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.
Run the SAM3 Tracker model faster on macOS devices using MLX.
github.com/ryouchinsa/sam3-t…
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?
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.
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.
rectlabel.com/rfdetr_segment…
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.
colab.research.google.com/gi…
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.
rectlabel.com/rfdetr_detecti…
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.
colab.research.google.com/gi…
- 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.