深度学习python之制作VOC数据集中的xml文件（Annotations文件夹内）

深度学习python之制作VOC数据集中的xml文件（Annotations文件夹内）

from lxml.etree import Element, SubElement, tostring
from xml.dom.minidom import parseString

def make_xml(xmin_tuple, ymin_tuple, xmax_tuple, ymax_tuple, image_name):

    node_root = Element('annotation')

    node_folder = SubElement(node_root, 'folder')
    node_folder.text = 'VOC'

    node_filename = SubElement(node_root, 'filename')
    node_filename.text = image_name + '.jpg'

    node_object_num = SubElement(node_root, 'object_num')
    node_object_num.text = str(len(xmin_tuple))

    node_size = SubElement(node_root, 'size')
    node_width = SubElement(node_size, 'width')
    node_width.text = '512'

    node_height = SubElement(node_size, 'height')
    node_height.text = '384'

    node_depth = SubElement(node_size, 'depth')
    node_depth.text = '3'

    for i in xrange(len(xmin_tuple)):  
        node_object = SubElement(node_root, 'object')
        node_name = SubElement(node_object, 'name')
        node_name.text = 'ship'
        node_difficult = SubElement(node_object, 'difficult')
        node_difficult.text = '0'

        node_bndbox = SubElement(node_object, 'bndbox')
        node_xmin = SubElement(node_bndbox, 'xmin')
        node_xmin.text = str(xmin_tuple[i])
        node_ymin = SubElement(node_bndbox, 'ymin')
        node_ymin.text = str(ymin_tuple[i])
        node_xmax = SubElement(node_bndbox, 'xmax')
        node_xmax.text = str(xmax_tuple[i])
        node_ymax = SubElement(node_bndbox, 'ymax')
        node_ymax.text = str(ymax_tuple[i])


    xml = tostring(node_root, pretty_print = True)
    dom = parseString(xml)
    #print xml 打印查看结果
    return dom

调用格式

    dom = make_xml(xmin_tuple, ymin_tuple, xmax_tuple, ymax_tuple, image_name)

    xml_name = os.path.join(save_xml_path, image_name + '.xml')
    with open(xml_name, 'w') as f:
        f.write(dom.toprettyxml(indent='\t', encoding='utf-8'))

其中
image_name 没有扩展名，比如 ‘000001’
xmin_tuple = []
xmin_tuple.append(xmin) # xmin 为坐标值，有多少物体，len(xmin_tuple)就是多少

某一打印结果为：

<annotation>
  <folder>VOC</folder>
  <filename>000077.jpg</filename>
  <object_num>3</object_num>
  <size>
    <width>512</width>
    <height>384</height>
    <depth>3</depth>
  </size>
  <object>
    <name>ship</name>
    <difficult>0</difficult>
    <bndbox>
      <xmin>20</xmin>
      <ymin>1</ymin>
      <xmax>50</xmax>
      <ymax>67</ymax>
    </bndbox>
  </object>
  <object>
    <name>ship</name>
    <difficult>0</difficult>
    <bndbox>
      <xmin>1</xmin>
      <ymin>119</ymin>
      <xmax>27</xmax>
      <ymax>201</ymax>
    </bndbox>
  </object>
  <object>
    <name>ship</name>
    <difficult>0</difficult>
    <bndbox>
      <xmin>290</xmin>
      <ymin>1</ymin>
      <xmax>409</xmax>
      <ymax>365</ymax>
    </bndbox>
  </object>
</annotation>