dgl.DGLGraph.edge_attr_schemes¶
-
DGLGraph.
edge_attr_schemes
(etype=None)¶ Return the edge feature schemes for the specified type.
The scheme of a feature describes the shape and data type of it.
- Parameters
etype (str or (str, str, str), optional) –
The type names of the edges. The allowed type name formats are:
(str, str, str)
for source node type, edge type and destination node type.or one
str
edge type name if the name can uniquely identify a triplet format in the graph.
Can be omitted if the graph has only one type of edges.
- Returns
A dictionary mapping a feature name to its associated feature scheme.
- Return type
Examples
The following example uses PyTorch backend.
>>> import dgl >>> import torch
Query for a homogeneous graph.
>>> g = dgl.graph((torch.tensor([0, 1]), torch.tensor([1, 2]))) >>> g.edata['h1'] = torch.randn(2, 1) >>> g.edata['h2'] = torch.randn(2, 2) >>> g.edge_attr_schemes() {'h1': Scheme(shape=(1,), dtype=torch.float32), 'h2': Scheme(shape=(2,), dtype=torch.float32)}
Query for a heterogeneous graph of multiple edge types.
>>> g = dgl.heterograph({('user', 'plays', 'game'): ... (torch.tensor([1, 2]), torch.tensor([3, 4])), ... ('user', 'follows', 'user'): ... (torch.tensor([3, 4]), torch.tensor([5, 6]))}) >>> g.edges['plays'].data['h1'] = torch.randn(2, 1) >>> g.edges['plays'].data['h2'] = torch.randn(2, 2) >>> g.edge_attr_schemes('plays') {'h1': Scheme(shape=(1,), dtype=torch.float32), 'h2': Scheme(shape=(2,), dtype=torch.float32)}
See also