KittiFlow — Torchvision 0.22 documentation (original) (raw)

class torchvision.datasets.KittiFlow(root: ~typing.Union[str, ~pathlib.Path], split: str = 'train', transforms: ~typing.Optional[~typing.Callable] = None, loader: ~typing.Callable[[str], ~typing.Any] = <function default_loader>)[source]¶

KITTI dataset for optical flow (2015).

The dataset is expected to have the following structure:

root KittiFlow testing image_2 training image_2 flow_occ

Parameters:

• root (str or pathlib.Path) – Root directory of the KittiFlow Dataset.
• split (string , optional) – The dataset split, either “train” (default) or “test”
• transforms (callable , optional) – A function/transform that takes inimg1, img2, flow, valid_flow_mask and returns a transformed version.
• 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 intorchvision.io.decode_image for decoding image data into tensors directly.

Special-members:

__getitem__(index: int) → Union[Tuple[Image, Image, Optional[ndarray], Optional[ndarray]], Tuple[Image, Image, Optional[ndarray]]][source]¶

Return example at given index.

Parameters:

index (int) – The index of the example to retrieve

Returns:

A 4-tuple with (img1, img2, flow, valid_flow_mask)where valid_flow_mask is a numpy boolean mask of shape (H, W) indicating which flow values are valid. The flow is a numpy array of shape (2, H, W) and the images are PIL images. flow and valid_flow_mask are None ifsplit="test".

Return type:

tuple