Update app.py

app.py

@@ -22,7 +22,7 @@ def make_prediction(img, feature_extractor, model):
         processed_outputs[0],
         outputs["decoder_attentions"],
         outputs["encoder_attentions"],
-        outputs["cross_attentions"],
+        # outputs["cross_attentions"],
     )
 
 
@@ -54,13 +54,13 @@ def detect_objects(model_name, image_input, threshold, display_mask=False, img_i
     encoder_attention_map_img = visualize_attention_map(
         image_input, encoder_attention_map
     )
-    cross_attention_map_img = visualize_attention_map(image_input, cross_attention_map)
+    # cross_attention_map_img = visualize_attention_map(image_input, cross_attention_map)
 
     return (
         viz_img,
         decoder_attention_map_img,
         encoder_attention_map_img,
-        cross_attention_map_img,
+        # cross_attention_map_img,
         model_details
     )
 
@@ -123,9 +123,9 @@ with gr.Blocks(css=css) as app:
             gr.Markdown("""Decoder attentions""")
             with gr.Row():
                 decoder_att_map_output = gr.Image(shape=(850, 850))
-            gr.Markdown("""Cross attentions""")
-            with gr.Row():
-                cross_att_map_output = gr.Image(shape=(850, 850))
+            # gr.Markdown("""Cross attentions""")
+            # with gr.Row():
+            #    cross_att_map_output = gr.Image(shape=(850, 850))
         with gr.TabItem("Model details"):
             with gr.Row():
                 model_details = gr.Markdown(""" """)
@@ -140,7 +140,7 @@ with gr.Blocks(css=css) as app:
             img_output_from_upload,
             decoder_att_map_output,
             encoder_att_map_output,
-            cross_att_map_output,
+            # cross_att_map_output,
             model_details,
         ],
         queue=True,