Research

Research

81600 bookmarks
Newest
Wiley
Wiley
Be seen. Be cited. Engineering and technology research helps solve society’s challenges. This is why IET journals are openly accessible to all.
Wiley
Human Development Index
Human Development Index
composite statistic of life expectancy, education, and income indices
Human Development Index
Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System
Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System
Real-time object detection demands high throughput and low latency, necessitating the use of hardware accelerators. NPU is specialized hardware designed to accelerate the calculation of deep learning models, providing better energy efficiency and parallel processing performance than existing CPUs or GPUs. In particular, it plays an important role in reducing latency and improving processing speed in applications that require real-time processing. In this paper, we construct a real-time object detection system based on YOLOv3, utilizing Neubla’s Antara NPU, and propose two approaches for performance optimization. First, we ensure the continuity of NPU inference by allowing the CPU to process data in advance through double buffering. Second, in a multi-NPU environment, we distribute tasks among NPUs through queue-based processing and analyze the performance limits using Amdahl’s law. Experimental results demonstrate that compared to a CPU-only environment, applying the NPU in single buffering improved throughput by 2.13 times, double buffering by 3.35 times, and in a multi-NPU environment by 4.81 times. Latency decreased by 1.6 times in single and double buffering, and by 1.18 times in the multi-NPU environment. The accuracy remained consistent, with 31.4 mAP on the CPU and 31.8 mAP on the NPU.
Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System
Cash App Support
Cash App Support
Get help with Cash App. Find answers to common questions, troubleshoot issues, and contact support for your Cash App account, payments, and Cash Card.
Cash App Support
Understanding Vanishing and Exploding Gradients in Deep Learning
Understanding Vanishing and Exploding Gradients in Deep Learning
Understanding Vanishing and Exploding Gradients in Deep Learning by Oluwaseyi Akinsanya This article is a continuation of my previous Medium post on Gradient Descent Optimization, where we explored …
Understanding Vanishing and Exploding Gradients in Deep Learning
FFI Utilities and JSON Parsing | cactus-compute/cactus | DeepWiki
FFI Utilities and JSON Parsing | cactus-compute/cactus | DeepWiki
This page documents the utility functions and data structures that support the FFI layer by providing JSON parsing, JSON construction, error handling, and helper operations. These utilities bridge the
FFI Utilities and JSON Parsing | cactus-compute/cactus | DeepWiki
Tensor.Art
Tensor.Art
AI model sharing platform, online run models to generate image,viode and traning model for free. Your can upload and download models, include Checkpoint, Embedding, ControlNet, LoRA, Pony, LoCon, LyCORIS. Also we offer some base model like Stable Diffusion 1.5, SDXL and Hunyuan-DiT, Wan, FLUX, VACE to generate.
Tensor.Art
Salt Spring dollar
Salt Spring dollar
local currency issued by the Salt Spring Island Monetary Foundation and used in Salt Spring Island, British Columbia, Canada
Salt Spring dollar