debug

app.py

@@ -13,7 +13,7 @@ model.to(device)
 
 def image_text_zeroshot(image, text_list):
     image_paths = [image]
-    labels = [label.strip(" ") for label in text_list.strip(" ").split(",")]
+    labels = [label.strip(" ") for label in text_list.strip(" ").split("|")]
     inputs = {
         ModalityType.TEXT: data.load_and_transform_text(text_list, device),
         ModalityType.VISION: data.load_and_transform_vision_data(image_paths, device),