Deploy a vision AI model with Visual Studio Code
What you will do
- Configure VS Code for model deployment
- Build and deploy a default AIVisionDevKitGetStartedModule or a module based on your own Vision AI model to the Visual AI DevKit hardware
What you will need
- Visual Studio (VS) Code with required extentions (Instructions)
- Contents of the GitHub repository opened in VS Code
- Azure IoT Hub and Azure IoT Edge device configured for your Vision AI DevKit hardware (Instructions)
- Active Wi-Fi access point with Internet connectivity.
- Azure Container Registry
- ADB command line utility (Instructions)
- (optional) HDMI cable and monitor to view video from the Visual AI DevKit
How can you identify that this tutorial has worked?
If you want to build default AIVisionDevKitGetStartedModule using VS Code, we propose creating a new IoT Edge device in IoT Hub, copying the connection string and re-running your OOBE using the existing connection string. This way, you will be able to manually deploy AIVisionDevKitGetStartedModule. Using the Getting Started guide would launch your device with the default module already running, impacting its manual deployment.
If you have your own model for example from customvision.ai, you can run this tutorial with the existing AIVisionDevKitGetStartedModule running on a device.
Instructions in GitHub
- Please access GitHub for Instructions. The instructions are maintained in the GitHub as assets for this tutorial are stored on GitHub and need to be kept in sync with any instructions as the content evolves.