- Added "Convert to box using SAM" hotkey on Edit menu. - Shows rotated box rotation degrees at the bottom-left corner.

- Added "Create box using Tracking" on Edit menu.

- Improved Create keypoints mode so that both keypoints and the bounding box are shown and can be edited. To hide the bounding box, use View menu -> Hide keypoints boxes. - Added "Set window size" on View menu.

- Fixed the problem that the change button is not shown on the open table. - Removed the titlebar and updated the design for the macOS Tahoe.

- Improved not to crash for broken webp images. - Improved converting a pixels mask with holes to polygons.

- Added "Rename image" on File menu. - Added "Hide image name" on View menu. - Improved drawing selected multiple polygons not to show edit points.

- Added ONNX menu -> Load Cellpose ONNX Model. - Added "Export a Cellpose 16bit PNG file" option when exporting mask images. - Added "Import Cellpose 16bit PNG files" on Export menu. - Improved "Convert mask to polygon" feature so that you can use the smoothness slider to control the number of points. - Improved the speed and stability of Core ML segmentation models processed for all images. - Fixed so that when on search and changed the label name and memo, those changes are updated for the next search result. - Fixed so that when on search and relaunch app, the gallery view is correctly generated. - Fixed so that when exporting the settings file, CoreML and SAM panels are not shown.

When your YOLO text files are using the CRLF line break, RectLabel saves each YOLO text file using the CRLF line break, not LF line break.

When using "Create polygon using SAM" mode, after preprocessing the image, using the right click menu, you can use "Convert to box using SAM" feature to tighten selected existing boxes.

To save a track id for each box in the YOLO format, add an attribute named as “track id” of “Text input” type. class_index center_x center_y width height track_id 0 0.464615 0.594724 0.680000 0.769784 1 https://rectlabel.com/export/#export-yolo-txt-files

- When exporting the CreateML JSON file and training on Create ML, the error message "Data Analysis stopped without finishing" was shown if the first image has no annotations, so that RectLabel exports images with annotations first, and images witout annotations are appended to the last. - When exporting the CreateML JSON file from a single images folder, each image path included the subpath such as "person/0.jpg", but it was reverted to "image.jpg", so that you can drag & drop the CreateML JSON file into the images folder and start training on CreateML. - When converting a video file to image frames, image size was specified to 1500px, but sometimes the image was exported as 1499px, this problem was fixed. - Added "Show image full path" hotkey on View menu.

- Hidden objects are not exported. - Once opened images and annotations folders, from the second launch, you can use command line arguments to RectLabel which image files should be opened. open -a RectLabel --args -images 000000000872.jpg,000000010363.jpg open -a RectLabel\ Pro --args -images 000000000872.jpg,000000010363.jpg single folder open -a RectLabel --args -images 000000000872.jpg open -a RectLabel --args -images /Users/ryo/rcam/test_annotations/test/_test_min/images1500/000000000872.jpg multiple folders open -a RectLabel --args -images alice-pasqual-cOKmuKWSsiM-unsplash.jpg open -a RectLabel --args -images chocolate/images/alice-pasqual-cOKmuKWSsiM-unsplash.jpg open -a RectLabel --args -images /Users/ryo/rcam/test_annotations/test/_nested/donut-A/chocolate/images/alice-pasqual-cOKmuKWSsiM-unsplash.jpg nested folders open -a RectLabel --args -images alice-pasqual-cOKmuKWSsiM-unsplash.jpg open -a RectLabel --args -images donut/chocolate/alice-pasqual-cOKmuKWSsiM-unsplash.jpg open -a RectLabel --args -images /Users/ryo/rcam/test_annotations/test/_nested/nested1500/donut/chocolate/alice-pasqual-cOKmuKWSsiM-unsplash.jpg

- Added "Multi-Label Classification" option to the Export CreateML JSON file feature. - Fixed the copy/paste problem when you check on the “Auto copy from previous image” checkbox.

- Improved the search indexing so that when you changed the annotations, the search index is updated for the changes. - Fixed the heap memory crash when you run YOLOv5/v8/11 segmentation models.

- Fixed the problem when export train/val/test folders. - Fixed the problem when open a folder which includes a yaml file. - Improved so that when open images and annotations folders, you can drag & drop the root folder. For example, you can drag&drop the dataset-A folder to the open table and the child folders are automatically set. ~/Documents/dataset-A/dataset-A0/images ~/Documents/dataset-A/dataset-A0/annotations ~/Documents/dataset-A/dataset-A1/images ~/Documents/dataset-A/dataset-A1/annotations

- Improved so that when open an images folder which includes sub-folders recursively, the same sub-folders are structured in the annotations folder.

- Added the smooth slider on the Create polygon using SAM panel. Dragging the smooth slider, the number of polygon points changes. - Improved the “Convert pixels to polygon” feature to preserve each hole using the appropriate number of points.

- Added "Convert to polygon/pixels using SAM" right click menu for selected boxes. After preprocessing the image using SAM, you can convert each box to the polygon or pixels.

- Corresponded to the Segment Anything Model 2 in the Create polygon using SAM mode. SAM2 Tiny takes 1s for preprocessing. SAM2 Small takes 2s for preprocessing. SAM2 BasePlus takes 4s for preprocessing. SAM2 Large takes 10s for preprocessing.

- You can auto label when change the image if you check on the "Auto process" checkbox on the Core ML dialog. - You can auto label polygons or pixels if you check on/off the "Polygon" checkbox on the Core ML dialog when using the PASCAL VOC XML format. - Added "Delete image" hotkey. Deleted images and annotations are moved to the app folder. - Improved the crash when you edited the annotations and changed the image. For searching, indexing was updated everytime you changed the annotations, and the code was causing the crash. If you changed the annotations, when search, the indexing is done again.

- You can check off the "Split to train/val/test folders" feature when export.

- Fixed the backup problem when you import or process all images. - Added "Locate settings file" in App menu. You can share the settings file on iCloud drive among multiple devices.

- Improved the YOLO format so that you can save object names combined with attributes in "_name.txt" file. When train, use Export YOLO feature and check on the "Export only used names" option, all "_name.txt" files are scanned and the new objects table created, based on the objects table, each object index is written in each YOLO text file. - Improved exporting features of Create ML, Classification, COCO, YOLO, DOTA formats so that you can resize images and split them into train/val/test folders at once. - Corresponded to the Depth Anything model and DEtection TRansformer (DETR) model. - Improved running YOLOv5/v8 models using VNImageCropAndScaleOptionCenterCrop for classification models and VNImageCropAndScaleOptionScaleFit for detection/segmentation/pose/obb models. - Added "Search incorrectly predicted images" to show training images which predicted labels and boxes are incorrect compared with the current annotations. Such as "Not detected", "Not classified", and "Falsely detected". - Added hotkeys of "Copy as erase mask", "Cut using erase mask", and "Start SAM preprocessing".

- Added "Create memo" feature on Edit menus. You can add text memo to each image and can be used for searching. - Improved "Resize images" so that it does not resize the image if the image size is not changed.

- Improved "Resize images" feature so that it does not save empty xml files if there are no annotation files. - Improved "Resize images" feature so that it remembers the resized size. - Improved "Export COCO JSON file" feature so that when there are no annotations, "annotations" dictionary is not included. This is necesary for Detectron2 to evaluate the test dataset using inference_on_dataset funciton. - Improved "Import COCO JSON file" feature so that when evaluating the test dataset on Detectron2 using inference_on_dataset function, the result COCO JSON file can be imported to RectLabel.