blueprtints
Collection
6 items โข Updated
How to use GreenMap/yolo11x-blueprint-legend-layout-detector with ultralytics:
from huggingface_hub import hf_hub_download
from ultralytics import YOLO
# pick the weights file from this repo's "Files and versions" tab
weights = hf_hub_download("GreenMap/yolo11x-blueprint-legend-layout-detector", "<weights>.pt")
model = YOLO(weights)
source = 'http://images.cocodataset.org/val2017/000000039769.jpg'
model.predict(source=source, save=True)YOLO11x model trained to detect structural elements inside blueprint legends on architectural and construction drawings.
| 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. |
| Class | Images | Instances | Precision | Recall | mAP50 | mAP50-95 |
|---|---|---|---|---|---|---|
| all | 68 | 2821 | 0.912 | 0.903 | 0.918 | 0.735 |
| legend_symbol | 68 | 907 | 0.982 | 0.986 | 0.993 | 0.890 |
| legend_description | 68 | 956 | 0.977 | 0.984 | 0.993 | 0.831 |
| legend_row | 68 | 901 | 0.962 | 0.984 | 0.990 | 0.799 |
| continuous_elements_block | 41 | 57 | 0.727 | 0.655 | 0.696 | 0.421 |