Scribd
Upload
22 views16 pages

VLSID 2024 DC OrientationSession

Uploaded by

Robins kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
22 views16 pages

VLSID 2024 DC OrientationSession

Uploaded by

Robins kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

VLSID-2024 : Design Contest

Orientation Session

21st August 2023


Agenda

# About Design Contest

# About STM32 Model Zoo

# Tools & Technologies

# Question & Answers

2
About Design Contest
• The theme of the contest is Artificial Intelligence on the Edge
• The objective is to use the STM32Cube.AI Edge AI development tools and
ecosystem to create and deploy embedded AI/ML based solutions to real world
problems from the following domains: Robotics, Healthcare, Agriculture, Battery
Management, Digital Power, and Renewable Energy Management Systems.
• Important dates
• Idea Submission by : 10th September,2023
• Selected idea Announcement on : 18th September 2023
• Kit Dispatch by : 21st September 2023
• Project Submission by : 5th December ,2023
• Selected Demo Announcement on : 12th December 2023
• Final Demonstration on : 9th Jan 2024
3
About STM32 Model Zoo

• STM32 Model Zoo : GitHub - STMicroelectronics/stm32ai-modelzoo: AI Model Zoo


for STM32 devices
X-CUBE-AI : AI Tool Features

• Generation of an STM32-optimized library from • Support for deeply quantized neural networks
pretrained neural network and classical machine (down to 1-bit) from QKeras and Larq
learning models
• Relocatable option enabling standalone model
• Native support for various deep learning update during product lifecycle by creating a model
frameworks such as Keras and TensorFlow™ Lite, binary code separated from the application code
and support for all frameworks that can export to
• Possibility to use larger networks by storing weights
the ONNX standard format such as PyTorch™,
in external flash memory and activation buffers in
MATLAB®, and more
external RAM
• Support for various built-in scikit-learn models such
• Easy portability across different STM32
as isolation forest, support vector machine (SVM),
microcontroller series through STM32Cube
K-means, and more
integration
• Support for 8-bit quantized neural network format
• With a TensorFlow™ Lite neural network, code
(TensorFlow™ Lite and ONNX Tensor-oriented
generation using either the STM32Cube.AI runtime
QDQ)
or TensorFlow™ Lite for Microcontrollers runtime
STM32 IoT Kit
• Ultra-low-power STM32L4 Series MCUs based on Arm® Cortex®-
M4 core with 1 Mbyte of Flash memory and 128 Kbytes of SRAM,
in LQFP100 package
• 64-Mbit Quad-SPI Flash memory
• Bluetooth® V4.1 module (SPBTLE-RF)
• Sub-GHz (868 MHz or 915 MHz) low-power-programmable RF
module (SPSGRF-868 or SPSGRF-915)
• 802.11 b/g/n compliant Wi-Fi® module from Inventek Systems
(ISM43362-M3G-L44)
• Dynamic NFC tag based on M24SR
• 2 digital omnidirectional microphones (MP34DT01)
• Capacitive digital sensor (HTS221). 3-axis magnetometer
(LIS3MDL)
• 3D accelerometer and 3D gyroscope (LSM6DSL)
• 260-1260 hPa absolute digital output barometer (LPS22HB)
• Time-of-Flight and gesture-detection sensor (VL53L0X)
Resources
• Top level ST page on AI, https://www.st.com/content/st_com/en/about/innovation---
technology/artificial-intelligence.html
• Webpage aggregating all ST AI tool solution
• MOOC on ST AI developer tool
• ST sensor portfolio
• MOOC on Intro to STM32 microcontroller
Tools & Technology

• STM32CubeMx :STM32CubeMX - STM32Cube initialization code generator -


STMicroelectronics
• Video : STM32CubeMX - STM32Cube initialization code generator – STMicroelectronics

• STM32CubeIDE : STM32CubeIDE - Integrated Development Environment for


STM32 - STMicroelectronics
STM32CubeMX
STM32CubeMX key steps

Power Consumption
MCU / board / Example Selector
Calculator

Code Generation Pinout Configuration

Software Components Clock Tree Initialization


Parameters

Peripherals Configuration

I2C SPI UART


CAN 24
MCU / MPU selection

MCU / MPU
SELECTOR

BOARD
SELECTOR

EXAMPLE
SELECTOR

11
Add Expansion Middleware and build your own

or

Download and install Build your own Expansion Package


existing Expansion Package… with STM32PackCreator

…and select components to add to your project


12
STM32CubeIDE
One tool for all your STM32 development

Chipset / Board Code Validation


Configuration Development Debug

14
Free multi-platform development tool
FREE

Eclipse/GCC Based Free for Commercial Development Multi-OS Support

15
Find out more at www.st.com

© STMicroelectronics - All rights reserved.


ST logo is a trademark or a registered trademark of STMicroelectronics International NV or its affiliates in the EU and/or other countries.
For additional information about ST trademarks, please refer to www.st.com/trademarks.
All other product or service names are the property of their respective owners.

You might also like