Create app.py

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+import torch
+from ultralytics import YOLO
+from PIL import Image
+import numpy as np
+
+# Load your model
+model = YOLO('yolov8m_defence.pt')  # Replace with your model path
+
+# Define class names (based on your 18 categories)
+class_names = {
+    0: "Cargo Aircraft", 1: "Commercial Aircraft", 2: "Drone", 3: "Fighter Jet",
+    4: "Fighter Plane", 5: "Helicopter", 6: "Light Aircraft", 7: "Missile",
+    8: "Truck", 9: "Car", 10: "Tank", 11: "Bus", 12: "Van",
+    13: "Cargo Ship", 14: "Yacht", 15: "Cruise Ship", 16: "Warship", 17: "Sailboat"
+}
+
+def predict(image):
+    """Run inference on uploaded image"""
+    if image is None:
+        return None, "Please upload an image"
+    
+    # Run inference
+    results = model(image)
+    
+    # Get the plotted image with bounding boxes
+    annotated_image = results[0].plot()
+    
+    # Convert BGR to RGB for display
+    annotated_image = annotated_image[..., ::-1]
+    
+    # Generate detection summary
+    detections = results[0].boxes
+    if len(detections) == 0:
+        summary = "No objects detected"
+    else:
+        summary = f"Detected {len(detections)} objects:\n\n"
+        for i, box in enumerate(detections):
+            class_id = int(box.cls[0])
+            confidence = float(box.conf[0])
+            class_name = class_names.get(class_id, f"Class {class_id}")
+            summary += f"• {class_name}: {confidence:.2%}\n"
+    
+    return annotated_image, summary
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil", label="Upload Image"),
+    outputs=[
+        gr.Image(type="numpy", label="Detection Results"),
+        gr.Textbox(label="Detection Summary", lines=10)
+    ],
+    title="🛡️ YOLOv8m Defence Object Detection",
+    description="""
+    Upload an image to detect military and civilian vehicles, aircraft, and ships.
+    
+    **Detectable Objects:** Aircraft (cargo, commercial, fighter, helicopter, etc.), 
+    Vehicles (car, truck, tank, bus, van), Ships (cargo, yacht, cruise, warship, sailboat), 
+    and specialized items (drone, missile).
+    
+    *Developed for DSTA Brainhack 2025 - TIL-AI Category*
+    """,
+    examples=[
+        ["example1.jpg"],  # Add your example images
+        ["example2.jpg"],
+        ["example3.jpg"],
+    ],
+    theme=gr.themes.Soft(),
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()