Update app.py

app.py

@@ -15,6 +15,7 @@ if torch.cuda.is_available():
 else:
     device = 'cpu'
     print("Using CPU inference")
+    torch.set_num_threads(2)
 
 model.to(device)
 
@@ -65,11 +66,11 @@ iface = gr.Interface(
     fn=predict_image,
     inputs=[
         gr.Image(type="pil", label="Upload Image"),
-        gr.Slider(minimum=0, maximum=1, value=0.25, label="Confidence threshold"),
-        gr.Slider(minimum=0, maximum=1, value=0.45, label="IoU threshold"),
+        gr.Slider(minimum=0, maximum=1, value=0.25, step=0.05, label="Confidence threshold"),
+        gr.Slider(minimum=0, maximum=1, value=0.45, step=0.05, label="IoU threshold"),
     ],
     outputs=gr.Image(type="pil", label="Detection Results"),
-    title="YOLOv8m Defence Object Detection",
+    title="🛡️ YOLOv8m Defence Object Detection",
     description="""
     Upload images to detect military and civilian vehicles, aircraft, and ships using our fine-tuned YOLOv8m model.
     Developed for DSTA Brainhack 2025 - TIL-AI Category (Semi-Finalist).
@@ -80,7 +81,7 @@ iface = gr.Interface(
     Vehicles (car, truck, tank, bus, van), Ships (cargo, yacht, cruise, warship, sailboat), 
     and specialized items (drone, missile).
     
-    **Note:** Running on Free Tier - inference may take up to 40 seconds per image.
+    **Performance:** Running on Free Tier - inference may take up to 40 seconds per image.
     """,
     examples=[
         ["examples/test1.jpg", 0.25, 0.45],
@@ -95,7 +96,8 @@ iface = gr.Interface(
         ["examples/test10.jpg", 0.25, 0.45],
     ],
     css=css,
-    cache_examples=True
+    cache_examples=True,
+    allow_flagging="never"
 )
 
 if __name__ == "__main__":