Update app.py

app.py

@@ -23,16 +23,14 @@ def run_commands():
         except subprocess.CalledProcessError as e:
             print(f"Command '{command}' failed with error: {e.stderr.decode()}")
             
-run_commands()
+
 
 from typing import List
 from Utils import get_video_properties
-from GroundingDINO.groundingdino.util.inference import load_model, predict
 import cv2
 import numpy as np
 import torch
 from PIL import Image
-import GroundingDINO.groundingdino.datasets.transforms as T
 from torchvision.ops import box_convert
 from torchvision import transforms
 from torch import nn
@@ -218,9 +216,12 @@ class VideoObjectDetection:
             time.sleep(time_to_wait)
 
         frame_count += 1
-    
-            
-if __name__ == "__main__":
+
+@spaces.GPU()
+def pipeline_to_setup_with_gpu():
+    run_commands()
+    from GroundingDINO.groundingdino.util.inference import load_model, predict
+    import GroundingDINO.groundingdino.datasets.transforms as T
     
     video_annotator = VideoObjectDetection(
             text_prompt='human face')
@@ -233,4 +234,9 @@ if __name__ == "__main__":
                          outputs=output_image)
 
     iface.launch(share=False, debug=True)
+    
+            
+if __name__ == "__main__":
+    pipeline_to_setup_with_gpu()
+