Update README.md
Browse files
README.md
CHANGED
|
@@ -174,6 +174,18 @@ These errors highlight an important limitation, the model relies heavily on visu
|
|
| 174 |
|
| 175 |
---
|
| 176 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
## Performance Analysis
|
| 178 |
|
| 179 |
The model performs best when:
|
|
|
|
| 174 |
|
| 175 |
---
|
| 176 |
|
| 177 |
+
## Evaluation
|
| 178 |
+
|
| 179 |
+
The model was evaluated using standard object detection metrics.
|
| 180 |
+
|
| 181 |
+
The precision and recall curves illustrate the model’s ability to detect bike lanes while minimizing false positives. The F1 curve shows the optimal balance between precision and recall, and the PR curve summarizes overall detection performance across confidence thresholds.
|
| 182 |
+
|
| 183 |
+
### Curves
|
| 184 |
+
|
| 185 |
+
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
|
| 189 |
## Performance Analysis
|
| 190 |
|
| 191 |
The model performs best when:
|