PCAM — Torchvision 0.22 documentation (original) (raw)

class torchvision.datasets.PCAM(root: Union[str, Path], split: str = 'train', transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, download: bool = False)[source]¶

PCAM Dataset.

The PatchCamelyon dataset is a binary classification dataset with 327,680 color images (96px x 96px), extracted from histopathologic scans of lymph node sections. Each image is annotated with a binary label indicating presence of metastatic tissue.

This dataset requires the h5py package which you can install with pip install h5py.

Parameters:

• root (str or pathlib.Path) – Root directory of the dataset.
• split (string , optional) – The dataset split, supports "train" (default), "test" or "val".
• 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/pcam. If dataset is already downloaded, it is not downloaded again.
  Warning
  To download the dataset gdown is required.

Special-members:

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

Parameters:

index (int) – Index

Returns:

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

Return type:

(Any)