YOLO-V3 实战（暗网）

git clone https://github.com/pjreddie/darknet.git

测试单张图片(下面两个指令相同)
./darknet detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights data/dog.jpg
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
测试多张图片
./darknet detect cfg/yolov3.cfg yolov3.weights
~根据提示输入图片路径

./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

①sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')] #替换为自己的数据集
②classes = ["head", "eye", "nose"] #修改为自己的类别
③in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id)) #将数据集放于当前目录下
④os.system("cat 2007_train.txt 2007_val.txt > train.txt") #修改为自己的数据集用作训练

python voc_label.py# 执行脚本，获得所需的“.txt”文件

batch=64   # 一批训练样本的样本数量，每batch个样本更新一次参数
subdivisions=32   # 它会让你的每一个batch不是一下子都丢到网络里。而是分成subdivision对应数字的份数，一份一份的跑完后，在一起打包算作完成一次iteration
width=416     # 只可以设置成32的倍数
height=416    # 只可以设置成32的倍数

channels=3 # 若为灰度图，则chennels=1，另外还需修改/scr/data.c文件中的load_data_detection函数；若为RGB则 channels=3 ，无需修改/scr/data.c文件

momentum=0.9      # 最优化方法的动量参数，这个值影响着梯度下降到最优值得速度 
decay=0.0005   　 # 权重衰减正则项，防止过拟合
angle=0    # 通过旋转角度来生成更多训练样本
saturation = 1.5  # 通过调整饱和度来生成更多训练样本
exposure = 1.5    # 通过调整曝光量来生成更多训练样本
hue=.1　     　# 通过调整色调来生成更多训练样本


learning_rate=0.001        # 学习率, 刚开始训练时, 以 0.01 ~ 0.001 为宜, 一定轮数过后,逐渐减缓。
burn_in=1000　       # 在迭代次数小于burn_in时，其学习率的更新有一种方式，大于burn_in时，才采用policy的更新方式
max_batches = 50200     # 训练步数
policy=steps　    # 学习率调整的策略
steps=40000,45000     　    # 开始衰减的步数
scales=.1,.1    　# 在第40000和第45000次迭代时，学习率衰减10倍
...
[convolutional]——YOLO层前一层卷积层
...
filters=24    # 每一个[yolo]层前的最后一个卷积层中的 filters=num(yolo层个数)*(classes+5)
...

[yolo]
mask = 6,7,8
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326#如果想修改默认anchors数值，使用k-means即可；
classes=3  # 修改为自己的类别数
num=9　   　# 每个grid cell预测几个box,和anchors的数量一致。调大num后训练时Obj趋近0的话可以尝试调大object_scale
jitter=.3　# 利用数据抖动产生更多数据, jitter是crop的参数, jitter=.3，就是在0~0.3中进行crop
ignore_thresh = .5   # 决定是否需要计算IOU误差的参数，大于thresh，IOU误差不会夹在cost function中
truth_thresh = 1
random=1　  # 如果为1，每次迭代图片大小随机从320到608，步长为32，如果为0，每次训练大小与输入大小一致
...

head #自己需要探测的类别，一行一个
eye
nose

data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, float jitter, float hue, float saturation, float exposure)
{
    char **random_paths = get_random_paths(paths, n, m);
    int i;
    data d = {0};
    d.shallow = 0;

    d.X.rows = n;
    d.X.vals = calloc(d.X.rows, sizeof(float*));
    d.X.cols = h*w;                   //灰阶图
    //d.X.cols = h*w*3;               //RGB图
    
...    

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

./darknet detector train <data_cfg> <model_cfg> <weights> -nogpu 

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg | tee result/log/training.log

python  drawcurve.py training.log 0

import argparse
import sys
import matplotlib.pyplot as plt
def main(argv):
    parser = argparse.ArgumentParser()
    parser.add_argument("log_file",  help = "path to log file"  )
    parser.add_argument( "option", help = "0 -> loss vs iter"  )
    args = parser.parse_args()
    f = open(args.log_file)
    lines  = [line.rstrip("\n") for line in f.readlines()]
    # skip the first 3 lines
    lines = lines[3:]
    numbers = {'1','2','3','4','5','6','7','8','9','0'}
    iters = []
    loss = []
    for line in lines:
        if line[0] in numbers:
            args = line.split(" ")
            if len(args) >3:
                iters.append(int(args[0][:-1]))
                loss.append(float(args[2]))
    plt.plot(iters,loss)
    plt.xlabel('iters')
    plt.ylabel('loss')
    plt.grid()
    plt.show()
if __name__ == "__main__":
    main(sys.argv)

