VOC_KITTI之modify_annotations_txt.py 编辑label.txt 内的种类 可合并或者忽略

# modify_annotations_txt.py
import glob
import string

txt_list = glob.glob('./labels/just_for_test/*.txt')

#txt_list = glob.glob('./labels/data_object_label_2 _dealed/training/label_2/*.txt') # 存储Labels文件夹所有txt文件路径
#/home/studieren/PycharmProjects/keras-yolo3-master/VOC_KITTI/labels/just_for_test
#/home/studieren/PycharmProjects/keras-yolo3-master/VOC_KITTI/labels/data_object_label_2 _dealed/training/label_2
#显示所有.txt文件内的类别
def show_category(txt_list):
    category_list= []
    for item in txt_list:
        try:
            with open(item) as tdf:
                for each_line in tdf:
                    labeldata = each_line.strip().split(' ') # 去掉前后多余的字符并把其分开
                    category_list.append(labeldata[0]) # 只要第一个字段，即类别
        except IOError as ioerr:
            print('File error:'+str(ioerr))
    #这个set很关键，就是把相同的类别都去除了，保留了最简洁直接的所有类别，就是一堆元素整合成集合。
    print(set(category_list)) # 输出集合
#merge函数的作用就是把'car','1.0','2.0','3.0','4.0','...'等合成一行   car 1.0 2.0 3.0 4.0 ...
def merge(line):
    each_line=''
    for i in range(len(line)):
        if i!= (len(line)-1):
            each_line=each_line+line[i]+' '
        else:
            each_line=each_line+line[i] # 最后一条字段后面不加空格
    each_line=each_line+'\n'
    return (each_line)
print('before modify categories are:\n')
show_category(txt_list)

#对每一个文件
for item in txt_list:
    new_txt=[]
    try:
        with open(item, 'r') as r_tdf:
            #对该文件下的每行，进行合并或者忽略工作。能被忽略是因为continue，他会跳过for循环接下来的语句
            for each_line in r_tdf:
                labeldata = each_line.strip().split(' ')
                if labeldata[0] in ['Truck','Van','Tram']: # 合并汽车类
                    labeldata[0] = labeldata[0].replace(labeldata[0],'Car')
                if labeldata[0] == 'Person_sitting': # 合并行人类
                    labeldata[0] = labeldata[0].replace(labeldata[0],'Pedestrian')
                if labeldata[0] == 'DontCare': # 忽略Dontcare类
                    continue
                if labeldata[0] == 'Misc': # 忽略Misc类
                    continue
                new_txt.append(merge(labeldata)) # 重新写入新的txt文件

        with open(item,'w+') as w_tdf: # w+是打开原文件将内容删除，另写新内容进去
            #一行一行的写入
            for temp in new_txt:
                w_tdf.write(temp)
    except IOError as ioerr:
        print('File error:'+str(ioerr))
print('\nafter modify categories are:\n')
show_category(txt_list)

glob.glob() 命令  可以读取路径下文件夹内的所有尾缀为 .txt的文件路径

['./labels/just_for_test/000010.txt', './labels/just_for_test/000003.txt', './labels/just_for_test/000005.txt', './labels/just_for_test/000000.txt', './labels/just_for_test/000006.txt', './labels/just_for_test/000001.txt', './labels/just_for_test/000002.txt', './labels/just_for_test/000009.txt', './labels/just_for_test/000007.txt', './labels/just_for_test/000004.txt', './labels/just_for_test/000008.txt']

 

执行命令python modify_annotations_txt.py运行脚本，将原来的8类物体转换为现在的3类。这里以000010.txt为例，展示原来的8类标签格式和现在的3类标签格式。

# 原来的标签
Car 0.80 0 -2.09 1013.39 182.46 1241.00 374.00 1.57 1.65 3.35 4.43 1.65 5.20 -1.42
Car 0.00 0 1.95 354.43 185.52 549.52 294.49 1.43 1.70 3.95 -2.39 1.66 11.80 1.76
Pedestrian 0.00 2 1.41 859.54 159.80 879.68 221.40 1.96 0.72 1.09 8.33 1.55 23.51 1.75
Car 0.00 0 -1.78 819.63 178.12 926.85 251.56 1.51 1.60 3.24 5.85 1.64 16.50 -1.44
Car 0.00 2 -1.69 800.54 178.06 878.75 230.56 1.45 1.74 4.10 6.87 1.62 22.05 -1.39
Car 0.00 0 1.80 558.55 179.04 635.05 230.61 1.54 1.68 3.79 -0.38 1.76 23.64 1.78
Car 0.00 2 1.77 598.30 178.68 652.25 218.17 1.49 1.52 3.35 0.64 1.74 29.07 1.79
Car 0.00 1 -1.67 784.59 178.04 839.98 220.10 1.53 1.65 4.37 7.88 1.75 28.53 -1.40
Car 0.00 1 1.92 663.74 175.36 707.21 204.15 1.64 1.45 3.48 4.50 1.80 42.85 2.02
DontCare -1 -1 -10 737.69 163.56 790.86 197.98 -1 -1 -1 -1000 -1000 -1000 -10
DontCare -1 -1 -10 135.60 185.44 196.06 202.15 -1 -1 -1 -1000 -1000 -1000 -10
DontCare -1 -1 -10 796.02 162.52 862.73 183.40 -1 -1 -1 -1000 -1000 -1000 -10
DontCare -1 -1 -10 879.35 165.65 931.48 182.36 -1 -1 -1 -1000 -1000 -1000 -10

# 现在生成的标签
Car 0.80 0 -2.09 1013.39 182.46 1241.00 374.00 1.57 1.65 3.35 4.43 1.65 5.20 -1.42
Car 0.00 0 1.95 354.43 185.52 549.52 294.49 1.43 1.70 3.95 -2.39 1.66 11.80 1.76
Pedestrian 0.00 2 1.41 859.54 159.80 879.68 221.40 1.96 0.72 1.09 8.33 1.55 23.51 1.75
Car 0.00 0 -1.78 819.63 178.12 926.85 251.56 1.51 1.60 3.24 5.85 1.64 16.50 -1.44
Car 0.00 2 -1.69 800.54 178.06 878.75 230.56 1.45 1.74 4.10 6.87 1.62 22.05 -1.39
Car 0.00 0 1.80 558.55 179.04 635.05 230.61 1.54 1.68 3.79 -0.38 1.76 23.64 1.78
Car 0.00 2 1.77 598.30 178.68 652.25 218.17 1.49 1.52 3.35 0.64 1.74 29.07 1.79
Car 0.00 1 -1.67 784.59 178.04 839.98 220.10 1.53 1.65 4.37 7.88 1.75 28.53 -1.40
Car 0.00 1 1.92 663.74 175.36 707.21 204.15 1.64 1.45 3.48 4.50 1.80 42.85 2.02