pyg-team/pytorch_geometric

Improve `NNConv` runtimes

开放

#602 创建于 2019年8月6日

 (8 条评论) (0 个反应) (0 位负责人)Python (3,514 个派生)batch import
2 - Priority P2benchmarkfeaturehelp wantednn

仓库指标

星标
 (19,985 个星标)
PR 合并指标
 (平均合并 35天 1小时) (30 天内合并 14 个 PR)

描述

🐛 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

贡献者指南