blob: 65acb0e28b15500b4942e03ff85b230aebdab09e [file] [log] [blame]
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
import os
import urllib.request
def check_exist_or_download(url):
download_dir = '/tmp/'
name = url.rsplit('/', 1)[-1]
filename = os.path.join(download_dir, name)
if not os.path.isfile(filename):
print("Downloading %s" % url)
urllib.request.urlretrieve(url, filename)
else:
print("Already Downloaded: %s" % url)
if __name__ == '__main__':
#url of the mnist dataset
train_x_url = 'http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz'
train_y_url = 'http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz'
valid_x_url = 'http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz'
valid_y_url = 'http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz'
#download the mnist dataset
check_exist_or_download(train_x_url)
check_exist_or_download(train_y_url)
check_exist_or_download(valid_x_url)
check_exist_or_download(valid_y_url)