Hi,
I’m trying to import tensorrt in my python script but is saying No module named tensorrt though i did pip3 install tensorrt.
Jetpack 4.6.2(L4T 32.7.2)
CUDA 10.2
Tensorrt 8.2.1.8
Cudnn 8.2.1.32
Here’s the output for dpkg -l | grepTensorRT
mahesh@jetson-nano:~$ dpkg -l | grep TensorRT
ii libnvinfer-bin 8.2.1-1+cuda10.2 arm64 TensorRT binaries
ii libnvinfer-dev 8.2.1-1+cuda10.2 arm64 TensorRT development libraries and headers
ii libnvinfer-doc 8.2.1-1+cuda10.2 all TensorRT documentation
ii libnvinfer-plugin-dev 8.2.1-1+cuda10.2 arm64 TensorRT plugin libraries
ii libnvinfer-plugin8 8.2.1-1+cuda10.2 arm64 TensorRT plugin libraries
ii libnvinfer-samples 8.2.1-1+cuda10.2 all TensorRT samples
ii libnvinfer8 8.2.1-1+cuda10.2 arm64 TensorRT runtime libraries
ii libnvonnxparsers-dev 8.2.1-1+cuda10.2 arm64 TensorRT ONNX libraries
ii libnvonnxparsers8 8.2.1-1+cuda10.2 arm64 TensorRT ONNX libraries
ii libnvparsers-dev 8.2.1-1+cuda10.2 arm64 TensorRT parsers libraries
ii libnvparsers8 8.2.1-1+cuda10.2 arm64 TensorRT parsers libraries
ii nvidia-container-csv-tensorrt 8.2.1.8-1+cuda10.2 arm64 Jetpack TensorRT CSV file
ii tensorrt 8.2.1.8-1+cuda10.2 arm64 Meta package of TensorRT
Here’s the output for dpkg -l | grep nvinfer
mahesh@jetson-nano:~$ dpkg -l | grep nvinfer
ii libnvinfer-bin 8.2.1-1+cuda10.2 arm64 TensorRT binaries
ii libnvinfer-dev 8.2.1-1+cuda10.2 arm64 TensorRT development libraries and headers
ii libnvinfer-doc 8.2.1-1+cuda10.2 all TensorRT documentation
ii libnvinfer-plugin-dev 8.2.1-1+cuda10.2 arm64 TensorRT plugin libraries
ii libnvinfer-plugin8 8.2.1-1+cuda10.2 arm64 TensorRT plugin libraries
ii libnvinfer-samples 8.2.1-1+cuda10.2 all TensorRT samples
ii libnvinfer8 8.2.1-1+cuda10.2 arm64 TensorRT runtime libraries
And if the issue is due to python3-libnvinfer and python3-libnvinfer-dev please let me know how to install them. Itried pip3 install but getting the error
mahesh@jetson-nano:~$ sudo pip3 install libnvinfer
[sudo] password for proxmaq:
WARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.
Please see https://github.com/pypa/pip/issues/5599 for advice on fixing the underlying issue.
To avoid this problem you can invoke Python with '-m pip' instead of running pip directly.
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
ERROR: Could not find a version that satisfies the requirement libnvinfer (from versions: none)
Please help me to fix this issue.