在linux(ubuntu)操作系统中使用自定义数据及darknet进行目标检测

1、数据集制作

1.1数据文件夹创建

创建如图下所示的文件夹：

VOCdevkit

VOC2007

Annotations ----> Annotations用于存放使用labelImg生成的标记（XML）文件
JPEGImages ----> 存放对应的图片（jpg）文件
labels ----> 存放XML文件中类别标记和归一话的矩形框坐标
ImageSets

Main

test.txt
train.txt
trainval.txt
val.txt
文件夹Main下四个文本文件用来提取图片名作为训练集或测试集

1.2 训练集与测试集划分

使用以下的python脚本为Main文件夹下的四个文本文件填充内容

##get.py()##
#encoding=utf-8
import os  
import random   

xmlfilepath='/home/user/darknet/scripts/VOCdevkit/VOC2007/Annotations'  #改成自己的Annotations目录
saveBasePath='/home/user/darknet/scripts/VOCdevkit/VOC2007/ImageSets'	#改成自己的ImageSets目录用于寻找Main目录保存之前提到的四个txt文件
  
trainval_percent=0.7  # 根据自己的数据集设置划分比例
train_percent=0.7  
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)    
  
print("train and val size",tv)  
print("traub suze",tr)  
ftrainval = open(os.path.join(saveBasePath,'Main/trainval.txt'), 'w')    
ftest = open(os.path.join(saveBasePath,'Main/test.txt'), 'w')    
ftrain = open(os.path.join(saveBasePath,'Main/train.txt'), 'w')    
fval = open(os.path.join(saveBasePath,'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() 

执行以上python脚本,相应的图片名就会写入以上四个文本文件中。

1.3 运行脚本voc_label.py生成绝对路径及标注信息

将VOCdevkit文件夹移动至darknet目录下的scripts目录下。目录下默认有一个voc_label.py文件，该文件用于将Main目录下的txt的图片名的绝对路径保存到scripts目录下的train.txt、2007_train.txt 、2007_val.txt、 2007_test.txt、train.all.txt文件中来。同时，将xml文件转换为labels文件夹中对应的txt文件，txt文件中存放的是每个标记的类别下标，以及归一化的标记矩形框的坐标。

运行voc_label.py脚本之前的修改：

• 将sets=[(‘2012’, ‘train’), (‘2012’, ‘val’),(‘2007’, ‘train’), (‘2007’, ‘val’), (‘2007’, ‘test’)]改为：sets=[(‘2007’, ‘train’), (‘2007’, ‘val’), (‘2007’, ‘test’)]，因为我们这里只使用了2007数据集。
• 将classes = [" "] 改为自己的类别名，作者这里只使用了一类标签所以改为：classes = [“insulator”]
• 将os.system(“cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt> train.txt”)改为：os.system(“cat 2007_train.txt 2007_val.txt > train.txt”)
• 将os.system(“cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_val.txt 2012_test.txt > train.all.txt”)改为：os.system(“cat 2007_train.txt 2007_val.txt 2007_test.txt > train.all.txt”)

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

sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]

classes = ["insulator"]


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:
            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()

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 修改配置文件

• 修改data/voc.names
• 修改cfg/yolov3-tiny.cfg

  [net]  
  # Testing
  # batch=1
  # subdivisions=1
  # Training
  batch=64
  subdivisions=2
  ######################
  batch=64
  subdivisions=2
  width=52
  height=52
  #根据显存调节这几个
#################
  #每一个yolo层和其前面的卷积曾都要修改
  [convolutional]
  filters=18    # 改成3*(classes + 5),# 该处只有一种类别
  [yolo]
  classes=1
  random=0 # 显存不够改成0

• 修改cfg/voc.data

  classes= 1          # 实际需要识别的类
  train  = /home/ubuntu/darknet/scripts/2007_train.txt      # 指向刚刚生成的文件2007_train.txt
  valid  = /home/ubuntu/darknet/scripts/2007_val.txt        # 指向刚刚生成的文件2007_val.txt
  names = data/voc.names
  backup = backup

• 修改examples文件夹下的detector.c、darknet.c

void validate_detector_flip(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
    int j;
    list *options = read_data_cfg(datacfg);
    char *valid_images = option_find_str(options, "valid", "data/train.list");
    // char *name_list = option_find_str(options, "names", "data/names.list");
    char *name_list = option_find_str(options, "names", "data/voc.names");
    char *prefix = option_find_str(options, "results", "results");
    char **names = get_labels(name_list);
    char *mapf = option_find_str(options, "map", 0);
    int *map = 0;
    if (mapf) map = read_map(mapf);

        float thresh = find_float_arg(argc, argv, "-thresh", .5);
        char *filename = (argc > 4) ? argv[4]: 0;
        char *outfile = find_char_arg(argc, argv, "-out", 0);
        int fullscreen = find_arg(argc, argv, "-fullscreen");
        // test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, .5, outfile, fullscreen);
        test_detector("cfg/voc.data", argv[2], argv[3], filename, thresh, .5, outfile, fullscreen);
    } else if (0 == strcmp(argv[1], "cifar")){
        run_cifar(argc, argv);

3 模型编译及训练

• 模型编译

• 修改makefile

  sudo vi Makefile

修改Makefile如下：

根据自己的环境修改Makefile,其中CUAD和OPENCV必须安装配置好，修改Makefile才能成功编译

  make -j8

• 模型训练

模型训练命令

./darknet detector test <data_cfg> <models_cfg> <weights> <test_file> [-thresh] [-out]
./darknet detector train <data_cfg> <models_cfg> <weights> [-thresh] [-gpu] [-gpus] [-clear]
./darknet detector valid <data_cfg> <models_cfg> <weights> [-out] [-thresh]
./darknet detector recall <data_cfg> <models_cfg> <weights> [-thresh]

'< >'必选项，’[ ]‘可选项

• data_cfg：数据配置文件，eg：cfg/voc.data
• models_cfg：模型配置文件，eg：cfg/yolov3-voc.cfg
• weights：权重配置文件，eg：weights/yolov3.weights
• test_file：测试文件，eg：//*/test.txt
• -thresh：显示被检测物体中confidence大于等于 [-thresh] 的bounding-box，默认0.005
• -out：输出文件名称，默认路径为results文件夹下，eg：-out “” //输出class_num个文件，文件名为class_name.txt；若不选择此选项，则默认输出文件名为comp4_det_test_“class_name”.txt
• -i/-gpu：指定单个gpu，默认为0，eg：-gpu 2
• -gpus：指定多个gpu，默认为0，eg：-gpus 0,1,2

根据以上命令格式，训练自己的模型

  ./darknet detector train cfg/voc.data cfg/yolov3-tiny.cfg