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

[Relay] symbolic max_output_size #5844

Merged
merged 3 commits into from
Jun 29, 2020
Merged

Conversation

yongwww
Copy link
Member

@yongwww yongwww commented Jun 18, 2020

  • modify nms to support symbolic max_output_size
  • stop iou computation once get enough boxes

@kevinthesun @zhiics @icemelon9 @lixiaoquan

@yongwww
Copy link
Member Author

yongwww commented Jun 18, 2020

Tested with 20000 random boxes (score_threshold=0, iou_threshold=0.6, max_output_size=7) on my local env., the execution time of nms decreased to 0.003057119846343994 second from 0.39738729953765867

@kevinthesun kevinthesun added the status: need update need update based on feedbacks label Jun 19, 2020
@kevinthesun
Copy link
Contributor

Can we also add a TODO to topi cuda nms?

@yongwww yongwww force-pushed the max_outputs branch 3 times, most recently from def4ac1 to e8192a2 Compare June 25, 2020 23:02
Copy link
Contributor

@kevinthesun kevinthesun left a comment

Choose a reason for hiding this comment

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

LGTM

@kevinthesun kevinthesun merged commit 78d7992 into apache:master Jun 29, 2020
@kevinthesun
Copy link
Contributor

Thanks @yongwww

trevor-m pushed a commit to trevor-m/tvm that referenced this pull request Jun 30, 2020
* symbolic max_output_size

* pylint

* fix ci
zhiics pushed a commit to neo-ai/tvm that referenced this pull request Jul 2, 2020
* symbolic max_output_size

* pylint

* fix ci
@yongwww yongwww deleted the max_outputs branch December 8, 2020 13:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
status: need update need update based on feedbacks
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants