yinfan98

` raw_metric, interested = self.structure.measurer.validate_measure( batch, output) ` i just delete the para interseted and then it works

r u using the python==3.6? python 3.6 don't support the latest version opencv-python. Try the earlier opencv-python. > Reference https://github.com/opencv/opencv-python/issues/812

@L-Carson Hi, This may not caused by the mmcv... maybe you can find solution in opencv repo

Hi, maybe mmdeploy version is old?

@Jasonlaiya I replied your new issue. I think the most direct way is to use docker...

I will add the other file later

Hi, @RunningLeon where can I add the Jetson docker CI, and can I make an individual CI file for Jetson docker？ (I will fix the lint later TAT

Hi, I think you trans your onnx -> TensorRT in windows? This step should in your device.

Hi @HEIseYOUmolc , you need to export the TensorRT model on the Jetson device. Maybe you can try deployee: https://platform.openmmlab.com/deploee to export TensorRT model on Jetson. I've submitted a PR...

Hi, you mean custom ops? maybe you can see this folder > https://github.com/open-mmlab/mmdeploy/tree/main/csrc/mmdeploy/backend_ops