The solution of cluster servers is characterized by low power consumption, high manageability and great flexibility
Based on the AI-specific APiM framework, a modular deep neural network learning accelerator without any external caching can be used for high-performance edge computing, as a vision-based deep learning computing and AI algorithm acceleration.
Firefly-RK3399/AIO-3399J Android8.1 firmware supports Android Neural Networks API (NNAPI), which fully invokes the neural network API for hardware acceleration, and improves the AI computing performance of the RK3399 greatly.
The kernel code of Firefly ROC-RK3328-CC has been officially approved by kernel.org. The related BSP support has been added to Linux Kernel 4.17 version.
Quad-core ARM Cortex-A7, frequency up to 1.3GHz, integrated Mali-400 MP2 graphics processor, built-in 2D accelerator.
Firefly core board series is a small-sized main board that retains the core hardware and software functions.
Firefly first ultra-small open-source board ROC-RK3328-CC, using the RK3328 quad-core A53x4 64-bit processor, the size as a credit card, but contains a strong performance.
On February 3, 2018, Firefly held the Spring Festival Celebration.
Now into the era of face recognition, how to quickly build DEMO in the Firefly open source board, and rapid product In order to allow more products...
Firefly-RK3288 open source board with Flint OS becomes a computer host. Open the browser, you can use the massive web end application...
2017-08-04 16:49
2016-11-01 16:45