将yolo格式的标注文件转化为voc格式的标注文件

1.yolo格式的标注文件

7 0.534896 0.599074 0.025 0.205556
2 0.376042 0.903241 0.0145833 0.0694444
2 0.475781 0.0291667 0.0161458 0.0583333
2 0.409115 0.87963 0.0161458 0.0685185
2 0.472917 0.555556 0.0145833 0.0703704
2 0.348958 0.914815 0.0145833 0.0611111
0 0.29974 0.835648 0.00572917 0.0157407
2 0.411719 0.568056 0.0171875 0.0638889
2 0.4125 0.141204 0.0145833 0.0657407
2 0.378906 0.418056 0.0161458 0.075

2.voc格式的标注文件

<annotation>
    <folder>VOC2007</folder>
    <filename>DJI_0113-2-2040.jpg</filename>
    <size>
        <width>1920</width>
        <height>1080</height>
        <depth>3</depth>
    </size>
    <object>
        <name>7</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>1003</xmin>
            <ymin>536</ymin>
            <xmax>1051</xmax>
            <ymax>758</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>708</xmin>
            <ymin>938</ymin>
            <xmax>736</xmax>
            <ymax>1013</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>897</xmin>
            <ymin>0</ymin>
            <xmax>928</xmax>
            <ymax>63</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>770</xmin>
            <ymin>913</ymin>
            <xmax>801</xmax>
            <ymax>987</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>894</xmin>
            <ymin>562</ymin>
            <xmax>922</xmax>
            <ymax>638</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>656</xmin>
            <ymin>955</ymin>
            <xmax>684</xmax>
            <ymax>1021</ymax>
        </bndbox>
    </object>
    <object>
        <name>0</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>570</xmin>
            <ymin>893</ymin>
            <xmax>581</xmax>
            <ymax>910</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>774</xmin>
            <ymin>579</ymin>
            <xmax>807</xmax>
            <ymax>648</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>778</xmin>
            <ymin>117</ymin>
            <xmax>806</xmax>
            <ymax>188</ymax>
        </bndbox>
    </object>
    <object>
        <name>2</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>711</xmin>
            <ymin>411</ymin>
            <xmax>742</xmax>
            <ymax>492</ymax>
        </bndbox>
    </object>
</annotation>

3.转换代码

#! /usr/bin/python
# -*- coding:UTF-8 -*-
import os, sys
import glob
from PIL import Image

# 图像存储位置
src_img_dir = " "  # 添加你的路径
# 图像的 ground truth 的 txt 文件存放位置
src_txt_dir = " "
src_xml_dir = " "

img_Lists = glob.glob(src_img_dir + '/*.jpg')

img_basenames = [] # e.g. 100.jpg
for item in img_Lists:
    img_basenames.append(os.path.basename(item))

img_names = [] # e.g. 100
for item in img_basenames:
    temp1, temp2 = os.path.splitext(item)
    img_names.append(temp1)

for img in img_names:
    im = Image.open((src_img_dir + '/' + img + '.jpg'))
    width, height = im.size

    # open the crospronding txt file
    gt = open(src_txt_dir + '/' + img + '.txt').read().splitlines()

    # write in xml file
    xml_file = open((src_xml_dir + '/' + img + '.xml'), 'w')
    xml_file.write('<annotation>\n')
    xml_file.write('    <folder>VOC2007</folder>\n')
    xml_file.write('    <filename>' + str(img) + '.jpg' + '</filename>\n')
    xml_file.write('    <size>\n')
    xml_file.write('        <width>' + str(width) + '</width>\n')
    xml_file.write('        <height>' + str(height) + '</height>\n')
    xml_file.write('        <depth>3</depth>\n')
    xml_file.write('    </size>\n')



    # write the region of image on xml file
    for img_each_label in gt:
        spt = img_each_label.split(' ') #这里如果txt里面是以逗号‘，’隔开的，那么就改为spt = img_each_label.split(',')。
        label = int(float(spt[0].strip()))
        center_x = round(float(str(spt[1]).strip()) * width)
        center_y = round(float(str(spt[2]).strip()) * height)
        bbox_width = round(float(str(spt[3]).strip()) * width)
        bbox_height = round(float(str(spt[4]).strip()) * height)
 
        xmin = str(int(center_x - bbox_width / 2 ))
        ymin = str(int(center_y - bbox_height / 2))
        xmax = str(int(center_x + bbox_width / 2))
        ymax = str(int(center_y + bbox_height / 2))

        xml_file.write('    <object>\n')
        xml_file.write('        <name>' + str(label)+ '</name>\n')
        xml_file.write('        <pose>Unspecified</pose>\n')
        xml_file.write('        <truncated>0</truncated>\n')
        xml_file.write('        <difficult>0</difficult>\n')
        xml_file.write('        <bndbox>\n')
        xml_file.write('            <xmin>' + str(xmin) + '</xmin>\n')
        xml_file.write('            <ymin>' + str(ymin) + '</ymin>\n')
        xml_file.write('            <xmax>' + str(xmax) + '</xmax>\n')
        xml_file.write('            <ymax>' + str(ymax) + '</ymax>\n')
        xml_file.write('        </bndbox>\n')
        xml_file.write('    </object>\n')

    xml_file.write('</annotation>')