► ST Edge AI Developer Cloud (online)

Online tool for fast AI optimization and benchmark

ST Edge AI Developer Cloud is a free online service for developing AI on ST devices, offering tools for creation, optimization, and benchmarking. It leverages ST Edge AI Core technology and supports AI hardware acceleration (NPU) on compatible devices.
This tool integrates what was previously available in STM32Cube.AI Developer Cloud.

Open online platform

Main features

– Support of Neural-ART Accelerator NPU
– Board farm now includes STM32N6 and STM32MP2
– Online GUI secured by ST user credentials
– AI optimizer and visualizer
– STM32 model zoo with training scripts

Read more in this presentation

Benchmark your AI models in few clicks

With ST Edge AI Developer Cloud, accessing an online platform for AI model optimization and remote benchmarking is as straightforward as logging in with your MyST credentials. Once inside, you’ll have the ability to fine-tune and test your AI models on a variety of genuine STM32 evaluation boards, all conveniently located and maintained at our facilities, ensuring you get real-world performance data for your projects.

An easy to use online platform

Create, optimize, and benchmark your neural network for a variety of ST devices. No software installation, no board required.

1
Load AI model
2
Select platform
3
Quantize
4
Optimize AI model
5
Benchmark
6
Results
7
Generate
Load a model from ST model zoo or own your trained model from your favorite AI framework: Tensorflow Lite, Pytorch, ONNX, scikit Learn, … Supported format are FLOAT32 or quantized INT8.
Select your platform of choice between STM32 MCU, STM32 MPU, Stellar MCU and MEMS ISPU
Perform post-training quantization to further reduce your NN model parameter size.
Select your preferred model optimization options between the RAM or latency most critical parameter.
Access the online benchmark service to remotely evaluate your AI performance on various STM32 boards.
Visualize and optionally export the performance benchmark report.
Generate your optimized AI code in C-code or in a format compatible with the STM32CubeMX software suites.

REST APIs – Seamless integration in your online workflow

All the services of the ST Edge AI Developer Cloud can be directly accessed online via a REST (Representational State Transfer) API. This makes it very easy to automate tasks or integrate the tool into your MLOps flow.

Read the REST APIs’ documentation

STM32 model zoo – Find the best edge AI model

The STM32 AI model zoo is a collection of pre-trained machine learning models that are optimized to run on STM32 microcontrollers. Available on GitHub, this is a valuable resource for anyone looking to add AI capabilities to their STM32-based projects.

Learn more about STM32 model zoo

Boost your application with ST Edge AI Developer Cloud

Using AI opens the door to new application possibilities! Discover inspiring real-world examples and use our resources to create your own application.

Browse use-cases

Get started with the Dev Cloud

Discover how to optimize your AI Neural Network and create processing libraries for your STM32 project

See all documentation
Open online platform