Create app.py

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import cv2
+import tempfile
+import numpy as np
+from ultralytics import YOLO
+
+# Load the YOLOv8 model
+model = YOLO('yolov8m.pt')  # Ensure you have the correct model path
+
+def process_video(video_file):
+    # Create a temporary directory to store processed frames
+    temp_dir = tempfile.TemporaryDirectory()
+    
+    # Open the video file
+    cap = cv2.VideoCapture(video_file.name)
+    
+    # Get video properties
+    fps = int(cap.get(cv2.CAP_PROP_FPS))
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    codec = cv2.VideoWriter_fourcc(*'mp4v')
+    
+    # Create a VideoWriter object to save the processed video
+    output_path = f"{temp_dir.name}/output.mp4"
+    out = cv2.VideoWriter(output_path, codec, fps, (width, height))
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Use YOLO model to detect objects in the frame
+        results = model(frame)
+
+        # Draw bounding boxes and labels on the frame
+        annotated_frame = results[0].plot()
+
+        # Write the frame to the output video
+        out.write(annotated_frame)
+    
+    # Release the VideoCapture and VideoWriter objects
+    cap.release()
+    out.release()
+
+    return output_path
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=process_video,
+    inputs=gr.inputs.Video(type="file"),
+    outputs=gr.outputs.Video(),
+    title="YOLOv8 Video Object Detection",
+    description="Upload a video and apply YOLOv8 object detection."
+)
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    iface.launch()