frarch.datasets.oxford_pets module#

class frarch.datasets.oxford_pets.OxfordPets(subset: str = 'train', transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, download: bool = True, root: Union[str, pathlib.Path] = '~/.cache/frarch/datasets/oxford_pets/')[source]#

Bases: torch.utils.data.dataset.Dataset

Oxford Pets dataset object.

Data loader for the Oxford Pets dataset for pet recognition. The dataset can be obtained from https://www.robots.ox.ac.uk/~vgg/data/pets/data/images.tar.gz and their corresponding labels in https://www.robots.ox.ac.uk/~vgg/data/pets/data/annotations.tar.gz.

Parameters

  • subset (str) – “train” or “valid”. Subset to load. Defaults to “train”.

  • transform (Callable) – a callable object that takes an PIL.Image object and returns a modified PIL.Image object. Defaults to None, which won’t apply any transformation.

  • target_transform (Callable) – a callable object that the label data and returns modified label data. Defaults to None, which won’t apply any transformation.

  • download (bool) – True for downloading and storing the dataset data in the root directory if it’s not present. Defaults to True.

  • root (Union[str, Path]) – root directory for the dataset. Defaults to ~/.cache/frarch/datasets/oxford_pets/.

References

Examples

Simple usage of the dataset class:

from frarch.datasets import Mit67
from frarch.utils.data import create_dataloader
from torchvision.transforms import ToTensor

dataset = OxfordPets( "train", ToTensor, None, True, "./data/")
dataloader = create_dataloader(dataset)
for batch_idx, (batch, labels) in enumerate(dataloader):
    # process batch
get_number_classes() → int[source]#

Get number of target labels.

Returns

number of target labels.

Return type

int