Subscribe to EDOM TECH Newsletter
Product Introduction
The STM32 AI model zoo is a collection of reference machine learning models that are optimized to run on STM32 microcontrollers. Available on GitHub and Hugging Face, this is a valuable resource for anyone looking to add AI capabilities to their STM32-based projects.Scripts to easily retrain, quantize, evaluate or benchmark any model from user datasets as well as application code examples automatically generated from user AI model can be found in the stm32ai-modelzoo-services GitHub
These models can be useful for quick deployment if you are interested in the categories that they were trained. We also provide training scripts to do transfer learning or to train your own model from scratch on your custom dataset.
The performances on reference STM32 MCU, NPU and MPU are provided for float and quantized models.
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.
Use Cases
► 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.
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.
*STMicroelectronics Authorized Distributor
