Three Practical Insights on Multi-task Learning

Three Practical Insights on Multi-task Learning

Join the professional CV group at Jishi, and interact with 10,000+ visual developers from prestigious institutions like HKUST, Peking University, Tsinghua University, Chinese Academy of Sciences, CMU, Tencent, Baidu, and more! We also provide monthly expert live streams, real project demand connections, valuable information summaries, and industry technical exchanges. Follow the Jishi Platform public account, … Read more

RK3399Pro AI Development Board Supports Caffe/Tensorflow/Mxnet

RK3399Pro AI Development Board Supports Caffe/Tensorflow/Mxnet

Rockchip has released its first high-performance AI processor, the RK3399Pro, providing a one-stop turnkey solution for the AI field. Its on-chip NPU (Neural Processing Unit) has a computing performance of up to 3.0 TOPs, featuring high performance, low power consumption, and ease of development. The Three Major Features of the RK3399Pro AI Chip: 1. High … Read more

Understanding Pathways: Single-controller vs Multi-controller

Understanding Pathways: Single-controller vs Multi-controller

Source: OneFlow This article is approximately 7732 words long and is recommended to be read in 12 minutes. This article introduces the background of Pathways and provides an in-depth analysis. 01. Why Discuss Pathways? In the past two years, TensorFlow has been caught off guard by the rise of PyTorch, and the entire industry is … Read more

Can Low-Power MCUs Run AI? Unveiling TinyML Application Practices!

Can Low-Power MCUs Run AI? Unveiling TinyML Application Practices!

Artificial Intelligence(AI) on edge devices is revolutionizing the field of embedded electronics by enabling advanced computing capabilities directly on low-power devices. Traditionally, neural networks required powerful hardware and abundant resources, but with the development of technologies like TinyML, inference can now be performed directly on devices even with limited computational resources. Deploying neural networks on … Read more

Arm Ethos-U85 NPU: Implementing Generative AI on the Edge with Small Language Models

Arm Ethos-U85 NPU: Implementing Generative AI on the Edge with Small Language Models

With the evolution of artificial intelligence (AI), executing AI workloads on embedded devices using small language models (SLM) has become a focal point in the industry. Small language models such as Llama, Gemma, and Phi3 have gained widespread recognition for their excellent cost-effectiveness, high efficiency, and ease of deployment on resource-constrained devices. Arm expects the … Read more

MCU AI Deployment Technologies and Methods

MCU AI Deployment Technologies and Methods

Click the “blue text” above to follow us! 2025.07.16 Word count: 8484 Estimated reading time: 22 minutes Abstract Implementing artificial intelligence with microcontrollers has become a hot topic and challenge in embedded product development in recent years. This article discusses the methods, technologies, and tools for deploying deep network models on MCUs, analyzes the process … Read more

Getting Started with Nvidia Jetson Nano

Getting Started with Nvidia Jetson Nano

“ Nvidia launched a development board priced at only $99 at this year’s GTC – the Jetson Nano. This article will introduce how to get started with it, including the first boot, installing system packages, configuring the Python development environment, installing Keras and TensorFlow, modifying the default camera, and running classification and object detection tasks. … Read more

Implementing Pose Detection Using Raspberry Pi 4 and Coral USB Accelerator

Implementing Pose Detection Using Raspberry Pi 4 and Coral USB Accelerator

Click the card below to follow “Computer Vision Home“ Visual/Image processing insights delivered promptly! In this article, we will explore how to set up a pose detection AI system using the Raspberry Pi 4 and Coral USB Accelerator.Pose detection AI is an engaging application that allows computers to recognize and analyze human poses in real-time, … Read more

Nvidia Jetson Nano: Custom Object Detection from Scratch Using TensorFlow and OpenCV

Nvidia Jetson Nano: Custom Object Detection from Scratch Using TensorFlow and OpenCV

Author of this article: Reprinted from: https://medium.com/swlh/nvidia-jetson-nano-custom-object-detection-from-scratch-using-tensorflow-and-opencv-113fe4dba134 The purpose of this blog is to guide users in creating a custom object detection model optimized for performance to be used on the NVidia Jetson Nano. Table of Contents: Required Materials Creating a Custom Dataset Preprocessing Labeling Creating TFRecords CNN Training Model Installing Raspberry Pi Camera on … Read more

AI Revolution: 5 Open Source Tools to Break Through Technical Boundaries

AI Revolution: 5 Open Source Tools to Break Through Technical Boundaries

Artificial intelligence has fundamentally transformed various fields from software development to content creation. However, faced with a plethora of AI tools on the market, developers often find themselves in a dilemma: either pay for a subscription to commercial platforms or waste time on inefficient tools. In fact, the open-source community has long nurtured a batch … Read more