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
|
import pathlib
from typing import Any, Callable, Optional, Tuple, Union
from PIL import Image
from .utils import verify_str_arg
from .vision import VisionDataset
class StanfordCars(VisionDataset):
"""Stanford Cars 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
The original URL is https://ai.stanford.edu/~jkrause/cars/car_dataset.html, but it is broken.
Follow the instructions in ``download`` argument to obtain and use the dataset offline.
.. note::
This class needs `scipy <https://docs.scipy.org/doc/>`_ to load target files from `.mat` format.
Args:
root (str or ``pathlib.Path``): Root directory of dataset
split (string, optional): The dataset split, supports ``"train"`` (default) or ``"test"``.
transform (callable, optional): A function/transform that takes in a PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
download (bool, optional): This parameter exists for backward compatibility but it does not
download the dataset, since the original URL is not available anymore. The dataset
seems to be available on Kaggle so you can try to manually download and configure it using
`these instructions <https://github.com/pytorch/vision/issues/7545#issuecomment-1631441616>`_,
or use an integrated
`dataset on Kaggle <https://github.com/pytorch/vision/issues/7545#issuecomment-2282674373>`_.
In both cases, first download and configure the dataset locally, and use the dataset with
``"download=False"``.
"""
def __init__(
self,
root: Union[str, pathlib.Path],
split: str = "train",
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
download: bool = False,
) -> None:
try:
import scipy.io as sio
except ImportError:
raise RuntimeError("Scipy is not found. This dataset needs to have scipy installed: pip install scipy")
super().__init__(root, transform=transform, target_transform=target_transform)
self._split = verify_str_arg(split, "split", ("train", "test"))
self._base_folder = pathlib.Path(root) / "stanford_cars"
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. Try to manually download following the instructions in "
"https://github.com/pytorch/vision/issues/7545#issuecomment-1631441616."
)
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]:
"""Returns pil_image and class_id for given index"""
image_path, target = self._samples[idx]
pil_image = Image.open(image_path).convert("RGB")
if self.transform is not None:
pil_image = self.transform(pil_image)
if self.target_transform is not None:
target = self.target_transform(target)
return pil_image, target
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()
def download(self):
raise ValueError(
"The original URL is broken so the StanfordCars dataset is not available for automatic "
"download anymore. You can try to download it manually following "
"https://github.com/pytorch/vision/issues/7545#issuecomment-1631441616, "
"and set download=False to avoid this error."
)
|
