VOC2012数据集中筛选出指定类或者几类图片的实现

VOC2012训练数据集下载 https://download.csdn.net/download/dingding1022/12882251

VOC2007数据集下载 https://download.csdn.net/download/dingding1022/12882248

VOC2007测试集下载 https://download.csdn.net/download/dingding1022/12882245

可以与voc2007对照看，因为VOC2012中 2009年以后的图片标注中图片大小的信息在后面，如果用VOC2007的代码来做2012会出错，本文件可以在VOC2012中选取特定类或者指定的某些类

import os
import os.path
import shutil

fileDir_ann = "D:\\深度学习\\数据集\\VOC2012\\Annotations"
fileDir_img = "D:\\深度学习\\数据集\\VOC2012\\JPEGImages\\"
saveDir_img = "D:\\深度学习\\数据集\\VOC2012\\JPEGImages_ssd\\"

if not os.path.exists(saveDir_img):
    os.mkdir(saveDir_img)

names = locals()

for files in os.walk(fileDir_ann):
    for file in files[2]:

        print(file , "-->start!")

        saveDir_ann = "D:\\深度学习\\数据集\\VOC2012\\Annotations_ssd\\"
        if not os.path.exists(saveDir_ann):
            os.mkdir(saveDir_ann)

        fp = open(fileDir_ann + '\\' + file)
        saveDir_ann = saveDir_ann + file
        fp_w = open(saveDir_ann, 'w')
        classes = ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', '>cat<', 'chair', 'cow',
                   'diningtable', \
                   'dog', 'horse', 'motorbike', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor', 'person']

        lines = fp.readlines()

        ind_start = []
        ind_end = []
        lines_id_start = lines[:]
        lines_id_end = lines[:]
        print(lines_id_end)
        c1 = 0
        c2 = 1
        if "\t<segmented>0</segmented>\n" in lines_id_start:
            c1 = lines_id_start.index("\t<segmented>0</segmented>\n")
        if "\t<segmented>1</segmented>\n" in lines_id_start:
            c2 = lines_id_start.index("\t<segmented>1</segmented>\n")
        d = lines_id_start.index("\t</source>\n")
        while "\t<object>\n" in lines_id_start:
            a = lines_id_start.index("\t<object>\n")
            ind_start.append(a)
            lines_id_start[a] = "delete"

        while "\t</object>\n" in lines_id_end:
            b = lines_id_end.index("\t</object>\n")
            ind_end.append(b)
            lines_id_end[b] = "delete"

        i = 0
        for k in range(0, len(ind_start)):
            for j in range(0, len(classes)):
                if classes[j] in lines[ind_start[i] + 1]:
                    a = ind_start[i]
                    names['block%d' % k] = [lines[a], lines[a + 1], \
                                            lines[a + 2], lines[a + 3], lines[a + 4], \
                                            lines[a + 5], lines[a + 6], lines[a + 7], \
                                            lines[a + 8], lines[a + 9], lines[a + 10], \
                                            lines[ind_end[i]]]
                    break
            i += 1

        classes1 = '\t\t<name>bicycle</name>\n'
        classes2 = '\t\t<name>motorbike</name>\n'
        classes3 = '\t\t<name>bus</name>\n'
        classes4 = '\t\t<name>car</name>\n'


        string_start = lines[0:ind_start[0]]
        string_end = [lines[len(lines) - 1]] #最后一行 </annotation>
        a = ind_start[0] #修改了
        for k in range(0, len(ind_start)):
            if classes1 in names['block%d' % k]:
                a += 1
                string_start += names['block%d' % k]
            if classes2 in names['block%d' % k]:
                a += 1
                string_start += names['block%d' % k]
            if classes3 in names['block%d' % k]:
                a += 1
                string_start += names['block%d' % k]
            if classes4 in names['block%d' % k]:
                a += 1
                string_start += names['block%d' % k]

        if c1 != 0&a<d:
            string_start += lines[c1:d+1] #修改
        else:
            if c2 != 0&a<d:
                string_start += lines[c2:d+1] #修改


        string_start += string_end
        for c in range(0, len(string_start)):
            fp_w.write(string_start[c])
        fp_w.close()

        if a == ind_start[0]:#修改了
            os.remove(saveDir_ann)
        else:
            name_img = fileDir_img + os.path.splitext(file)[0] + ".jpg"
            shutil.copy(name_img, saveDir_img)
        fp.close()