Loaded: 4.533954 seconds
Region Avg IOU: 0.262313, Class: 1.000000, Obj: 0.542580, No Obj: 0.514735, Avg Recall: 0.162162,  count: 37
Region Avg IOU: 0.175988, Class: 1.000000, Obj: 0.499655, No Obj: 0.517558, Avg Recall: 0.070423,  count: 71
Region Avg IOU: 0.200012, Class: 1.000000, Obj: 0.483404, No Obj: 0.514622, Avg Recall: 0.075758,  count: 66
Region Avg IOU: 0.279284, Class: 1.000000, Obj: 0.447059, No Obj: 0.515849, Avg Recall: 0.134615,  count: 52
1: 629.763611, 629.763611 avg, 0.001000 rate, 6.098687 seconds, 64 images
Loaded: 2.957771 seconds
Region Avg IOU: 0.145857, Class: 1.000000, Obj: 0.051285, No Obj: 0.031538, Avg Recall: 0.069767,  count: 43
Region Avg IOU: 0.257284, Class: 1.000000, Obj: 0.048616, No Obj: 0.027511, Avg Recall: 0.078947,  count: 38
Region Avg IOU: 0.174994, Class: 1.000000, Obj: 0.030197, No Obj: 0.029943, Avg Recall: 0.088889,  count: 45
Region Avg IOU: 0.196278, Class: 1.000000, Obj: 0.076030, No Obj: 0.030472, Avg Recall: 0.087719,  count: 57
2: 84.804230, 575.267700 avg, 0.001000 rate, 5.959159 seconds, 128 images
iter  总损失      平均损失           学习率           花费时间    参与训练的图片总数

Region 82 Avg IOU: 0.798032, Class: 0.559781, Obj: 0.515851, No Obj: 0.006533, .5R: 1.000000, .75R: 1.000000, count: 2
Region 94 Avg IOU: 0.725307, Class: 0.830518, Obj: 0.506567, No Obj: 0.000680, .5R: 1.000000, .75R: 0.750000, count: 4
Region 106 Avg IOU: 0.579333, Class: 0.322556, Obj: 0.020537, No Obj: 0.000070, .5R: 1.000000, .75R: 0.000000, count: 2

2706: 1.350835, 1.386559 avg, 0.001000 rate, 3.323842 seconds, 173184 images
batch   总损失      平均损失       学习率　  　花费时间　     参与训练的图片总数 = 2706 * 64

#include <unistd.h>
#include <fcntl.h>

#include "darknet.h"
#include <sys/stat.h>
#include <stdio.h>
#include <time.h>
#include <sys/types.h>

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};

//产生的文件名与原文件名相同（去除路径和格式）
char *GetFilename(char *fullname)
{
    int from,to,i;
    char *newstr,*temp;
    if(fullname!=NULL){
        //if not find dot
        if((temp=strchr(fullname,'.'))==NULL){
        newstr = fullname;
        }
        else
        {
            from = strlen(fullname) - strlen(temp);
            to = (temp-fullname);
            //the first dot's index
            for (i=from; i<=to; i--){
                if (fullname[i]=='.') break;//find the last dot
            }
            newstr = (char*)malloc(i+1);
            strncpy(newstr,fullname,i);
            *(newstr+i)=0;
        }
    }
    static char name[50] = {""};
    char *q = strrchr(newstr,'/') + 1;
    strncpy(name,q,40);
    return name;
}

./darknet detector valid cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_final.weights -i 1 -out ""

./darknet detector test cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_final.weights -i 2 #enter

