1: Classification of AI Chips There are many AI chips on the market, which can be quite dazzling. Based on their application scope, they can generally be divided into several categories. Terminal AI Chips: Terminal AI chips require low power consumption and have relatively low computing power demands, mainly for AI inference applications. Terminal AI … Read more
1. Weight Initialization — The “Morning Star” of Neural Networks In the vast universe of neural networks, weight initialization serves as the morning star, guiding the direction of model training. It is not merely about randomly assigning initial values to weights; rather, it is a crucial factor that determines whether the model can learn efficiently … Read more
This article is compiled from the NVIDIA lecture “Empower Your Industrial Edge AI Applications with NVIDIA Jetson“ (This is not a complete lecture, just selected slides we believe are key) Let’s dive into the industrial aspects. What challenges exist in cognitive environments? Industrial applications need to consider various shock factors. For example, systems may experience … Read more
The NVIDIA Jetson platform provides extensive access to edge AI and robotics application development through the world’s most comprehensive AI software stack and ecosystem. It integrates scalable platform software, modern AI stacks, flexible microservices and APIs, ROS packages, and AI workflows tailored for specific applications. In this talk, you will learn the skills to accelerate … Read more
The AI Network Video Recorder (AI-NVR) is a reference application in NVIDIA’s Metropolis microservices for Jetson, which is a cloud-native component suite for developing edge AI applications and solutions. This video provides an overview of the system services, microservices, and an introduction to building the AI-NVR.
This article is organized from NVIDIA’s 2024 GTC lecture. Now, let’s dive deep into our Jetson platform. These are our Jetson Orin modules, and we have seven different modules covering the entire range from entry-level to high performance. The best part is that, unlike before, we have adopted a SOC (System on Chip) architecture across … Read more
Cloud Horse Intelligent Transportation is a technology innovation company focused on L4 level autonomous driving technology in urban scenarios. While pursuing technological innovation, it is also facing a series of challenges: Control algorithms for autonomous vehicles, increasing computational power requirements Flexible deployment to meet different scenarios and needs Maintaining reliability in various challenging work environments … Read more
Today, I would like to introduce a project: running the LLama 2 model on the Jetson AGX Orin. This project comes from: Don’t worry, we have already replicated this project on the Jetson AGX Xavier 32G, so it is feasible. Background Large language models (LLM) like ChatGPT and Llama 2 have the potential to change … Read more
RoboSense is a global leader in intelligent LiDAR systems technology. Through a closed loop of three core technologies: LiDAR hardware, perception software, and chips, RoboSense provides the market with intelligent LiDAR systems that have information understanding capabilities, redefining the traditional definition of LiDAR hardware as mere information collectors, empowering robots and vehicles with perception abilities … Read more