Source code for torch_geometric.loader.dataloader

from import Mapping
from typing import List, Optional, Sequence, Union

from import default_collate

from import Batch, Dataset
from import BaseData
from import DatasetAdapter

class Collater:
    def __init__(self, follow_batch, exclude_keys):
        self.follow_batch = follow_batch
        self.exclude_keys = exclude_keys

    def __call__(self, batch):
        elem = batch[0]
        if isinstance(elem, BaseData):
            return Batch.from_data_list(batch, self.follow_batch,
        elif isinstance(elem, torch.Tensor):
            return default_collate(batch)
        elif isinstance(elem, float):
            return torch.tensor(batch, dtype=torch.float)
        elif isinstance(elem, int):
            return torch.tensor(batch)
        elif isinstance(elem, str):
            return batch
        elif isinstance(elem, Mapping):
            return {key: self([data[key] for data in batch]) for key in elem}
        elif isinstance(elem, tuple) and hasattr(elem, '_fields'):
            return type(elem)(*(self(s) for s in zip(*batch)))
        elif isinstance(elem, Sequence) and not isinstance(elem, str):
            return [self(s) for s in zip(*batch)]

        raise TypeError(f'DataLoader found invalid type: {type(elem)}')

    def collate(self, batch):  # pragma: no cover
        # TODO Deprecated, remove soon.
        return self(batch)

[docs]class DataLoader( r"""A data loader which merges data objects from a :class:`` to a mini-batch. Data objects can be either of type :class:`` or :class:``. Args: dataset (Dataset): The dataset from which to load the data. batch_size (int, optional): How many samples per batch to load. (default: :obj:`1`) shuffle (bool, optional): If set to :obj:`True`, the data will be reshuffled at every epoch. (default: :obj:`False`) follow_batch (List[str], optional): Creates assignment batch vectors for each key in the list. (default: :obj:`None`) exclude_keys (List[str], optional): Will exclude each key in the list. (default: :obj:`None`) **kwargs (optional): Additional arguments of :class:``. """ def __init__( self, dataset: Union[Dataset, Sequence[BaseData], DatasetAdapter], batch_size: int = 1, shuffle: bool = False, follow_batch: Optional[List[str]] = None, exclude_keys: Optional[List[str]] = None, **kwargs, ): # Remove for PyTorch Lightning: kwargs.pop('collate_fn', None) # Save for PyTorch Lightning < 1.6: self.follow_batch = follow_batch self.exclude_keys = exclude_keys super().__init__( dataset, batch_size, shuffle, collate_fn=Collater(follow_batch, exclude_keys), **kwargs, )