► STM32 model zoo v3.2 (online)
Free AI models optimized for STM32
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.
The model zoo now includes the support of the Neural-ART Accelerator NPU embedded inside the STM32N6.
New in version 3.2
– Support for STM32EdgeAI Core v2.2.0
– New use cases added: StyleTransfer and FastDepth.
– New models added: Face Detection, and Face Landmarks
– Architecture and codebase clean-up
Get the best edge AI model for your application
– A large collection of application-oriented models ready for re-training.
– Scripts to easily retrain any model from user datasets.
– Application code examples automatically generated from user AI model.
► Image classification (IC): Models: EfficientNet, MobileNet v1, MobileNet v2, Resnet v1 including with hybrid quantization, SqueezeNet v1.1, STMNIST.
► Object detection (OD): Models: ST SSD MobileNet v1, Tiny YOLO v2, SSD MobileNet v2 fpn lite, ST Yolo LC v1.
► Human activity recognition (HAR): Models: CNN IGN, and CNN GMP for different settings.
► Pose estimation: Models: YOLOv8n, MoveNet, Hand landmarks.
► Instance segmentation: Model: YOLOv8n.
► Semantic segmentation: Model: Deeplabv3.
► Hand posture recognition (HPR): Model: ST CNN 2D Hand Posture.
► Audio event detection (AED): Models: Yamnet, MiniResnet, MiniResnet v2.
► Speech enhancement: Model: STFT-TCNN audio denoising.
STM32 model zoo setup essentials
To set up the STM32 Model Zoo, you will need to create a myST account, access STM32Cube.AI via ST Edge AI Developer Cloud or local installation, ensure Python version 3.9 to 3.10.x is installed, and if using a GPU, install the appropriate drivers along with CUDA and CUDNN, avoiding WSL on Windows for optimal GPU acceleration.
STM32 is now on Hugging Face
All STM32 model zoo services are available in a docker.
Browse NN models performances with the model cards.
Find application examples
based on the models of the zoo
Using AI opens the door to new application possibilities! Discover inspiring real-world examples and use our resources to create your own application.
Get started with the Model zoo
Discover how to optimize your AI Neural Network and create processing libraries for your STM32 project
