X-AnyLabeling v2.4.4

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	d8d33f16e5afae68b410ad331c98d2da
X-Anylabeling-Linux-CPU	1e6746f82e095dcc22d51b11594adc96

Note

For GPU acceleration and the macOS version, please consult the guide at this link.
To use the video tracking feature with segment-anything-2, refer to the same document.

Important updates

Add support for YOLO11 Det/OBB/Pose/Seg/Track models

• Integrate YOLO11 models from ultralytics v8.3.0
• Enable detection, oriented bounding box, pose estimation, segmentation, and tracking functionalities
• Update relevant documentation and dependencies)

Full Changelog: v2.4.3...v2.4.4

X-AnyLabeling v2.4.3

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	e51ee39db428686c6e1dfea53f80d148
X-Anylabeling-Linux-CPU	3d2a3751229e6a702b52862367306c4a

Note

For GPU acceleration and the macOS version, please consult the guide at this link.
To use the video tracking feature with segment-anything-2, refer to the same document.

Important updates

• [Bug fixed] Ensure integer values for shape dimensions in show_shape signal by @CVHub520 in f974994
• [Bug fixed] Fixed model loading error for YOLOv6lite face models (#638) by @CVHub520 in 995cf04
• [Refactor] Enhance logging with bold and colored headers for better readability by @CVHub520 in 73a4288
• [Model] Added support RMBG v1.4 model for image matting by @CVHub520 in 5a599e8
• [Optimize]: Modify indexing operations to improve file navigation efficiency by @CVHub520 in e67a79f
• [Optimize] Improve EXIF orientation handling with backup and logging by @CVHub520 in 59a73fa
• [Optimize] Implement natural sorting for QListWidget labels (#627) by @CVHub520 in 3638fa9
• [Optimize] Enable support for user-defined labels and track IDs (#629) by @CVHub520 in b173161

Full Changelog: v2.4.2...v2.4.3

X-AnyLabeling v2.4.2

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	870548a8ef4310f811ec205ab625cdef
X-Anylabeling-Linux-CPU	2df31af95c868640afc199772cbbf6d6

Note

For GPU acceleration and the macOS version, please consult the guide at this link.
To use the video tracking feature with segment-anything-2, refer to the same document.

Important updates

• [Model] Added support for interactive video object tracking by SAM2 (#602) by @CVHub520 in 0437e39
• [Feature] Implement functionality to visualize drawing results @CVHub520 in cf8faf5
• [Debug] Add vscode configuration files for module debugging and profiling by @CVHub520 in c807139
• [Update] Fix typo in upload_coco_annotation function by @CVHub520 in 6be1cc2

Full Changelog: v2.4.1...v2.4.2

X-AnyLabeling v2.4.1

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	99aafdfef8367fbe306425edae2745eb
X-Anylabeling-Linux-CPU	4c6358c7b6d1c0c3596b4c54e8ed6745

Note

To utilize GPU acceleration or the macOS version, refer to the guide at this.

Important updates

• [Bug fixed] Fixed patch memory leak in image caching during image transitions by @CVHub520 in 5c498c2
• [Bug fixed] Retain labels during switch model instances by @CVHub520 in 90217a9
• [Feature] Add dialog for modifying group_id by @CVHub520 in 04b6298
• [Feature] Add support to export mots annotations by @CVHub520 in da12032

Full Changelog: v2.4.0...v2.4.1

X-AnyLabeling v2.4.0

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	8442c84cafdf6deddfe9e5fceb9af17e
X-Anylabeling-Linux-CPU	b13829a34a1ff0f0b193c51fc4d951ea

Note

To utilize GPU acceleration or the macOS version, refer to the guide at this.

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	Bot-Sort, ByteTrack
Segment Anything	SAM2, SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM++, RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything v2, Depth Anything

Important updates

• Bumped to v2.4.0 with a refreshed X-Anything app icon by @CVHub520 in fd1d8e9
• Implement structured ISSUE_TEMPLATE for better issue management by @CVHub520 in 6c1a7b3
• Create SECURITY.md file by @CVHub520 in 838bc29
• Optimize code related to "actions" by @PairZhu in a377764

New features

• Implemented masked image saving functionality by @CVHub520 in f076e28
• Add support to tracking by hbb/obb/seg/pose task by @CVHub520 in 479bfce
• Support GroundingSAM2 model by @CVHub520 in b242f15
• Support lightweight model for Japanese recognition by @CVHub520 in 1a6abf5
• Support Segment-Anything-2 model by @CVHub520 in 4e68572
• Enable move_mode parameter in label_dialog for enhanced interaction control by @CVHub520 in 4a943ad
• Add use_system_clipboard action by @PairZhu in d7c9430
• Enable import/export of ODVG annotations to and from the Grounding DINO dataset by @CVHub520 in 918a8b5
• Add support to RT-DETRv2 model by @CVHub520 in 0fe5cff
• Add support RAM++ and YOLOW-RAM++ model by @CVHub520 in c1aa103
• Implement feature to draw KIE linking lines with arrowheads by @CVHub520 in b8f98f1
• Add support for displaying and exporting shape-level information by @CVHub520 in b9f201c
• Enable Depth-Anything model prediction with color and grayscale rendering modes by @CVHub520 in 837a642
• Add import and export functionality for PPOCR-KIE annotations by @CVHub520 in bbab395
• Add support to annotate KIE linking field by @CVHub520 in 4441704
• Add support for annotating out-of-pixmap rotation shapes by @CVHub520 in fe3cb53
• Add support for the depth-anything-v2 model by @CVHub520 in 6dd8ab1
• Add import and export functionality for PPOCR label by @CVHub520 in ae79d56
• Add toggle for continuous drawing mode without automatic switch to edit mode by @CVHub520 in 7ba6458
• Support union of multiple selected rectangle shapes by @CVHub520 in 8244cce
• Add system_clipboard copy mode by @PairZhu in 24d14f2
• Add ability to delete label items based on checkbox selection by @CVHub520 in 6020b85
• Enable opening previous/next labeled image by @CVHub520 in 8f5d0e6
• Implement crosshair and marking box style customization by @CVHub520 in 233dd4f
• Add widget for converting polygon to hbb support by @CVHub520 in 00d3fff
• Add yolo-pose import and export functionality by @CVHub520 in 99fb6c8
• Enable export voc-format annotations for polygon shape by @CVHub520 in 15ee242
• Add preserve existing annotations checkbox to auto-labeling settings and allow real-time confidence parameter adjustments on the interface by @CVHub520 in ec1ae44
• Add visibility feature for keypoint detection task by @CVHub520 in 5d8a7c1
• Support yolov8-world and yolov8-oiv7 model by @CVHub520 in 98a95db
• Add feature to display confidence score by @CVHub520 in e6de5e6

Docs

• Add faq.md file by @CVHub520 in ea098d0
• Add OCR example by @CVHub520 in 37b3150
• Add MOT example by @CVHub520 in 66d1a55
• Add Pose Estimation example by @CVHub520 in 9874bee
• Add Segmentation example by @CVHub520 in b49bd61
• Add HBB Object Detection example by @CVHub520 in e52c501
• Add OBB Object Detection example by @CVHub520 in 34d6411
• Add Depth Estimation example by @CVHub520 in f650b9a
• Add Description examples by @CVHub520 in 106c1bf
• Add Shape-level Classification examples by @CVHub520 in cf7ff2c
• Add Image-level Classification examples by @CVHub520 in c8109c1

Bug fixed

• Fixed image distortion issue during brightness and contrast adjustment by @CVHub520 in 252ded0
• Fixed type error in fillRect by converting float values to int for compatibility with higher Python version by @CVHub520 in 71cfc30
• Resolved too many values to unpack error during YOLO class post-process by @CVHub520 in a69077d
• Fixed invalid literal for int() with base issue by @CVHub520 in 9380142
• Avoided directory not empty error when loading model @CVHub520 in 599327b
• Prevented crash when switching from image directory to imported image by @CVHub520 in 2402268
• Fixed the issue where BMP image files could not be loaded due to the missing '_getexif' attribute by @UnlimitedWand in 6f64077

Full Changelog: v2.3.7...v2.4.0

X-AnyLabeling v2.3.7

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	OC-Sort, ByteTrack
Segment Anything	SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything

X-AnyLabeling v2.3.6

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	e1116910bf307c1eeee4cfb2e23cad99
X-AnyLabeling-GPU.exe	c42b79aad0c77526fa0e155ad4f2b13c
X-Anylabeling-Linux-CPU	b19c67157a971ddc7d6e3b69ca53d9c7
X-Anylabeling-Linux-GPU	e5cfa26a75c1b77b50197bbc8b708087

Note: The GPU version mentioned above is compiled based on CUDA 11.6. Different versions may result in issues with xxx functionality. It is recommended to consider running the application using the source code, especially if compatibility issues arise.

