torch_concepts.data.datasets.cub.CUBDataset¶

class CUBDataset(split='train', uncertain_concept_labels=False, root='./CUB200/', path_transform=None, sample_transform=None, concept_transform=None, label_transform=None, uncertainty_based_random_labels=False, unc_map=[{0: 0.5, 1: 0.5, 2: 0.5, 3: 0.75, 4: 1.0}, {0: 0.5, 1: 0.5, 2: 0.5, 3: 0.75, 4: 1.0}], selected_concepts=None, training_augment=True)[source]¶

TODO

__init__(split='train', uncertain_concept_labels=False, root='./CUB200/', path_transform=None, sample_transform=None, concept_transform=None, label_transform=None, uncertainty_based_random_labels=False, unc_map=[{0: 0.5, 1: 0.5, 2: 0.5, 3: 0.75, 4: 1.0}, {0: 0.5, 1: 0.5, 2: 0.5, 3: 0.75, 4: 1.0}], selected_concepts=None, training_augment=True)[source]¶: TODO: Define different arguments

Methods

`__init__`([split, uncertain_concept_labels, ...])	TODO: Define different arguments
`concept_weights`()	Calculate class imbalance ratio for binary attribute labels