data_processing.py

# Copyright 2019 Huawei Technologies Co., Ltd
#
# Licensed 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 mindspore.dataset as ds
import mindspore.dataset.transforms.vision.c_transforms as CV
import mindspore.dataset.transforms.c_transforms as C
from mindspore.dataset.transforms.vision import Inter
import mindspore.common.dtype as mstype


def generate_mnist_dataset(data_path, batch_size=32, repeat_size=1,
                           num_parallel_workers=1, sparse=True):
    """
    create dataset for training or testing
    """
    # define dataset
    ds1 = ds.MnistDataset(data_path)

    # define operation parameters
    resize_height, resize_width = 32, 32
    rescale = 1.0 / 255.0
    shift = 0.0

    # define map operations
    resize_op = CV.Resize((resize_height, resize_width),
                          interpolation=Inter.LINEAR)
    rescale_op = CV.Rescale(rescale, shift)
    hwc2chw_op = CV.HWC2CHW()
    type_cast_op = C.TypeCast(mstype.int32)

    # apply map operations on images
    if not sparse:
        one_hot_enco = C.OneHot(10)
        ds1 = ds1.map(input_columns="label", operations=one_hot_enco,
                      num_parallel_workers=num_parallel_workers)
        type_cast_op = C.TypeCast(mstype.float32)
    ds1 = ds1.map(input_columns="label", operations=type_cast_op,
                  num_parallel_workers=num_parallel_workers)
    ds1 = ds1.map(input_columns="image", operations=resize_op,
                  num_parallel_workers=num_parallel_workers)
    ds1 = ds1.map(input_columns="image", operations=rescale_op,
                  num_parallel_workers=num_parallel_workers)
    ds1 = ds1.map(input_columns="image", operations=hwc2chw_op,
                  num_parallel_workers=num_parallel_workers)

    # apply DatasetOps
    buffer_size = 10000
    ds1 = ds1.shuffle(buffer_size=buffer_size)
    ds1 = ds1.batch(batch_size, drop_remainder=True)
    ds1 = ds1.repeat(repeat_size)

    return ds1