MNIST数据集是ubyte格式存储的,现在转化为png格式:
训练集:
import numpy as np
import struct
from PIL import Image
import os
data_file = 'train-images-idx3-ubyte'
# It's 47040016B, but we should set to 47040000B
data_file_size = 47040016
data_file_size = str(data_file_size - 16) + 'B'
data_buf = open(data_file, 'rb').read()
magic, numImages, numRows, numColumns = struct.unpack_from(
'>IIII', data_buf, 0)
datas = struct.unpack_from(
'>' + data_file_size, data_buf, struct.calcsize('>IIII'))
datas = np.array(datas).astype(np.uint8).reshape(
numImages,