Object Detection
ultralytics
yolo
yolo11
blueprint
floorplan
architecture
construction
legend
document-layout
cad
Instructions to use GreenMap/yolo11x-blueprint-legend-layout-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use GreenMap/yolo11x-blueprint-legend-layout-detector with ultralytics:
# Couldn't find a valid YOLO version tag. # Replace XX with the correct version. from ultralytics import YOLOvXX model = YOLOvXX.from_pretrained("GreenMap/yolo11x-blueprint-legend-layout-detector") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
GreenMap/yolo11x-blueprint-legend-detector
Overview
YOLO11x model trained to detect structural elements inside blueprint legends on architectural and construction drawings.
- Detects legend symbols (hatch patterns and graphical symbols).
- Detects legend descriptions.
- Detects complete legend rows.
- Detects legend continuation blocks.
- Trained on architectural floor plans and construction drawings.
Classes
| ID | Class | Purpose |
|---|---|---|
| 0 | legend_symbol | Graphical symbol or hatch pattern representing a construction element or material. |
| 1 | legend_description | Text description corresponding to a legend symbol. |
| 2 | legend_row | Complete legend entry containing a symbol and its associated description. |
| 3 | legend_continuation_block | A block containing the continuous legend elements. |
Training Metrics
Validation Metrics
| Class | Images | Instances | Precision | Recall | mAP50 | mAP50-95 |
|---|---|---|---|---|---|---|
| all | 30 | 839 | 0.748 | 0.850 | 0.817 | 0.588 |
| legend_symbol | 30 | 263 | 0.919 | 0.947 | 0.964 | 0.834 |
| legend_description | 30 | 280 | 0.847 | 0.939 | 0.911 | 0.670 |
| legend_row | 30 | 254 | 0.886 | 0.965 | 0.972 | 0.686 |
| continuous_elements_block | 30 | 42 | 0.338 | 0.548 | 0.423 | 0.162 |
Training
- Base model: YOLO11x
- Task: Object Detection
- Input size: 1472 ร 1472
- Framework: Ultralytics YOLO
- Downloads last month
- 81

