YOLOv3训练自己的VOC数据(一)——前期准备工作
yolo官网 https://pjreddie.com/darknet/yolo/
- 下载darknet 以及VOCdevkit 按官网跑通
- 准备自己的VOC数据集，可以在本地先建立一个如下格式的文件夹
JPEGImages和Annotations中文件名是相互对应的 如 1.jpg对应的标注是1.xml
可以使用LabelImage工具快捷生成xml文件
也可以将原本已标注的1.txt通过代码转换为1.xml
假设你原本有一个标注好的1.txt 它里面每一行的内容为“数字1 数字2 数字3 数字4 类别”
你可以使用如下的python代码将txt格式转化为xml。
label.py
#! /usr/bin/python
# -*- coding:UTF-8 -*-
import os, sys
import glob
from PIL import Image
src_img_dir = 'D:\\study\\xmu\\design\\VOC\\JPEGImage'
src_txt_dir = 'D:\\study\\xmu\\design\\VOC\\label'
src_xml_dir ='D:\\study\\xmu\\design\\VOC\\Annotations'
img_Lists = glob.glob(src_img_dir + '/*.png')
img_basenames = [] # e.g. 100.jpg
for item in img_Lists:
img_basenames.append(os.path.basename(item))
img_names = [] # e.g. 100
for item in img_basenames:
temp1, temp2 = os.path.splitext(item)
img_names.append(temp1)
for img in img_names:
im = Image.open((src_img_dir + '/' + img + '.png'))
width, height = im.size
# open the crospronding txt file
gt = open(src_txt_dir + '/' + img + '.txt').read().splitlines()
#gt = open(src_txt_dir + '/gt_' + img + '.txt').read().splitlines()
# write in xml file
#os.mknod(src_xml_dir + '/' + img + '.xml')
xml_file = open((src_xml_dir + '/' + img + '.xml'), 'w')
xml_file.write('<annotation>\n')
xml_file.write(' <folder>VOC2007</folder>\n')
xml_file.write(' <filename>' + str(img) + '.png' + '</filename>\n')
xml_file.write(' <size>\n')
xml_file.write(' <width>' + str(width) + '</width>\n')
xml_file.write(' <height>' + str(height) + '</height>\n')
xml_file.write(' <depth>3</depth>\n')
xml_file.write(' </size>\n')
# write the region of image on xml file
for img_each_label in gt:
spt = img_each_label.split(' ')
xml_file.write(' <object>\n')
xml_file.write(' <name>' + 'ship' + '</name>\n')
xml_file.write(' <pose>Unspecified</pose>\n')
xml_file.write(' <truncated>0</truncated>\n')
xml_file.write(' <difficult>0</difficult>\n')
xml_file.write(' <bndbox>\n')
xml_file.write(' <xmin>' + str(spt[0]) + '</xmin>\n')
xml_file.write(' <ymin>' + str(spt[1]) + '</ymin>\n')
xml_file.write(' <xmax>' + str(spt[2]) + '</xmax>\n')
xml_file.write(' <ymax>' + str(spt[3]) + '</ymax>\n')
xml_file.write(' </bndbox>\n')
xml_file.write(' </object>\n')
xml_file.write('</annotation>')
生成的xml格式大致如下
ImageSet里需要建立一个main文件夹，main文件夹下有四个txt文件，分别为train.txt test.txt val.txt traval.txt
你可以通过以下代码来生成它们
ImageSet.py
#! /usr/bin/python
# -*- coding:UTF-8 -*-
import os
import random
trainval_percent = 0.66
train_percent = 0.5
xmlfilepath = 'D:\\study\\xmu\\design\\VOC\\Annotations'
txtsavepath = 'D:\\study\\xmu\\design\\VOC\\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('D:\\study\\xmu\\design\\VOC\\ImageSets\\Main\\trainval.txt', 'w')
ftest = open('D:\\study\\xmu\\design\VOC\\ImageSets\\Main\\test.txt', 'w')
ftrain = open('D:\\study\\xmu\\design\VOC\\ImageSets\\Main\\train.txt', 'w')
fval = open('D:\\study\\xmu\\design\VOC\\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()
生成的txt文件格式大概如下，内容是用于训练或测试的图片文件名字
将这些所有的这几个文件放入服务器刚才下载的darknet中,放入的路径是/home/wyd/workplace/darknet/VOCdevkit/VOC2007/下面
找到下载好的darknet里darknet/scripts ，目录下有一个voc_label.py文件
打开voc_label.py 将类别改为你需要的分类，并且本次使用的是VOC2007所以可以删去VOC2012
代码后面部分的路径也要根据你的位置修改
修改后的voc_label如下：
voc_label.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
#sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
#classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes = ["ship"]
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(year, image_id):
in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, 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:
if cls not in classes:
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")
# out_file.write(" ".join([str(a) for a in bb]) + "\n")
wd = getcwd()
for year, image_set in sets:
if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
list_file = open('%s_%s.txt'%(year, image_set), 'w')
for image_id in image_ids:
list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
convert_annotation(year, image_id)
list_file.close()
os.system("cat 2007_train.txt 2007_val.txt > train.txt")
os.system("cat 2007_train.txt 2007_val.txt > train.all.txt")
通过顺利运行voc_label.py我们将在labels里生成VOC格式训练所需要的txt文件
它的内容应该是每一行五个数字，第一个表示类别 其余都是一些坐标信息
例如
至此，前期的VOC数据准备工作就结束了~
未完待续