RectLabel

An offline image annotation tool for object detection and segmentation.

[RectLabel @rectlabel]

Updated to RF-DETR 1.7.

How to Train a RF-DETR Instance Segmentation Model with Custom Data
https://t.co/HbKhbLUGLN

Goolge Colab
https://t.co/78I6TmNLQx

[RectLabel @rectlabel]

RF-DETR to CoreML works with RF-DETR 1.7.1 with Ultralytics YOLO 26 like names export.
https://t.co/AsjN7Mozx8

[RectLabel @rectlabel]

Updated to RF-DETR 1.7.
How to Train a RF-DETR Object Detection Model with Custom Data
https://t.co/YBT3Y2azaj

Google Colab.
https://t.co/aRPqTmt0mK

[RectLabel @rectlabel]

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

[RectLabel @rectlabel]

Annotations were labeled in RectLabel Pro on Arabidopsis images: the bounding box tightly encloses both guard cells, the mask traces the outer stomata boundary, and keypoints define two biological axes.

[RectLabel @rectlabel]

Towards Morphology Aware Stomata Keypoint Detection: Benchmarking Foundation Models Under Distribution Shift
https://t.co/JC7gWk809J

[RectLabel @rectlabel]

Run the SAM3 Tracker model faster on macOS devices using MLX.
https://t.co/RVXgJ22Ibx
We improved the MLX-VLM by @Prince_Canuma so that point, box, and mask input prompts work correctly.
If you have Apple M2 - M5 devices, could you tell us the processing time on your device?

[RectLabel @rectlabel]

When start SAM preprocessing, how to close the panel? For some users, it might be annoying.

[RectLabel @rectlabel]

RF-DETR to CoreML is a helpful repository when you convert RF-DETR PyTorch models to Core ML models for iOS and macOS.
https://t.co/3wmshJ1hhA

[RectLabel @rectlabel]

The new version 2026.04.02 was released.
- Corresponded to RF-DETR Core ML models.
- Exported split folders became train/valid/test.
- Exported COCO file name became _annotations.coco.json.
- Added "Convert pixels mask to polygon" option when exporting a COCO file.

[RectLabel @rectlabel]

We will show you how to train a RF-DETR instance segmentation model with your images and annotations and export to a Core ML model which can be used for auto labeling on RectLabel.
https://t.co/HbKhbLUGLN

[RectLabel @rectlabel]

We will show you how to train a RF-DETR instance segmentation model with your images and annotations and export to a Core ML model which can be used for auto labeling on RectLabel.
https://t.co/78I6TmNLQx

[RectLabel @rectlabel]

We will show you how to train a RF-DETR object detection model with your images and annotations and export to a Core ML model which can be used for auto labeling on RectLabel.
https://t.co/YBT3Y2azaj

[RectLabel @rectlabel]

We will show you how to train a RF-DETR object detection model with your images and annotations and export to a Core ML model which can be used for auto labeling on RectLabel.
https://t.co/aRPqTmt0mK

[RectLabel @rectlabel]

The new version 2026.03.22 was released.

[RectLabel @rectlabel]

- When "Delete this point" for a keypoints object, RectLabel makes a backup of all annotations, deletes the point from the skeleton, and deletes the point from all keypoints objects in annotation folders.

[RectLabel @rectlabel]

- "Create polygon using SAM3" feature corresponds to multiple text input such as "zebra,water,tree".

[RectLabel @rectlabel]

- Show label names with colored text according to the object color.

[RectLabel @rectlabel]

- Improved drawing speed of keypoint names, point indexes, and point coordinates.

[RectLabel @rectlabel]

From Captive to Wild Jaguars: Automated Behavioral Classification and Space Use Monitoring with Machine Learning
https://t.co/8Br63SmJnP