pyg-team/pytorch_geometric

Improve `NNConv` runtimes

Aberta

#602 aberto em 6 de ago. de 2019

 (8 comentários) (0 reação) (0 responsável)Python (3.514 forks)batch import
2 - Priority P2benchmarkfeaturehelp wantednn

Métricas do repositório

Stars
 (19.985 estrelas)
Métricas de merge de PR
 (Mesclagem média 35d 1h) (14 fundiu PRs em 30d)

Description

🐛 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

Guia do colaborador