Spange
March 3, 2023, 2:05pm
1
I just installed python 3.11 and noticed modules are missing.
I am working on Jetpack 5.0.2 it comes with ubuntu 20.04 and python 3.8.
In python 3.8 I can run import tensorrt
, but in python 3.11 I get No module named "tensorrt"
I tried
python3.8 -m pip freeze > requirements.txt
python3.11 -m pip install -r requirements.txt
But I quickly get:
ERROR: Could not find a version that satisfies the requirement tensorrt==8.4.1.5 (from versions: 0.0.1.dev5, 0.0.1)
ERROR: No matching distribution found for tensorrt==8.4.1.5
Can python 3.11 use python3.8 modules, or do I have to install them with correct distribution?
Hi,
No, but you can build pybinding for 3.11 on your own.
Please check the document and the steps below:
release/8.4/python
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applicat...
Thanks.
Spange
March 7, 2023, 11:30am
6
Thank you @AastaLLL
Thank you, I got it to work
I ended up following your procedure: Tensorrt on Jetson with python 3.9 - #9 by AastaLLL , but with some changes:
I installed python 3.11 rather than compiled it
(sudo add-apt-repository --yes ppa:deadsnakes/ppa
sudo apt install -y python3.11-minimal)
I swapped TensorRT 8.0 with 8.4
I swapped cmake 3.15.5 with 3.25.2
I can now run import tensorrt
in python 3.11
Any tutorial for this to do on windows can someone share the whl file for amd64 python 3.11
Spange
March 9, 2023, 8:59am
8
I didn’t cross compile.
I compiled on a Jetson Xavier for Jetson Xaviers
So I don’t know of any such tutorial.
This question is not directly for you but thank you for trying to help me im trying to get tensorRT on python 3.11
1 Like
Spange
March 10, 2023, 10:11am
10
A Warning for other reading this thread:
Python3.8 is default with Jetpack 5.0.2, manually installing python3.11 and installing libraries has it’s drawback. And might cause you days of work.
E.G. pytorch is not compatible with 3.11
Below are pre-built PyTorch pip wheel installers for Jetson Nano, TX1/TX2, Xavier, and Orin with JetPack 4.2 and newer.
Download one of the PyTorch binaries from below for your version of JetPack, and see the installation instructions to run on your Jetson. These pip wheels are built for ARM aarch64 architecture, so run these commands on your Jetson (not on a host PC). You can also use the pre-built l4t-pytorch and l4t-ml container images and Dockerfiles .
PyTorch pip wheels
JetPack 5
PyTo…
system
Closed
April 5, 2023, 1:01am
12
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.