Updated reference for road-segmentation-adas-0001 model (#3282)

Author: Anna Grebneva

models/intel/road-segmentation-adas-0001/README.md

@@ -24,11 +24,11 @@ that was converted for four class classification task are:
 
 | Label    |       IOU |       ACC |
 |----------|-----------|-----------|
-| **mean** | **0.844** | **0.901** |
+| **mean** | **0.844** | **0.899** |
 | BG       |     0.986 |     0.994 |
 | road     |     0.954 |     0.974 |
-| curbs    |     0.727 |     0.831 |
-| marks    |     0.708 |     0.806 |
+| curbs    |     0.727 |     0.825 |
+| marks    |     0.707 |     0.803 |
 
 - `IOU=TP/(TP+FN+FP)`
 - `ACC=TP/GT`

models/intel/road-segmentation-adas-0001/accuracy-check.yml

@@ -13,14 +13,14 @@ models:
             reference:
               BG: 0.986
               curbs: 0.727
-              marks: 0.708
+              marks: 0.707
               mean: 0.844
               road: 0.954
           - type: mean_accuracy
             presenter: print_vector
             reference:
               BG: 0.994
-              curbs: 0.831
-              marks: 0.806
-              mean: 0.901
+              curbs: 0.825
+              marks: 0.803
+              mean: 0.899
               road: 0.974