分配訓練和測試數據集（python）——Faster-RCNN

#!/usr/bin/env python
# vim:set fileencoding=utf-8:
#讀取xml文件存入xml_list
#隨機讀取xml_list的內容，按照比例存儲在對應的txt中
#保存txt文件
import os, random
import copy#use copy.deepcopy to copy list
#xml的路徑以及分配後的txt存儲路徑
xml_path = '/home/lys/py-faster-rcnn/data/mydata/image_with_object/Annotations/'
txt_path = '/home/lys/py-faster-rcnn/data/mydata/image_with_object/Main/'

test_percent = 0.2#測試集所佔比例
val_percent = 0.2#驗證集所佔比例
xml_list = os.listdir(xml_path)

#remove the extend .xml
xml_list = [xml.split('.')[0] for xml in xml_list]

xml_len = len(xml_list)
#allot randomly
test = random.sample(xml_list, int(xml_len * test_percent))
trainval = copy.deepcopy(xml_list)
for xml in test:
    trainval.remove(xml)
val = random.sample(trainval, int(len(trainval) * val_percent))
train = copy.deepcopy(trainval)
for xml in val:
    train.remove(xml)

#renew txt and write
trainval_path = open(os.path.join(txt_path,'trainval.txt'),'w+')
train_path = open(os.path.join(txt_path,'train.txt'),'w+')
val_path = open(os.path.join(txt_path,'val.txt'),'w+')
test_path = open(os.path.join(txt_path,'test.txt'),'w+')
# add enter to each line
for trainval_xml in trainval:
    trainval_path.write(trainval_xml+'\n')
for train_xml in train:
    train_path.write(train_xml+'\n')
for val_xml in val:
    val_path.write(val_xml+'\n')
for test_xml in test:
    test_path.write(test_xml+'\n')

trainval_path.close()
train_path.close()
val_path.close()
test_path.close()

遇到的問題：

     移除後綴，需要逐個移除

    複製list，直接賦值，list a = list b，這樣並沒有創建新的list只是將b指向了a，修改會互相影響，需要使用copy.deepcopy進行復制

    換行問題，list中的元素換行，writeline直接複製，不換行;想要換行需要逐個訪問list的元素然後+'\n'

    新建文件，使用w+，存在則重寫，否則新建。會覆蓋之前的文件內容

用於分配驗證集，測試集，訓練集；生成的txt存在一個Main文件下，替換‘/home/lys/py-faster-rcnn/data/VOCdevkit2007/VOC2007/ImageSets/’下的Main文件