Fail to import tensorRT on Jetson Nano


Im trying to set up a virtual Network on the Jetson Nano using Miniforge.
I am trying to install the package “torch2trt” but therefore need the package “tensorRT”.
Now I have updated my Jetpack version to v4.4.1.

When I Type “sudo jetson_release” i get:

When i Type “dpkg -l | grep TensorRT” i get:

My goal is to make: “python3 -c “import tensorrt”” work but i always get the Error:

So it seems to me that i have TensorRT v7.1.3 installed but cannot import it.
I am sorry if this is a stupid rookie mistake, but it has puzzled me for a long time now…
If someone could give me a hint on how to fix my problem i would be really glad.

Thanks for reading :)

This looks like a Jetson issue. Please refer to the below samlples in case useful.

For any further assistance, we recommend you to raise it to the respective platform from the below link


Just for the Record:
My sys.path was not looking for tensorrt in the right location.
(You can see where sys.path looks for importable Packages with: “import sys sys.path” in Python)
I therefore had to either:

  • Put the TensorRT Folder in one of the sys.path’s
  • add the location of TensorRT to sys.path by: “export PYTHONPATH=/usr/lib/python3.6/dist-packages:$PYTHONPATH” in Terminal (Note: my TensorRT package was located at /usr/lib/python3.6/dist-packages)

I’ve jetpack 4.6 installed on my 2 GB jetson nano and I’ve interfacd Rasbperry pi V2 CSI Camera.

The issue which I am facing right now is the live execution of Thumbs task in free DLI course (sample programs).

Nano is working fine while taking samples of thumbs up and down Infact it is training the neural network perfectly.

But during Live execution for prediction purposes it is unable to determine whether I am holding thumbs up or down.

I’ve been stucked to this matter months ago rather I’ve ran the same sample on my friends nano but i couldn’t find a remedy.

Will be waiting for beneficial responses.