mindspore/example/vgg16_cifar10/dataset.py

66 lines
2.5 KiB
Python

# 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.
# ============================================================================
"""
Data operations, will be used in train.py and eval.py
"""
import os
import mindspore.dataset as ds
import mindspore.dataset.transforms.c_transforms as C
import mindspore.dataset.transforms.vision.c_transforms as vision
import mindspore.common.dtype as mstype
from config import cifar_cfg as cfg
def create_dataset(data_home, repeat_num=1, training=True):
"""Data operations."""
ds.config.set_seed(1)
data_dir = os.path.join(data_home, "cifar-10-batches-bin")
if not training:
data_dir = os.path.join(data_home, "cifar-10-verify-bin")
data_set = ds.Cifar10Dataset(data_dir)
resize_height = cfg.image_height
resize_width = cfg.image_width
rescale = 1.0 / 255.0
shift = 0.0
# define map operations
random_crop_op = vision.RandomCrop((32, 32), (4, 4, 4, 4)) # padding_mode default CONSTANT
random_horizontal_op = vision.RandomHorizontalFlip()
resize_op = vision.Resize((resize_height, resize_width)) # interpolation default BILINEAR
rescale_op = vision.Rescale(rescale, shift)
normalize_op = vision.Normalize((0.4465, 0.4822, 0.4914), (0.2010, 0.1994, 0.2023))
changeswap_op = vision.HWC2CHW()
type_cast_op = C.TypeCast(mstype.int32)
c_trans = []
if training:
c_trans = [random_crop_op, random_horizontal_op]
c_trans += [resize_op, rescale_op, normalize_op,
changeswap_op]
# apply map operations on images
data_set = data_set.map(input_columns="label", operations=type_cast_op)
data_set = data_set.map(input_columns="image", operations=c_trans)
# apply repeat operations
data_set = data_set.repeat(repeat_num)
# apply shuffle operations
data_set = data_set.shuffle(buffer_size=10)
# apply batch operations
data_set = data_set.batch(batch_size=cfg.batch_size, drop_remainder=True)
return data_set