TensorRT Broken in JetPack 5.0.2

I just flashed my Xavier NX dev kit with JetPack 5.0.2.

The problem is that I get an undefined symbol if I just try to import tensorrt. See below:

Python 3.8.10 (default, Jun 22 2022, 20:18:18)
[GCC 9.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorrt
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib/python3.8/dist-packages/tensorrt/__init__.py", line 68, in <module>
    from .tensorrt import *
ImportError: /lib/aarch64-linux-gnu/libnvinfer.so.8: undefined symbol: _ZN5nvdla8IProfile17setUseSoftMaxOptzEb

Error is reproducible by just upgrading to JetPack 5.0.2 and trying to import tensorrt

Hi,

We cannot reproduce this issue in our environment.
Could you double-check if everything is well-installed?

$ python3
Python 3.8.10 (default, Jun 22 2022, 20:18:18)
[GCC 9.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorrt
>>> tensorrt.__version__
'8.4.1.5'
>>>

Thanks.

What package(s) should I check that would cause this error?

Here’s what I have installed:

ii  python3-libnvinfer                   8.4.1-1+cuda11.4                  arm64        Python 3 bindings for TensorRT
ii  python3-libnvinfer-dev               8.4.1-1+cuda11.4                  arm64        Python 3 development package for TensorRT
ii  tensorrt                             8.4.1.5-1+cuda11.4                arm64        Meta package for TensorRT

Here are some more packages. All look correct to me.

ii  libcudnn8                            8.4.1.50-1+cuda11.4               arm64        cuDNN runtime libraries
ii  libcudnn8-dev                        8.4.1.50-1+cuda11.4               arm64        cuDNN development libraries and headers
ii  libnvinfer-bin                       8.4.1-1+cuda11.4                  arm64        TensorRT binaries
ii  libnvinfer-dev                       8.4.1-1+cuda11.4                  arm64        TensorRT development libraries and headers
ii  libnvinfer-plugin-dev                8.4.1-1+cuda11.4                  arm64        TensorRT plugin libraries
ii  libnvinfer-plugin8                   8.4.1-1+cuda11.4                  arm64        TensorRT plugin libraries
ii  libnvinfer-samples                   8.4.1-1+cuda11.4                  all          TensorRT samples
ii  libnvinfer8                          8.4.1-1+cuda11.4                  arm64        TensorRT runtime libraries
ii  libnvonnxparsers-dev                 8.4.1-1+cuda11.4                  arm64        TensorRT ONNX libraries
ii  libnvonnxparsers8                    8.4.1-1+cuda11.4                  arm64        TensorRT ONNX libraries
ii  libnvparsers-dev                     8.4.1-1+cuda11.4                  arm64        TensorRT parsers libraries
ii  libnvparsers8                        8.4.1-1+cuda11.4                  arm64        TensorRT parsers libraries

FYI, I just re-flashed my board using the SD card method and things work. Previously I was upgrading from the developer preview using the method outlined here: Jetpack 5.0.2 with Jetson Linux 35.1 is now live!

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