You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
84 lines
2.7 KiB
84 lines
2.7 KiB
# 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 config import config
|
|
|
|
|
|
def create_dataset(dataset_path, do_train, repeat_num=1, batch_size=32):
|
|
"""
|
|
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
|
|
|
|
Returns:
|
|
dataset
|
|
"""
|
|
device_num = int(os.getenv("DEVICE_NUM"))
|
|
rank_id = int(os.getenv("RANK_ID"))
|
|
|
|
if device_num == 1:
|
|
ds = de.Cifar10Dataset(dataset_path, num_parallel_workers=4, shuffle=True)
|
|
else:
|
|
ds = de.Cifar10Dataset(dataset_path, num_parallel_workers=4, shuffle=True,
|
|
num_shards=device_num, shard_id=rank_id)
|
|
|
|
resize_height = config.image_height
|
|
resize_width = config.image_width
|
|
rescale = 1.0 / 255.0
|
|
shift = 0.0
|
|
|
|
# define map operations
|
|
random_crop_op = C.RandomCrop((32, 32), (4, 4, 4, 4))
|
|
random_horizontal_flip_op = C.RandomHorizontalFlip(rank_id / (rank_id + 1))
|
|
|
|
resize_op = C.Resize((resize_height, resize_width))
|
|
rescale_op = C.Rescale(rescale, shift)
|
|
normalize_op = C.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010])
|
|
|
|
change_swap_op = C.HWC2CHW()
|
|
|
|
trans = []
|
|
if do_train:
|
|
trans += [random_crop_op, random_horizontal_flip_op]
|
|
|
|
trans += [resize_op, rescale_op, normalize_op, change_swap_op]
|
|
|
|
type_cast_op = C2.TypeCast(mstype.int32)
|
|
|
|
ds = ds.map(input_columns="label", operations=type_cast_op)
|
|
ds = ds.map(input_columns="image", operations=trans)
|
|
|
|
# apply shuffle operations
|
|
ds = ds.shuffle(buffer_size=config.buffer_size)
|
|
|
|
# apply batch operations
|
|
ds = ds.batch(batch_size, drop_remainder=True)
|
|
|
|
# apply dataset repeat operation
|
|
ds = ds.repeat(repeat_num)
|
|
|
|
return ds
|