I encountered an error while converting XML format in CVAT to YOLO format

Question

I am trying to convert an XML file in CVAT format to YOLO format.

but I am encountering a type error while trying to obtain yolo_x, y, w, and h

enter image description here

tried using 'int' to resolve the issue, but I am still encountering a 'value error'.

enter image description here

I would appreciate it if you could provide a good solution. Also, could you please evaluate the code I am currently working on for converting from CVAT format to YOLO format? If there is a better way, please let me know. Thank you.

xml

<image id="0" name="20230226_145238.jpg" width="510" height="680">
  <box label="meter" source="manual" occluded="0" xtl="202.10" ytl="259.28" xbr="314.74" ybr="305.89" z_order="0">
  </box>
  <box label="zero" source="manual" occluded="0" xtl="219.68" ytl="269.57" xbr="234.84" ybr="293.43" z_order="0">
  </box>
  <box label="eight" source="manual" occluded="0" xtl="234.84" ytl="270.35" xbr="249.11" ybr="293.99" z_order="0">
  </box>
  <box label="one" source="manual" occluded="0" xtl="249.78" ytl="271.69" xbr="263.38" ybr="293.88" z_order="0">
  </box>
  <box label="one" source="manual" occluded="0" xtl="263.38" ytl="272.69" xbr="278.99" ybr="295.10" z_order="0">
  </box>
  <box label="eight" source="manual" occluded="0" xtl="279.55" ytl="272.80" xbr="293.71" ybr="296.33" z_order="0">
  </box>
  <box label="three" source="manual" occluded="0" xtl="295.38" ytl="272.58" xbr="308.68" ybr="297.33" z_order="0">
  </box>
  <box label="dot" source="manual" occluded="0" xtl="289.47" ytl="292.43" xbr="293.93" ybr="296.55" z_order="0">
  </box>
</image>

code

import os
import glob
from xml.etree.ElementTree import parse

xml_dir = "./data/"

class Voc_to_yolo_convter():
    def __init__(self, xml_path):
        self.xml_path_list = glob.glob(os.path.join(xml_path, "*.xml"))
        # print(self.xml_path_list)

    def get_voc_to_yolo(self):
        for xml_path in self.xml_path_list:
            tree = parse(xml_path)
            root = tree.getroot()

            # image_meta
            meta = root.findall("image")
            for image in meta:
                image_name = image.attrib["name"]
                image_width = image.attrib["width"]
                image_height = image.attrib["height"]
                # print(image_width, image_height)

                # object_meta
                object_metas = image.findall("box")
                for bbox in object_metas:
                    label = bbox.attrib["label"]
                    xtl = int(bbox.attrib["xtl"])
                    ytl = bbox.attrib["ytl"]
                    xbr = bbox.attrib["xbr"]
                    ybr = bbox.attrib["ybr"]

                    # CVAT to yolo
                    yolo_x = round(((xtl + xbr)/2)/image_width, 6)
                    yolo_y = round(((ytl + ybr)/2)/image_height, 6)
                    yolo_w = round((xbr - xtl)/image_width, 6)
                    yolo_h = round((ybr - ytl)/image_height, 6)

                    print(yolo_x, yolo_y, yolo_w, yolo_h)



test= Voc_to_yolo_convter(xml_dir)
test.get_voc_to_yolo()