pyg-team/pytorch_geometric

Improve `NNConv` runtimes

Offen

#602 geöffnet am 06.08.2019

 (8 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (3.514 Forks)batch import
2 - Priority P2benchmarkfeaturehelp wantednn

Repository-Metriken

Stars
 (19.985 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 35T 1h) (14 gemergte PRs in 30 T)

Beschreibung

🐛 Bug

I have benchmarked EEC vs https://github.com/mys007/ecc implementation. The code is 3-5 times slower in pytorch_geometric.

I think it is due to the entire pseudo tensor which is given to every message function. Maybe, only weight_j should be given there.

To Reproduce

Steps to reproduce the behavior:

Expected behavior

Environment

  • OS:
  • Python version:
  • PyTorch version:
  • CUDA/cuDNN version:
  • GCC version:
  • Any other relevant information:

Additional context

Contributor Guide