Update app.py

app.py

@@ -83,7 +83,7 @@ def video_text_zeroshot(image, text_list):
     return score_dict
 
 def doubleimage_text_zeroshot(image, image2,  text_list):
-    image_paths = [image]
+    image_paths = [image, image2]
     labels = [label.strip(" ") for label in text_list.strip(" ").split("|")]
     inputs = {
         ModalityType.TEXT: data.load_and_transform_text(labels, device),