製作VOC格式的數據集

VOC2007格式

-VOC2007 建項目名稱
–Annotations 爲圖像標註信息xml文件
–ImageSets 爲訓練集、測試集、驗證、訓練驗證集圖像名的txt文件
–JPEGImages 爲原始的圖片

新建項目名稱，如VOC2007/mkdir.py

import os
def mkdir(path):

    # 去除首位空格
    path = path.strip()
    # 去除尾部 \ 符號S
    path = path.rstrip("\\")

    # 判斷路徑是否存在
    # 存在     True
    # 不存在   False
    isExists = os.path.exists(path)

    # 判斷結果
    if not isExists:
        # 如果不存在則創建目錄
        # 創建目錄操作函數
        os.makedirs(path)

        print(path + ' 創建成功')
        return True
    else:
        # 如果目錄存在則不創建，並提示目錄已存在
        print(path + ' 目錄已存在')
        return False

if __name__=='__main__':
    rootPath = os.getcwd()
    mkdir(os.path.join(rootPath, 'Annotations'))
    mkdir(os.path.join(rootPath,'ImageSets'))
    mkdir(os.path.join(rootPath,'JPEGImages'))
    mkdir(os.path.join(rootPath,'ImageSets/Main'))

VOC2007/matxt.py 將圖片分成訓練集和測試集(1)

import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = './Annotations'
txtsavepath = './ImageSets/Main/'
total_xml = os.listdir(xmlfilepath)
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(txtsavepath+'trainval.txt', 'w')
ftest = open(txtsavepath+'test.txt', 'w')
ftrain = open(txtsavepath+'train.txt', 'w')
fval = open(txtsavepath+'val.txt', 'w')
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

這裏得到的train.txt test.txt只有圖片的名稱。

VOC2007/matxt.py 帶路徑的訓練集和labels(2)

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets=['train', 'val',  'test']

classes = ["person"]


def convert(size, box):
    dw = 1./(size[0])
    dh = 1./(size[1])
    x = (box[0] + box[1])/2.0 - 1
    y = (box[2] + box[3])/2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):
    in_file = open('./Annotations/%s.xml'%(image_id))
    out_file = open('./labels/%s.txt'%(image_id), 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()
print(wd)

for image_set in sets:
    if not os.path.exists('./labels/'):
        os.makedirs('./labels/')
    image_ids = open('./ImageSets/Main/%s.txt'%(image_set)).read().strip().split()
    list_file = open('VOC2007_%s.txt'%(image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/JPEGImages/%s.jpg\n'%(wd, image_id))
        convert_annotation(image_id)
    list_file.close()

有時候不能使用，或者生成的labels沒有信息，此時需要注意一下路徑問題。

標註採用yolo格式(txt格式文件)

使用labelimg 標註，

PascalVoc—>xml
YOLO -->txt (txt的信息直接放在labels文件中)
上述的樣本集製作中的地一個腳本正常運行，第二個腳本需要簡單的修改

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets=['train', 'val',  'test']

classes = ["person"]


def convert(size, box):
    dw = 1./(size[0])
    dh = 1./(size[1])
    x = (box[0] + box[1])/2.0 - 1
    y = (box[2] + box[3])/2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):
    in_file = open('./Annotations/%s.xml'%(image_id))
    out_file = open('./labels/%s.txt'%(image_id), 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()
print(wd)

for image_set in sets:
#    if not os.path.exists('./labels/'):  # TXT存儲位置創建
#        os.makedirs('./labels/')
    image_ids = open('./ImageSets/Main/%s.txt'%(image_set)).read().strip().split()
    list_file = open('VOC2007_%s.txt'%(image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/JPEGImages/%s.jpg\n'%(wd, image_id))
 #       convert_annotation(image_id)   # XML 轉換成TXT
    list_file.close()