darknet-训练自己的yolov3模型

Yolo v3的使用方法

参考自@zhaonan

目录
  • Yolo v3的使用方法
    • 安装darknet
    • 训练Pascal VOC格式的数据
      • 修改cfg文件中的voc.data
      • 修改VOC.names
      • 下载预训练卷积层权重
      • 修改cfg/yolov3-voc.cfg
    • 训练自己的模型
    • 测试Yolo模型
      • 测试单张图片:
      • 批量测试图片
    • 生成预测结果
    • 采用第三方compute_mAP
    • 高级进阶
    • Reference

安装darknet

  • 下载库文件
git clone https://github.com/pjreddie/darknet
cd darknet
  • 修改Makefile
GPU=1  #0或1
CUDNN=1  #0或1
OPENCV=0  #0或1
OPENMP=0
DEBUG=0
  • 编译
make
  • 下载预训练模型
wget https://pjreddie.com/media/files/yolov3.weights
  • 用预训练模型进行简单的测试
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

训练Pascal VOC格式的数据

  • 生成Labels,因为darknet不需要xml文件,需要.txt文件(格式: )

用voc_label.py(位于./scripts)cat voc_label.py 共修改四处

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')]  #替换为自己的数据集
classes = ["head", "eye", "nose"]     #修改为自己的类别

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))  #将数据集放于当前目录下
    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")     #修改为自己的数据集用作训练
wget https://pjreddie.com/media/files/voc_label.py
python voc_label.py

VOCdevkit/VOC2007/labels/中:

learner@learner-pc:~/darknet/scripts$ ls
2007_test.txt #0   dice_label.sh        imagenet_label.sh  VOCdevkit_original
2007_train.txt #1  gen_tactic.sh        train.txt #3        voc_label.py
2007_val.txt #2 get_coco_dataset.sh  VOCdevkit

这时darknet需要一个txt文件,其中包含了所有的图片

cat 2007_train.txt 2007_val.txt 2012_*.txt > train.txt

修改cfg文件中的voc.data

classes= 3    #修改为自己的类别数
train  = /home/learner/darknet/data/voc/train.txt   #修改为自己的路径 or /home/learner/darknet/scripts/2007_test.txt
valid  = /home/learner/darknet/data/voc/2007_test.txt   #修改为自己的路径 or /home/learner/darknet/scripts/2007_test.txt
names = /home/learner/darknet/data/voc.names  #修改见voc.names
backup = /home/learner/darknet/backup   #修改为自己的路径,输出的权重信息将存储其内

修改VOC.names

head  #自己需要探测的类别,一行一个
eye
nose

下载预训练卷积层权重

wget https://pjreddie.com/media/files/darknet53.conv.74

修改cfg/yolov3-voc.cfg

[net]
# Testing
 batch=64
 subdivisions=32   #每批训练的个数=batch/subvisions,根据自己GPU显存进行修改,显存不够改大一些
# Training
# batch=64
# subdivisions=16
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 50200  #训练步数
policy=steps
steps=40000,45000  #开始衰减的步数
scales=.1,.1



[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

.....

[convolutional]
size=1
stride=1
pad=1
filters=24   #filters = 3 * ( classes + 5 )   here,filters=3*(3+5)
activation=linear

[yolo]
mask = 6,7,8
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=3    #修改为自己的类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1

[route]
layers = -4

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 61



[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=24    #filters = 3 * ( classes + 5 )   here,filters=3*(3+5)
activation=linear

[yolo]
mask = 3,4,5
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=3  #修改为自己的类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1

[route]
layers = -4

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 36



[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=24    #filters = 3 * ( classes + 5 )   here,filters=3*(3+5)
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
classes=3   #修改为自己的类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1

训练自己的模型

1 单GPU训练:./darknet -i detector train

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74

2 多GPU训练,格式为0,1,2,3./darknet detector train -gpus

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74 -gpus 0,1,2,3

测试Yolo模型

测试单张图片:

