Skip to content

Conversation

@grzegorz-roboflow
Copy link
Collaborator

Description

Speed up webrtc inference pipeline:

  • replace locking with async queue
  • utilize grab to allow inference_pipeline to adapt fps
  • do not drop frames in aiortc recv event
  • only obtain np array in retrieve

Type of change

  • Bug fix (non-breaking change which fixes an issue)

How has this change been tested, please provide a testcase or example of how you tested the change?

e2e test

Any specific deployment considerations

N/A

Docs

N/A

@PawelPeczek-Roboflow PawelPeczek-Roboflow merged commit c585553 into main Oct 17, 2024
57 checks passed
@PawelPeczek-Roboflow PawelPeczek-Roboflow deleted the fix/speed-up-webrtc-pipeline branch October 17, 2024 11:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants