Update app.py

app.py

@@ -1,7 +1,4 @@
 from transformers import Owlv2Processor, Owlv2ForObjectDetection
-
-processor = Owlv2Processor.from_pretrained("google/owlv2-base-patch16-ensemble")
-model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16-ensemble").to("cuda")
 from typing import List
 import os
 import numpy as np
@@ -13,7 +10,10 @@ import gradio as gr
 import torch
 import numpy as np
 from PIL import Image
+import spaces
 
+processor = Owlv2Processor.from_pretrained("google/owlv2-base-patch16-ensemble")
+model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16-ensemble").to("cuda")
 
 BOUNDING_BOX_ANNOTATOR = sv.BoundingBoxAnnotator()
 MASK_ANNOTATOR = sv.MaskAnnotator()
@@ -74,7 +74,7 @@ def process_video(
             sink.write_frame(frame)
     return result_file_path
 
-
+@spaces.GPU
 def query(image, texts):
   inputs = processor(text=texts, images=image, return_tensors="pt").to("cuda")
   with torch.no_grad():