updates

app.py

@@ -27,23 +27,22 @@ try:
     print("Dataset features:", dataset.features)  # Check if 'split' is part of features
 
 
-    # Check if the 'split' column exists; if not, add it
-    if 'split' not in dataset.column_names:
-        split_values = []
-        for example in dataset:
-            match = re.search(r'_(\d+)\.', example["image_id"])
-            image_id = match.group(1).lstrip('0') 
-
-            if image_id in results:
-                split_values.append("dev")
-            else:
-                split_values.append("train")
-
-        # Add 'split' column to the dataset
-        dataset = dataset.replace_column("split", split_values)
-        print("Added 'split' column to dataset.")
-    else:
-        print("'split' column already exists.")
+    # # Check if the 'split' column exists; if not, add it
+    # if 'split' not in dataset.column_names:
+    split_values = []
+    for example in dataset:
+        match = re.search(r'_(\d+)\.', example["image_id"])
+        image_id = match.group(1).lstrip('0') 
+        if image_id in results:
+            split_values.append("dev")
+        else:
+            split_values.append("train")
+        
+    dataset = dataset.replace_column("split", split_values)
+    # print("Added 'split' column to dataset.")
+    
+    # else:
+        # print("'split' column already exists.")
     
     # Create a dictionary to keep track of the highest annotation count for each image
     annotation_counts = {}