Rectlabel-support

ryouchinsa更新放缓

RectLabel 是一款离线图像标注工具，用于给目标检测和分割任务画框、打标签、生成掩码，支持 Faster R-CNN、Mask R-CNN、Detectron 等格式。

RectLabel is an offline image annotation tool for object detection and segmentation.

暂无版本552star71fork同步于 2026-11-07 07:30 UTC

怎么上手

由 README 提炼，执行前请确认

从 App Store 安装 RectLabel 或 RectLabel Pro：https://apps.apple.com/app/id1210181730

硬件要求按 README 说明

README 未说明硬件要求；从 App Store 下载的 macOS 应用，离线运行。

由 README 自动翻译提炼

Mac 上的离线图像标注工具，用 SAM、Cellpose 和 Core ML 模型自动生成检测与分割标注

RectLabel 是一款离线图像标注工具，用于给目标检测和分割任务画框、打标签、生成掩码，支持 Faster R-CNN、Mask R-CNN、Detectron 等格式。

需从 Mac App Store 下载安装，仓库本身只是支持页不含源码；自动标注依赖内置 Core ML 模型，具体可用模型以应用内为准；使用前需阅读官方 Help 页了解操作流程

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

登录用户的真实使用记录，可按版本和硬件筛选

共 0 条

还没有人点评。第一个说出真实体验的人最有价值。

未翻译

This is the support page for RectLabel.

To download RectLabel apps.

How to use? Read our Help page.

Post feature requests to Issues page.

If you need to implement RectLabel-like app in your system, please contact us. [email protected]

Using text and box prompts of Segment Anything Model 3, multiple objects are labeled at once
Label polygons and pixels using Segment Anything Model 2
Label polygons and pixels using Cellpose model
Label bounding boxes using Tracking model
Automatic labeling using Core ML models including RF-DETR and YOLO26
Automatic text recognition for lines and words
Label cubic bezier curves, line segments, and points
Label oriented bounding boxes in aerial images
Label keypoints with a skeleton
Label pixels with brushes and superpixels
Settings for objects, attributes, hotkeys, and labeling fast
Search object, attribute, image names, and memo in a gallery view
Export to YOLO, COCO, CreateML, and DOTA formats
Export indexed color mask image and grayscale mask images
Video to image frames, augment images, etc.

sam3_polygon sam3_pixels sam2_polygon sam2_pixels cellpose_polygon coreml_polygon ocr draw_obb search5