目的:福彩快三平台出租haozbbs.comQ1446595067
实现利用yolov3训练自己的数据集(voc格式)
方法:
1)构建VOC数据集
将你手中的数据集的标注txt修改成voc格式的txt,voc格式如下:
000002.jpg car 44 28 132 121
000003.jpg car 54 19 243 178
000004.jpg car 168 6 298 164
其中第一列为图片名,第二列为目标类别,最后是目标的包围框坐标(左上角和右下角坐标)。
批量修改文件名python代码:
pic_path = "D:/VOCdevkit/VOC2007/JPEGImages/"
piclist = os.listdir(pic_path)
total_num = len(piclist)
i = 1
for pic in piclist:
if pic.endswith(".jpg"):
old_path = os.path.join(os.path.abspath(pic_path), pic)
new_path = os.path.join(os.path.abspath(pic_path), ‘000‘ + format(str(i), ‘0>5‘) + ‘.jpg‘)
os.renames(old_path, new_path)
i = i + 1
批量合并文件夹内所有txt文件python代码:
import os
filedir = "D:/DET/"
filenames=os.listdir(filedir)
f=open(‘train.txt‘,‘w‘)
for filename in filenames:
filepath = filedir+‘/‘+filename
for line in open(filepath):
f.writelines(line)
f.close()
将该train.txt转换成voc数据所需要的xml,matlab代码如下:
clc;
clear;
imgpath=‘D:/VOCdevkit/VOC2007/JPEGImages/‘;%图像存放文件夹
txtpath=‘D:/train.txt‘;%txt文件
xmlpath_new=‘D:/VOCdevkit/VOC2007/Annotations/‘;%修改后的xml保存文件夹
foldername=‘JPEGImages‘;
path=‘/home/zhangzhi/darknet/scripts/VOCdevkit/VOC2007/JPEGImages/‘;
fidin=fopen(txtpath,‘r‘);
lastname=‘begin‘;
while ~feof(fidin)
tline=fgetl(fidin);
str = regexp(tline, ‘ ‘,‘split‘);
filepath=[imgpath,str{1}];
ppath=[path,str{1}];
img=imread(filepath);
[h,w,d]=size(img);
% imshow(img);
% rectangle(‘Position‘,[str2double(str{3}),str2double(str{4}),str2double(str{5})-str2double(str{3}),str2double(str{6})-str2double(str{4})],‘LineWidth‘,4,‘EdgeColor‘,‘r‘);
pause(0.1);
if strcmp(str{1},lastname)%如果文件名相等,只需增加object
object_node=Createnode.createElement(‘object‘);
Root.appendChild(object_node);
node=Createnode.createElement(‘name‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,str{2})));
object_node.appendChild(node);
node=Createnode.createElement(‘pose‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘Unspecified‘)));
object_node.appendChild(node);
node=Createnode.createElement(‘truncated‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘0‘)));
object_node.appendChild(node);
node=Createnode.createElement(‘difficult‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘0‘)));
object_node.appendChild(node);
bndbox_node=Createnode.createElement(‘bndbox‘);
object_node.appendChild(bndbox_node);
node=Createnode.createElement(‘xmin‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{3}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘ymin‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{4}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘xmax‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{5}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘ymax‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{6}))));
bndbox_node.appendChild(node);
else
copyfile(filepath, ‘JPEGImages‘);
if exist(‘Createnode‘,‘var‘)
tempname=lastname;
tempname=strrep(tempname,‘.jpg‘,‘.xml‘);
xmlwrite(tempname,Createnode);
end
Createnode=com.mathworks.xml.XMLUtils.createDocument(‘annotation‘);
Root=Createnode.getDocumentElement;
node=Createnode.createElement(‘folder‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,foldername)));
Root.appendChild(node);
node=Createnode.createElement(‘filename‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,str{1})));
Root.appendChild(node);
node=Createnode.createElement(‘path‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,ppath)));
