Seeed Studio BeiQi RK1808 AIoT 96Boards Compute SoM
Seeed Studio BeiQi RK1808 AIoT 96Boards Compute SoM is a high-powered core board designed for the Artificial Intelligence of Things (AIoT) field. This Seeed Studio System-On-Module (SOM) uses the Rockchip RK1808 System on a Chip (SoC) as the main control chip. The BeiQi RK1808 SoM features the dual-core ARM Cortex-A53 CPU for ultra-low power consumption. This SoM supports single and double-precision operations with the help of the VFP v4 hardware. The BeiQi RK1808 SoM is compatible with Mxnet/Caffe/TensorFlow models and supports mainstream layer type and multi-class framework. This SoM provides easy-to-use development tools, performance estimation, accuracy verification, and PC-side model conversion.
The BeiQi RK1808 SoM features a powerful Neural Network Processing Unit (NPU) with a computing power of up to 3.0TOPS and supports 8-bit/16-bit operation. This SoM includes the MIPI-CSI camera interface that supports a maximum resolution of 1920 x 1080 and a USB camera. Typical applications include smart speakers, automotive products, drones, security monitoring, smart wear, and AI computing modules.
Features
- Dual-core ARM Cortex-A53 CPU for ultra-low power consumption
- Includes VFP v4 hardware that supports single and double precision operations
- ARM Neon Advanced Single Instruction, Multiple Data (SIMD) supports accelerated media and signal processing calculations
- Built-in neural network processor NPU for super-high AI computing power
- Compatible with Caffe/Mxnet/TensorFlow models
- Support multi-class framework, support mainstream layer type, and easy to add custom layer
- Provide easy-to-use development tools, PC-side model conversion, performance estimation, and accuracy verification
- AI Application Develop Flow
- Video decoder
- Video encoder
- Camera interface
- MIPI-CSI x 1 with a built-in ISP image processor
- Supports maximum input resolution of 1920 x 1080
- Display output interface
- Audio port
Specifications
- Rockchip RK1808 SoC
- Dual Cortex-A35 @ 1.6GHz CPU
- NPU with computing power up to 3.0TOPS
- Supports 8-bit/16-bit operation
- Supports TensorFlow and Caffe models
- 1GB LPDDR3 RAM
- 16GB eMMC
- Built-in Gigabit Ethernet PHY chip
- Built-in WiFi/BT module
- 5V DC power input
Applications
- Sweeping robot
- Drone
- Smart speaker
- Automotive products
- Smart wear
- Security monitoring
- AI computing modules
Additional Resource
Yayınlandı: 2019-09-17
| Güncellenmiş: 2023-12-29