Enter Image Path: data/voc/2007_test.txt

306   746   783       RPs/Img: 21.45  IOU: 75.59%     Recall:95.27%
307   748   785       RPs/Img: 21.43  IOU: 75.62%     Recall:95.29%
308   750   787       RPs/Img: 21.42  IOU: 75.59%     Recall:95.30%
309   752   789       RPs/Img: 21.43  IOU: 75.62%     Recall:95.31%
310   754   791       RPs/Img: 21.44  IOU: 75.63%     Recall:95.32%
No.  Correct total

        for (j = 0; j < num_labels; ++j) {
            ++total;
            box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
            printf("truth x=%f, y=%f, w=%f,h=%f\n",truth[j].x,truth[j].y,truth[j].w,truth[j].h);//添加代码
            float best_iou = 0;
            for(k = 0; k < l.w*l.h*l.n; ++k){
                float iou = box_iou(dets[k].bbox, t);
                if(dets[k].objectness > thresh && iou > best_iou){
                    printf("predict=%f x=%f, y=%f, w=%f,h=%f\n",dets[k].objectness,dets[k].bbox.x,dets[k].bbox.y,dets[k].bbox.w,dets[k].bbox.h);//添加代码
                    best_iou = iou;
                }
            }

void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
{
    ...
    //layer l = net->layers[net->n-1]; //注释掉
    ...
            for(k = 0; k < l.w*l.h*l.n; ++k){ //改为for(k = 0; k < nboxes; ++k){
    ...

.xml文件结构中

      ①若无pose
22    #obj_struct['pose'] = obj.find('pose').text      #    注释掉

      ②若无truncated
23    #obj_struct['truncated'] = int(obj.find('truncated').text) #    注释掉

      ③若无difficult
24    #obj_struct['difficult'] = int(obj.find('difficult').text)    #    注释掉
137    #if use_diff: #    注释掉
138        #difficult = np.array([False for x in R]).astype(np.bool)　  #注释掉
139    #else:　#    注释掉　
140        #difficult = np.array([x['difficult'] for x in R]).astype(np.bool) # 注释掉
142    npos = npos +len(R)    　   # 更改npos = npos + sum(~difficult)
145    #'difficult': difficult,    　 #    注释掉
197    #if not R['difficult'][jmax]:    　#注释掉

#!/home/xieqi/anaconda2/envs/py2.7/bin python2.7
# -*- coding:utf-8 -*-

from voc_eval import voc_eval

print(voc_eval('/home/xieqi/darknet/results/{}.txt', '/home/xieqi/project/traffic_object_detection/voc_data/Annotations/{}.xml', 
'/home/xieqi/project/traffic_object_detection/voc_data/ImageSets/Main/test.txt', 'vehicle', '/home/xieqi/project/traffic_object_detection/result/'))

# "第一个参数为detector valid 按类别分类后的txt路径"
# "第二个参数为验证集对应的xml标签路径"
# "第三个为验证集txt文本路径，内容必须是无路径无后缀的图片名"
# "第四个为待验证的类别名"
# "第五个为pkl文件保存的路径"

#!/home/xieqi/anaconda2/envs/py2.7/bin python2.7
# -*- coding:utf-8 -*-

from voc_eval import voc_eval

import os

current_path = os.getcwd()
results_path = current_path+"/results"
sub_files = os.listdir(results_path)

mAP = []
for i in range(len(sub_files)):
    class_name = sub_files[i].split(".txt")[0]
    rec, prec, ap = voc_eval('/home/xieqi/darknet/results/{}.txt',
　'
																				

						

							上一篇：							
								YOLO 系列梳理 (I) YOLOv1-YOLOv3							
						
						

							下一篇：							
								程序员机器学习入门 (XI) - 物体识别 YOLO - 识别人脸位置和是否佩戴人脸面具							
						
					
															

						

							推荐阅读						
						

														

								
									

										主流技术一网打尽！我推出了一个令人惊叹的项目实战教程网站！									
								
							
														

								
									

										探秘网宿如何运用新一代QUIC协议进行深度优化实战									
								
							
														

								
									

										2020全新微信小程序学习宝典：一网打尽文档、视频教程、实战课、开源项目及框架资源									
								
							
														

								
									

										抓包与分析Wi-Fi网络实战：无线局域网数据包探索(第四部分)									
								
							
														

								
									

										实战练习：水果主题网页设计 using HTML, CSS & JavaScript，以及企业官网的模拟创建示例									
								
							
														

								
									

										ArchR官网教学实战心得15：探索ArchR的综合分析功能指南									
								
							
														

								
									

										YOLO-V3 实战（暗网）									
								
							
														

								
									

										基于 YOLO-V3 的缺陷检测（暗网框架）									
								
							
														

								
									

										小说|暗网成人礼									
								
							
														

								
									

										令人毛骨悚然的暗网《海绵宝宝》电影中隐藏着什么？