torch_geometric.transforms.ToSparseTensor
- class ToSparseTensor(attr: Optional[str] = 'edge_weight', remove_edge_index: bool = True, fill_cache: bool = True, layout: Optional[int] = None)[source]
Bases:
BaseTransform
Converts the
edge_index
attributes of a homogeneous or heterogeneous data object into a transposedtorch_sparse.SparseTensor
or PyTorchtorch.sparse.Tensor
object with keyadj_t
(functional name:to_sparse_tensor
).Note
In case of composing multiple transforms, it is best to convert the
data
object viaToSparseTensor
as late as possible, since there exist some transforms that are only able to operate ondata.edge_index
for now.- Parameters:
attr (str, optional) – The name of the attribute to add as a value to the
SparseTensor
ortorch.sparse.Tensor
object (if present). (default:edge_weight
)remove_edge_index (bool, optional) – If set to
False
, theedge_index
tensor will not be removed. (default:True
)fill_cache (bool, optional) – If set to
True
, will fill the underlyingtorch_sparse.SparseTensor
cache (if used). (default:True
)layout (torch.layout, optional) – Specifies the layout of the returned sparse tensor (
None
,torch.sparse_coo
ortorch.sparse_csr
). If set toNone
and thetorch_sparse
dependency is installed, will convertedge_index
into atorch_sparse.SparseTensor
object. If set toNone
and thetorch_sparse
dependency is not installed, will convertedge_index
into atorch.sparse.Tensor
object with layouttorch.sparse_csr
. (default:None
)