File size: 4,633 Bytes
9c6594c |
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 |
from pathlib import Path
from typing import Any, Callable, Optional, Tuple, Union
from .folder import default_loader, find_classes, make_dataset
from .utils import download_and_extract_archive, verify_str_arg
from .vision import VisionDataset
class Imagenette(VisionDataset):
"""`Imagenette <https://github.com/fastai/imagenette#imagenette-1>`_ image classification dataset.
Args:
root (str or ``pathlib.Path``): Root directory of the Imagenette dataset.
split (string, optional): The dataset split. Supports ``"train"`` (default), and ``"val"``.
size (string, optional): The image size. Supports ``"full"`` (default), ``"320px"``, and ``"160px"``.
download (bool, optional): If ``True``, downloads the dataset components and places them in ``root``. Already
downloaded archives are not downloaded again.
transform (callable, optional): A function/transform that takes in a PIL image or torch.Tensor, depends on the given loader,
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the target and transforms it.
loader (callable, optional): A function to load an image given its path.
By default, it uses PIL as its image loader, but users could also pass in
``torchvision.io.decode_image`` for decoding image data into tensors directly.
Attributes:
classes (list): List of the class name tuples.
class_to_idx (dict): Dict with items (class name, class index).
wnids (list): List of the WordNet IDs.
wnid_to_idx (dict): Dict with items (WordNet ID, class index).
"""
_ARCHIVES = {
"full": ("https://s3.amazonaws.com/fast-ai-imageclas/imagenette2.tgz", "fe2fc210e6bb7c5664d602c3cd71e612"),
"320px": ("https://s3.amazonaws.com/fast-ai-imageclas/imagenette2-320.tgz", "3df6f0d01a2c9592104656642f5e78a3"),
"160px": ("https://s3.amazonaws.com/fast-ai-imageclas/imagenette2-160.tgz", "e793b78cc4c9e9a4ccc0c1155377a412"),
}
_WNID_TO_CLASS = {
"n01440764": ("tench", "Tinca tinca"),
"n02102040": ("English springer", "English springer spaniel"),
"n02979186": ("cassette player",),
"n03000684": ("chain saw", "chainsaw"),
"n03028079": ("church", "church building"),
"n03394916": ("French horn", "horn"),
"n03417042": ("garbage truck", "dustcart"),
"n03425413": ("gas pump", "gasoline pump", "petrol pump", "island dispenser"),
"n03445777": ("golf ball",),
"n03888257": ("parachute", "chute"),
}
def __init__(
self,
root: Union[str, Path],
split: str = "train",
size: str = "full",
download=False,
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
loader: Callable[[str], Any] = default_loader,
) -> None:
super().__init__(root, transform=transform, target_transform=target_transform)
self._split = verify_str_arg(split, "split", ["train", "val"])
self._size = verify_str_arg(size, "size", ["full", "320px", "160px"])
self._url, self._md5 = self._ARCHIVES[self._size]
self._size_root = Path(self.root) / Path(self._url).stem
self._image_root = str(self._size_root / self._split)
if download:
self._download()
elif not self._check_exists():
raise RuntimeError("Dataset not found. You can use download=True to download it.")
self.wnids, self.wnid_to_idx = find_classes(self._image_root)
self.classes = [self._WNID_TO_CLASS[wnid] for wnid in self.wnids]
self.class_to_idx = {
class_name: idx for wnid, idx in self.wnid_to_idx.items() for class_name in self._WNID_TO_CLASS[wnid]
}
self._samples = make_dataset(self._image_root, self.wnid_to_idx, extensions=".jpeg")
self.loader = loader
def _check_exists(self) -> bool:
return self._size_root.exists()
def _download(self):
if self._check_exists():
return
download_and_extract_archive(self._url, self.root, md5=self._md5)
def __getitem__(self, idx: int) -> Tuple[Any, Any]:
path, label = self._samples[idx]
image = self.loader(path)
if self.transform is not None:
image = self.transform(image)
if self.target_transform is not None:
label = self.target_transform(label)
return image, label
def __len__(self) -> int:
return len(self._samples)
|