feat: clean code

app.py

@@ -45,11 +45,12 @@ def inference_image_caption(raw_image):
         caption = model.generate(image, sample=True, top_p=0.9, max_length=20, min_length=5)
     return caption[0]
 
-inputs = gr.Image(type='pil')
+inputs = gr.Image(type='pil', label="Input")
 outputs = gr.outputs.Textbox(label="Output")
 
 title = "BLIP"
 
 description = "Gradio demo for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation"
 
-gr.Interface(inference_image_caption, inputs, outputs, title=title, description=description, examples=[['starrynight.jpeg',]]).launch(enable_queue=True, share=True)
+app = gr.Interface(inference_image_caption, inputs, outputs, title=title, description=description, examples=[['starrynight.jpeg',]])
+app.launch(enable_queue=True, share=True)