  • 测试单张图片,需要编译时有OpenCV支持:./darknet detector test #本次测试无opencv支持
  • 文件中batchsubdivisions两项必须为1。
  • 测试时还可以用-thresh-hier选项指定对应参数。
  • ./darknet detector test cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_20000.weights Eminem.jpg

批量测试图片

  • yolov3-voc.cfg(cfg文件夹下)文件中batchsubdivisions两项必须为1。

  • 在detector.c中增加头文件:

    #include   /* Many POSIX functions (but not all, by a large margin) */
    #include    /* open(), creat() - and fcntl() */
    
  • 在前面添加*GetFilename(char *p)函数

    #include "darknet.h"
    #include   //需增加的头文件
    #include
    #include
    #include  //需增加的头文件
    static int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
     
    char *GetFilename(char *p)
    { 
        static char name[30]={""};
        char *q = strrchr(p,'/') + 1;
        strncpy(name,q,20);
        return name;
    }
    
  • 用下面代码替换detector.c文件(example文件夹下)的void test_detector函数(注意有3处要改成自己的路径)

void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen)
{
    list *options = read_data_cfg(datacfg);
    char *name_list = option_find_str(options, "names", "data/names.list");
    char **names = get_labels(name_list);
 
    image **alphabet = load_alphabet();
    network *net = load_network(cfgfile, weightfile, 0);
    set_batch_network(net, 1);
    srand(2222222);
    double time;
    char buff[256];
    char *input = buff;
    float nms=.45;
    int i=0;
    while(1){
        if(filename){
            strncpy(input, filename, 256);
            image im = load_image_color(input,0,0);
            image sized = letterbox_image(im, net->w, net->h);
        //image sized = resize_image(im, net->w, net->h);
        //image sized2 = resize_max(im, net->w);
        //image sized = crop_image(sized2, -((net->w - sized2.w)/2), -((net->h - sized2.h)/2), net->w, net->h);
        //resize_network(net, sized.w, sized.h);
            layer l = net->layers[net->n-1];
 
 
            float *X = sized.data;
            time=what_time_is_it_now();
            network_predict(net, X);
            printf("%s: Predicted in %f seconds.\n", input, what_time_is_it_now()-time);
            int nboxes = 0;
            detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);
            //printf("%d\n", nboxes);
            //if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
            if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
                draw_detections(im, dets, nboxes, thresh, names, alphabet, l.classes);
                free_detections(dets, nboxes);
            if(outfile)
             {
                save_image(im, outfile);
             }
            else{
                save_image(im, "predictions");
#ifdef OPENCV
                cvNamedWindow("predictions", CV_WINDOW_NORMAL); 
                if(fullscreen){
                cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
                }
                show_image(im, "predictions",0);
                cvWaitKey(0);
                cvDestroyAllWindows();
#endif
            }
            free_image(im);
            free_image(sized);
            if (filename) break;
         } 
        else {
            printf("Enter Image Path: ");
            fflush(stdout);
            input = fgets(input, 256, stdin);
            if(!input) return;
            strtok(input, "\n");
   
            list *plist = get_paths(input);
            char **paths = (char **)list_to_array(plist);
             printf("Start Testing!\n");
            int m = plist->size;
            if(access("/home/learner/darknet/data/outv3tiny_dpj",0)==-1)//"/home/learner/darknet/data"修改成自己的路径
            {
              if (mkdir("/home/learner/darknet/data/outv3tiny_dpj",0777))//"/home/learner/darknet/data"修改成自己的路径
               {
                 printf("creat file bag failed!!!");
               }
            }
            for(i = 0; i < m; ++i){
             char *path = paths[i];
             image im = load_image_color(path,0,0);
             image sized = letterbox_image(im, net->w, net->h);
        //image sized = resize_image(im, net->w, net->h);
        //image sized2 = resize_max(im, net->w);
        //image sized = crop_image(sized2, -((net->w - sized2.w)/2), -((net->h - sized2.h)/2), net->w, net->h);
        //resize_network(net, sized.w, sized.h);
        layer l = net->layers[net->n-1];
 
