[refactor] start refactor app.py

app.py

@@ -2,6 +2,7 @@ import argparse
 import os
 import re
 import sys
+from typing import Callable
 
 import nh3
 import cv2
@@ -9,7 +10,6 @@ import gradio as gr
 import numpy as np
 import torch
 import torch.nn.functional as F
-from PIL import Image
 from transformers import AutoTokenizer, BitsAndBytesConfig, CLIPImageProcessor
 
 from model.LISA import LISAForCausalLM
@@ -334,25 +334,40 @@ def inference(input_str, input_image):
     return output_image, output_str
 
 
-demo = gr.Interface(
-    inference,
-    inputs=[
-        gr.Textbox(lines=1, placeholder=None, label="Text Instruction"),
-        gr.Image(type="filepath", label="Input Image"),
-    ],
-    outputs=[
-        gr.Image(type="pil", label="Segmentation Output"),
-        gr.Textbox(lines=1, placeholder=None, label="Text Output"),
-    ],
-    title=title,
-    description=description,
-    article=article,
-    examples=examples,
-    allow_flagging="auto",
-)
 
-demo.queue()
-demo.launch(
-    share=False,
-    server_name="0.0.0.0"
-)
+def server_runner(
+        fn_inference: Callable,
+        debug: bool = False,
+        server_name: str = "0.0.0.0"
+    ):
+    inference_app = gr.Interface(
+        fn_inference,
+        inputs=[
+            gr.Textbox(lines=1, placeholder=None, label="Text Instruction"),
+            gr.Image(type="filepath", label="Input Image")
+        ],
+        outputs=[
+            gr.Image(type="pil", label="Segmentation Output"),
+            gr.Textbox(lines=1, placeholder=None, label="Text Output"),
+        ],
+        title=title,
+        description=description,
+        article=article,
+        examples=examples,
+        allow_flagging="auto",
+    )
+
+    inference_app.queue()
+    inference_app.launch(
+        share=False,
+        debug=debug,
+        server_name=server_name
+    )
+
+
+if __name__ == '__main__':
+    server_runner(
+        inference,
+        debug=True,
+        server_name="0.0.0.0"
+    )