README.md

Run ROS2-torch2trt in Docker

For more Jetson dockers, please have a look at jetson-containers github repository.

Docker Default Runtime

To enable access to the CUDA compiler (nvcc) during docker build operations, add "default-runtime": "nvidia" to your /etc/docker/daemon.json configuration file before attempting to build the containers:

{
    "runtimes": {
        "nvidia": {
            "path": "nvidia-container-runtime",
            "runtimeArgs": []
        }
    },

    "default-runtime": "nvidia"
}

You will then want to restart the Docker service or reboot your system before proceeding.

Building the Containers

$cp /etc/apt/trusted.gpg.d/jetson-ota-public.asc .
$sh docker_build.sh
Once you sucessfully build, you will have a ros2-eloquent container with all necessary packages required for this repository.

Run Container

sh docker_run.sh
This will initialize docker. Clone this repository using following command and follow build and run instructions for ros2 package from here.