Update app.py

app.py

@@ -6,8 +6,7 @@ from transformers import Owlv2Processor, Owlv2ForObjectDetection
 import numpy as np
 import os
 
-# Check if CUDA is available, otherwise use CPU
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
+device = 'cuda'
 
 processor = Owlv2Processor.from_pretrained("google/owlv2-base-patch16")
 model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16").to(device)
@@ -33,7 +32,7 @@ def detect_objects_in_frame(image, target):
     boxes, scores, labels = results[i]["boxes"], results[i]["scores"], results[i]["labels"]
 
     for box, score, label in zip(boxes, scores, labels):
-        if score.item() >= 0.25:
+        if score.item() >= 0.5:
             box = [round(i, 2) for i in box.tolist()]
             object_label = text[label]
             confidence = round(score.item(), 3)
@@ -64,7 +63,7 @@ def process_video(video_path, target, progress=gr.Progress()):
     fourcc = cv2.VideoWriter_fourcc(*'mp4v')
     out = cv2.VideoWriter(output_path, fourcc, original_fps, (int(cap.get(3)), int(cap.get(4))))
 
-    batch_size = 16
+    batch_size = 64
     frames = []
 
     for frame in progress.tqdm(range(frame_count)):