phoronix.com
OpenCV 5.0 Released With Rewritten DNN Engine, Built-In LLM & VLM Support
OpenCV 5.0 released today as a major update to this widely-used, open-source computer vision (CV) library.
[!quote]+
OpenCV 5.0 今天发布，是这个广泛使用的开源计算机视觉 (CV) 库的重大更新。
OpenCV 5.0 采用了重写的深度神经网络（DNN）引擎，ONNX 覆盖率超过 80%，内置大型语言模型（LLM）和视觉语言模型（VLM）支持，以及新的硬件抽象层和更好的 3D 视觉工具包。
OpenCV 5.0 目前已为英特尔 IPP（内核经过 SSE/AVX 优化）、Arm KleidiCV、高通 FastCV 和 RISC-V Vector RVV 调整了路径。 接下来，OpenCV 开发人员计划在其新的 DNN 引擎中开发原生 GPU 支持。
OpenCV 5.0 在与微软 ONNX Runtime 的较量中表现出色：
OpenCV – 5 Jun 26
OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision
OpenCV 5 is here! A massive modernization brings a graph-based DNN engine, over 80% ONNX coverage, hardware acceleration, LLM/VLM support, and a faster Python-first core. Learn why this isn't just an incremental update.
Est. reading time: 19 minutes
3 个帖子 - 3 位参与者
来源: LinuxDo 最新话题查看原文