use gpu is available

app.py

@@ -2,16 +2,23 @@ import torch
 import cv2
 import gradio as gr
 import numpy as np
-from PIL import Image, ImageDraw, ImageFont
 from transformers import OwlViTProcessor, OwlViTForObjectDetection
 
-model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32").eval()
+
+# Use GPU if available
+if torch.cuda.is_available():
+    device = torch.device("cuda")
+else:
+    device = torch.device("cpu")
+
+model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32").to(device)
+model.eval()
 processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
 
 
 def query_image(img, text_queries):
     text_queries = text_queries.split(",")
-    inputs = processor(text=text_queries, images=img, return_tensors="pt")
+    inputs = processor(text=text_queries, images=img, return_tensors="pt").to(device)
 
     with torch.no_grad():
         outputs = model(**inputs)

requirements.txt

@@ -3,6 +3,5 @@
 numpy>=1.18.5
 torch>=1.7.0
 torchvision>=0.8.1
-Pillow
 transformers
 opencv-python