In this online course, we explain the STM32 model zoo services as assets of scripts, services, and application code. The services are used to ease the end to end AI models integration on ST devices, in particular STM32N6 embedding neural processing unit. This can be used with the STM32 model zoo, which contains a collection of reference deep learning models optimized to run on STM32 microcontrollers. We propose a lab, implementing automated deployment of object detection AI model on STM32N6570-DK board as an example of STM32 model zoo services operation.
What you'll learn
STM32 model zoo services repository structure and supported operations
How to configure/create yaml script to perform automated operation or chain of operation
How to deploy an object detection model on STM32N6570-DK board, having in mind, the flow is similar for another use cases
How to update your embedded project with a new model and/or a new version of ST Edge AI Core
What is the difference between STM32 model zoo services and STM32 model zoo
STEdgeAI-Core v2.2, target folder: C:\ST\ - Optionally modify paths and parameters accordingly in the following scripts: config.json and config_n6l.json in the folder C:\ST\STEdgeAI\2.2\scripts\N6_scripts\ - see section “n6_loader configurations” of STM32N6 NPU Getting Started
The ZIP repository ofSTM32 model zoo servicesextracted to the target folder: C:\ST\ - optionally follow and implement as instructed in the details section“Before you start”, and create a Python virtual environment
