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 Team,Which specific ST board to used for AI Appplications or AI product development.I have stm32h7b3-dk or Nucleo-F401RE board , which boards supports running a Machine learning model,Please do let me know.
Trying to start with STM32 and AI. Ubuntu 19.04 STM32Cube.MX 5.3.0 with STM32Cube.AI installed. ,STM32CubeMX IDE 1.0.1. Using an STM32F411CEU6 (8x compression). Following this example"Getting Started with STM32Cube.AI" but using the STM32 Toolchain (...
I receive the following error when I try to load a model I created with Keras: INVALID MODEL: Couldn't load Keras model, error: Model saved with Keras 2.4.0 but <= 2.3.1 is supportedAs you can see in attached screenshot I'm working with a python virt...
the model I have bulit:the config of my project:only use cubemx.ai for Application Template，without any other config in my projectin keil project, run the model and see the output in debug window, I find it's all -NaN:in earlier experiment, when I u...
I am using CubeAI to load a model from Target Selection. However this model was trained using google Colab. So when I load it and Analyze it I got the error: Unknown Initializer GlorotUniform .Searching through the web the solution provided is not wh...
Hi,We are working to an ANN development on TensorFlow, this ANN works on computer and not on MCU.During implementation throught CubeMX, an estimation of RAM and Flash permit to select an appropriate MCU.My question is, ANN implementation is only avai...
Here i only found years old https://community.st.com/s/question/0D50X00009XkZkuSAFI have idea in application detect some cocncrete texts example "HEY ALEXA"and need good probability of detection in ADC received voice.Exist any new examples? Info?
Hello, I meet an error when I try to use the function ai_network_create() as the format of tutorial,The error report is:invalid conversion from 'ai_handle {aka void*}' to ‘const ai_buffer*{aka const ai_buffer_*}’However, I see every one use such func...
HiI imported simple CNN to STM32L462RCT using STM32CUBE-AI v5.1.2 ApplicationTemplateI found that compressing the model has no effect on inference time.The aiRun procedure runs for 115ms both in 8-bit compression and "none" configurations although th...
I want to use my converted model, and the first step as is mentioned in the instructions, is to use this function. But I don't exactly understand what should I pass as the first argument (network) to the function. should I pass "ai_linearmodel_data_w...