我的代码中有一个bug，我知道原因，但我不知道如何修复它

Question

我正在做一个开放式cv项目，使用网络摄像头进行人脸检测。我收到了这个错误，下面的错误，看起来灰度变量是非类型的，但是idk如何修复它：

注意：xml文件已与源代码位于同一文件夹中

face_coordinates = trained_face_data.detectMultiScale(grayscale)
cv2.error: OpenCV(4.5.1) C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-wvn_it83\opencv\modules\objdetect\src\cascadedetect.cpp:1689: error: (-215:Assertion failed) !empty() in function 'cv::CascadeClassifier::detectMultiScale'

[ WARN:0] global C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-wvn_it83\opencv\modules\videoio\src\cap_msmf.cpp (434) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback

以下是源代码：

import cv2
from random import randrange

# load some pre-trained data on face frontal from opencv
trained_face_data = cv2.CascadeClassifier('haarcasde_frontalface_default.xml')

# Capture video from webcam:
webcam = cv2.VideoCapture(0)  # 0 is the default cam, u can put a video file in it too

while True:

    # Read the current frame
    successful_frame_read, frame = webcam.read()
    """
    The first argument will return us a boolean, True or False, telling us if it can read the frame, 
    and the second argument is the frame that is getting read 
    """
    if frame is not None:
        grayscale = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        # Detect faces
        face_coordinates = trained_face_data.detectMultiScale(grayscale)
        # Reminder:
        # trained_face_data = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
        print(face_coordinates)
        for (x, y, w, h) in face_coordinates:
            cv2.rectangle(frame, (x, y), (x + w, y + h),
                          (randrange(128, 256), randrange(256), randrange(256)), 2)
        cv2.imshow('face detected', frame)
        cv2.waitKey(1)
        """
        1 represents how many milliseconds, before it automatically press any key and go to the next frame to 
        scan ur face 
        """

        print("Code Completed")

    elif frame is None:
        print('fail')
        break