STMicroelectronics – STM32 model zoo

Welcome to STM32 model zoo!

The STM32 AI model zoo is a collection of reference 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.

• A large collection of application-oriented models ready for re-training
• Scripts to easily retrain any model from user datasets
• Pre-trained models on reference datasets
• Application code examples automatically generated from user AI model

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 and MPU are provided for float and quantized models.

This project is organized by application, for each application you will have a step by step guide that will indicate how to train and deploy the models.

What's new in release 2.0:

• An aligned and uniform architecture for all the use case
• A modular design to run different operation modes (training, benchmarking, evaluation, deployment, quantization) independently or with an option of chaining multiple modes in a single launch.
• A simple and single entry point to the code : a .yaml configuration file to configure all the needed services.
• Support of the Bring Your Own Model (BYOM) feature to allow the user (re-)training his own model. Example is provided here.
• Support of the Bring Your Own Data (BYOD) feature to allow the user finetuning some pretrained models with his own datasets. Example is provided here.

Available use-cases

[!TIP] For all use-cases below, quick and easy examples are provided and can be executed for a fast ramp up (click on use cases links below)

• Image classification (IC)
  • Models: EfficientNet, MobileNet v1, MobileNet v2, Resnet v1 including with hybrid quantization, SqueezeNet v1.1, STMNIST.
  • Deployment: getting started application
    • On STM32H747I-DISCO with B-CAMS-OMV camera daughter board.
    • On NUCLEO-H743ZI2 with B-CAMS-OMV camera daughter board, webcam or Arducam Mega 5MP as input and USB display or SPI display as output.
• Object detection (OD)
  • Models: ST SSD MobileNet v1, Tiny YOLO v2, SSD MobileNet v2 fpn lite, ST Yolo LC v1.
  • Deployment: getting started application
    • On STM32H747I-DISCO with B-CAMS-OMV camera daughter board.
• Human activity recognition (HAR)
  • Models: CNN IGN, and CNN GMP for different settings.
  • Deployment: getting started application
    • On B-U585I-IOT02A using ThreadX RTOS.
• Audio event detection (AED)
  • Models: Yamnet, MiniResnet, MiniResnet v2.
  • Deployment: getting started application
    • On B-U585I-IOT02A using RTOS, ThreadX or FreeRTOS.
• Hand posture recognition (HPR)
  • The hand posture use case is based on the ST multi-zone Time-of-Flight sensors: VL53L5CX, VL53L7CX, VL53L8CX. The goal of this use case is to recognize static hand posture such as a like, dislike or love sign done with user hand in front of the sensor. We are providing a complete workflow from data acquisition to model training, then deployment on an STM32 NUCLEO-F401RE board.
  • Model: ST CNN 2D Hand Posture.
  • Deployment: getting started application
    • On NUCLEO-F401RE with X-NUCLEO-53LxA1 Time-of-Flight Nucleo expansion board

Available tutorials and utilities

• stm32ai_model_zoo_colab.ipynb: a Jupyter notebook that can be easily deployed on Colab to exercise STM32 model zoo training scripts.
• stm32ai_devcloud.ipynb: a Jupyter notebook that shows how to access to the STM32Cube.AI Developer Cloud through ST Python APIs (based on REST API) instead of using the web application https://stm32ai-cs.st.com.
• stm32ai_quantize_onnx_benchmark.ipynb: a Jupyter notebook that shows how to quantize ONNX format models with fake or real data by using ONNX runtime and benchmark it by using the STM32Cube.AI Developer Cloud.
• STM32 Developer Cloud examples: a collection of Python scripts that you can use in order to get started with STM32Cube.AI Developer Cloud ST Python APIs.
• Tutorial video: discover how to create an AI application for image classification using the STM32 model zoo.
• stm32ai-tao: this GitHub repository provides Python scripts and Jupyter notebooks to manage a complete life cycle of a model from training, to compression, optimization and benchmarking using NVIDIA TAO Toolkit and STM32Cube.AI Developer Cloud.
• stm32ai-nota: this GitHub repository contains Jupyter notebooks that demonstrate how to use NetsPresso to prune pre-trained deep learning models from the model zoo and fine-tune, quantize and benchmark them by using STM32Cube.AI Developer Cloud for your specific use case.

Before you start

For more in depth guide on installing and setting up the model zoo and its requirement on your PC, specially in the cases when you are running behind the proxy in corporate setup, follow the detailed wiki article on How to install STM32 model zoo.

• Create an account on myST and then sign in to STM32Cube.AI Developer Cloud to be able access the service.

• Or, install STM32Cube.AI locally by following the instructions provided in the user manual in section 2, and get the path to stm32ai executable.

  • Alternatively, download latest version of STM32Cube.AI for your OS, extract the package and get the path to stm32ai executable.

• If you don't have python already installed, you can download and install it from here, a 3.9 <= Python Version <= 3.10.x is required to be able to use TensorFlow later on, we recommand using Python v3.10. (For Windows systems make sure to check the Add python.exe to PATH option during the installation process).

• If using GPU make sure to install the GPU driver. For NVIDIA GPUs please refer to https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html to install CUDA and CUDNN. On Windows, it is not recommended to use WSL to get the best GPU training acceleration. If using conda, see below for installation.

• Clone this repository using the following command:

git clone https://github.com/STMicroelectronics/stm32ai-modelzoo.git

• Create a python virtual environment for the project:

  cd stm32ai-modelzoo
  python -m venv st_zoo
  

  Activate your virtual environment On Windows run:

  st_zoo\Scripts\activate.bat
  

  On Unix or MacOS, run:

  source st_zoo/bin/activate
  

• Or create a conda virtual environment for the project:

  cd stm32ai-modelzoo
  conda create -n st_zoo
  

  Activate your virtual environment:

  conda activate st_zoo
  

  Install python 3.10:

  conda install -c conda-forge python=3.10
  

  If using NVIDIA GPU, install cudatoolkit and cudnn and add to conda path:

  conda install -c conda-forge cudatoolkit=11.8 cudnn
  

  Add cudatoolkit and cudnn to path permanently:

  mkdir -p $CONDA_PREFIX/etc/conda/activate.d
  echo 'export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/' > $CONDA_PREFIX/etc/conda/activate.d/env_vars.sh
  

• Then install all the necessary python packages, the requirement file contains it all.

pip install -r requirements.txt

Jump start with Colab

In tutorials/notebooks you will find a jupyter notebook that can be easily deployed on Colab to exercise STM32 model zoo training scripts.

[!IMPORTANT] In this project, we are using TensorFLow version 2.8.3 following unresolved issues with newest versions of TensorFlow, see more.

[!CAUTION] If there are some white spaces in the paths (for Python, STM32CubeIDE, or, STM32Cube.AI local installation) this can result in errors. So avoid having paths with white spaces in them.

[!TIP] In this project we are using the mlflow library to log the results of different runs. Depending on which version of Windows OS are you using or where you place the project the output log files might have a very long path which might result in an error at the time of logging the results. As by default, Windows uses a path length limitation (MAX_PATH) of 256 characters: Naming Files, Paths, and Namespaces. To avoid this potential error, create (or edit) a variable named LongPathsEnabled in Registry Editor under Computer/HKEY_LOCAL_MACHINE/SYSTEM/CurrentControlSet/Control/FileSystem/ and assign it a value of 1. This will change the maximum length allowed for the file length on Windows machines and will avoid any errors resulting due to this. For more details have a look at this link.