update

src/about.py

@@ -25,7 +25,7 @@ class Tasks(Enum):
 
 class Quotas(Enum):
     Perception = Task("Perception", "overall", "Perception")
-    Perception_VisualGrounding = Task("Perception_VisualGrounding", "VisualGrounding", "VisualGrounding")
+    Perception_VisualGrounding = Task("Perception", "VisualGrounding", "per_VisualGrounding")
     SpatialReasoning = Task("SpatialReasoning", "overall", "SpatialReasoning")
     Prediction = Task("Prediction", "overall", "Prediction")
     Planning = Task("Planning", "overall", "Planning")

src/leaderboard/read_evals.py

@@ -85,7 +85,7 @@ class EvalResult:
  
         for task in Quotas:
             task = task.value
-
+            print("task.value",task.value, "task.metric",task.metric, "task.benchmark", task.benchmark)
             # We average all scores of a given metric (not all metrics are present in all files)
             accs = np.array([v.get(task.metric, None) for k, v in data["results"].items() if task.benchmark == k])
             if accs.size == 0 or any([acc is None for acc in accs]):