torch_geometric.datasets.MNISTSuperpixels

class MNISTSuperpixels(root: str, train: bool = True, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

MNIST superpixels dataset from the “Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs” paper, containing 70,000 graphs with 75 nodes each. Every graph is labeled by one of 10 classes.

Parameters:

  • root (str) – Root directory where the dataset should be saved.

  • train (bool, optional) – If True, loads the training dataset, otherwise the test dataset. (default: True)

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • pre_filter (callable, optional) – A function that takes in an torch_geometric.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

  • force_reload (bool, optional) – Whether to re-process the dataset. (default: False)

STATS:

#graphs

#nodes

#edges

#features

#classes

70,000

75

~1,393.0

1

10