Objective of This Article This article will detail how to configure the RKNN Docker environment on an Android development board equipped with the RK3588 chip in a Windows 11 system environment, and how to run the YOLOv5 object detection model accelerated by NPU on the development board using the adb tool. Development Environment Description Host … Read more
Are you still struggling to find a mini PC that offers explosive performance while being power-friendly? Today, we must unveil the RK3588 Mini PC, which will definitely break your preconceived notions about mini PCs! 🎯It is equipped with Rockchip’s new generation flagship AIoT SoC, meticulously crafted using advanced 8nm lithography technology. What does this mean? … Read more
The RK3588, as Rockchip’s flagship chip, has garnered attention from many industries due to its industrial-grade computing power. However, not every RK3588 image processing board can be used directly, as it requires deep customization based on the camera interface and application scenario. Chengdu Huishi possesses the capability for rapid integration and customization. With years of … Read more
The Objective of This Article This article will practice the PPOCR example in the RKNN Docker environment and deploy it to the RK3588 development board using the adb tool. Development Environment Description Host System: Windows 11 Target Device: Android development board equipped with the RK3588 chip Core Tools: Docker image containing rknn-toolkit2, rknn_model_zoo, and other … Read more
iTOP-3588 development board uses the Rockchip RK3588 processor, which is a new generation high-end application chip for AloT, utilizing an 8nm LP process, equipped with an octa-core 64-bit CPU, consisting of four Cortex-A76 and four Cortex-A55 cores, with a maximum frequency of 2.4GHz. It is a high-performance product suitable for internet devices and other digital … Read more
The Objective of This Article This article will practice the MobileNet image classification example in the RKNN Docker environment and deploy it to the RK3588 development board using the adb tool. For an introduction to MobileNet, please refer to the previous article. Development Environment Description Host System: Windows 11 Target Device: Android development board equipped … Read more
After the iTOP-RK3588 development board supports Preemption and the Xenomai kernel, Beijing Xunwei has joined forces with Wanghuo Real-time Linux system, achieving new breakthroughs in the field of industrial control. The iTOP-RK3588 development board has successfully adapted to Wanghuo Real-time Linux, and this update will provide stronger support for applications requiring higher real-time performance. Testing … Read more
The real-time kernel of RK3588 is tested here to verify its metrics for subsequent evaluation and reference of real-time indicators related to RK3588. The test results may vary, and the final results are based on actual tests. 1. Compiling the Kernel Two patches need to be modified for the RT kernel, as follows: diff –git … Read more
In the field of artificial intelligence and natural language processing, utilizing powerful tools and frameworks to interact with locally deployed models is a common and important task. Today, I will share how to use the LangChain framework to access models deployed locally on the RK3588. Background Knowledge Introduction to LangChain LangChain is a powerful Python … Read more
Using the NPU to run inference on large models can more effectively plan resource allocation, achieving more efficient applications. 1 Preparation Before Deployment To deploy large language models using the NPU on RK3588, the following files need to be prepared in advance, which include the corresponding files for Rockchip’s NPU and the DeepSeek inference model … Read more