Dear community members,Here’s your chance to win some prizes from ST until November 29, 2024! You can join the challenge by sharing your ISPU neural network implementation. We’ll provide instructions and hints during the ISPU webinar held on October ...
The free online platform (formerly named STM32Cube.AI Developer Cloud) now supports MPUs and smart sensors in addition to MCUs. It also supports AI hardware acceleration (NPU) on compatible devices. Leveraging the ST Edge AI Core technology, the to...
I used a quantization tool called ppq to quantize my onnx model because the activation values in the middle layer of this model were too large and I needed to quantize it from float32 type to int8 type. By the way, this model was defined and trained ...
Hi all, I installed Unicleo-GUI on my Windows laptop, and was able to read sensor data from my NUCLEO-IKS01A3 board successfully. The board was automatically identified by the software as being connected to COM4 yesterday. For some reason today the s...
D:\stm32ai-modelzoo\object_detection\scripts\deployment> python .\deploy.py[INFO] : Successfully connected, starting the model validation on target ...[INFO] : Starting the benchmark on target STM32H747I-DISCO, other available boards ['STM32F469I-DIS...
Hello,I'm working on artificial intelligence on STM32H747. I started my work with projects on FP-AI-VISION. First, I solved the display problem caused by NT35510 and tried the project again. When I tried it, I got the look in the first photo. At firs...
It can be analyzed normally in CUBEAI7.1 without error. Change to CUBEAI8.1 error, [AI:network] 'utf-8' codec can't decode byte 0xe5 in position 8: invalid continuation byte. Attached is my network model. Thank you very much
Hi, I am running a project on NanoEdge AI (anomaly detection), using STEVAL-STWINKT1B SensorTile Wireless Industrial Node and STLINK-V3MINI. I am following st's youtube turotial NanoEdge AI Studio V3 - Anomaly Detection demo. I would like to load dat...
NanoEdge AI Studio v4.3 is now offered for free to all engineers, giving them the opportunity to create highly efficient TinyML libraries that can be deployed on Cortex-M based microcontrollers. In addition, other enhancements have been integrated to...
Hello,I am currently working on a ML project for an STM MCU and am in a state where I have chosen an compatible board based on inference time and Flash/RAM consumption, but I don't yet have a physical board. Is it possible to get an estimate of pow...
Hello,I am trying to explore the STWIN Starter Kit (SensorTile Wireless Industrial Mode) functionality. My OS is Windows 11. I plan to collect data and train models, so I am trying to use Unicleo GUI to define the sensors to be used, the full scale, ...
Kindly provide a step-by-step procedure or tutorial on how to use generated C code from X-CUBE-AI 8.1.0.How to use embedded client API (generated by X-CUBE)?Minimal application is provided in Documentation section. If possible kindly provide any elab...