Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

use batch idx and node id as unique key for dedup in temporal sampling #267

Merged
merged 1 commit into from
Aug 11, 2022

Conversation

yaoyaowd
Copy link
Contributor

This PR would fix the issue where we sample the same node multiple times and blow up batch size.

Copy link
Owner

@rusty1s rusty1s left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Wow, this is really cool!

Copy link
Contributor

@RexYing RexYing left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The idea looks good to me! I think the code is correct. Look forward to the results after testing! It should save gpu memory for temporal minibatches.

csrc/cpu/neighbor_sample_cpu.cpp Outdated Show resolved Hide resolved
@codecov-commenter
Copy link

codecov-commenter commented Aug 11, 2022

Codecov Report

Merging #267 (abf957b) into master (916ba55) will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##           master     #267   +/-   ##
=======================================
  Coverage   72.32%   72.32%           
=======================================
  Files          28       28           
  Lines        1120     1120           
=======================================
  Hits          810      810           
  Misses        310      310           

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

@rusty1s rusty1s merged commit 6143af2 into rusty1s:master Aug 11, 2022
yanbing-j pushed a commit to yanbing-j/pytorch_sparse that referenced this pull request Aug 18, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants