GitHubYuxiao

I also get the problems，data["img_metas] are on the cpu,but onnx need on the same device. Are you save it?

> Thanks for adding to this issue. Demo.py and lazyconfig both do not work with the LVIS models / configs and it is not clear how to do basic inference...

> 您好，大佬 请问下这个问题应该如何解决呢，谢谢 **ImportError: dynamic module does not define module export function (PyInit_MultiScaleDeformableAttention)** hi，have you save this problem，I also meet it

> 我是使用mmsegmentation 平台，然后转onnx有很多问题， 你部署成功了吗 可以联系我吗

> It is a problem of the mmdeploy version. I solved it by using the version 0.14.0. @goldentimecoolk When I convert the model to tensorrt, I want to infer it...

@monologuesmw hello，I meet the same problem, and I want to use C++ API to deploy the tensorrt engine. Can you achieve it? please reply~

@calebhemara hello,do you achieve the segmentation model convert. I meet some problem