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

[runtime] support MNN inference engine #310

Merged
merged 14 commits into from
Apr 23, 2024
Merged

[runtime] support MNN inference engine #310

merged 14 commits into from
Apr 23, 2024

Conversation

cdliang11
Copy link
Collaborator

@cdliang11 cdliang11 commented Apr 17, 2024

Support MNN inference engine:

  • export_mnn.py
  • runtime code
  • add README.md
  • test rtf & performance

@cdliang11
Copy link
Collaborator Author

cdliang11 commented Apr 23, 2024

Benchmark

  1. RTF

num_threads = 1

samples_per_chunk = 32000

Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz

Model Params FLOPs engine RTF
ResNet-34 6.63 M 4.55 G onnxruntime 0.1377
ResNet-34 6.63 M 4.55 G mnn 0.1333
ResNet-34 6.63 M 4.55 G mnn mini_libs 0.05262

@cdliang11 cdliang11 marked this pull request as ready for review April 23, 2024 08:24
@cdliang11
Copy link
Collaborator Author

这个pr中对rtf做了初步测试,后续会详细对比onnxruntime/MNN/ncnn。:)
actions:

  • ncnn支持
  • 重构pipeline

1. RTF
> num_threads = 1
>
> samples_per_chunk = 3200
Copy link
Collaborator

Choose a reason for hiding this comment

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

32000 ?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

已修正

--config config.yaml \
--checkpoint model.pt \
--output_model model.onnx
# When it finishes, you can find `model.mnn`.
Copy link
Collaborator

Choose a reason for hiding this comment

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

model.onnx ??

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

已修正

Copy link
Collaborator

@JiJiJiang JiJiJiang left a comment

Choose a reason for hiding this comment

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

Well done!!

@JiJiJiang JiJiJiang merged commit 9bb65c9 into master Apr 23, 2024
4 checks passed
@JiJiJiang JiJiJiang deleted the mnn branch April 23, 2024 13:10
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