torch_geometric.datasets.LRGBDataset

class LRGBDataset(root: str, name: str, split: str = 'train', transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The “Long Range Graph Benchmark (LRGB)” datasets which is a collection of 5 graph learning datasets with tasks that are based on long-range dependencies in graphs. See the original source code for more details on the individual datasets.

Dataset

Domain

Task

PascalVOC-SP

Computer Vision

Node Classification

COCO-SP

Computer Vision

Node Classification

PCQM-Contact

Quantum Chemistry

Link Prediction

Peptides-func

Chemistry

Graph Classification

Peptides-struct

Chemistry

Graph Regression
Parameters:

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

  • name (str) – The name of the dataset (one of "PascalVOC-SP", "COCO-SP", "PCQM-Contact", "Peptides-func", "Peptides-struct")

  • split (str, optional) – If "train", loads the training dataset. If "val", loads the validation dataset. If "test", loads the test dataset. (default: "train")

  • 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:

Name

#graphs

#nodes

#edges

#classes

PascalVOC-SP

11,355

~479.40

~2,710.48

21

COCO-SP

123,286

~476.88

~2,693.67

81

PCQM-Contact

529,434

~30.14

~61.09

1

Peptides-func

15,535

~150.94

~307.30

10

Peptides-struct

15,535

~150.94

~307.30

11