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

Performance exploration with onnx #2

Merged
merged 3 commits into from
Nov 12, 2024
Merged

Conversation

sfc-gh-dkajtoch
Copy link
Collaborator

  • Performance benchmark of onnx model for different session options
  • Quality benchmark not included
  • quantization to int8 produces errors (won't explore in this PR)

Comment on lines +49 to +50
print(f"Mean time: {np.mean(times[1:])}")
print(f"Std time: {np.std(times[1:])}")
Copy link
Collaborator

Choose a reason for hiding this comment

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

Why are we skipping the first time? Are we sure that Paddle won't cache some results during the process?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I noticed that for the first run, the paddle is always much slower due to warm-up. I didn't see any caching mechanism in the paddleocr

Copy link
Collaborator

@sfc-gh-lduhr sfc-gh-lduhr left a comment

Choose a reason for hiding this comment

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

lg

@sfc-gh-dkajtoch sfc-gh-dkajtoch merged commit 65d4e39 into main Nov 12, 2024
1 check passed
@sfc-gh-dkajtoch sfc-gh-dkajtoch deleted the dkajtoch/profile-onnx branch November 12, 2024 13:37
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.

2 participants