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

Can this model run on mobile devices? #32

Open
ExplodedJelly opened this issue Jun 30, 2023 · 10 comments
Open

Can this model run on mobile devices? #32

ExplodedJelly opened this issue Jun 30, 2023 · 10 comments

Comments

@ExplodedJelly
Copy link

I'm considering the possibility of exporting MobileSam as an ONNX model and running it on mobile devices using onnxruntime.

@elblogbruno
Copy link

I am interested on this too!

@ivyas21
Copy link

ivyas21 commented Jun 30, 2023

check this out: #7

@ChaoningZhang
Copy link
Owner

ChaoningZhang commented Jun 30, 2023

I'm considering the possibility of exporting MobileSam as an ONNX model and running it on mobile devices using onnxruntime.

We have implemented this and are now testing it before merging it. Stay tuned.

@ChaoningZhang
Copy link
Owner

I am interested on this too!

We have implemented this and are now testing it before merging it. Stay tuned.

@ChaoningZhang
Copy link
Owner

check this out: #7

Thanks for your help. We haven't got time for checking the pull request yet, however, we really appreciate your effort.

@fakeyee
Copy link

fakeyee commented Jul 14, 2023

I am interested on this too!

We have implemented this and are now testing it before merging it. Stay tuned.

I'm wondering how is the progress about this great work?

@lizhiwen19900709
Copy link

@ChaoningZhang exporting MobileSam as an ONNX model and running it on mobile devices using onnxruntime,Can you provide the example code?

@ryouchinsa
Copy link

Here is the Segment Anything CPP Wrapper for macOS.
This code is originated from Segment Anything CPP Wrapper and implemented on macOS app RectLabel. We customized the original code so that getMask() uses the previous mask result called as low_res_logits and retain the previous mask array for undo/redo actions.

We hope this macOS version would help to develop the iOS version.
Please let us know your opinion.

sam_polygon

@ryouchinsa
Copy link

Improved "Create polygon using SAM" feature so that you can label pixels using the pixels option. You can label Segment Anything 1 Billion (SA-1B) like dataset by yourself.

sam-pixels

@RobSchilderr
Copy link

I'm considering the possibility of exporting MobileSam as an ONNX model and running it on mobile devices using onnxruntime.

We have implemented this and are now testing it before merging it. Stay tuned.

Is this still coming?

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

No branches or pull requests

8 participants