-
Notifications
You must be signed in to change notification settings - Fork 1
/
stanford_cars.py
113 lines (86 loc) · 4.14 KB
/
stanford_cars.py
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
# ---------------------------------------
# Modified from torchvision by QIU Tian
# ---------------------------------------
__all__ = ['StanfordCars']
import pathlib
from typing import Any, Tuple
from torchvision.datasets.utils import download_and_extract_archive, download_url, verify_str_arg
from ._base_ import BaseDataset
from ..utils.decorators import main_process_only
class StanfordCars(BaseDataset):
"""`Stanford Cars <https://ai.stanford.edu/~jkrause/cars/car_dataset.html>`_ Dataset
The Cars dataset contains 16,185 images of 196 classes of cars. The data is
split into 8,144 training images and 8,041 testing images, where each class
has been split roughly in a 50-50 split
.. note::
This class needs `scipy <https://docs.scipy.org/doc/>`_ to load target files from `.mat` format.
"""
def __init__(self, root, split, transform=None, target_transform=None, batch_transform=None, loader=None,
download=False):
try:
import scipy.io as sio
except ImportError:
raise RuntimeError("Scipy is not found. This dataset needs to have scipy installed: pip install scipy")
split = verify_str_arg(split, "split", ("train", "test"))
super().__init__(root, split, transform, target_transform, batch_transform, loader)
self._base_folder = pathlib.Path(root)
devkit = self._base_folder / "devkit"
if self.split == "train":
self._annotations_mat_path = devkit / "cars_train_annos.mat"
self._images_base_path = self._base_folder / "cars_train"
else:
self._annotations_mat_path = self._base_folder / "cars_test_annos_withlabels.mat"
self._images_base_path = self._base_folder / "cars_test"
if download:
self.download()
if not self._check_exists():
raise RuntimeError("Dataset not found. You can use download=True to download it")
self._samples = [
(
str(self._images_base_path / annotation["fname"]),
annotation["class"] - 1, # Original target mapping starts from 1, hence -1
)
for annotation in sio.loadmat(self._annotations_mat_path, squeeze_me=True)["annotations"]
]
self.classes = sio.loadmat(str(devkit / "cars_meta.mat"), squeeze_me=True)["class_names"].tolist()
self.class_to_idx = {cls: i for i, cls in enumerate(self.classes)}
def __len__(self) -> int:
return len(self._samples)
def __getitem__(self, idx: int) -> Tuple[Any, Any]:
image_path, target = self._samples[idx]
image = self.loader(image_path, format='RGB')
if self.transform is not None:
image = self.transform(image)
if self.target_transform is not None:
target = self.target_transform(target)
return image, target
@main_process_only
def download(self) -> None:
if self._check_exists():
return
download_and_extract_archive(
url="https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz",
download_root=str(self._base_folder),
md5="c3b158d763b6e2245038c8ad08e45376",
)
if self.split == "train":
download_and_extract_archive(
url="https://ai.stanford.edu/~jkrause/car196/cars_train.tgz",
download_root=str(self._base_folder),
md5="065e5b463ae28d29e77c1b4b166cfe61",
)
else:
download_and_extract_archive(
url="https://ai.stanford.edu/~jkrause/car196/cars_test.tgz",
download_root=str(self._base_folder),
md5="4ce7ebf6a94d07f1952d94dd34c4d501",
)
download_url(
url="https://ai.stanford.edu/~jkrause/car196/cars_test_annos_withlabels.mat",
root=str(self._base_folder),
md5="b0a2b23655a3edd16d84508592a98d10",
)
def _check_exists(self) -> bool:
if not (self._base_folder / "devkit").is_dir():
return False
return self._annotations_mat_path.exists() and self._images_base_path.is_dir()