In this section, you will deploy the model directly on the STM32 board.
X-CUBE-AI 7.0.0. Please select this version when installing. Later versions may not connect successfully.
Download the Windows installer for STM32CubeMX from the STM32CubeMX product page .
Run the Windows installer and install in desired location of your Windows Machine.
Open STM32CubeMX IDE.
Access to Board Selector. Find your
B-L475E-IOT01A board and click
Project Manager. Enter a project name and select the project location where the project will be saved.
Pinout & Configuration, expand
Pinout menu, and click
Now install Cube AI and enable it for your project.
Software Packs menu, and click
X-CUBE-AI, and click its
Expand the menu and enable
Core. For device application, choose
Validation. If the status shows a yellow warning, click
Resolve to install any necessary dependencies.
OK when done.
Access to Board Selector.
B-L475E-IOT01A2 board and click
Start Project. Accept any defaults.
Project Manager. Set the project name and save location.
Pinout & Configuration and clear pinouts from the
Software Packs menu, click
Select Components. Enable
X-CUBE-AI. For device application, choose
OK to save.
Add network. Browse to the model provided (
Data/models/cifar10_model.h5) or the model you trained by yourself (
Analyze to check the model.
Generate the validation code for the model by clicking
STM32 Project from an Existing STM32CubeMX Configuration File.
Go to the project folder and open the
Ensure that the board is connected to your computer. If it is correctly connected, build and flash the code by clicking
static from the declaration of the
MX_USART1_UART_Init() function and also from its definition. Try
Run As again.
With the model now deployed on the STM32 board, you are ready to test it.