Note: This kit comes with 2.4 inch TFT Display starting 18 Nov 19 onwards.
Sipeed MAIX module is designed to run AI at the edge, delivering high performance in a small footprint. The competitive price makes it possible to embed the module into any IoT devices. Unlike Google Edge TPU, Sipeed MAIX acts as the master controller, not an accelerator like the Edge TPU. So it can achieve a lower power and lower cost solution if compared to the AP+Edge TPU system.
Maixduino comes with the Sipeed M1 module and ESP32 module for WiFi and Bluetooth connectivity in the Arduino UNO form factor.
- MAIX is not only hardware. It also provides an end-to-end, hardware + software infrastructure for facilitating the deployment of customers' AI-based solutions.
- Thanks to its performance, small footprint, low power, and low cost, MAIX enables for broader deployment of high-quality AI at the edge.
- MAIX has a growing number of industrial use cases such as predictive maintenance, anomaly detection, machine vision, robotics, voice recognition, and many more. It can be used in manufacturing, on-premise, healthcare, retail, smart spaces, transportation, etc.
- With a powerful Kendryte K210 dual-core RISC-V processor, MAIX offers many exciting features:
- It's the 1st competitive RISC-V chip with AI capability, newly released in Sep 2018
- 28nm process, dual-core RISC-V 64bit IMAFDC, on-chip huge 8MB high-speed SRAM (not for XMR :D), 400MHz frequency (able to 800MHz)
- KPU (Neural Network Processor) inside, 64 KPU which is 576bit width, supports convolution kernels, any form of activation function. It offers 0.25TOPS@0.3W,400MHz, when overclock to 800MHz, it offers 0.5TOPS. It means you can do object recognition 60fps@VGA
- APU (Audio Processor) inside, support 8mics, up to 192KHz sample rate, hardcore FFT unit inside, easy to make a Mic Array (MAIX offer it too)
- Flexible FPIOA (Field Programmable IO Array), you can map 255 functions to all 48 GPIOs on the chip
- DVP camera and MCU LCD interface, you can connect a DVP camera, run your algorithm, and display on LCD
- Many other accelerators and peripherals: AES Accelerator, SHA256 Accelerator, FFT Accelerator (not APU's one), OTP, UART, WDT, IIC, SPI, I2S, TIMER, RTC, PWM, etc.
Sipeed MAIX-I module, or called M1, integrate Kendryte K210, 3-channel DC-DC power, 8MB/16MB/128MB Flash into Square Inch Module. All usable IOs are broken out as 1.27mm(50mil) pins, and the pin's voltage is selectable between 3.3V and 1.8V.
Face detection demo
MAIX supports original standalone SDK, FreeRTOS SDK base on C/C++. The team has also ported micropython on it. It supports FPIOA, GPIO, TIMER, PWM, Flash, OV2640, LCD, etc. And it has zmodem, vi, SPIFFS on it, you can edit python directly or sz/rz file to board.
MAIX's Deep Learning:
MAIX supports fixed-point model that the mainstream training framework trains, according to specific restriction rules, and have a model compiler to compile models to its own model format. It supports Tiny YOLO, MobileNetV1 and TensorFlow Lite! Many TensorFlow Lite models can be compiled and run on MAIX!
- 1 x Maixduino board
- 1 x OV2640 Camera
- 1 x 2.4 inch TFT Display (18 Nov 19 Onwards)