dataset.py

# Copyright 2020 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.
# ============================================================================
"""
Produce the dataset
"""

import mindspore.dataset as ds
import mindspore.dataset.transforms.c_transforms as C
import mindspore.dataset.transforms.vision.c_transforms as CV
from mindspore.common import dtype as mstype
from .config import alexnet_cfg as cfg


def create_dataset_cifar10(data_path, batch_size=32, repeat_size=1, status="train"):
    """
    create dataset for train or test
    """
    cifar_ds = ds.Cifar10Dataset(data_path)
    rescale = 1.0 / 255.0
    shift = 0.0

    resize_op = CV.Resize((cfg.image_height, cfg.image_width))
    rescale_op = CV.Rescale(rescale, shift)
    normalize_op = CV.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
    if status == "train":
        random_crop_op = CV.RandomCrop([32, 32], [4, 4, 4, 4])
        random_horizontal_op = CV.RandomHorizontalFlip()
    channel_swap_op = CV.HWC2CHW()
    typecast_op = C.TypeCast(mstype.int32)
    cifar_ds = cifar_ds.map(input_columns="label", operations=typecast_op)
    if status == "train":
        cifar_ds = cifar_ds.map(input_columns="image", operations=random_crop_op)
        cifar_ds = cifar_ds.map(input_columns="image", operations=random_horizontal_op)
    cifar_ds = cifar_ds.map(input_columns="image", operations=resize_op)
    cifar_ds = cifar_ds.map(input_columns="image", operations=rescale_op)
    cifar_ds = cifar_ds.map(input_columns="image", operations=normalize_op)
    cifar_ds = cifar_ds.map(input_columns="image", operations=channel_swap_op)

    cifar_ds = cifar_ds.shuffle(buffer_size=cfg.buffer_size)
    cifar_ds = cifar_ds.batch(batch_size, drop_remainder=True)
    cifar_ds = cifar_ds.repeat(repeat_size)
    return cifar_ds