MXNET笔记（二）准备数据

MXNET并不直接读入图像，而是读入其自定义的一种格式。为了生成这种格式，需要利用/mxnet/tools/im2rec.py工具来对数据库图像进行处理而生成。我现在手头没有现成的数据库可以使用，而现在一般的数据库又太大了，所以我把Rec格式的MNIST数据库还原成图像文件。

#利用mxnet提供的代码下载MNIST数据库
import numpy as np
import os
import urllib
import gzip
import struct
def download_data(url, force_download=True): 
    fname = url.split("/")[-1]
    if force_download or not os.path.exists(fname):
        urllib.urlretrieve(url, fname)
    return fname

def read_data(label_url, image_url):
    with gzip.open(download_data(label_url)) as flbl:
        magic, num = struct.unpack(">II", flbl.read(8))
        label = np.fromstring(flbl.read(), dtype=np.int8)
    with gzip.open(download_data(image_url), 'rb') as fimg:
        magic, num, rows, cols = struct.unpack(">IIII", fimg.read(16))
        image = np.fromstring(fimg.read(), dtype=np.uint8).reshape(len(label), rows, cols)
    return (label, image)

path='http://yann.lecun.com/exdb/mnist/'
(train_lbl, train_img) = read_data(
    path+'train-labels-idx1-ubyte.gz', path+'train-images-idx3-ubyte.gz')
(val_lbl, val_img) = read_data(
    path+'t10k-labels-idx1-ubyte.gz', path+'t10k-images-idx3-ubyte.gz'