Edge AI

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Resolved! Interrupt behavior of LSM6DSOX?

I am looking to create a project where I can set/latch the interrupt pin INT1 on high when the LSM6DSOX is detecting state X (where X is state 1/2/3 etc.) and goes down (low) when in a generic/static state (state 0). How is this possible? I found in ...

Is SoftMax function supported by CubeMx-AI?

I am building CNN model on TensorFlow and after that I generate C code for STM32 micro using CubeMX-AI.Here's my modelmodel = models.Sequential() model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32,1))) model.add(layers.MaxPool...

0693W000000UhNcQAK.png
HAlzo by Senior
  • 580 Views
  • 2 replies
  • 0 kudos

Weights quantization to uint8

Hi, As the title says, I'm trying to use a model with integer weights in cube_ai for speed and size performances. I converted the original keras model to int operations using TFtiny, but when I try to import it, cube_ai throws an error warning me tha...

AAnci.1 by Associate II
  • 704 Views
  • 1 replies
  • 0 kudos

Downsampling image on f746

Hi, I'm working on a project involving using NN with cube ai to track objects from images coming from a camera sensor. I would like to find a way to downsample an image in the fastest / less cpu intensive way possible (the video feed is approximately...

AAnci.1 by Associate II
  • 559 Views
  • 1 replies
  • 0 kudos

Different behavior between model on Python and on STM32

Hello,I created a CNN model used Keras with tensorflow here's the modelmodel = models.Sequential() model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32,1))) model.add(layers.MaxPooling2D((2, 2))) model.add(layers.Conv2D(64, (3, ...

HAlzo by Senior
  • 472 Views
  • 0 replies
  • 0 kudos

Multi-sensing evaluation/prototyping board for various ML models

Hi,I am looking for a dev. tool to try to implement pre-trained various classifiers from sensors data into a microcontroller.I want to implement various ML models including NNs, SVM, Random Forest and Naïve Bayes. The sensor types for the inputs woul...

bardetad by Associate II
  • 1475 Views
  • 7 replies
  • 0 kudos