Why is the Jupyter kernel dead during the second iteration of object tracking using YOLOv8 and DeepSORT?

Question

I am going to detect and track the objects in a video file using YOLOv8 and DeepSORT respectively by importing their packages. In the first iteration of the frame reading, everything is normal but, in the second iteration, Jupyter notebook kernel is dead at tracks = tracker.update_tracks(results, frame=frame) line. What can be the reason? Code is the following:

import torch
import cv2
import ultralytics
from deep_sort_realtime.deepsort_tracker import DeepSort

model = ultralytics.YOLO("yolov8m.pt")
tracker = DeepSort(max_age=50)

CONFIDENCE_THRESHOLD = 0.8

cap = cv2.VideoCapture('video.mp4')

while True:
    ret, frame = cap.read()

    if not ret:
        break
        
    detections = model(frame)[0]
    
    results = []
    for data in detection.boxes.data.tolist():
        
        confidence = data[4]

        if float(confidence) < CONFIDENCE_THRESHOLD:
            continue
        xmin, ymin, xmax, ymax = int(data[0]), int(data[1]), int(data[2]), int(data[3])
        class_id = int(data[5])
        results.append([[xmin, ymin, xmax - xmin, ymax - ymin], confidence, class_id])
        
    tracks =tracker.update_tracks(results, frame=frame)
    for track in tracks:
        if not track.is_confirmed():
            continue

        bbox = track.to_tlbr()
        track_id = track.track_id
        class_name = track.get_class()        
        
    cv2.imshow("Frame", frame)

    if cv2.waitKey(1) == ord("q"):
        break

cap.release()
cv2.destroyAllWindows()

Answer 1

The solution was upgrading the numpy and scipy to the latest version since, I was using the latest version of Jupyter Notebook.