Update app.py

app.py

@@ -18,7 +18,7 @@ import numpy as np
 from ultralytics import YOLO
 
 # load trained model
-model = YOLO("best.pt")
+model = YOLO("best.onnx")
 
 # image inference function
 def predict_image(img, conf_threshold, iou_threshold):
@@ -67,7 +67,7 @@ def pil_to_cv2(pil_image):
 # process video, convert frame to PIL image 
 def process_video(video_path):
     cap = cv2.VideoCapture(video_path)
-    processed_frames = []
+    
     while cap.isOpened():
         ret, frame = cap.read()
         if not ret:
@@ -77,15 +77,13 @@ def process_video(video_path):
         result = model.predict(source=pil_img)
         for r in result:
             im_array = r.plot()
-            processed_frames.append(Image.fromarray(im_array[..., ::-1]))  # Convert RGB back to BGR
+            processed_frame = Image.fromarray(im_array[..., ::-1])  # Convert RGB back to BGR
+        yield processed_frame # generate frame one by one
     cap.release()
+    
     # You may choose to display each frame or compile them back using cv2 or a similar library
     # Display the processed frames
-    for frame in processed_frames:
-        cv2.imshow("Processed Frame", pil_to_cv2(frame))
-        if cv2.waitKey(25) & 0xFF == ord('q'):
-            break
-    cv2.destroyAllWindows()
+    
     # return processed_frames[-1]  # Example, returning the last processed frame
 
 # interface setting for video
@@ -94,11 +92,11 @@ video_iface = gr.Interface(
     inputs=[
         gr.Video(label="Upload Video", interactive=True)
     ],
-    outputs=gr.Image(type="numpy",label="Result"),
+    outputs=gr.Image(type="pil",label="Result"),
     title="Fire Detection using YOLOv8n on Gradio",
     description="Upload video for inference. The Ultralytics YOLOv8n trained model is used for inference.",
     examples=[
-        # [os.path.join(video_directory, "video_fire_1.mp4")],
+        [os.path.join(video_directory, "video_fire_1.mp4")],
         [os.path.join(video_directory, "video_fire_2.mp4")],
     ]
 )