Issue running the sgie model in deepstream 7.1

[kushagra.tomar]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Orin NX
• DeepStream Version 7.1
• JetPack Version (valid for Jetson only) 6.2
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I have converted the .onnx file into engine file using tao-deploy running tensorRt 8.6.3 in my laptop . But then when I am using this engine file for my sgie in jetson orin where the tensorRt version is 10.3.0 the depstream project is not able to run.

I have attached the log files below:

i am trying to uninstall the tensort version 8.6.3 from tao-deploy docker container and pip installing tensorRt 10.3.0 version but i g the cmd is stuck over here and moving forward

this is the cuda version in my device:

[yuweiw]

When you change platforms or update the version of TensorRT, you need to regenerate the engine file.

[kushagra.tomar]

Yes I am trying to update the TensorRt version in my device to make it match the tensorRt version of the Jetson.

I have uninstalled the previous version of tensorRt. an installing 10.3 verisong using pip but it is stuck here:

[yuweiw]

@kushagra.tomar

Yes I am trying to update the TensorRt version in my device to make it match the tensorRt version of the Jetson.

If you switch to a different platform, you also need to regenerate the engine file. And you can refer to our Guide to learn how to install tensorrt on your jetson.

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks