hellcaster commited on
Commit
d267531
Β·
verified Β·
1 Parent(s): 74ed2d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -3
README.md CHANGED
@@ -1,3 +1,102 @@
1
- ---
2
- license: agpl-3.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Ultralytics/YOLO11
4
+ pipeline_tag: object-detection
5
+ library_name: ultralytics
6
+ tags:
7
+ - yolov11
8
+ - ultralytics
9
+ - yolo
10
+ - vision
11
+ - object-detection
12
+ - pytorch
13
+ - ui
14
+ datasets:
15
+ - MacPaw/Screen2AX-Group
16
+ license: agpl-3.0
17
+ ---
18
+
19
+ # πŸ” YOLOv11l β€” UI Groups Detection
20
+
21
+ This model is a fine-tuned version of [`Ultralytics/YOLO11`](https://huggingface.co/Ultralytics/YOLO11), trained to detect **UI groups** (e.g., toolbars, tab groups) in macOS application screenshots.
22
+
23
+ It is part of the **Screen2AX** project, a research-driven effort to generate accessibility metadata for macOS applications using vision-based techniques.
24
+
25
+ ---
26
+
27
+ ## 🧠 Task Overview
28
+
29
+ - **Task:** Object Detection
30
+ - **Target:** macOS UI groups
31
+ - **Supported Label(s):**
32
+ ```
33
+ ['AXGroup']
34
+ ```
35
+
36
+ This model detects higher-level UI groupings that are commonly used to structure accessible interfaces (e.g., `AXGroup`, `AXTabGroup`, `AXToolbar`, etc.).
37
+
38
+ ---
39
+
40
+ ## πŸ—‚ Dataset
41
+
42
+ - **Training data:** [`MacPaw/Screen2AX-Group`](https://huggingface.co/datasets/MacPaw/Screen2AX-Group)
43
+
44
+ ---
45
+
46
+ ## πŸš€ How to Use
47
+
48
+ ### πŸ”§ Install Dependencies
49
+
50
+ ```bash
51
+ pip install huggingface_hub ultralytics
52
+ ```
53
+
54
+ ### πŸ§ͺ Load the Model and Run Predictions
55
+
56
+ ```python
57
+ from huggingface_hub import hf_hub_download
58
+ from ultralytics import YOLO
59
+
60
+ # Download the model from the Hugging Face Hub
61
+ model_path = hf_hub_download(
62
+ repo_id="MacPaw/yolov11l-ui-groups-detection",
63
+ filename="ui-groups-detection.pt"
64
+ )
65
+
66
+ # Load and run prediction
67
+ model = YOLO(model_path)
68
+ results = model.predict("/path/to/your/image")
69
+
70
+ # Visualize or process results
71
+ results[0].show()
72
+ ```
73
+
74
+ ---
75
+
76
+ ## πŸ“œ License
77
+
78
+ This model is licensed under the **GNU Affero General Public License v3.0 (AGPL-3.0)**, inherited from the original YOLOv11 base model.
79
+
80
+ ---
81
+
82
+ ## πŸ”— Related Projects
83
+
84
+ - [Screen2AX Project](https://github.com/MacPaw/Screen2AX)
85
+ - [Screen2AX HuggingFace Collection](https://huggingface.co/collections/MacPaw/screen2ax-687dfe564d50f163020378b8)
86
+ - [YOLOv11l β€” UI Elements Detection](https://huggingface.co/MacPaw/yolov11l-ui-elements-detection)
87
+
88
+ ---
89
+
90
+ ## ✍️ Citation
91
+
92
+ If you use this model, please cite the Screen2AX paper:
93
+
94
+ ```bibtex
95
+ ...
96
+ ```
97
+
98
+ ---
99
+
100
+ ## 🌐 MacPaw Research
101
+
102
+ Learn more at [https://research.macpaw.com](https://research.macpaw.com)