The Xiaoml kit is one of the Devkits that complements Harvard University's Vijay Janapa Reddi's book “Machine Learning Systems to Machine Learning Systems,” which is available free of charge as a 2050-page PDF file.
The Xiaoml kit, created by Seed Studio, is Xiao ESP32S3 Sense ESP32-S3 WiFi and Bluetooth SoC, MicroSD card slot, built-in OV3660 Camera and microphone, andIMU Breakout BoardIt features a 6-axis IMU and a 0.42-inch OLED display. The kit allows students, educators and developers to build vision, sound, and motion applications through Marcelo Rovai (UNIFEI) and developed TINYML lab sessions.
xiaoml kit specifications:
- Main board – Xiao ESP32S3 Sense
- SOC – Espressif Systems ESP32-S3R8 Dual-Core Tensilica LX7 Microcontroller @240MHz 512kb SRAM, 8MB PSRAM, Wi-Fi 4 & Bluetooth 5.0 Dual Mode (Classic + BLE) Connectivity
- Storage – 8MB Flash, microSD card slot
- Sensors – OV3660 camera, digital microphone
- USB – USB-C port for power and programming
- Expansion Board – IMU Breakout Board
- Display – 0.42 inch OLED with SSD1315 driver IC
- Sensor – 6-axis LSM6DS3TR-C IMU
- Headers and pogo pins for connection to Xiao ESP32S3 sense
- Others – Reset button, battery header
- power supply
- 5V via USB Type C
- 3.7V battery connector on IMU breakout board
- Dimensions – 21 x 17.8 x 30 mm
- Weight – 10.6 grams
The full kit includes the XIAO ESP32-S3 Sense with pre-soldered headers, the IMU Breakout Board, a 2.4GHz FPC antenna (1.16dBi), two heatsinks (not sure why), and a MicroSD card tool kit included of a 32GB SanDisk microSD card, a USB Type-C to USB Type-A converter, and a 20cm Type-A to Type-C cable.
Lessons specific to the XiaOML kit can be found directly from the PDF or on the book website. There are four exercises: image classification and object detection, camera use, keyword spotting with built-in microphones, and motion classification and anomaly detection with IMU.
As mentioned in the introduction, the Xiaoml kit is just one of the hardware platforms used in the “Introduction to Machine Learning Systems” book. Others are the Raspberry Pi 4/5/Zero 2W SBCS, Arduino Nicla Vision, and Grove Vision AI V2 modules. Each one has its own advantages and disadvantages, as shown in the table below, but I don't know why the Raspberry Pi ecosystem is not ideal for production deployments (you should probably read the book…).
If you're particularly interested in Xiaoml kits, you can find them on Seed Studio for $38.90. It should soon be listed on your company's Aliexpress store.
Before quitting his job as a software engineering manager, Jean-Luc started CNX Software as a part-time effort in 2010 and began reviewing full-time in the second half of 2011.
Supports CNX software! Donate via cryptocurrency, become a patreon sponsor, or buy items on Amazon or Aliexpress. Also, if you purchase after clicking on these links, you will use the affiliate links in the article to win the committee.
