Open Junyoungpark opened 3 years ago
g = dgl.batch([g0,g1,g2]) g.node_type_subgraph(['type1']) print(g.batch_size)
I assumed the node_type_subgraph returns the subgraphs of inputs, hence the output g has to have batch size of 3. But it actually give me a single graph.
node_type_subgraph
g
@jermainewang @mufeili Do we have any concrete plan on preserving batch information through graph transformations?
This looks like a feature requested by many. Let's open an RFC on this. @BarclayII
🐛 Bug
To Reproduce
Expected behavior
I assumed the
node_type_subgraph
returns the subgraphs of inputs, hence the outputg
has to have batch size of 3. But it actually give me a single graph.