MUAD#
- class torch_uncertainty.datasets.MUAD(root, split, version='full', min_depth=None, max_depth=None, target_type='semantic', transforms=None, download=False, use_train_ids=True)[source]#
The MUAD Dataset.
- Parameters:
root (str | Path) – Root directory of dataset where directory
leftImg8bit
andleftLabel
orleftDepth
are located.split (str, optional) – The image split to use,
train
,val
,test
orood
.version (str, optional) – The version of the dataset to use,
small
orfull
. Defaults tofull
.min_depth (float, optional) – The maximum depth value to use if target_type is
depth
. Defaults toNone
.max_depth (float, optional) – The maximum depth value to use if target_type is
depth
. Defaults toNone
.target_type (str, optional) – The type of target to use,
semantic
ordepth
. Defaults tosemantic
.transforms (callable, optional) – A function/transform that takes in a tuple of PIL images and returns a transformed version. Defaults to
None
.download (bool, optional) – If
True
, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again. Defaults toFalse
.use_train_ids (bool, optional) – If
True
, uses the train ids instead of the original ids. Defaults toTrue
. Note that this is only used for thesemantic
target type.
- Reference:
Note
MUAD cannot be used for commercial purposes. Read MUAD’s license carefully before using it and verify that you can comply.