Root.appendChild(node);
source_node=Createnode.createElement(‘source‘);
Root.appendChild(source_node);
node=Createnode.createElement(‘database‘);
node.appendChild(Createnode.createTextNode(sprintf(‘My Database‘)));
source_node.appendChild(node);
size_node=Createnode.createElement(‘size‘);
Root.appendChild(size_node);
node=Createnode.createElement(‘width‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(w))));
size_node.appendChild(node);
node=Createnode.createElement(‘height‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(h))));
size_node.appendChild(node);
node=Createnode.createElement(‘depth‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(d))));
size_node.appendChild(node);
node=Createnode.createElement(‘segmented‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘0‘)));
Root.appendChild(node);
object_node=Createnode.createElement(‘object‘);
Root.appendChild(object_node);
node=Createnode.createElement(‘name‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,str{2})));
object_node.appendChild(node);
node=Createnode.createElement(‘pose‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘Unspecified‘)));
object_node.appendChild(node);
node=Createnode.createElement(‘truncated‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘0‘)));
object_node.appendChild(node);
node=Createnode.createElement(‘difficult‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,‘0‘)));
object_node.appendChild(node);
bndbox_node=Createnode.createElement(‘bndbox‘);
object_node.appendChild(bndbox_node);
node=Createnode.createElement(‘xmin‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{3}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘ymin‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{4}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘xmax‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{5}))));
bndbox_node.appendChild(node);
node=Createnode.createElement(‘ymax‘);
node.appendChild(Createnode.createTextNode(sprintf(‘%s‘,num2str(str{6}))));
bndbox_node.appendChild(node);
lastname=str{1};
end
if feof(fidin)
tempname=lastname;
tempname=strrep(tempname,‘.jpg‘,‘.xml‘);
xmlwrite(tempname,Createnode);
end
end
fclose(fidin);
file=dir(pwd);
for i=1:length(file)
if length(file(i).name)>=4 && strcmp(file(i).name(end-3:end),‘.xml‘)
fold=fopen(file(i).name,‘r‘);
fnew=fopen([xmlpath_new file(i).name],‘w‘);
line=1;
while ~feof(fold)
tline=fgetl(fold);
if line==1
line=2;
continue;
end
expression = ‘ ‘;
replace=char(9);
newStr=regexprep(tline,expression,replace);
fprintf(fnew,‘%s\n‘,newStr);
end
fprintf(‘已处理%s\n‘,file(i).name);
fclose(fold);
fclose(fnew);
delete(file(i).name);
end
end
生成的xml如下所示
<annotation>
<folder>JPEGImages</folder>
<filename>00000000.jpg</filename>
<path>/home/zhangzhi/darknet/scripts/VOCdevkit/VOC2007/JPEGImages/00000000.jpg</path>
<source>
<database>My Database</database>
</source>
<size>
<width>512</width>
<height>512</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>car</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>277</xmin>
<ymin>498</ymin>
<xmax>304</xmax>
<ymax>511</ymax>
</bndbox>
</object>
</annotation>
生成Main中的四个txt(train.txt,val.txt,test.txt,trainval.txt)
txt的内容为没有后缀名的图片名称:
000005
000027
000028
000033
000042
000045
000048
000058
