Update app.py

app.py

@@ -53,7 +53,7 @@ def inference(raw_image, model_n, question, strategy):
               caption = model.generate(image, sample=False, num_beams=3, max_length=20, min_length=5)
           else:
               caption = model.generate(image, sample=True, top_p=0.9, max_length=20, min_length=5)
-          return 'caption: '+caption[0]
+          return caption[0]
 
     else:   
         image_vq = transform_vq(raw_image).unsqueeze(0).to(device)  
@@ -71,4 +71,13 @@ description = "Gradio demo for BLIP: Bootstrapping Language-Image Pre-training f
 article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.12086' target='_blank'>BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation</a> | <a href='https://github.com/salesforce/BLIP' target='_blank'>Github Repo</a></p>"
 
 
-gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=[['starrynight.jpeg',"Image Captioning","None","Nucleus sampling"]]).launch(enable_queue=True)
+gr.Interface(inference, 
+             inputs, 
+             outputs, 
+             title=title, 
+             description=description, 
+             article=article, 
+             examples=[['starrynight.jpeg',"Image Captioning","None","Nucleus sampling"]]
+             allow_flagging='never',
+             theme="default",
+             cache_examples=False).launch(enable_queue=True, debug=True)