Hello, here is the page

Sintel Multi (Flow + Disparity)

class alodataset.sintel_multi_dataset.SintelMultiDataset(cameras=None, labels=None, passes=None, sintel_sequences=None, *args, **kwargs)

Bases: Generic[torch.utils.data.dataset.T_co]

Combination of MPI Sintel dataset for joint use of Optical Flow and Disparity

Parameters

cameraslist of string

One frame is returned for each camera. Possible cameras : {‘left’, ‘right’}.

labelslist

Labels that will be attached to the frame Possible labels : {‘flow’, ‘flow_occ’}

passeslist

Image passes {“albedo”, “clean”, “final”}

**kwargs :

aloscene.BaseDataset parameters

CAMERAS = ['left', 'right']

DISP_LABELS = ['disp', 'disp_occ']

FLOW_LABELS = ['flow', 'flow_occ']

LABELS = ['flow', 'flow_occ', 'disp', 'disp_occ']

PASSES = ['clean', 'final']

SINTEL_SEQUENCES = ['alley_1', 'alley_2', 'ambush_2', 'ambush_4', 'ambush_5', 'ambush_6', 'ambush_7', 'bamboo_1', 'bamboo_2', 'bandage_1', 'bandage_2', 'cave_2', 'cave_4', 'market_2', 'market_5', 'market_6', 'mountain_1', 'shaman_2', 'shaman_3', 'sleeping_1', 'sleeping_2', 'temple_2', 'temple_3']

get_dataset_dir()

Look for dataset_dir based on the given name. To work properly a alodataset_config.json file must be save into /home/USER/.aloception/alodataset_config.json

getitem(idx)

set_dataset_dir(dataset_dir)

Set the dataset_dir into the config file. This method will write the path into /home/USER/.aloception/alodataset_config.json by replacing the current one (if any)

Parameters

dataset_dir: str

Path to the new directory