Update app.py

app.py

@@ -5,7 +5,6 @@ import cv2
 import time
 from PIL import Image
 
-# Check device availability
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # Load YOLOv5 model
@@ -23,17 +22,18 @@ colors = {i: [int(c) for c in np.random.randint(0, 255, 3)] for i in range(len(m
 def detect_objects(image):
     start_time = time.time()  # Start FPS measurement
 
-    image_pil = Image.fromarray(image)
+   
+    img_tensor = torch.from_numpy(image).permute(2, 0, 1).float().to(device) / 255.0
+    img_tensor = img_tensor.unsqueeze(0)  
 
     with torch.no_grad():
-        results = model(image_pil, conf=0.3, iou=0.3)  # Apply NMS with IoU = 0.3
+        results = model(img_tensor)  
+    
+    detections = results.xyxy[0].cpu().numpy()  
 
-    rendered_images = results.render()  # Get rendered image with default YOLOv5 visualization
+    img_cv = image.copy() 
 
-    # Get bounding boxes and draw color-coded boxes
-    img_cv = np.array(rendered_images[0]) if rendered_images else image
-
-    for det in results.xyxy[0]:  # Bounding box format: x1, y1, x2, y2, conf, cls
+    for det in detections:
         x1, y1, x2, y2, conf, cls = map(int, det[:6])
         label = f"{model.names[cls]}: {conf:.2f}"
 
@@ -53,9 +53,8 @@ iface = gr.Interface(
     inputs=gr.Image(type="numpy", label="Upload Image"),
     outputs=gr.Image(type="numpy", label="Detected Objects"),
     title="Object Detection with YOLOv5",
-    description="Use webcam or upload an image to detect objects. Optimized for speed and accuracy!",
+    description="Optimized for 30+ FPS real-time object detection!",
     allow_flagging="never",
-    examples=["spring_street_after.jpg", "pexels-hikaique-109919.jpg"],
 )
 
 iface.launch()