Rename app (1).py to app .py

app (1).py

@@ -1,30 +0,0 @@
-from ultralytics import YOLO
-import cv2
-
-# Load the YOLO model (YOLOv8 in this case)
-model = YOLO('yolov8n.pt') 
-
-# Open webcam
-cap = cv2.VideoCapture(0)
-
-while True:
-    ret, frame = cap.read()
-    if not ret:
-        break
-
-    # Make prediction
-    results = model(frame)
-    
-    # results is a list, so we need to iterate through it
-    for result in results:
-        # Visualize results
-        annotated_frame = result.plot()
-    
-        # Display the frame
-        cv2.imshow("Real-time Object Detection", annotated_frame)
-
-    if cv2.waitKey(1) & 0xFF == ord('q'):
-        break
-
-cap.release()
-cv2.destroyAllWindows()

app .py

@@ -0,0 +1,32 @@
+from ultralytics import YOLO
+import cv2
+import gradio as gr
+
+# Load the YOLO model
+model = YOLO('yolov8n.pt')
+
+def detect_objects(image):
+    # Convert PIL image (from Gradio webcam) → OpenCV format (BGR)
+    frame = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+
+    # Perform object detection
+    results = model(frame)
+
+    # Plot detections (draw bounding boxes)
+    annotated_frame = results[0].plot()
+
+    # Convert back to RGB for displaying in Gradio
+    annotated_frame = cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB)
+
+    return annotated_frame
+
+# Create Gradio interface (this works in Hugging Face Spaces)
+demo = gr.Interface(
+    fn=detect_objects,
+    inputs=gr.Image(source="webcam", streaming=True),  # Enable live camera
+    outputs="image",
+    title="🎥 Real-time Object Detection (YOLOv8)",
+    description="Detects and labels objects in live camera feed using YOLOv8."
+)
+
+demo.launch()