Sipeed AI & IoT board is not only hardware but also provide an end-to-end, hardware + software infrastructure for the deployment of AI-based solutions.
Sipeed AI & IoT board can be used for a growing number of use-cases such as:
- predictive maintenance
- machine vision
- voice recognition
- anomaly detection
|CPU: RISC-V Dual Core 64bit, 400Mh adjustable
||Powerful dual-core 64-bit open architecture-based
processor with rich community resources
||High-speed UART and JTAG interface for debugging
||All GPIOs connected to header 2*20 2.54mm
|Micro SD card（TF card） slot
||Support Self-elastic card holder
|One-click Download circuit
||Just connect the USB typeC cable to complete the download
Onboard CH340, 2Mbps baud rate
|DVP Camera connector
||24P 0.5mm FPC connector
||8bit MCU LCD 24P 0.5mm FPC connector
||RST button and USR button
- 1st competitive RISC-V chip
- 28nm process, dual-core RISC-V 64bit IMAFDC, on-chip huge 8MB high-speed SRAM, 400MHz frequency (able up to 800MHz)
- KPU (Neural Network Processor):
- 64 KPU
- 576bit width
- convolution kernels
- any form of activation function.
- 0.25TOPS (trillion operations per second) @ 0.3W 400MHz,
- When overclocked to 800MHz, it offers 0.5TOPS
- APU (Audio Processor)
- 8 mics
- up to 192 kHz sample rate
- FFT unit
- 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
- Other accelerators and peripherals
- AES Accelerator
- SHA256 Accelerator
- FFT Accelerator (not APU's one)
The Sipeed AI & IoT board supports original standalone SDK, FreeRTOS SDK based on C/C++.
You can port micropython on it: http://en.maixpy.sipeed.com/.
It also supports FPIOA, GPIO, TIMER, PWM, Flash, OV2640, LCD. And it has zmodem, vi, SPIFFS on it, so that you can edit python directly or sz/rz file to board.
Seedstudio offers even more support to your project with their GitHub contributions:
The Sipeed AI & IoT board supports a fixed-point model that the mainstream training framework trains, according to specific restriction rules, and have a model compiler to compile models to its model format.
It supports tiny-yolo, mobilenet-v1, and, TensorFlow Lite! Many TensorFlow Lite model can be compiled and run on the Sipeed AI & IoT board!
- Support FreeRtos and Standard development kit
- Support MicroPython on M1
- Machine vision based on convolutional neural network
- High-performance microphone array processor
||4.8 V ~ 5.2 V
||> 600 mA
||< 30 K
||- 30 ℃ ~ 85 ℃