example/python-howto/data.py

# 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.

# pylint: skip-file
""" data iterator for mnist """
import sys
import os
# code to automatically download dataset
curr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))
sys.path.append(os.path.join(curr_path, "../../tests/python/common"))
import get_data
import mxnet as mx

def mnist_iterator(batch_size, input_shape):
    """return train and val iterators for mnist"""
    # download data
    get_data.GetMNIST_ubyte()
    flat = False if len(input_shape) == 3 else True

    train_dataiter = mx.io.MNISTIter(
        image="data/train-images-idx3-ubyte",
        label="data/train-labels-idx1-ubyte",
        input_shape=input_shape,
        batch_size=batch_size,
        shuffle=True,
        flat=flat)

    val_dataiter = mx.io.MNISTIter(
        image="data/t10k-images-idx3-ubyte",
        label="data/t10k-labels-idx1-ubyte",
        input_shape=input_shape,
        batch_size=batch_size,
        flat=flat)

    return (train_dataiter, val_dataiter)