本人纯属新手,要是有什么讲的不对的地方,请各位大神批评指正。
yolo仅测试图片所需要的配置不是很高,没有装cuda,没有装opencv也能跑起来,在cpu模式下,测试一张图片需要6~7秒的时间。
下面是跑yolo代码的过程:
首先从官网克隆代码,以及下载预训练的模型(一个正常版本的和一个快速版本的),前提是你不想训练自己的模型的话。
克隆:git clone https://github.com/pjreddie/darknet
下载两个预训练模型,下载完放入darknet文件夹下面即可
http://pjreddie.com/media/files/yolo.weights
http://pjreddie.com/media/files/tiny-yolo-voc.weights
测试图片:
cd darknet
make
./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg
这条语句的意思是进入darknet.c文件,这个文件在src文件夹中,然后进入darknet.c的main函数中,
main函数主要是判断输入的参数,判断的时候以空格左键分隔符,下面给出main函数的主要代码:
int main(int argc, char **argv) #argc表示输入参数的个数,argv是输入参数的内容
{
//test_resize("data/bad.jpg");
//test_box();
//test_convolutional_layer();
if(argc < 2){
fprintf(stderr, "usage: %s <function>\n", argv[0]);
return 0;
}
gpu_index = find_int_arg(argc, argv, "-i", 0);
if(find_arg(argc, argv, "-nogpu")) {
gpu_index = -1;
}
#ifndef GPU
gpu_index = -1;
#else
if(gpu_index >= 0){
cuda_set_device(gpu_index);
}
#endif
if (0 == strcmp(argv[1], "average")){
average(argc, argv);
} else if (0 == strcmp(argv[1], "yolo")){
run_yolo(argc, argv);
} else if (0 == strcmp(argv[1], "voxel")){
run_voxel(argc, argv);
} else if (0 == strcmp(argv[1], "super")){
run_super(argc, argv);
} else if (0 == strcmp(argv[1], "detector")){
run_detector(argc, argv);
} else if (0 == strcmp(argv[1], "detect")){
float thresh = find_float_arg(argc, argv, "-thresh", .24);
char *filename = (argc > 4) ? argv[4]: 0;
test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, .5);
...}
这个函数的作用就是判断我们输入的命令中的一些参数,像我们测试图片就会检测到“detect”这个关键字,然后读取阈值(没有的话默认是
0.24),读取图片的地址(没有的话会提示让你输入图片的路径),然后就进入test_detector函数,下面贴出这个函数以及我做的一些备注:
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh)
{
list *options = read_data_cfg(datacfg);#读取数据文件
char *name_list = option_find_str(options, "names", "data/names.list");
#读取namelist(coco.name)
char **names = get_labels(name_list);
#读取标签
image **alphabet = load_alphabet();
#读取labels下面的图片
network net = parse_network_cfg(cfgfile);
#读取网络架构
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
#将网络的batch设置为1
srand(2222222);
clock_t time;#开始计时
char buff[256];
char *input = buff;
int j;
float nms=.4; #nms阈值
while(1){
if(filename){
strncpy(input, filename, 256); #复制图片路径
} else {
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input,0,0);#
image sized = resize_image(im, net.w, net.h);#将图片的resize到416*416
layer l = net.layers[net.n-1];#网络最后一层
box *boxes = calloc(l.w*l.h*l.n, sizeof(box)); #分配box的空间
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));#分配分数的空间
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
float *X = sized.data; #resize之后的图片
time=clock();
network_predict(net, X);%开始检测图片,返回最后一层的输出
printf("%s: Predicted finised in %f seconds.\n", input, sec(clock()-time));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0, hier_thresh);#得到预测的所有框
if (l.softmax_tree && nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
else if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
#极大值抑制
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
#输出各个框的置信度得分以及画出这些框
save_image(im, "predictions");
show_image(im, "predictions");
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
上面中的每一个函数都在其他的.c文件中能够找到,不懂的可以去找一找。
下面给出如何在电脑上基于yolo算法使用摄像头进行检测或者是检测视频:(前提是要装好cuda和opencv)
./darknet detector demo cfg/coco.data cfg/yolo.cfg yolo.weights
这条命令是打开摄像头进行实时检测,能检测的类别数在data文件夹下面的coco.name中,这个文件大家可以自行更改。
./darknet detector demo cfg/coco.data cfg/yolo.cfg yolo.weights <video file>
这条命令是检测视频,视频要放在darknet的根目录下面。
使用摄像头或者是检测 视频都会进入run_detector()这个函数,下面贴出这个函数的代码,如果上面的检测过程你很熟悉了,
那下面的代码看起来也不是很难了
void run_detector(int argc, char **argv)
{
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .24);
float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
}
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
char *outfile = find_char_arg(argc, argv, "-out", 0);
int *gpus = 0;
int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
int len = strlen(gpu_list);
ngpus = 1;
int i;
for(i = 0; i < len; ++i){
if (gpu_list[i] == ',') ++ngpus;
}
gpus = calloc(ngpus, sizeof(int));
for(i = 0; i < ngpus; ++i){
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
} else {
gpu = gpu_index;
gpus = &gpu;
ngpus = 1;
}
int clear = find_arg(argc, argv, "-clear");
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, hier_thresh);
}
}
。。。。
未完待续
,下面贴出这个函数的代码,如果上面的检测过程你很熟悉了,
那下面的代码看起来也不是很难了
void run_detector(int argc, char **argv)
{
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .24);
float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
}
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
char *outfile = find_char_arg(argc, argv, "-out", 0);
int *gpus = 0;
int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
int len = strlen(gpu_list);
ngpus = 1;
int i;
for(i = 0; i < len; ++i){
if (gpu_list[i] == ',') ++ngpus;
}
gpus = calloc(ngpus, sizeof(int));
for(i = 0; i < ngpus; ++i){
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
} else {
gpu = gpu_index;
gpus = &gpu;
ngpus = 1;
}
int clear = find_arg(argc, argv, "-clear");
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, hier_thresh);
}
}