Using the RK3588 Chip NPU: Running YOLOv5 Object Detection Model on Windows 11 with RKNN Docker

Using the RK3588 Chip NPU: Running YOLOv5 Object Detection Model on Windows 11 with RKNN Docker

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

Axera Technology | Axera Tongyuan NPU Adaptation for Qwen2.5-VL-3B

Axera Technology | Axera Tongyuan NPU Adaptation for Qwen2.5-VL-3B

Qwen2.5-VL:the new flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. Axera Tongyuan:an AI computing processor based on operator as the atomic instruction set. It efficiently supports mixed precision algorithm design and Transformers, providing a strong foundation for large models (DeepSeek, Qwen, MiniCPM, etc.) in “cloud-edge-end” AI applications. https://www.axera-tech.com/Skill/166.html TLDR … Read more

Xiangteng NPU Chip (1) – Fully Domestic Autonomous Defined Neural Network Chip for Strong Real-Time, High-Performance, and High-Concurrency Application Scenarios

Xiangteng NPU Chip (1) - Fully Domestic Autonomous Defined Neural Network Chip for Strong Real-Time, High-Performance, and High-Concurrency Application Scenarios

The Xiangteng NPU chip HKN201 is a fully domestic autonomous defined neural network chip, aimed at strong real-time, high-performance, and high-concurrency application scenarios.1. Chip Specifications Overview of Chip Specifications Chip Specification List AI Processor 4-core 2048MAC NPU core Clock frequency 1GHz AI Computing Power 16TOPS INT8 8TFLOPS FP16 Software Specifications Supports PyTorch, Caffe, Darknet deep … Read more

Xiangteng NPU Chip (2) – AI Chip for Inference Applications

Xiangteng NPU Chip (2) - AI Chip for Inference Applications

The Xiangteng NPU chip is an AI chip designed for inference.When applying artificial intelligence, we encounter two concepts: Training and Inference, which are two stages in the implementation of AI. Let’s first understand these two issues. What is the difference between training and inference? What key points should we focus on to distinguish between AI … Read more

Using the RK3588 Chip NPU: Example of Running PPOCRv4 in Windows 11 Docker

Using the RK3588 Chip NPU: Example of Running PPOCRv4 in Windows 11 Docker

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

Xiangteng NPU Chip (4) – Core Board Hardware Design Reference Materials Summary

Xiangteng NPU Chip (4) - Core Board Hardware Design Reference Materials Summary

The Xiangteng NPU chip HKN201 neural network processor is a domestically produced, high-performance, multi-core processor designed for strong real-time, high-performance, and high-concurrency application scenarios by Xi’an Xiangteng Microelectronics Technology Co., Ltd.The hardware design of the HKN201 neural network processor core board requires reference documents including the hardware design guide, core board hardware schematic reference, schematic … Read more

From Principles to Programming: A Step-by-Step Guide to PLC Analog Input Temperature Measurement

From Principles to Programming: A Step-by-Step Guide to PLC Analog Input Temperature Measurement

Click the blue text above to follow us Task Control A certain equipment manufacturer uses a temperature sensor to measure the workshop temperature, with a range of -30℃ to 150℃. When the measured workshop temperature is -30℃, the current output from the sensor is 0mA, corresponding to a PLC digital value of 0; when the … Read more

Beyond CPU/GPU: How NPU Enables AI to Operate Lightly

Beyond CPU/GPU: How NPU Enables AI to Operate Lightly

The report from Electronic Enthusiasts (by Li Wanwan) states that the NPU is a processor specifically designed for artificial intelligence (AI) computations, primarily used for efficiently executing operations related to neural networks (such as matrix multiplication, convolution, activation functions, etc.). Compared to traditional CPU/GPU, the NPU has advantages in energy efficiency and computational speed, making … Read more

World’s First Photon-Based NPU

World's First Photon-Based NPU

👆If you would like to meet regularly, feel free to star 🌟 and bookmark it~Source: ContentTranslated fromthebrighterside, thank you. From online shopping to medical research, artificial intelligence (AI) continues to impact our daily lives. However, behind every click or discovery lies a world of computational power facing significant challenges. Today’s computers consume vast amounts of … Read more

Expert Interview Summary: Don’t Just Focus on NVIDIA, ASICs are the Ultimate Solution for AI Chips

Expert Interview Summary: Don't Just Focus on NVIDIA, ASICs are the Ultimate Solution for AI Chips

1、Summary of “In the Era of DeepSeek, ASIC Chips Crowned as Kings” ■ With rapid iterations of models like GPT-4.5, Grok-3, Claude 3.5, and LLaMA 4, the number of domestic generative AI users has surpassed 300 million, leading to a massive demand for inference computing power. ■ NPU (Edge AI) is suitable for terminal devices … Read more