HD1K¶
- class torchvision.datasets.HD1K(root, split='train', transforms=None)[source]¶
HD1K dataset for optical flow.
The dataset is expected to have the following structure:
root hd1k hd1k_challenge image_2 hd1k_flow_gt flow_occ hd1k_input image_2
- Parameters:
root (string) – Root directory of the HD1K Dataset.
split (string, optional) – The dataset split, either “train” (default) or “test”
transforms (callable, optional) – A function/transform that takes in
img1, img2, flow, valid_flow_mask
and returns a transformed version.
- Special-members:
- __getitem__(index)[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)
wherevalid_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
andvalid_flow_mask
are None ifsplit="test"
.- Return type: