把 YOLOv8 的检测、分割、姿态模型导出为 ONNX 并用 TensorRT 加速推理，支持 Jetson 和 DeepStream 部署。
用 C++ 把 YOLOv8 模型部署到 TensorRT 上做高性能推理，适合需要低延迟目标检测的工程落地场景。
用 YOLOv8 做检测、ByteTrack 做跟踪的目标跟踪工程，通过 C++ 和 TensorRT 加速推理，适合需要实时多目标跟踪的部署场景。
基于 ONNX/YOLOv8 和 DirectML 的通用 AI 瞄准辅助工具，为行动不便的玩家提供视觉对齐能力，用 C# 实现。
为 ComfyUI 提供抠图与分割节点，集成 RMBG、BiRefNet、SAM、YOLO、GroundingDINO 等模型，可去背景并分割物体、人脸、服装。
…⚠️ Breaking changes Three legacy models are gone. yolov8 old , yolov8 pose old and yolov8 seg old — kept as A/B references for the fused rewrite — are removed, along with
…orRT 官方 ONNX Parser。 已支持模型 - 检测 : YOLOv3, YOLOv5, YOLOv8, YOLOv10, YOLOv11, YOLOv12, YOLOv13, YOLO26, YOLOX, RT-DETR, RF-DETR - 分割 : YOLOv5-Seg, YOLOv8-Seg, YOLO26-Seg -
…(light, ~23 MB) and FastSAM-x (quality, ~138 MB). YOLOv8-seg architecture; outputs boxes + scores + mask coefficients + mask protos. License: AGPL-3.0 (Ultralytics). See
…o have initially installed - Some modules (Coral, Yolov8) now allow you to download individual models at runtime via the dashboard. - A new generative AI module (Llama LL
…b.com/PaddlePaddle/X2Paddle/pull/954 [Bug]Support YOLOv8-cls by @wjj19950828 in https://github.com/PaddlePaddle/X2Paddle/pull/952 New Contributors @rainyfly made their fi
YOLOv8 Object Tracking Ultralytics