Can we achieve the to_homogeneous() in ‘batch’ manner? Now I think this function can only convert a single graph, right?
Any thoughts about how to enhance this function?
Currently not supported. Do you need it during data processing? If so, you could just to_homogeneous before batching and use multi-processing dataloader for acceleration.
1 Like
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.