Update README.md

README.md

@@ -200,13 +200,22 @@ The diversity of landscapes and scenes of the test set should closely match the
 
 #### Metrics
 
-The **FRACTAL-LidarHD_7cl_randlanet** model achieves a performance of mIoU=77.2%.
+The **FRACTAL-LidarHD_7cl_randlanet** model achieves a performance of **mIoU=77.2%** and **OA=96.1%**.
 
 The following table gives the class-wise metrics on the test set:
 
-**Classes**|other|ground|vegetation|building|water|bridge|permanent structure|
-|---------|-----|-----|-----|-----|-----|-----|-----|
-**IoU**|52.0|91.7|93.6|90.6|91.2|56.8|62.1|
+**Class**|**IoU**|**Accuracy**|**Precision**|**Recall**|**F1**
+-----|---|--------|---------|------|---
+**other**|52.0|54.9|77.8|54.9|64.4
+**ground**|91.7|97.7|93.8|97.7|95.8
+**vegetation**|93.6|95.6|98.0|95.6|96.8
+**building**|90.6|93.7|96.2|93.7|95.0
+**water**|91.2|92.6|97.1|92.6|94.8
+**bridge**|56.8|96.1|79.3|78.6|79.0
+**permanent structure**|62.1|76.6|78.9|76.6|77.7
+-----|---|--------|---------|------|---
+**Macro Average**|77.5|86.7|88.7|84.2|86.2
+
 
 
 The following illustration gives the resulting confusion matrix :