voc2darknet.py

# Convert to darknet annotation format from pascal voc
# [email protected]
from __future__ import print_function
import xml.etree.ElementTree as ET
import os
import glob

"""
    Change classes and annotations_dir_voc to match your setup.
"""
classes = ["class1", "class2"]
annotations_dir_voc = "../annotations_xml"

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

annotations_dir_darknet = os.path.join(os.path.dirname(os.path.abspath(annotations_dir_voc)), "annotations_darknet")
if not os.path.exists(annotations_dir_darknet):
    os.makedirs(annotations_dir_darknet)

in_files = glob.glob(os.path.join(annotations_dir_voc, "*.xml"))

for in_file in in_files:
    tree=ET.parse(in_file)

    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)

        out_file = open(os.path.join(annotations_dir_darknet, str(os.path.splitext(os.path.basename(in_file))[0]+".txt")), "a+")
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')