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	OC-Sort, ByteTrack
Segment Anything	SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything

Important Updates

• ✅ [Fixed TypeError in YOLO model by ensuring setText accepts only string… · CVHub520/X-AnyLabeling@6f44](b73c268)
• ✅ Temporarily fixed ValueError by adding a check for selected shape existence in the shapes list (https://github.com/CVHub520/X-AnyLabeling/pull/388[)](https://github.com/CVHub520/X-AnyLabeling/commit/dca185a1f06956f29ce0356f1793277f8e886070)
• ✅ Fix bug: list index out of range for exporting dota annotations
• ✅ perf: Optimize the brightness contrast adjustment

X-AnyLabeling v2.3.5

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	960a981d31231a6cc2af1a5ca108e1cb
X-AnyLabeling-GPU.exe	fc8aaf1ff6133b0edc0a38b6553bf04a
X-Anylabeling-Linux-CPU	cb69ed2b1e5e8c4daf273853631e7a5d
X-Anylabeling-Linux-GPU	7509bfcbc1ef7c85bdaf152c14030072

Note: The GPU version mentioned above is compiled based on CUDA 11.6. Different versions may result in issues with xxx functionality. It is recommended to consider running the application using the source code, especially if compatibility issues arise.

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	OC-Sort, ByteTrack
Segment Anything	SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything

Important Updates

• ✅ Fixed TypeError in YOLO model by ensuring setText accepts only string… · CVHub520/X-AnyLabeling@6f44
• ✅ Add: Refine canvas reset behavior to prevent unintended blank canvas … · CVHub520/X-AnyLabeling@59c8
• ✅ Improve performance for loading large image files by optimizing proce… · CVHub520/X-AnyLabeling@a48b
• ✅ Enhanced image cropping: polygon and rotation shape_type support (#331) · CVHub520/X-AnyLabeling@cbbdc19
• ✅ Fixed IndexError in Canvas widget's shape module (#332) · CVHub520/X-AnyLabeling@5b31655
• ✅ Fixed invalid path issue when loading JSON file in Windows environmen… · CVHub520/X-AnyLabeling@3707
• ✅ Enhancement: Add widget for converting obb to hbb support · CVHub520/X-AnyLabeling@16d7f23

X-AnyLabeling v2.3.4

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	dee1df2f1cd1863d621fc2f4fe97017f
X-AnyLabeling-GPU.exe	642bcca37562f77885d8d6df373e78ab
X-Anylabeling-Linux-CPU	02c93aa107858a722a26aecc9aa081c9
X-Anylabeling-Linux-GPU	6a8388edff8dd4805262b5e516c47ea2

Note: The GPU version mentioned above is compiled based on CUDA 11.6. Different versions may result in issues with xxx functionality. It is recommended to consider running the application using the source code, especially if compatibility issues arise.

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	OC-Sort, ByteTrack
Segment Anything	SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything

Important Updates

• ✨✨✨ Support YOLO-World model.
• ✅ Enable label display feature.

X-AnyLabeling v2.3.3

Released versions

Version	MD5
X-AnyLabeling-CPU.exe	46810294c6cdf6978e8d0cb8a9561cd2
X-AnyLabeling-GPU.exe	05da78ffbb076e4e7db546ff336f3f59
X-Anylabeling-Linux-CPU	9168a0caa444fb294c08cb75bce782d5
X-Anylabeling-Linux-GPU	4ab880f23d90323b5423baaba92a2540

Note: The GPU version mentioned above is compiled based on CUDA 11.6. Different versions may result in issues with xxx functionality. It is recommended to consider running the application using the source code, especially if compatibility issues arise.

Supported models

Task	Model
Image Classification	ResNet50, InternImage, YOLOv5-cls, YOLOv8-cls, PULC Person/Vehicle Attribute
Object Detection	YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOX, YOLO-NAS, DAMO_YOLO, GOLD_YOLO, RT-DETR, RTMDet
Instance Segmentation	YOLOv5-seg, YOLOv8-seg
Keypoint Detection	RTMPose, DWPose, YOLOv6-face, YOLOv8-pose
Oriented Object Detection	YOLOv5_obb, YOLOv8_obb
Multi-Object Tracking	OC-Sort, ByteTrack
Segment Anything	SAM, SAM-HQ, EdgeSAM, MobileSAM, EfficientViT-SAM, Med-SAM2D
Optical Character Recognition	PPOCRv4
Land Detection	CLRNet
Image Captioning	RAM
Visual Language Model	Grounding-DINO, Chinese-CLIP, YOLO-World
Depth Estimation	Depth Anything

Important Updates

• ✨✨✨ Support YOLO-World model.
• ✅ Add expanded sub-image save feature.
• ✅ Support convert YOLO-Hbb/Obb/Seg label to custom.
• ✅ Add real-time progress bar for mask annotation uploads.