Nx AI Manager Documentation
  • Nx AI Manager plugin v4.3
  • Nx AI Manager
    • Get started with the NX AI Manager plugin
    • 1. Install Network Optix
    • 2. Install Nx AI Manager Plugin
    • 3. Configure the Nx AI Manager plugin
      • 3.1 Model Settings
      • 3.2 Model pipeline selection and configuration
      • 3.3 Model pipelines on multiple devices
    • 4. Other Network Optix Plugin Settings
    • 5. Manual Plugin Installation
    • 6. Removing the Nx AI Manager
    • 7. Advanced configuration
      • 7.1 Nx AI Manager Manual Installation
      • 7.2 External Post-processing
      • 7.3 External Pre-processing
      • 7.4 Training Loop
      • 7.5 Enable ini settings
  • Nx AI Cloud
    • Introduction
    • Registration and log-in
    • Deployment and device management
    • Upload your model
      • Normalization
    • Use your model
    • API Documentation
  • SUPPORT & TROUBLESHOOTING
    • How to get support
    • Troubleshooting
      • Plugin checks
      • OS checks
      • System checks
      • Things to try
      • Controlling the server and the plugin
      • Q&A
  • Videos
    • Howto videos
  • AI Accelerators Support
    • Introduction
    • Supported AI accelerators
    • Nvidia Support
    • OpenVino Support
    • Hailo Support
  • For Data Scientists
    • Introduction
    • About ONNX
    • Custom model creation
    • ONNX requirements
    • Importing models
      • From Edge Impulse
      • From Nota AI
      • From Teachable Machine
      • From Hugging Face
      • From Ultralytics
      • From PyTorch
      • From TensorFlow / TFLite
      • From Scikit-learn
      • Common Models
  • Miscellaneous
    • Nx AI Certification Test
    • Nx AI Manager on SCAiLX
    • Privacy policy
    • Support
    • End user license agreement
    • Nx cloud cookie statement
Powered by GitBook
On this page
  • An overview of your sites and devices
  • Overview of a single site
  • AI model pipeline deployment and management
  • Assign or replace a model pipeline on a single device
  • Assign a single model pipeline to all the selected devices
  1. Nx AI Cloud

Deployment and device management

How do we use the platform for model deployment.

PreviousRegistration and log-inNextUpload your model

Last updated 3 months ago

The Nx AI Cloud platform allows you to (mass) deploy model pipelines to target devices. Effectively, you can "swap" the models that run on a device (configured using the ) remotely and change the device configuration. The latter you can do at a large scale: you can deploy models to all the devices on a server.

An overview of your sites and devices

The Sites tab on the Nx AI Cloud platform shows all systems registered to your cloud account.

If the system is on-online the name of the system and the Details button are available.

If the site is off-line you cannot continue until the system comes on-line.

Overview of a single site

If you select an on-line site you are directed to the site details page.

The page shows the servers in the site and lists all the devices and their groups.

The same page when the site is off-line. You cannot do anything now.

AI model pipeline deployment and management

You can assign or replace a model pipeline on a single device or you can select multiple devices and assign a single model pipeline to all the selected devices.

Assign or replace a model pipeline on a single device

To assign or replace a model on a single device you need to click on the 'Details' button on the system or server page. You will be directed to the device page.

To assign an additional model pipeline to the device you can press 'Add a new pipeline' or the 'add' button. To replace a model pipeline press the button with the left-right arrow in it.

You will be directed to the 'Models listing'.

On the top you get a new notification bar that shows you are currently in assigning mode. You can use that to go back to the models listing page, back to the device or cancel the whole assignment process.

Once you have found the model you want to assign or replace use the button 'Add to [x] pipeline'.

Now, the model pipeline will be deployed and if all is well you will see the following notice and you are redirected to the device page.

Assign a single model pipeline to all the selected devices

To start you need to be on the site or server page, which shows you all the servers and all devices in the site.

Just below the 'Devices' header on this page there is a link called 'here' which starts the process of selecting devices to assign a model pipeline to.

Once pressed, a new column with checkboxes will be added to the devices and you can use them to select the devices you want to assign a new model pipeline to.

If you select one or more servers the 'Assign a new pipeline' will activate. Pressing this button will start the model assignment just like updating a model for a single device.

Note: assigning a model pipeline to multiple devices will always remove all other pipelines and replace them with the new pipeline you selected.

AI manager
overview of sites with one on-line system
listing of one site that is off-line
overview of a single on-line system
overview of a single off-line system
Overview of a single device in the system
models listing
multiple server selection activated