tensorflow中對於標註好的文件以及圖片在訓練之前會將其打散然後分成訓練用的,測試用的,驗證用的;
以下代碼就是幹這事~
import os
import random
trainval_percent = 0.66 # 標註文件中訓練驗證所佔的比例
train_percent = 0.5 # 訓練驗證中訓練所佔的比例
xmlfilepath = '/mydata/Annotations' # 標註文件的路徑 ,格式爲.xml的
txtsavepath = 'ImageSets/Main' # 生成的各個txt存放的路徑
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') # 用於寫訓練驗證的序列
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()