Models Overview
Overview of creating and uploading vision models for deployment with the AI Manager.
Last updated
Overview of creating and uploading vision models for deployment with the AI Manager.
This section describes how to create vision models that deploy to edge devices running the AI Manager.
The main model categories with seamless integration are image classification models (for instance trained on Google's Teachable Machine) and object detection (for example trained using Ultralytics). However, integrating any vision model is possible with a few tweaks.
The standard process for creating and uploading models to the AI Manager Cloud is:
Create a model using a preferred training tool. Create an ONNX model from scratch, or import one using a supported training tool.
Upload the finished model to the AI Manager Cloud platform. The platform automatically converts it into several device-type (see the AI Accelerators section) optimized versions and ensures it deploys efficiently to any edge device running the AI Manager.
Last updated