Tensorrt package for python3.8 in Xavier NX with jetpack4.6

I am trying to reproduce the mlperf_inference_result_v1.1 in Xavier NX, but I got the following error message:

Traceback (most recent call last):
  File "code/main.py", line 47, in <module>
    import code.common.arguments as common_args
  File "/workspace/projects_zhr/mlperf/inference_results_v1.1/closed/NVIDIA/code/__init__.py", line 22, in <module>
    from code.common import logging
  File "/workspace/projects_zhr/mlperf/inference_results_v1.1/closed/NVIDIA/code/common/__init__.py", line 33, in <module>
    from code.common.system_list import KnownSystems, MIGConfiguration
  File "/workspace/projects_zhr/mlperf/inference_results_v1.1/closed/NVIDIA/code/common/system_list.py", line 22, in <module>
    from code.common.constants import CPUArch
  File "/workspace/projects_zhr/mlperf/inference_results_v1.1/closed/NVIDIA/code/common/constants.py", line 27, in <module>
    import tensorrt as trt
ModuleNotFoundError: No module named 'tensorrt'

I think I need to install tensorrt for python3.8, but I can’t find any introduction in the inference_results_v1.1/closed/NVIDIA at main · mlcommons/inference_results_v1.1 · GitHub.
Please help me.

Hi,

We don’t have a TensorRT package for python 3.8 on Jetson.
Please follow the below tutorial to build it from the pybinding:

Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.