images =f'{path}/t10k-images-idx3-ubyte'
test_labels = f'{path}/t10k-labels-idx1-ubyte'
save_train =f'{path}/MNIST_data/train_images/'
save_test =f'{path}/MNIST_data/test_images/'
if not os.path.exists(save_train):
os.makedirs(save_train)
if not os.path.exists(save_test):
os.makedirs(save_test)
trans(test_images, test_labels, save_test)
trans(train_images, train_labels, save_train) |