I am trying to install on a docker (Ubuntu18.04 image) on AGX Xavier TensorRT.
I copied from the sdk image the file tensorrt_7.1.3.0-1+cuda10.2_arm64.deb, but I do not know what to do now.
Hi,
This looks like a Jetson issue. We recommend you to raise it to the respective platform from the below link
Thanks!
Hi @lorenzo.appino12, for Docker container, you should use l4t-base container as your base with --runtime nvidia
flag. Then CUDA/cuDNN/TensorRT will automatically be mounted into your container at runtime. There are also other containers available such as l4t-pytorch, l4t-tensorflow, and l4t-ml if you want to use those.
I cannot change my starting container.
Hi,
What is your starting container?
Please noted that you will need an l4t
based image for the Jetson platform.
Thanks.
This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.