Как запустить обнаружение объектов tensorflow? Запускается только видео, обнаружение объектов не накладывается

До этого обнаружение объектов работало как надо, только видео запускалось в новом окне. Когда мне удалось поставить видео в окно PyQt5 обнаружение объектов перестало работать. Как это исправить? Мне кажется что все дело в frame, только я не понимаю как правильно добавить его к этой строке self.thread = ThreadOpenCV ('20201024161726.mp4', self.frame).

import os
import cv2
import numpy as np
import tensorflow as tf
import sys

from PyQt5 import QtCore, QtGui, QtWidgets, uic
from PyQt5.QtWidgets import QLabel, QVBoxLayout
from PyQt5.QtCore import QThread, pyqtSignal, Qt
from PyQt5.QtGui import QImage, QPixmap

from PyQt5.QtWidgets import QWidget
from PyQt5.QtWidgets import QMainWindow

from utils import label_map_util
from utils import visualization_utils as vis_util


class ThreadOpenCV(QThread):
    changePixmap = pyqtSignal(QImage)

    def __init__(self, source):
        super().__init__()

    def run(self):

        MODEL_NAME = 'inference_graph'
        VIDEO_NAME = '20201024161726.mp4'

        # Grab path to current working directory
        CWD_PATH = os.getcwd()

        # Path to frozen detection graph .pb file, which contains the model that is used
        # for object detection.
        PATH_TO_CKPT = os.path.join(CWD_PATH, MODEL_NAME, 'frozen_inference_graph.pb')

        # Path to label map file
        PATH_TO_LABELS = os.path.join(CWD_PATH, 'training', 'labelmap.pbtxt')

        # Path to video
        PATH_TO_VIDEO = os.path.join(CWD_PATH, VIDEO_NAME)

        # Number of classes the object detector can identify
        NUM_CLASSES = 2

        # Load the label map.
        # Label maps map indices to category names, so that when our convolution
        # network predicts `5`, we know that this corresponds to `king`.
        # Here we use internal utility functions, but anything that returns a
        # dictionary mapping integers to appropriate string labels would be fine
        label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
        categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
                                                                    use_display_name=True)
        category_index = label_map_util.create_category_index(categories)

        # Load the Tensorflow model into memory.
        detection_graph = tf.Graph()
        with detection_graph.as_default():
            od_graph_def = tf.GraphDef()
            with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
                serialized_graph = fid.read()
                od_graph_def.ParseFromString(serialized_graph)
                tf.import_graph_def(od_graph_def, name='')

            sess = tf.Session(graph=detection_graph)

        # Define input and output tensors (i.e. data) for the object detection classifier

        # Input tensor is the image
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

        # Output tensors are the detection boxes, scores, and classes
        # Each box represents a part of the image where a particular object was detected
        detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

        # Each score represents level of confidence for each of the objects.
        # The score is shown on the result image, together with the class label.
        detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
        detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')

        # Number of objects detected
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')

        cap = cv2.VideoCapture(PATH_TO_VIDEO)
        while (cap.isOpened()):
            ret, frame = cap.read()


            rgbImage = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            frame_expanded = np.expand_dims(rgbImage, axis=0)
            h, w, ch = rgbImage.shape
            bytesPerLine = ch * w
            convertToQtFormat = QImage(rgbImage.data, w, h, bytesPerLine, QImage.Format_RGB888)
            p = convertToQtFormat.scaled(640, 480, Qt.KeepAspectRatio)

            # Perform the actual detection by running the model with the image as input
            (boxes, scores, classes, num) = sess.run(
                [detection_boxes, detection_scores, detection_classes, num_detections],
                feed_dict={image_tensor: frame_expanded})

            # Draw the results of the detection (aka 'visulaize the results')
            vis_util.visualize_boxes_and_labels_on_image_array(
                frame,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=8,
                min_score_thresh=0.60)
            self.changePixmap.emit(p)
        cap.release()

class Widget(QtWidgets.QMainWindow):
    def __init__(self):
        super().__init__()

        uic.loadUi('fire_detection.ui', self)
        self.show()

        self.label_video = QLabel()

        layout = QVBoxLayout()
        layout.addWidget(self.label_video)

        self.widget.setLayout(layout)
        self.frame = ThreadOpenCV.frame
        self.thread = ThreadOpenCV('20201024161726.mp4', self.frame)
        # self.pushButton.clicked.connect(lambda checked: functioni(self.le.text())
        self.thread.changePixmap.connect(self.setImage)

        self.btn1.clicked.connect(self.playVideo)
        self.btn2.clicked.connect(Database.LoadData)

    def playVideo(self):
        self.thread.start()

    def setImage(self, image):
        self.label_video.setPixmap(QPixmap.fromImage(image))


if __name__ == '__main__':
    app = QtWidgets.QApplication(sys.argv)

    mw = Widget()
    mw.show()
    sys.exit(app.exec_())