DTD

class torchvision.datasets.DTD(root: ~typing.Union[str, ~pathlib.Path], split: str = 'train', partition: int = 1, transform: ~typing.Optional[~typing.Callable] = None, target_transform: ~typing.Optional[~typing.Callable] = None, download: bool = False, loader: ~typing.Callable[[~typing.Union[str, ~pathlib.Path]], ~typing.Any] = <function default_loader>)

Describable Textures Dataset (DTD).

Parameters:

• root (str or pathlib.Path) – Root directory of the dataset.

• split (string, optional) – The dataset split, supports "train" (default), "val", or "test".

• partition (int, optional) –

  The dataset partition. Should be 1 <= partition <= 10. Defaults to 1.

  Note

  The partition only changes which split each image belongs to. Thus, regardless of the selected partition, combining all splits will result in all images.

• 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.

• download (bool, optional) – If True, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again. Default is False.

• 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.

Special-members:

__getitem__(idx: int) → Tuple[Any, Any]

Parameters:

index (int) – Index

Returns:

Sample and meta data, optionally transformed by the respective transforms.

Return type:

(Any)