Skip to content

Instantly share code, notes, and snippets.

@orionpax00
Created March 25, 2019 21:10
Show Gist options
  • Select an option

  • Save orionpax00/52472f12b06f01737e3297a1ff177338 to your computer and use it in GitHub Desktop.

Select an option

Save orionpax00/52472f12b06f01737e3297a1ff177338 to your computer and use it in GitHub Desktop.
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
def xml_to_csv(path):
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text)
)
xml_list.append(value)
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
def main():
for folder in ['train','test']:
image_path = os.path.join(os.getcwd(), ('images/' + folder))
xml_df = xml_to_csv(image_path)
xml_df.to_csv(('images/' + folder + '_labels.csv'), index=None)
print('Successfully converted xml to csv.')
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment