Kitti2015Stereo — Torchvision 0.22 documentation (original) (raw)

class torchvision.datasets.Kitti2015Stereo(root: Union[str, Path], split: str = 'train', transforms: Optional[Callable] = None)[source]

KITTI dataset from the 2015 stereo evaluation benchmark.

The dataset is expected to have the following structure:

root Kitti2015 testing image_2 img1.png img2.png ... image_3 img1.png img2.png ... training image_2 img1.png img2.png ... image_3 img1.png img2.png ... disp_occ_0 img1.png img2.png ... disp_occ_1 img1.png img2.png ... calib

Parameters:

Special-members:

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

Return example at given index.

Parameters:

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

Returns:

A 4-tuple with (img_left, img_right, disparity, valid_mask). The disparity is a numpy array of shape (1, H, W) and the images are PIL images.valid_mask is implicitly None if the transforms parameter does not generate a valid mask. Both disparity and valid_mask are None if the dataset split is test.

Return type:

tuple