File size: 4,722 Bytes
deb7039 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
from .utils import check_integrity, download_and_extract_archive
from torch.utils.data import Dataset
from PIL import Image
import os
import os.path
import numpy as np
import pickle
from typing import Any, Callable, Optional, Tuple
import torchvision.transforms.functional as TF
class UpsideDownDataset(Dataset):
"""
Adapted from torchvision source code.
Horizontally flips every other image and makes its label '1',
otherwise makes its label '0'
"""
base_folder = 'cifar-10-batches-py'
url = "https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz"
filename = "cifar-10-python.tar.gz"
tgz_md5 = 'c58f30108f718f92721af3b95e74349a'
train_list = [
['data_batch_1', 'c99cafc152244af753f735de768cd75f'],
['data_batch_2', 'd4bba439e000b95fd0a9bffe97cbabec'],
['data_batch_3', '54ebc095f3ab1f0389bbae665268c751'],
['data_batch_4', '634d18415352ddfa80567beed471001a'],
['data_batch_5', '482c414d41f54cd18b22e5b47cb7c3cb'],
]
test_list = [
['test_batch', '40351d587109b95175f43aff81a1287e'],
]
meta = {
'filename': 'batches.meta',
'key': 'label_names',
'md5': '5ff9c542aee3614f3951f8cda6e48888',
}
def __init__(
self,
root: str,
train: bool = True,
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
download: bool = False,
) -> None:
# super(CIFAR10, self).__init__(root, transform=transform,
# target_transform=target_transform)
self.train = train # training set or test set
self.root = root
self.transform = transform
self.target_transform = target_transform
if download:
self.download()
# if not self._check_integrity():
# raise RuntimeError('Dataset not found or corrupted.' +
# ' You can use download=True to download it')
if self.train:
downloaded_list = self.train_list
else:
downloaded_list = self.test_list
self.data: Any = []
self.targets = []
# now load the picked numpy arrays
for file_name, checksum in downloaded_list:
file_path = os.path.join(self.root, self.base_folder, file_name)
with open(file_path, 'rb') as f:
entry = pickle.load(f, encoding='latin1')
self.data.append(entry['data'])
if 'labels' in entry:
self.targets.extend(entry['labels'])
else:
self.targets.extend(entry['fine_labels'])
self.data = np.vstack(self.data).reshape(-1, 3, 32, 32)
self.data = self.data.transpose((0, 2, 3, 1)) # convert to HWC
# self._load_meta()
# def _load_meta(self) -> None:
# path = os.path.join(self.root, self.base_folder, self.meta['filename'])
# if not check_integrity(path, self.meta['md5']):
# raise RuntimeError('Dataset metadata file not found or corrupted.' +
# ' You can use download=True to download it')
# with open(path, 'rb') as infile:
# data = pickle.load(infile, encoding='latin1')
# self.classes = data[self.meta['key']]
# self.class_to_idx = {_class: i for i, _class in enumerate(self.classes)}
def __getitem__(self, index: int) -> Tuple[Any, Any]:
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
img, target = self.data[index], self.targets[index]
# doing this so that it is consistent with all other datasets
# to return a PIL Image
img = Image.fromarray(img)
if index % 2 == 0:
img = TF.vflip(img)
target = 1
if index % 2 != 0:
target = 0
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target
def __len__(self) -> int:
return len(self.data)
def download(self) -> None:
# if self._check_integrity():
# print('Files already downloaded and verified')
# return
download_and_extract_archive(self.url, self.root, filename=self.filename, md5=self.tgz_md5)
def extra_repr(self) -> str:
return "Split: {}".format("Train" if self.train is True else "Test") |