即图片名字(无后缀),test.txt是测试集,train.txt是训练集,val.txt是验证集,trainval.txt是训练和验证集。VOC2007中,trainval大概是整个数据集的50%,test也大概是整个数据集的50%;train大概是trainval的50%,val大概是trainval的50%。可参考以下代码:
%%
%该代码根据已生成的xml,制作VOC2007数据集中的trainval.txt;train.txt;test.txt和val.txt
%trainval占总数据集的50%,test占总数据集的50%;train占trainval的50%,val占trainval的50%;
%上面所占百分比可根据自己的数据集修改,如果数据集比较少,test和val可少一些
%注意修改下面四个值
xmlfilepath=‘F:/VOCdevkit/VOC2007/Annotations/‘;
txtsavepath=‘F:/VOCdevkit/VOC2007/ImageSets/Main/;
trainval_percent=0.5;%trainval占整个数据集的百分比,剩下部分就是test所占百分比
train_percent=0.5;%train占trainval的百分比,剩下部分就是val所占百分比
%%
xmlfile=dir(xmlfilepath);
numOfxml=length(xmlfile)-2;%减去.和.. 总的数据集大小
trainval=sort(randperm(numOfxml,floor(numOfxml*trainval_percent)));
test=sort(setdiff(1:numOfxml,trainval));
trainvalsize=length(trainval);%trainval的大小
train=sort(trainval(randperm(trainvalsize,floor(trainvalsize*train_percent))));
val=sort(setdiff(trainval,train));
ftrainval=fopen([txtsavepath ‘trainval.txt‘],‘w‘);
ftest=fopen([txtsavepath ‘test.txt‘],‘w‘);
ftrain=fopen([txtsavepath ‘train.txt‘],‘w‘);
fval=fopen([txtsavepath ‘val.txt‘],‘w‘);
for i=1:numOfxml
if ismember(i,trainval)
fprintf(ftrainval,‘%s\n‘,xmlfile(i+2).name(1:end-4));
if ismember(i,train)
fprintf(ftrain,‘%s\n‘,xmlfile(i+2).name(1:end-4));
else
fprintf(fval,‘%s\n‘,xmlfile(i+2).name(1:end-4));
end
else
fprintf(ftest,‘%s\n‘,xmlfile(i+2).name(1:end-4));
end
end
fclose(ftrainval);
fclose(ftrain);
fclose(fval);
fclose(ftest);
整合文件
新建立一个VOC2007文件夹,在该文件夹下面新建JPEGImages,Annotations,labels,ImageSets文件夹,将所有训练的图片均放置在JPEGImages文件夹下,将第二步生成的xml文件放置在Annotations文件夹中,在ImageSets下新建Main文件夹,将第三步生成的四个txt放入其中,将下面步骤生成的文件放置于labels文件夹中
上面步骤的代码均是在Windows下使用,下面代码在Ubuntu下使用。生成labels文件:
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
#修改
#sets=[(‘2012‘, ‘train‘), (‘2012‘, ‘val‘), (‘2007‘, ‘train‘), (‘2007‘, ‘val‘), (‘2007‘, ‘test‘)]
sets=[(‘2007‘, ‘train‘), (‘2007‘, ‘val‘), (‘2007‘, ‘test‘)]
#修改
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes = ["car", "van", "truck ", "bus"]
def convert(size, box):
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
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:
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()
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()
#如果需要用train和val的数据一起用来训练,合并文件:
os.system("cat 2007_train.txt 2007_val.txt > train.txt")
os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt > train.all.txt")
2)修改yolov3的相关文件
修改cfg/voc.data文件,进行如下修改:
classes= 4 # 自己数据集的类别数
train = /home/zhangzhi/darknet/VOCdevkit/2007_train.txt # train文件的路径
valid = /home/zhangzhi/darknet/VOCdevkit/2007_test.txt # test文件的路径
names = data/voc.names
backup = backup
修改data/voc.names文件,对应自己的数据集修改类别。
car
van
truck
bus
下载Imagenet上预先训练的权重
wget https://pjreddie.com/media/files/darknet53.conv.74
修改cfg/yolov3-voc.cfg
找到文件中类似的部分进行修改,共有3处:
[convolutional]
size=1
stride=1
pad=1
<span style="color:#FF6666;">filters=27</span>
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
<span style="color:#FF6666;">classes=4</span>
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1
需要改变filters为num/3(classes+1+4),即3(classes+1+4),参考https://github.com/pjreddie/darknet/issues/582,同时需要修改下面的classes的种类。
3)训练,测试
./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74
./darknet detector test cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_final.weights data/dog.jpg
原文地址:http://blog.51cto.com/13861859/2139883