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

Does RTMDet instance segmentation support onnx conversion? #9615

Closed
mattiasbax opened this issue Jan 11, 2023 · 4 comments
Closed

Does RTMDet instance segmentation support onnx conversion? #9615

mattiasbax opened this issue Jan 11, 2023 · 4 comments
Assignees
Milestone

Comments

@mattiasbax
Copy link

What's the feature?

As the title says, does the RTMDet instance segmentation models support conversion to the .onnx format?

When reading the documentation for the 3.x branch the section regarding tutorials and onnx conversion is removed (https://mmdetection.readthedocs.io/en/3.x/overview.html).
Additionally, the master branch documentation does not mention RTMDet as supported models for onnx conversion.
(https://mmdetection.readthedocs.io/en/latest/tutorials/pytorch2onnx.html#results-and-models)

If no: Is there any plans to support onnx conversion for the RTMDet instance segmentation models?

Any other context?

No response

@RangiLyu
Copy link
Member

RangiLyu commented Jan 12, 2023

We will support RTMDet-Ins ONNXRuntime and TensorRT deployment soon. If the PR is ready, I'll inform you.

@RangiLyu RangiLyu added this to the 3.0.0rc6 milestone Jan 12, 2023
@RangiLyu RangiLyu self-assigned this Jan 12, 2023
@RangiLyu
Copy link
Member

Hi, I opened a PR to support RTMDet-Ins in MMDeploy: open-mmlab/mmdeploy#1662.
We will merge it soon.

@mattiasbax
Copy link
Author

That's great news!
Do you want any help to test it out?

@mchaniotakis
Copy link

I would also be willing to help out here if needed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

5 participants