Shortcuts

Source code for torchvision.datasets.oxford_iiit_pet

import os
import os.path
import pathlib
from typing import Any, Callable, Optional, Sequence, Tuple, Union

from PIL import Image

from .utils import download_and_extract_archive, verify_str_arg
from .vision import VisionDataset


[docs]class OxfordIIITPet(VisionDataset): """`Oxford-IIIT Pet Dataset <https://www.robots.ox.ac.uk/~vgg/data/pets/>`_. Args: root (string): Root directory of the dataset. split (string, optional): The dataset split, supports ``"trainval"`` (default) or ``"test"``. target_types (string, sequence of strings, optional): Types of target to use. Can be ``category`` (default) or ``segmentation``. Can also be a list to output a tuple with all specified target types. The types represent: - ``category`` (int): Label for one of the 37 pet categories. - ``segmentation`` (PIL image): Segmentation trimap of the image. If empty, ``None`` will be returned as target. 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): If True, downloads the dataset from the internet and puts it into ``root/oxford-iiit-pet``. If dataset is already downloaded, it is not downloaded again. """ _RESOURCES = ( ("https://www.robots.ox.ac.uk/~vgg/data/pets/data/images.tar.gz", "5c4f3ee8e5d25df40f4fd59a7f44e54c"), ("https://www.robots.ox.ac.uk/~vgg/data/pets/data/annotations.tar.gz", "95a8c909bbe2e81eed6a22bccdf3f68f"), ) _VALID_TARGET_TYPES = ("category", "segmentation") def __init__( self, root: str, split: str = "trainval", target_types: Union[Sequence[str], str] = "category", transforms: Optional[Callable] = None, transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, download: bool = False, ): self._split = verify_str_arg(split, "split", ("trainval", "test")) if isinstance(target_types, str): target_types = [target_types] self._target_types = [ verify_str_arg(target_type, "target_types", self._VALID_TARGET_TYPES) for target_type in target_types ] super().__init__(root, transforms=transforms, transform=transform, target_transform=target_transform) self._base_folder = pathlib.Path(self.root) / "oxford-iiit-pet" self._images_folder = self._base_folder / "images" self._anns_folder = self._base_folder / "annotations" self._segs_folder = self._anns_folder / "trimaps" if download: self._download() if not self._check_exists(): raise RuntimeError("Dataset not found. You can use download=True to download it") image_ids = [] self._labels = [] with open(self._anns_folder / f"{self._split}.txt") as file: for line in file: image_id, label, *_ = line.strip().split() image_ids.append(image_id) self._labels.append(int(label) - 1) self.classes = [ " ".join(part.title() for part in raw_cls.split("_")) for raw_cls, _ in sorted( {(image_id.rsplit("_", 1)[0], label) for image_id, label in zip(image_ids, self._labels)}, key=lambda image_id_and_label: image_id_and_label[1], ) ] self.class_to_idx = dict(zip(self.classes, range(len(self.classes)))) self._images = [self._images_folder / f"{image_id}.jpg" for image_id in image_ids] self._segs = [self._segs_folder / f"{image_id}.png" for image_id in image_ids] def __len__(self) -> int: return len(self._images)
[docs] def __getitem__(self, idx: int) -> Tuple[Any, Any]: image = Image.open(self._images[idx]).convert("RGB") target: Any = [] for target_type in self._target_types: if target_type == "category": target.append(self._labels[idx]) else: # target_type == "segmentation" target.append(Image.open(self._segs[idx])) if not target: target = None elif len(target) == 1: target = target[0] else: target = tuple(target) if self.transforms: image, target = self.transforms(image, target) return image, target
def _check_exists(self) -> bool: for folder in (self._images_folder, self._anns_folder): if not (os.path.exists(folder) and os.path.isdir(folder)): return False else: return True def _download(self) -> None: if self._check_exists(): return for url, md5 in self._RESOURCES: download_and_extract_archive(url, download_root=str(self._base_folder), md5=md5)

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources