Seeed Studio just released an AI and deep Learning Beast! It is none other than the ROCK Pi N10 – RK3399 Pro! Through this blog, you will learn about all about this RK3399Pro SBC!
We are going to cover:
- What is the RK3399Pro
- About Rock Pi N10 – RK3399Pro
- Comparison between Raspberry Pi and Jetson Nano
What is the RK3399Pro
- The RK3399Pro is an AI processor with high expansion capability.
- It features includes:
- Supports dual Type-C interfaces
- Dual ISPs
- Supports 4096×2160 display output and 8-channel digital microphone arrays input.
- This AI processor is special compared to other AI processors out there as it is the first to adopt a CPU + GPU + NPU hardware structure. With this combination, this chip is a beast when it comes to deep learning and AI.
- An NPU (Neural Network Processing Unit) is a specialized circuit that implements all necessary control and arithmetic logic necessary to execute machine learning algorithms.
- Some features of the Rockchip RK3399 Pro includes:
- High-Performance AI hardware. With its NPU and computing performance that reaches 2.4TOPs, the performance is 150% higher than other same type NPU processor and the power consumption is less than 1%, compared with other solutions adopting GPU as an AI computing unit.
- Interface compatibility. The RK3399Pro supports 8bit and 16bit which is compatible with various AI software frameworks like OpenVX and TensorFlow Lite/AndroidNN API.
Enough of the chip, let us jump right into the SBC! The Rock Pi N10 – RK3399Pro
- The Rock Pi N10. It is a new member of the Rock pi family that is born for AI and deep learning processing.
- It carries a powerful SoC(system on chip) which is RK3399Pro and as mentioned above, features a CPU, GPU and NPU.
- RK3399Pro’s CPU is a six-core CPU which includes Dual Cortex-A72(frequency 1.8GHz) and quad Cortex-A53(frequency 1.4GHz).
- The GPU of RK3399Pro is Mali T860MP4 which has the ability to support OpenGL ES 1.1 /2.0 /3.0 /3.1 /3.2, Vulkan 1.0, Open CL 1.1 1.2, DX1.
- As for NPU, the NPU can support 8/16 bit computing and up to 3.0 TOPS computing power.
- Rock Pi N10 also has plenty of resources for storage. 64 bits dual-channel 4GB LPDDR and 16GB eMMC 5.1 is embedded on the mainboard for providing enough storage for processing and saving data. Besides, the board also contains a μSD card slot for booting and even an M.2 SSD connector which supports up to 2T SSD for extending storage.
- The Rock Pi N10 is totally an interface monster. Like Raspberry 4B, Rock Pi N10 has rich interfaces for Audio, camera, display, Ethernet, USB and I/O pins. The Ethernet interface can support PoE function and has a PoE hat near the Ethernet interface. The SBC can not support wi-fi for now, but there will be an optional wi-fi module to be embedded on the board later soon
- The software system of this Rock Pi N10 board is Debian and Android 8.1. For the NPU, there is an upgraded firmware and booting procedure.
- Other boards that feature the RK3399Pro Rockchip like the Toybrick RK3399Pro AI Developer Kit costs above $200, but with the Rock Pi N10, it is more affordable starting at only $99.
- RK3399 PRO SoC which includes 6-Core CPU, GPU, and NPU.
- 4GB Dual channel LPDDR3, 16GB eMMC 5.1, μSD card slot(up to 128 G)and M.2 SSD connector (up to 2T)
- Support the Debian software system and Android 8.1.
- Includes an NPU that has the power of computing up to 3.0 TOPS especially for AI and deep learning processing.
|ROCK PI N10 Model A – RK3399Pro|
|RK3399Pro||CPU||Dual Cortex-A72, frequency 1.8GHz with quad Cortex-A53, frequency 1.4GHz|
|GPU||Mali T860MP4 GPU, OpenGL ES 1.1 /2.0 /3.0 /3.1 /3.2, Vulkan 1.0, Open CL 1.1 1.2, DX1|
|NPU||Support 8bit/16bit computing, up to 3.0TOPs computing power|
(depends on model)
|4 GB LPDDR3
6 GB LPDDR3
8 GB LPDDR3
|64bit dual channel [email protected]/s, 3GB for CPU/GPU, 1GB for NPU
64bit dual channel [email protected]/s, 4GB for CPU/GPU, 2GB for NPU
64bit dual channel [email protected]/s, 4GB for CPU/GPU, 4GB for NPU
|Storage||16 / 32 / 64 GB eMMC||High-performance eMMC 5.1|
|μSD card||μSD slot supports up to 128 GB uSD card|
|M.2 SSD||M.2 connector supports up to 2T M.2 NVMD SSD|
|Display||HDMI||Full-size HDMI 2.0 up to [email protected](Type A)|
|MIPI DSI||MIPI DSI 2 lanes via FPC connector(HDMI and MIPI can work at the same time, support mirror mode or extend mode)|
|Audio||3.5 jack with mic||HD codec that supports up to 24-bit/96 kHz audio|
|Camera||MIPI CSI||MIPI CSI 2 lanes via FPC connector, support up to 800MP camera|
|Wireless||–||Optional Rock Pi wireless module|
|USB 3.0 OTG x1||
Hardware switch for host/device switch, the front one
|USB 2.0 HOST x2|
|Ethernet||GbE LAN with PoE||Support additional HAT is required for powering from PoE|
|IO||40-pin expansion header||– 1 x UART
– 2 x SPI bus
– 2 x I2C bus
– 1 x PCM/I2S
– 1 x SPDIF
– 1 x PWM
– 1 x ADC
– 6 x GPIO
– 2 x 5V DC power in
– 2 x 3.3V power pin
|Power||USB PD||Support USB Type C PD 2.0, 9V/2A, 12V/2A, 15V/2A, 20V/2A|
|Qualcomm® Quick Charge™||Support QC3.0/2.0 adapter, 9V/2A, 12V/1.5A|
|Others||RTC||RTC battery connector for time backup(optional)|
||4GB LPDDR3 & 16GB eMMC
|6GB LPDDR3 & 32GB eMMC||$129.00|
|8GB LPDDR3 & 64GB eMMC||$169.00|
Comparison between Raspberry Pi and Jetson Nano
So, why use the Rock Pi N10 – RK3399 for deep learning and AI? How about other boards that can perform AI like the Raspberry Pi and Jetson Nano? How does the Rock Pi N10 fair against them?
No worries as today, we compare the Rock Pi N10 features and specs against the Raspberry Pi 4 and NVIDIA Jetson Nano:
|SBC||Rock Pi N10(Model A/B/C)||Raspberry Pi 4B||Jetson Nano|
|CPU||Dual [email protected] 1.8GHz and quad Cortex-A53 1.4GHz||Quad-core ARM Cortex-A72 64-bit @ 1.5 GHz||Quad-Core ARM Cortex-A57 64-bit @ 1.42 GHz|
|GPU||Mali T860MP4||Broadcom VideoCore VI (32-bit)||NVIDIA Maxwell w/ 128 CUDA cores @ 921 Mhz|
|NPU||3.0 TOPS computing power||–||–|
|LPDDR||4/6/8GB LPDDR3||4GB LPDDR4||4GB LPDDR4|
|Networking||Gigabit Ethernet only||Gigabit Ethernet / Wifi 802.11ac||Gigabit Ethernet / M.2 Key E (for Wifi support)|
|Display||HDMI 2.0||2x micro-HDMI (up to 4Kp60)||HDMI 2.0 and eDP 1.4|
|USB||1x USB 3.0, 2x USB 2.0||2x USB 3.0, 2x USB 2.0||4x USB 3.0, USB 2.0 Micro-B|
|Video Encoder||H264(1080p30) and VP8||H264(1080p30)||H.264/H.265 (4Kp30)|
VC-1, MPEG-1/2/4, VP8
|H.264/H.265 (4Kp60, 2x 4Kp30)|
|GPIO||40-pin GPIO||40-pin GPIO||40-pin GPIO|
As you can tell, each SBCs have its own advantages and disadvantages.
- The cheapest at only $55
- Strong community with good support for debugging. Tutorials on the Raspberry Pi 4 can also be found readily on the internet.
- Powerful CPU (Quad-core ARM Cortex-A72 64-bit @ 1.5 GHz)
- Weaker GPU compared to the other boards.
- Requires additional heatsink and fan for sustained inference and heavy loads like deep learning to prevent overheating
- Features a super GPU (NVIDIA Maxwell w/ 128 CUDA cores @ 921 Mhz) that has 128 cores to process complex images and videos which allows it to perform well in AI image processing area.
- Requires an additional external wifi dongle for Wifi.
Rock Pi N10
- Powerful NPU for complex processing, so it is also able to perform well in the situation of AI or deep learning processing.
- Cost higher than the others
The Rock Pi N10 – RK3399Pro is definitely a monster when it comes to deep learning and AI because of its powerful NPU which offers up to 3.0 TOPS computing power! At its price point, you will definitely get your money worth with this SBC.
What do you think? Let us know about your thought on the Rock Pi N10 -RK3399Pro in the comments section down below!
Want to learn more about microcontrollers for AI and deep learning? You can check out our other blog here!