Update app.py

app.py

@@ -98,7 +98,7 @@ def inference(img):
 
     box_locations = outputs["instances"].pred_boxes
     box_loc_screen = box_locations.tensor.cpu().numpy()
-
+    unique_object_dict = {}
     for i, box_coord in enumerate(box_loc_screen):
         x0, y0, x1, y1 = box_coord
         width = x1 - x0
@@ -113,9 +113,11 @@ def inference(img):
                 "h": int(height),
             }
         )
-        object_list_str.append(
+        if (predicted_label not in unique_object_dict):
+            object_list_str.append(
             f"{predicted_label} - X:{int(x0)} Y: {int(y0)} Width: {int(width)} Height: {int(height)}"
-        )
+            )
+            unique_object_dict[predicted_label] = 1
 
 
     output_str = "Imagine you are an intelligent image captioner. Describe each object in detail separately, in a scene where the X,Y coordinates and width,height of  each object is given below. In the end give an overall summary of the scene\n"