|
- # Copyright 2021 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 as ds
- import mindspore.dataset.vision.c_transforms as C
- import mindspore.dataset.transforms.c_transforms as C2
- from mindspore.communication.management import init, get_rank, get_group_size
-
- def create_dataset1(dataset_path, do_train, repeat_num=1, batch_size=32, target="Ascend", distribute=False,
- enable_cache=False, cache_session_id=None):
- """
- create a train or evaluate cifar10 dataset for sknet50
- 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
- distribute(bool): data for distribute or not. Default: False
- enable_cache(bool): whether tensor caching service is used for eval. Default: False
- cache_session_id(int): If enable_cache, cache session_id need to be provided. Default: None
-
- Returns:
- dataset
- """
- if do_train:
- dataset_path = os.path.join(dataset_path, 'cifar-10-batches-bin')
- else:
- dataset_path = os.path.join(dataset_path, 'cifar-10-verify-bin')
- if target == "Ascend":
- device_num, rank_id = _get_rank_info()
- else:
- if distribute:
- init()
- rank_id = get_rank()
- device_num = get_group_size()
- else:
- device_num = 1
- if device_num == 1:
- data_set = ds.Cifar10Dataset(dataset_path, num_parallel_workers=8, shuffle=True)
- else:
- data_set = ds.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((224, 224)),
- 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)
-
- data_set = data_set.map(operations=type_cast_op, input_columns="label", num_parallel_workers=8)
- # only enable cache for eval
- if do_train:
- enable_cache = False
- if enable_cache:
- if not cache_session_id:
- raise ValueError("A cache session_id must be provided to use cache.")
- eval_cache = ds.DatasetCache(session_id=int(cache_session_id), size=0)
- data_set = data_set.map(operations=trans, input_columns="image", num_parallel_workers=8, cache=eval_cache)
- else:
- data_set = data_set.map(operations=trans, input_columns="image", num_parallel_workers=8)
-
- # apply batch operations
- data_set = data_set.batch(batch_size, drop_remainder=True)
- # apply dataset repeat operation
- data_set = data_set.repeat(repeat_num)
-
- return data_set
-
- def _get_rank_info():
- """
- get rank size and rank id
- """
- rank_size = int(os.environ.get("RANK_SIZE", 1))
-
- if rank_size > 1:
- rank_size = get_group_size()
- rank_id = get_rank()
- else:
- rank_size = 1
- rank_id = 0
-
- return rank_size, rank_id
|