Edge AI

Ask questions and find answers on how to deploy, debug, and optimize AI models on ST microcontrollers, microprocessors, and smart sensors.

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

How to generate the capsule network codes using cubemx.ai

I create a capsule layer for my capsule network, as follows.#A Capsule Implement with Pure Kerasclass Capsule(Layer):   def __init__...   def build(....):   def call(...): ...model = Model(...)model.compile(...)model.fit(...)model.save('***.h5')But ...

Swu.4 by Associate II
  • 498 Views
  • 0 replies
  • 0 kudos

X-Cube-AI and C++

Hey Community,did anyone run a X-Cube-AI project using C++ successfully?I get undefined reference errors when adding X-Cube-AI via CubeMX to my perfectly running cpp project in CubeIDE.steps to reproduce: create new project with cubemx, specified as...

FFrai.1 by Associate II
  • 990 Views
  • 2 replies
  • 1 kudos

X-CUBE-AI 6.0.0 (Windows): ImportError: cannot import name 'get_all_providers' from 'onnxruntime.capi._pybind_state'

With a fresh installation of STM32CubeIDE 1.6.1 on a clean WIndows 10 Pro 20H2, after adding X-CUBE-AI 6.0.0 to a new STM32 project, Analyze fails with:ImportError: cannot import name 'get_all_providers' from 'onnxruntime.capi._pybind_state' (C:\User...

piernov by Associate II
  • 1331 Views
  • 1 replies
  • 0 kudos

Resolved! stm32ai quantize error?

I'm trying to use STM32AI quantize -q .json to quantize a Keras .H5. However, I never got it working.Version: STM32 XCUBE-AI 6.0.0tensorflow: I tried tf 2.0 and tf 1.15 installed Platform. tried on both window and Linux (ubuntu 18.04)Command line:C:\...

GWang.3 by Associate III
  • 1492 Views
  • 4 replies
  • 0 kudos

Resolved! Validation on Target - running time layer by layer

I am trying to follow the DM00570145 and validate on target (STM32F746 Discovery Board, XCUBE-AI 6.0.0, toolchain: STM32CUBE IDE), I cannot get the output listed on Figure 61. "Layer by layer results - Validation on target", especially the "ms" runni...

GWang.3 by Associate III
  • 1188 Views
  • 2 replies
  • 0 kudos

Resolved! Platform Settings Tab missing on configuration of X-CUBE-AI

Hello,I am trying to generate the code for a neural network with STCubeMX, and I'm following the manual you have posted here (https://www.st.com/resource/en/user_manual/dm00570145-getting-started-with-xcubeai-expansion-package-for-artificial-intellig...

0693W000008xl61QAA.png 0693W000008xl6QQAQ.png 0693W000008xl6aQAA.png
DMart.13 by Associate
  • 1897 Views
  • 6 replies
  • 0 kudos

[x-cube-ai] Advanced settings button (Use external RAM & Copy weight to RAM) doesn't work (using STM32H747i-disco board) for cube-mx validate on target option

I use x-cube-ai 6.0 version & stm32h747i-disco board.By clicking on the [Advanced Settings] button, i use external flash memory for the weights and it works well.However, when [Use external RAM] button & copy weight to RAM , there's some problem and ...

0693W000008yF7JQAU.jpg
Yjang.1 by Associate II
  • 651 Views
  • 0 replies
  • 0 kudos

Resolved! Unsupervisory Machine learning examples using ST MEMS and STM32

Hi,I am wondering does ST Micro provides any example around unsupervisory Machine learning examples to implement on board learning using ST MEMS vibration sensor and STM32.As I can see Cartesiam provides some examples and the tools to does this work ...

Resolved! TOOL ERROR: Unknown layer type SHAPE, stopping.

Dear STM community,I am trying to deploy a simple tflite model on my STM32, but I can't get through the analyze step. I got the following error:TOOL ERROR: Unknown layer type SHAPE, stopping.If I convert the model to Keras (model and topology), it wo...

MKiss by Associate II
  • 1487 Views
  • 5 replies
  • 0 kudos