- Building a 3D Digital Clock with ArduinoPosted 4 months ago
- Creating a controller for Minecraft with realistic body movements using ArduinoPosted 5 months ago
- Snowflake with ArduinoPosted 5 months ago
- Holographic Christmas TreePosted 6 months ago
- Segstick: Build Your Own Self-Balancing Vehicle in Just 2 Days with ArduinoPosted 6 months ago
- ZSWatch: An Open-Source Smartwatch Project Based on the Zephyr Operating SystemPosted 7 months ago
- What is IoT and which devices to usePosted 7 months ago
- Maker Faire Rome Unveils Thrilling “Padel Smash Future” Pavilion for Sports EnthusiastsPosted 8 months ago
- Make your curtains smartPosted 8 months ago
- Configuring an ESP8266 for Battery PowerPosted 8 months ago
Bitmain and 96Boards Have Released the Sophon Edge Development Board for Deep Learning
Bitmain has been moving into the AI business with their offshoot Sophon, which specializes in TPU-equipped devices. The company has recently collaborated with 96Boards to launch the Sophon Edge Developer Board to bring deep-learning capabilities for any number of different projects, including edge AI applications.
The board conforms to the 96Boards CE specification, and include two Arm Cortex-A53 cores, a Bitmain Sophon Edge TPU delivering 1 TOPS performance on 8-bit integer operations, USB 3.0 and gigabit Ethernet. One interesting aspect is the mixture between Arm and RISC-V architectures in this chip.
Sophon Edge specifications:
- SoC ASIC – Sophon BM1880 dual core Cortex-A53 processor @ 1.5 GHz, single core RISC-V processor @ 1 GHz, 2MB on-chip RAM, and a TPU (Tensor Processing Unit) that can provide 1TOPS for INT8,and up to 2 TOPs by enabling Winograd convolution acceleration
- System Memory – 1GB LPDDR4 @ 3200Mhz
- Storage – 8GB eMMC flash + micro SD card slot
- Video Processing – H.264 decoder, MJPEG encoder/decoder, 1x 1080p @ 60fps or 2x 1080p @ 30fps H.264 decoder, 75fps for FHD images
- Connectivity – Gigabit Ethernet(RJ-45), Wifi, Bluetooth
- USB – 3x USB 3.0 for camera, U-disk..
- I/O Expansion – 40-pin 96Boards low-speed expansion header including 2x I2S audio interfaces among others
- Power Supply – 12V/2A
- Dimensions – 85mm x 55mm (96Boards Consumer Edition)
In terms of software, the Bitmain Sophon EDB runs Linux and can take advantage of Linaro 96Boards, Raspberry Pi, and Arduino add-on modules. This enables low cost & low power DL/ML applications such as facial detection and recognition, facial expression analysis, object detection and recognition, vehicle license plate recognition, voiceprint recognition, etc. Supported frameworks include Caffe, ONNX, Pytorch, and Tensorflow.
Hardware and software documentation is available on 96boards website.