fix

app.py

@@ -11,9 +11,7 @@ def process(input_image, prompt):
     image = vis_processors["eval"](input_image).unsqueeze(0).to(device)
     text_input = txt_processors["eval"](prompt)
     sample = {"image": image, "text_input": [text_input]}
-
-    output = model.forward_qa(samples=sample, num_captions=50)
-    pred_answers = output[0]
+    pred_answers, caption, gradcam = model.predict_answers(sample, num_captions=50, num_patches=20)
 
     return pred_answer