Kitti — Torchvision 0.22 documentation (original) (raw)

class torchvision.datasets.Kitti(root: Union[str, Path], train: bool = True, transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, transforms: Optional[Callable] = None, download: bool = False)[source]

KITTI Dataset.

It corresponds to the “left color images of object” dataset, for object detection.

Parameters:

Special-members:

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

Get item at a given index.

Parameters:

index (int) – Index

Returns:

(image, target), where target is a list of dictionaries with the following keys:

Return type:

tuple