# -*- coding: utf-8 -*-
# BSD 3-Clause License
#
# Copyright (c) 2017
# All rights reserved.
# Copyright 2022 Huawei Technologies Co., Ltd
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# ==========================================================================
# Copyright (c) 2015-present, Facebook, Inc.
# All rights reserved.
import os
import json
from torchvision import datasets, transforms
from torchvision.datasets.folder import ImageFolder, default_loader
from timm.data.constants import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.data import create_transform
from torch.utils.data import Dataset
def build_dataset(is_train, args):
transform = build_transform(is_train, args)
if args.data_set == 'IMNET':
root = os.path.join(args.data_path, 'train' if is_train else 'val')
dataset = datasets.ImageFolder(root, transform=transform)
nb_classes = 1000
else:
raise NotImplementedError("Support ImageNet only.")
return dataset, nb_classes
def build_transform(is_train, args):
resize_im = args.input_size > 32
if is_train:
# this should always dispatch to transforms_imagenet_train
transform = create_transform(
input_size=args.input_size,
is_training=True,
color_jitter=args.color_jitter,
auto_augment=args.aa,
interpolation=args.train_interpolation,
re_prob=args.reprob,
re_mode=args.remode,
re_count=args.recount,
)
if not resize_im:
# replace RandomResizedCropAndInterpolation with
# RandomCrop
transform.transforms[0] = transforms.RandomCrop(
args.input_size, padding=4)
return transform
t = []
if resize_im:
size = int((256 / 224) * args.input_size)
t.append(
transforms.Resize(size, interpolation=3), # to maintain same ratio w.r.t. 224 images
)
t.append(transforms.CenterCrop(args.input_size))
t.append(transforms.ToTensor())
t.append(transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD))
return transforms.Compose(t)