Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,60 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
library_name: ultralytics
|
| 4 |
+
pipeline_tag: object-detection
|
| 5 |
+
tags:
|
| 6 |
+
- yolo
|
| 7 |
+
- yolo11
|
| 8 |
+
- object-detection
|
| 9 |
+
- blueprint
|
| 10 |
+
- floorplan
|
| 11 |
+
- architecture
|
| 12 |
+
- construction
|
| 13 |
+
- legend
|
| 14 |
+
- document-layout
|
| 15 |
+
- cad
|
| 16 |
---
|
| 17 |
+
|
| 18 |
+
# GreenMap/yolo11x-blueprint-legend-detector
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Overview
|
| 23 |
+
|
| 24 |
+
YOLO11x model trained to detect structural elements inside blueprint legends on architectural and construction drawings.
|
| 25 |
+
|
| 26 |
+
- Detects legend symbols (hatch patterns and graphical symbols).
|
| 27 |
+
- Detects legend descriptions.
|
| 28 |
+
- Detects complete legend rows.
|
| 29 |
+
- Detects legend continuation blocks.
|
| 30 |
+
- Trained on architectural floor plans and construction drawings.
|
| 31 |
+
|
| 32 |
+
## Classes
|
| 33 |
+
|
| 34 |
+
| ID | Class | Purpose |
|
| 35 |
+
|----|---------------------------|---------------------------------------------------------------|
|
| 36 |
+
| 0 | legend_symbol | Graphical symbol or hatch pattern representing a construction element or material. |
|
| 37 |
+
| 1 | legend_description | Text description corresponding to a legend symbol. |
|
| 38 |
+
| 2 | legend_row | Complete legend entry containing a symbol and its associated description. |
|
| 39 |
+
| 3 | legend_continuation_block | A block containing the continuous legend elements. |
|
| 40 |
+
|
| 41 |
+
## Training Metrics
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
## Validation Metrics
|
| 46 |
+
|
| 47 |
+
| Class | Images | Instances | Precision | Recall | mAP50 | mAP50-95 |
|
| 48 |
+
|-------|--------|-----------|-----------|--------|-------|----------|
|
| 49 |
+
| all | 29 | 671 | 0.722 | 0.834 | 0.792 | 0.569 |
|
| 50 |
+
| legend_symbol | 29 | 212 | 0.905 | 0.949 | 0.939 | 0.811 |
|
| 51 |
+
| legend_description | 29 | 218 | 0.830 | 0.931 | 0.923 | 0.670 |
|
| 52 |
+
| legend_row | 29 | 203 | 0.832 | 0.956 | 0.965 | 0.644 |
|
| 53 |
+
| continuous_elements_block | 27 | 38 | 0.322 | 0.500 | 0.343 | 0.152 |
|
| 54 |
+
|
| 55 |
+
## Training
|
| 56 |
+
|
| 57 |
+
- Base model: YOLO11x
|
| 58 |
+
- Task: Object Detection
|
| 59 |
+
- Input size: 1472 × 1472
|
| 60 |
+
- Framework: Ultralytics YOLO
|