tensorflow中对于标注好的文件以及图片在训练之前会将其打散然后分成训练用的,测试用的,验证用的;
以下代码就是干这事~
import os
import random
trainval_percent = 0.66 # 标注文件中训练验证所占的比例
train_percent = 0.5 # 训练验证中训练所占的比例
xmlfilepath = '/mydata/Annotations' # 标注文件的路径 ,格式为.xml的
txtsavepath = 'ImageSets/Main' # 生成的各个txt存放的路径
total_xml = os.listdir(xmlfilepath)
print(total_xml)
num=len(total_xml)
list=range(num)
tv=int(num*trainval_percent)
tr=int(tv*train_percent)
trainval= random.sample(list,tv)
train=random.sample(trainval,tr)
ftrainval = open('ImageSets/Main/trainval.txt', 'w') # 用于写训练验证的序列
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')
for i in list:
name=total_xml[i][:-4]+'\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest .close()