mindspore/example/resnet50_cifar10/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.
# ============================================================================
"""
create train or eval dataset.
"""
import os
import mindspore.common.dtype as mstype
import mindspore.dataset.engine as de
import mindspore.dataset.transforms.vision.c_transforms as C
import mindspore.dataset.transforms.c_transforms as C2
from mindspore.communication.management import init, get_rank, get_group_size
from config import config


def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32, target="Ascend"):
    """
    create a train or eval dataset

    Args:
        dataset_path(string): the path of dataset.
        do_train(bool): whether dataset is used for train or eval.
        repeat_num(int): the repeat times of dataset. Default: 1
        batch_size(int): the batch size of dataset. Default: 32
        target(str): the device target. Default: Ascend

    Returns:
        dataset
    """
    if target == "Ascend":
        device_num = int(os.getenv("DEVICE_NUM"))
        rank_id = int(os.getenv("RANK_ID"))
    else:
        init("nccl")
        rank_id = get_rank()
        device_num = get_group_size()

    if device_num == 1:
        ds = de.Cifar10Dataset(dataset_path, num_parallel_workers=8, shuffle=True)
    else:
        ds = de.Cifar10Dataset(dataset_path, num_parallel_workers=8, shuffle=True,
                               num_shards=device_num, shard_id=rank_id)

    # define map operations
    trans = []
    if do_train:
        trans += [
            C.RandomCrop((32, 32), (4, 4, 4, 4)),
            C.RandomHorizontalFlip(prob=0.5)
        ]

    trans += [
        C.Resize((config.image_height, config.image_width)),
        C.Rescale(1.0 / 255.0, 0.0),
        C.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
        C.HWC2CHW()
    ]

    type_cast_op = C2.TypeCast(mstype.int32)

    ds = ds.map(input_columns="label", num_parallel_workers=8, operations=type_cast_op)
    ds = ds.map(input_columns="image", num_parallel_workers=8, operations=trans)

    # apply batch operations
    ds = ds.batch(batch_size, drop_remainder=True)

    # apply dataset repeat operation
    ds = ds.repeat(repeat_num)

    return ds