Skip to content

Latest commit

 

History

History
156 lines (98 loc) · 2.37 KB

README copy.md

File metadata and controls

156 lines (98 loc) · 2.37 KB

Marshall-Hand

Code for a hand

sudo vim /etc/systemd/system/docker-l4t-ml.service

Paste this text

[Unit]
Description=Autostart l4t-ml Docker container
Requires=docker.service
After=docker.service

[Service]
Restart=on-failure
ExecStart=/usr/bin/docker run --runtime nvidia --name l4t-ml-container --network host --volume /home/felg/l4t-data --device /dev/video0 nvcr.io/nvidia/l4t-ml:r32.7.1-py3
ExecStop=/usr/bin/docker stop l4t-ml-container

[Install]
WantedBy=multi-user.target

Then press ESC

then type ':wq'

  1. Reload systemd:

    sudo systemctl daemon-reload

  2. Enable the service to start on boot:

    sudo systemctl enable docker-l4t-ml.service

  3. Optionally, start the service immediately without rebooting:

    sudo systemctl start docker-l4t-ml.service

  4. Check the service status to ensure it's running properly:

    sudo systemctl status docker-l4t-ml.service

After Jupyter Notebook is running, open a terminal and run the following commands:

Install torch2trt

Clone torch2trt Repo to quick install pre-recs

git clone https://github.com/NVIDIA-AI-IOT/torch2trt

Go into torch2trt folder

cd torch2trt

Install torch2trt Pre-recs (takes a while)

python3 setup.py install --plugins

Install miscellaneous packages

pip3 install tqdm cython pycocotools

Install MathPlotLib

apt-get install python3-matplotlib

go back to root

cd /

Install trt_pose

Clone trt_pose Repo to quick install pre-recs

git clone https://github.com/NVIDIA-AI-IOT/trt_pose

Go into trt_pose folder

cd trt_pose

Install trt_pose Pre-recs (takes a while)

python3 setup.py install

Go back to root

cd /

Install jetcam

Clone Jetcam Repo to quick install pre-recs

git clone https://github.com/NVIDIA-AI-IOT/jetcam

Go into jetcam folder

cd jetcam

Install jetcam Pre-recs (takes a while)

python3 setup.py install

Go back to root

cd /

cd trt_pose

python3 setup.py install