跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

yolo-models

Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable detection/segmentation, custom architecture, Platform Explore, or exact weight names and availability.

ultralytics · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add ultralytics/skills --skill yolo-models

技能说明


name: yolo-models description: > Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable detection/segmentation, custom architecture, Platform Explore, or exact weight names and availability.

Choosing an Ultralytics model

Default recommendation: YOLO26, pretrained. Latest generation, with an optional NMS-free head (nms=False) for the fastest CPU inference and simplest deployment. Use YOLO11/YOLOv8 only to match an existing codebase or a deployment target that doesn't support YOLO26 yet. Most official weights auto-download on first use; sam3.pt and sam3.1_multiplex.pt require manual access and download.

Choose in Platform

For the quickest no-code start, click New Model in a project. Its Official tab lists YOLO26 (recommended), YOLO11, YOLOv8, and YOLOv5 models whose task can train the selected dataset; My Models lists your completed or uploaded checkpoints for further fine-tuning. To browse the official models first, open the @ultralytics projects under Projects in Platform Explore.

Use a Platform model page to inspect metrics, test it in Predict, export it, deploy it, clone a public model into your workspace, or download its .pt weights for the Python/CLI workflows below. See Platform Models and Explore.

Model = family + size + task suffix

yolo26 + n/s/m/l/x + task suffix → yolo26s-seg.pt

SizeCOCO mAP50-95ParamsT4 TensorRTPick for
n40.92.4M~1.7 msedge/mobile, CPU realtime, first prototype
s48.69.5M~2.5 msbalanced default for most projects
m53.120.4M~4.7 msGPU server, accuracy matters
l55.024.8M~6.2 msaccuracy-critical, ample GPU
x57.555.7M~11.8 msmax accuracy, offline/batch

Strategy: prototype on n to validate the pipeline cheaply, then scale up until accuracy stops paying for the latency. A bigger model never fixes bad labels.

SuffixTaskOutput
(none)detectboxes
-seginstance segmentationpolygons + boxes
-semsemantic segmentation (YOLO26+)per-pixel class mask
-depthmonocular depth (YOLO26+)depth map
-clsclassificationclass probabilities
-posepose/keypointskeypoints + boxes
-obboriented boxesrotated boxes

Notes on the newer tasks:

  • semantic (-sem): dataset uses PNG masks via masks_dir (default masks/) or polygon labels; metric is mIoU.
  • depth (-depth): targets are scaled uint16 PNG maps (preferred) or floating-point .npy maps in meters; metric is delta1. Depth models also expose model.calibrate(data=...), which fits a metric-scale correction; persist it with model.save(...).

Family cheat sheet

FamilyClassWhen
YOLO26 / YOLO11 / YOLO12 / YOLOv8–v10YOLO("yolo26n.pt")standard closed-set tasks; default choice
YOLO-WorldYOLOWorld("yolov8s-worldv2.pt")zero-shot detection of arbitrary text classes; model.set_classes(["person", "helmet"]); prefer -worldv2 (original -world weights cannot export)
YOLOEYOLOE("yoloe-26s-seg.pt")open-vocabulary detect+segment via text or visual prompts; set_classes(["person", "helmet"]), visual prompts via predict(..., visual_prompts={"bboxes": ..., "cls": ...}, predictor=YOLOEVPSegPredictor) (the default predictor returns boxes only); -pf variants are prompt-free
SAM / SAM2 / SAM3 / MobileSAMSAM("sam_b.pt")promptable segmentation: predict(source, bboxes=... / points=... / labels=...); SAM2/SAM3 add video predictors; SAM3 adds text/exemplar concept segmentation (SAM3SemanticPredictor); inference only
FastSAMFastSAM("FastSAM-s.pt")CNN-based segment-anything, much faster than SAM; no training
阅读完整来源 ↗