How we convert XML annotation folder into text or YOLOv3 Format for detection??? I used this code for conversion but it only take one xml image and convert into .txt ..but i want to convert my full folder at once time. You have Any easy solution to convert xml files into text files. i Have 15000+ images.
from xml.dom import minidom
import os
import glob
lut={}
lut["14111"] =0
lut["14131"] =1
lut["14141"] =2
def convert_coordinates(size, box):
dw = 1.0/size[0]
dh = 1.0/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)
def convert_xml2yolo( lut ):
for fname in glob.glob("/content/gdrive/MyDrive/Dataset /Annotation/14111_00000002.xml"):
xmldoc = minidom.parse(fname)
fname_out = (fname[:-4]+'.txt')
with open(fname_out, "w") as f:
itemlist = xmldoc.getElementsByTagName('object')
size = xmldoc.getElementsByTagName('size')[0]
width = int((size.getElementsByTagName('width')[0]).firstChild.data)
height = int((size.getElementsByTagName('height')[0]).firstChild.data)
for item in itemlist:
# get class label
classid = (item.getElementsByTagName('name')[0]).firstChild.data
if classid in lut:
label_str = str(lut[classid])
else:
label_str = "-1"
print ("warning: label '%s' not in look-up table" % classid)
# get bbox coordinates
xmin = ((item.getElementsByTagName('bndbox')[0]).getElementsByTagName('xmin')[0]).firstChild.data
ymin = ((item.getElementsByTagName('bndbox')[0]).getElementsByTagName('ymin')[0]).firstChild.data
xmax = ((item.getElementsByTagName('bndbox')[0]).getElementsByTagName('xmax')[0]).firstChild.data
ymax = ((item.getElementsByTagName('bndbox')[0]).getElementsByTagName('ymax')[0]).firstChild.data
b = (float(xmin), float(xmax), float(ymin), float(ymax))
bb = convert_coordinates((width,height), b)
#print(bb)
f.write(label_str + " " + " ".join([("%.6f" % a) for a in bb]) + '\n')
print ("wrote %s" % fname_out)
def main():
convert_xml2yolo( lut )
if __name__ == '__main__':
main()
Follow this github repository.