How to Install Shinobi on a Jetson Nano (4GB Model)

Jetson Nano is a small, powerful computer that delivers the power of modern AI in a single low-cost module.

By : Moe Alam

Date Added : Sun May 17 2020 22:35:58 GMT+0000 (Coordinated Universal Time)
Last Updated : Tue Apr 04 2023 22:25:22 GMT+0000 (Coordinated Universal Time)

Some information provided is from https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit.

UPDATE (26-112022) : You should install JetPack 4.6 at this time.

UPDATE (01-12-2021) : You now must install JetPack 4.4 with the newest installers provided.

UPDATE (24-7-2021) : when this article was originally written there was only the 4GB model. The 2GB Model is not recommended to use with Shinobi and will not be supported.

How to Install Ubuntu on Jetson Nano

First you need to prepare the operating system on the Jetson Nano. We will use their provided image that is based on Ubuntu. Make sure the Jetson Nano is off until step 4.

"To prepare your microSD card, you’ll need a computer with Internet connection and the ability to read and write SD cards, either via a built-in SD card slot or adapter." - NVIDIA Documentation

  1. Download the Jetson Nano Developer Kit SD Card Image, and note where it was saved on the computer.
  2. Write the image to your microSD card by following the instructions below according to the type of computer you are using: Windows, Mac, or Linux.
  3. Once completed with writing the image to the SD card, insert it into the Jetson Nano.
  4. Power on the Jetson Nano and complete the setup process that appears on first boot.
    • If you choose to leave the desktop interface but do not wish burn too much resources when the server is not in use : Set the Login screen to require input upon boot.
  5. Once completed you will see the desktop for Ubuntu.

How to Install Shinobi on Jetson Nano

  1. Now that you are on the Ubuntu desktop open Terminal.
  2. Become root.
    • sudo su
  3. Install curl, wget, nano and net-tools
    • apt update && apt install curl wget nano net-tools -y
  4. Run the Shinobi Installer.
    • sh <(curl -s https://cdn.shinobi.video/installers/shinobi-install.sh)
    • Select Ubuntu - Fast Touchless.
  5. Once completed you will be given the default login details for the Super User panel at http://YOUR_SHINOBI/super. Login to it.
    • Username : [email protected]
    • Password : admin
    • YOUR_SHINOBI : is your Jetson Nano's IP Address.
  6. Once inside the Super user panel you can create the account that will manage cameras.
    • You can modify the settings of this account later, in the Dashboard, after logging in.
  7. Once the account is created, log out and go to the Dashboard at http://YOUR_SHINOBI/ (without /super) and login with the account you just created.
  8. Enjoy!

Please note : You should avoid using the browser on the Jetson Nano to view the Shinobi dashboard. The Jetson Nano is already going to be working hard with it processing streams, the browser actions running at the same time is going to give it a bad day.

Tip : Reboot but don't log in to the desktop environment when the Jetson Nano reboots. This will save a large amount of processing power for the Jetson Nano.

How to Install Object Detection with the TensorFlow Plugin

You must install JetPack 4.6 to use the TensorFlow plugin.

These steps can be followed on Raspberry Pi with exclusion of step 4. Other CPU types can exclude steps 3 and 4.

  1. Login to your Superuser panel and open the Plugins Manager and select and download Object Detection (tfjs 2.3.0).
    • Specifically 2.3.0 because it has the installer written for Jetson Nano.
    • Do not install any NVIDIA or CUDA drivers, the Jetson Nano's JetPack image already comes with them pre-installed.
  2. Open the Commands dropdown for the plugin that appeared. Click on the "Install Plugin for Jetson Nano (4GB)" option to begin the install.
  3. Once completed click Enable for the plugin.
  4. Restart Shinobi to make it start the plugin.
  5. Open your Shinobi Dashboard in the web browser and open the Monitor Settings for any monitor (or create a new one). You will now see Connected : TensorFlow in the Global Detector Settings > Object Detection section.
  6. Enjoy!

For more information about downloading and installing plugins please see the documentation.

Additional Information