运行yolo_v3之路
一 准备-编译darknet
- 下载工程：
git clone https://github.com/pjreddie/darknet
cd darknet- 修改Makefile配置文件：
GPU=1
CUDNN=1 #我是用了gpu和cudnn
...
NVCC=/home/user/cuda_9.0/bin/nvcc #修改为自己的路径
...
ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda-9.0/include/ #修改为自己的路径
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda-9.0/lib64 -lcuda -lcudart -lcublas -lcurand #修改为自己的路径
endif - 修改完Makefile文件，在darknet文件夹下，终端make命令。
二 测试是否安装成功
- 下载训练好的权重（预训练权重）
wget https://pjreddie.com/media/files/darknet53.conv.74 
- 测试
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg在darknet文件夹下会出现predictions.jpg
三 准备自己的数据
- 在darknet文件夹下拷贝自己的数据命名为myData
myData
…JEPGImage #存放原图像
…Annotations #存放xml
…ImageSets
…-----Main #ImageSets 的子文件，存放训练，验证图像的名字val.txt，运行get_filename_to_txt.py得到
#get_filename_to_txt.py
import os
from os import listdir, getcwd
from os.path import join
if __name__ == '__main__':
source_folder='/media/ubuntu/storage/LXD/yolov3/darknet/myData/JPEGImages/'
dest2='/media/ubuntu/storage/LXD/yolov3/darknet/myData/ImageSets/Main/val.txt'
file_list=os.listdir(source_folder)
val_file=open(dest2,'a')
for file_obj in file_list:
file_path=os.path.join(source_folder,file_obj)
file_name,file_extend=os.path.splitext(file_obj)
file_num=int(file_name)
val_file.write(file_name+'\n')
val_file.close()- 将数据集转换为darknet支持的数据格式
在scripts/voc_label.py，在darknet文件夹下新建my_label.py，修改内容如下：
#sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[('myData', 'val')]
#classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes = ["your_classname", "...",]
...
def convert_annotation(year, image_id):
in_file = open('myData/Annotations/%s.xml'%( image_id))
out_file = open('myData/labels/%s.txt'%( 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 year, image_set in sets:
if not os.path.exists('myData/labels/'):
os.makedirs('myData/labels/')
image_ids = open('myData/ImageSets/Main/%s.txt'%(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_/myData/JPEGImages/%s.jpg\n'%(wd, image_id))
convert_annotation(year, image_id)
list_file.close()
#os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt")
#os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")运行之后会在./myData目录下生成labels，labels文件夹下有一系列的.txt文件，记录了每个.xml文件的类别，四个相对位置坐标。在darknet文件夹下会生成myData_val.txt文件，存储了每张图片所在的绝对路径。如下所示：
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/1243.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/6197.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/1345.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/6183.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/1758.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/5136.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/2351.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/4157.jpg
/media/ubuntu/storage/LXD/yolov3/darknet_/myData/JPEGImages/4200.jpg四 修改自己的配置文件
- 修改darknet/cfg 文件下voc.data和yolov3_voc.cfg文件（复制重命名为my_data.data和my_yolo_v3.cfg）。修改如下：
##修改mydata.data，按照自己的文件地址修改
classes= 2 #类别数
train = /media/ubuntu/storage/LXD/yolov3/darknet/myData/myData_train.txt #训练.txt文件
valid = /media/ubuntu/storage/LXD/yolov3/darknet/myData/myData_val.txt #验证.txt文件
names = /media/ubuntu/storage/LXD/yolov3/darknet/myData/voc.names #类别名称
backup = /media/ubuntu/storage/LXD/yolov3/darknet/myData/weights #训练权重放置的文件夹##修改my_yolo_v3.cfg，按照自己的文件地址修改
[net]
# Testing
#batch=1
#subdivisions=1
#Training
batch=64
subdivisions=16
...
[convolutional]
size=1
stride=1
pad=1
filters=21 #修改filters=anchors_num*(classes_num+5)，这里anchors_num=3，classes_num=2
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=2 #修改类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1
...
[convolutional]
size=1
stride=1
pad=1
filters=21 #修改filters=anchors_num*(classes_num+5)，这里anchors_num=3，classes_num=2
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=2 #修改类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1
...
[convolutional]
size=1
stride=1
pad=1
filters=21 #修改filters=anchors_num*(classes_num+5)，这里anchors_num=3，classes_num=2
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=2 #修改类别数
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1
- 在myData文件夹下新建voc.names文件（仿照./data/voc.name，放置自己的类别名）。
五 训练及测试
- 使用刚刚下好的预训练权重训练
./darknet detector train cfg/my_data.data cfg/my_yolov3.cfg darknet53.conv.74 >val_yolov3.log 2>&1 -gpu 1
# >val_yolov3.log 2>&1是保存训练日志，名称为：val_yolov3.log
#-gpu 1指定使用‘1’gpu，多gpu可使用-gpus 1,2,3- 批量测试模型（须修改./darknet/detector.c文件）
首先修改my_yolo_v3.cfg，
[net]
# Testing
batch=1
subdivisions=1
#Training
#batch=64
#subdivisions=16%修改dtector.c,重写test_detector函数
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);
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);
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");
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("/media/ubuntu/storage/LXD/darknet/myData/result",0)==-1)//修改成自己的路径
{
if (mkdir("/media/ubuntu/storage/LXD/darknet/myData/result",0777))//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);
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);
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,"/media/ubuntu/storage/LXD/darknet/myData/result/%s",GetFilename(path));//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;
}
}
}
}
在darknet文件夹下运行以下命令，查看0305_yolov3.log文件，最后一行为Enter Image Path:后在终端输入测试图片的.txt文件绝对路径如：（/media/ubuntu/storage/LXD/yolov3/darknet/myData/myData_val.txt），会在/darknet/myData/result文件夹下出现测试图片。如果测试结果名称不对，修改./darknet/data/coco.names为自己的类别。
./darknet detector test cfg/my_data.data cfg/my_yolov3.cfg myData/weights/my_yolov3_final.weights >0305_yolov3.log 2>&1PS：本博客参考多位博主的博客，网页，作为自己学习总结，时间有点儿长，不能一一列出参考来源，望见谅！！！