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

Improve non_max_suppression and get_valid_counts for CPU #3305

Merged
merged 4 commits into from
Jun 9, 2019

Conversation

kevinthesun
Copy link
Contributor

  1. Improve loop parallelization for performance
  2. Modify implementation a bit to fit for arbitrary input layouts.

@vinx13 @Laurawly

@kevinthesun kevinthesun requested review from Laurawly and vinx13 June 7, 2019 00:05
@kevinthesun kevinthesun changed the title Improve non_max_suppression for CPU Improve non_max_suppression and get_valid_counts for CPU Jun 7, 2019
Copy link
Contributor

@Laurawly Laurawly left a comment

Choose a reason for hiding this comment

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

LGTM

@vinx13 vinx13 merged commit 98a91af into apache:master Jun 9, 2019
@kevinthesun kevinthesun deleted the ImproveX86NMS branch June 13, 2019 20:10
wweic pushed a commit to wweic/tvm that referenced this pull request Jun 26, 2019
* Improve non_max_suppression for CPU

* Improve get_valid_counts

* Minor change

* Skip some unnecessary computes
wweic pushed a commit to neo-ai/tvm that referenced this pull request Jun 27, 2019
* Improve non_max_suppression for CPU

* Improve get_valid_counts

* Minor change

* Skip some unnecessary computes
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.

3 participants