Data

General: dataset, module and loader

This module contains the classes used for handling datasets and for feeding them to the Lightning trainer.

DictDataset([dictionary, feature_names, ...])	Define a torch dataset from a dictionary of lists/array/tensors and names.
DictLoader(dataset[, batch_size, shuffle])	PyTorch DataLoader for DictDataset .
DictModule(dataset[, lengths, batch_size, ...])	Lightning DataModule constructed for DictDataset .

Graph specific tools

This module contains the classes used for handling and creating graphs.

AtomicNumberTable(zs)	The atomic number table.
Configuration(atomic_numbers, positions, ...)	Internal helper class that describe a given configuration of the system.
get_neighborhood(positions, cutoff[, pbc, ...])	Get the neighbor list of a given set atoms.
create_dataset_from_configurations(config, ...)	Build DictDataset object containing torch_geometric graph data objects from configurations.