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

how to covert boxInst to onnx #12295

Open
StephenZhao1 opened this issue Jan 15, 2025 · 4 comments
Open

how to covert boxInst to onnx #12295

StephenZhao1 opened this issue Jan 15, 2025 · 4 comments
Assignees

Comments

@StephenZhao1
Copy link

how can I convert boxinst to onnx? Thx a lot.

@StephenZhao1
Copy link
Author

@jbwang1997 can I use mmdeploy directly to finish this job?

@tojimahammatov
Copy link

Hi, you can use mmdeploy tool to convert your PyTorch model to ONNX and TensorRT.

@StephenZhao1
Copy link
Author

boxInst is not listed on mmdeploy supported models.

@tojimahammatov
Copy link

tojimahammatov commented Feb 6, 2025

boxInst is not listed on mmdeploy supported models.

Yeah you are right.
I saw the boxInst model config and it looks like that model differs with a network head from other detectors since backbone is ResNet-50 and neck is FPN.
A few weeks ago I checked free anchor model and it worked without an issue although it was not mentioned in supported models. I guess you can have a try, it may work. But if it does not work, you might still have a chance like this to make it work assuming you are adding a new model.

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

3 participants