#

# This python script converts a sample of the notMNIST dataset into

# the same file format used by the MNIST dataset. If you have a program

# that uses the MNIST files, you can run this script over notMNIST to

# produce a new set of data files that should be compatible with

# your program.

#

# Instructions:

#

# 1) if you already have a MNIST data/ directory, rename it and create

# a new one

#

# $ mv data data.original_mnist

# $ mkdir convert_MNIST

#

# 2) Download and unpack the notMNIST data. This can take a long time

# because the notMNIST data set consists of ~500,000 files

#

# $ curl -o notMNIST_small.tar.gz http://yaroslavvb.com/upload/notMNIST/notMNIST_small.tar.gz

# $ curl -o notMNIST_large.tar.gz http://yaroslavvb.com/upload/notMNIST/notMNIST_large.tar.gz

# $ tar xzf notMNIST_small.tar.gz

# $ tar xzf notMNIST_large.tar.gz

#

# 3) Run this script to convert the data to MNIST files, then compress them.

# These commands will produce files of the same size as MNIST

# notMNIST is larger than MNIST, and you can increase the sizes if you want.

#

# $ python convert_to_mnist_format.py notMNIST_small test 1000

# $ python convert_to_mnist_format.py notMNIST_large train 6000

# $ gzip convert_MNIST/*ubyte

#

# 4) After update, we cancel output path and replace with 'train', 'test' or test ratio number,

# it not only work on 10 labels but more,

# it depends on your subdir number under target folder, you can input or not input more command

#

# Now we define input variable like following:

# $ python convert_to_mnist_format.py target_folder test_train_or_ratio data_number

#

# target_folder: must give minimal folder path to convert data

# test_train_or_ratio: must define 'test' or 'train' about this data,

# if you want seperate total data to test and train automatically,

# you can input one integer for test ratio,

# e.q. if you input 2, it mean 2% data will become test data

# data_number: if you input 0 or nothing, it convert total images under each label folder,

# e.q.

# a. python convert_to_mnist_format.py TS test 0

# b. python convert_to_mnist_format.py notMNIST_small test

# c. python convert_to_mnist_format.py TR train 0

# d. python convert_to_mnist_format.py notMNIST_small train

#

# Run this command in CMD

# `python convert_to_mnist_format.py TR train 0

# python convert_to_mnist_format.py TS test 0

import glob

import os

import random

import sys

import imageio

import numpy

height = 0

width = 0

dstPath = "convert_MNIST"

testLabelPath = dstPath+"/t10k-labels-idx1-ubyte"

testImagePath = dstPath+"/t10k-images-idx3-ubyte"

trainLabelPath = dstPath+"/train-labels-idx1-ubyte"

trainImagePath = dstPath+"/train-images-idx3-ubyte"

def get_subdir(folder):

return listDir

def get_labels_and_files(folder, number=0):

return labelsAndFiles

def make_arrays(labelsAndFiles, ratio):

return trainImagedata, trainLabeldata, testImagedata, testLabeldata

def write_labeldata(labeldata, outputfile):

f.write(labeldata.tobytes())

def write_imagedata(imagedata, outputfile):

f.write(imagedata.tobytes())

def main(argv):

write_imagedata(testImagedata, testImagePath)

if __name__ == '__main__':

main(sys.argv)