[数据集]visdrone转voc问题

转换脚本，只需要指定目录即可，保存目录不需要提前创建，路径最后带不带斜杠都不影响。

代码如下：

import os
from PIL import Image
from tqdm import tqdm

txt_dir = r'D:\BaiduNetdiskDownload\visdrone\VisDrone2019-DET-val\annotations'
image_dir = r'D:\BaiduNetdiskDownload\visdrone\VisDrone2019-DET-val\images'
xml_dir = r'D:\BaiduNetdiskDownload\visdrone\VisDrone2019-DET-val\xml'


if not os.path.exists(xml_dir):
    os.makedirs(xml_dir)
class_name = ['ignored regions', 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle',
              'awning-tricycle', 'bus', 'motor', 'others']

for filename in tqdm(os.listdir(txt_dir)):
    txt_file = os.path.join(txt_dir, filename)
    fin = open(txt_file, 'r')
    image_name = filename.split('.')[0]
    image_file = os.path.join(image_dir, image_name + '.jpg')
    img = Image.open(image_file)
    xml_name = os.path.join(xml_dir, image_name + '.xml')
    with open(xml_name, 'w') as fout:
        fout.write('<annotation>' + '\n')
        fout.write('\t' + '<folder>VOC2007</folder>' + '\n')
        fout.write('\t' + '<filename>' + image_name + '.jpg' + '</filename>' + '\n')
        fout.write('\t' + '<source>' + '\n')
        fout.write('\t\t' + '<database>' + 'VisDrone2018 Database' + '</database>' + '\n')
        fout.write('\t\t' + '<annotation>' + 'VisDrone2018' + '</annotation>' + '\n')
        fout.write('\t\t' + '<image>' + 'flickr' + '</image>' + '\n')
        fout.write('\t\t' + '<flickrid>' + 'Unspecified' + '</flickrid>' + '\n')
        fout.write('\t' + '</source>' + '\n')
        fout.write('\t' + '<owner>' + '\n')
        fout.write('\t\t' + '<flickrid>' + 'Haipeng Zhang' + '</flickrid>' + '\n')
        fout.write('\t\t' + '<name>' + 'Haipeng Zhang' + '</name>' + '\n')
        fout.write('\t' + '</owner>' + '\n')
        fout.write('\t' + '<size>' + '\n')
        fout.write('\t\t' + '<width>' + str(img.size[0]) + '</width>' + '\n')
        fout.write('\t\t' + '<height>' + str(img.size[1]) + '</height>' + '\n')
        fout.write('\t\t' + '<depth>' + '3' + '</depth>' + '\n')
        fout.write('\t' + '</size>' + '\n')
        fout.write('\t' + '<segmented>' + '0' + '</segmented>' + '\n')
        for line in fin.readlines():
            line = line.split(',')
            fout.write('\t' + '<object>' + '\n')
            fout.write('\t\t' + '<name>' + class_name[int(line[5])] + '</name>' + '\n')
            fout.write('\t\t' + '<pose>' + 'Unspecified' + '</pose>' + '\n')
            fout.write('\t\t' + '<truncated>' + line[6] + '</truncated>' + '\n')
            fout.write('\t\t' + '<difficult>' + str(int(line[7])) + '</difficult>' + '\n')
            fout.write('\t\t' + '<bndbox>' + '\n')
            fout.write('\t\t\t' + '<xmin>' + line[0] + '</xmin>' + '\n')
            fout.write('\t\t\t' + '<ymin>' + line[1] + '</ymin>' + '\n')
            # pay attention to this point!(0-based)
            fout.write('\t\t\t' + '<xmax>' + str(int(line[0]) + int(line[2]) - 1) + '</xmax>' + '\n')
            fout.write('\t\t\t' + '<ymax>' + str(int(line[1]) + int(line[3]) - 1) + '</ymax>' + '\n')
            fout.write('\t\t' + '</bndbox>' + '\n')
            fout.write('\t' + '</object>' + '\n')
        fin.close()
        fout.write('</annotation>')

转换后即可用labelImg查看即可，但是经过技术检查，发现train转换后VOC数据集里面有10个标注是存在问题的，这个需要注意删除，不然在训练时候可能会报错。val转换后数据集不存在标注问题。

参考文章：VisDrone转VOC、YOLO格式_C++有手就行的博客-CSDN博客