 
        float *X = sized.data;
        time=what_time_is_it_now();
        network_predict(net, X);
        printf("Try Very Hard:");
        printf("%s: Predicted in %f seconds.\n", path, what_time_is_it_now()-time);
        int nboxes = 0;
        detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);
        //printf("%d\n", nboxes);
        //if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
        if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
        draw_detections(im, dets, nboxes, thresh, names, alphabet, l.classes);
        free_detections(dets, nboxes);
        if(outfile){
            save_image(im, outfile);
        }
        else{
             
             char b[2048];
            sprintf(b,"/home/learner/darknet/data/outv3tiny_dpj/%s",GetFilename(path));//"/home/leaner/darknet/data"修改成自己的路径
            
            save_image(im, b);
            printf("save %s successfully!\n",GetFilename(path));
/*
#ifdef OPENCV
            //cvNamedWindow("predictions", CV_WINDOW_NORMAL); 
            if(fullscreen){
                cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
            }
            //show_image(im, "predictions");
            //cvWaitKey(0);
            //cvDestroyAllWindows();
#endif*/
        }
 
        free_image(im);
        free_image(sized);
        if (filename) break;
        }
      }
    }
}
  • 重新进行编译
make clean
make
  • 开始批量测试
./darknet detector test cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_20000.weights
  • 输入Image Path(所有的测试文件的路径,可以复制voc.data中valid后边的路径):
/home/learner/darknet/data/voc/2007_test.txt # 完整路径
  • 结果都保存在./data/out文件夹下

生成预测结果

生成预测结果

  • ./darknet detector valid
  • yolov3-voc.cfg(cfg文件夹下)文件中batchsubdivisions两项必须为1。
  • 结果生成在results指定的目录下以开头的若干文件中,若没有指定results,那么默认为/results
  • 执行语句如下:在终端只返回用时,在./results/comp4_det_test_[类名].txt里保存测试结果
./darknet detector valid cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_20000.weights

采用第三方compute_mAP

下载第三方库:

git clone https://github.com/LianjiLi/yolo-compute-map.git

进行如下修改:

  • 修改darknet/examples/detector.c中validate_detector()

    char *valid_images = option_find_str(options, "valid", "./data/2007_test.txt");//改成自己的测试文件路径
    
    if(!outfile) outfile = "comp4_det_test_";
            fps = calloc(classes, sizeof(FILE *));
            for(j = 0; j < classes; ++j){
                snprintf(buff, 1024, "%s/%s.txt", prefix, names[j]);//删除outfile参数以及对应的%s
                fps[j] = fopen(buff, "w");
    
  • 重新编译

    make clean
    make
    
  • 运行valid

    darknet文件夹下运行./darknet detector valid cfg/voc.data cfg/yolov3-tiny.cfg backup/yolov3-tiny_164000.weights(改为自己的模型路径)
    
  • 在本文件夹下运行python compute_mAP.py

  • 说明:compute_mAP.py中的test.txt文件内容只有文件名字,不带绝对路径,不带后缀

高级进阶

darknet的浅层特征可视化请参看:https://www.cnblogs.com/pprp/p/10146355.html

AlexyAB大神总结的优化经验请参看:https://www.cnblogs.com/pprp/p/10204480.html

如何使用Darknet进行分类请参看:https://www.cnblogs.com/pprp/p/10342335.html

Darknet loss可视化软件请参看:https://www.cnblogs.com/pprp/p/10248436.html

如何设计更改YOLO网络结构:https://pprp.github.io/2018/09/20/tricks.html

YOLO详细改进总结:https://pprp.github.io/2018/06/20/yolo.html

ps: 以上都是自己科研过程中总结内容,可能不够系统,欢迎留言讨论

Reference

YOLOv3目标检测总结

官方网站

思路整理自@zhaonan

转载请注明作者 _, 如有问题请留言。

你可能感兴趣的:(darknet-训练自己的yolov3模型)