pyg-team/pytorch_geometric

Improve `NNConv` runtimes

開放

#602 建立於 2019年8月6日

 (8 則留言) (0 個反應) (0 位負責人)Python (3,514 個分叉)batch import
2 - Priority P2benchmarkfeaturehelp wantednn

倉庫指標

星標
 (19,985 顆星)
PR 合併指標
 (平均合併 35天 1小時) (30 天內合併 14 個 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

貢獻者指南