diff --git a/mu_map/eval/measures.py b/mu_map/eval/measures.py
index b17f73a9b3ad8677585edac11a96a5bbe5338b14..f91c3e6e7cd450320af390b87729bf36b14e97c1 100644
--- a/mu_map/eval/measures.py
+++ b/mu_map/eval/measures.py
@@ -94,7 +94,7 @@ if __name__ == "__main__":
     )
 
     measures = {"NMAE": nmae, "MSE": mse}
-    values = pd.Dataframe(map(lambda x: (x, []), measures.keys()))
+    values = pd.DataFrame(dict(map(lambda x: (x, []), measures.keys())))
     for i, (recon, mu_map) in enumerate(dataset):
         print(
             f"Process input {str(i):>{len(str(len(dataset)))}}/{len(dataset)}", end="\r"
@@ -104,12 +104,15 @@ if __name__ == "__main__":
         prediction = prediction.squeeze().cpu().numpy()
         mu_map = mu_map.squeeze().cpu().numpy()
 
-        row = dict(
-            map(lambda item: (item[0], item[1](prediction, mu_map)), measures.items)
-        )
-        values = values.append(row, ignore_index=True)
+        row = pd.DataFrame(dict(
+            map(lambda item: (item[0], [item[1](prediction, mu_map)]), measures.items())
+        ))
+        values = pd.concat((values, row), ignore_index=True)
     print(f" " * 100, end="\r")
 
+    if args.out:
+        values.to_csv(args.out, index=False)
+
     print("Scores:")
     for measure_name, measure_values in values.items():
         mean = measure_values.mean()