分析过程
首先我们从yolo的训练命令开始分析(yolo的源码是用c++写的):
./darknet detector train cfg/voc.data cfg/yolo-voc.cfg darknet19_448.conv.23
从这里我们可以看出yolo主函数main中的参数argv[]在其中对应的值分别是 argv[0] -> darknet argv[1] -> detector argv[2] -> train .....(剩下的自己看),从这里我们可以看出,yolo主函数main一定在examples/darknet.c中,让我们来看一下主函数:
int main(int argc, char **argv)
{
//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], "lsd")){
run_lsd(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;
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);
} else if (0 == strcmp(argv[1], "cifar")){
run_cifar(argc, argv);
} else if (0 == strcmp(argv[1], "go")){
run_go(argc, argv);
} else if (0 == strcmp(argv[1], "rnn")){
run_char_rnn(argc, argv);
} else if (0 == strcmp(argv[1], "vid")){
run_vid_rnn(argc, argv);
} else if (0 == strcmp(argv[1], "coco")){
run_coco(argc, argv);
} else if (0 == strcmp(argv[1], "classify")){
predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
} else if (0 == strcmp(argv[1], "classifier")){
run_classifier(argc, argv);
} else if (0 == strcmp(argv[1], "regressor")){
run_regressor(argc, argv);
} else if (0 == strcmp(argv[1], "segmenter")){
run_segmenter(argc, argv);
} else if (0 == strcmp(argv[1], "art")){
run_art(argc, argv);
} else if (0 == strcmp(argv[1], "tag")){
run_tag(argc, argv);
} else if (0 == strcmp(argv[1], "compare")){
run_compare(argc, argv);
} else if (0 == strcmp(argv[1], "dice")){
run_dice(argc, argv);
} else if (0 == strcmp(argv[1], "writing")){
run_writing(argc, argv);
} else if (0 == strcmp(argv[1], "3d")){
composite_3d(argv[2], argv[3], argv[4], (argc > 5) ? atof(argv[5]) : 0);
} else if (0 == strcmp(argv[1], "test")){
test_resize(argv[2]);
} else if (0 == strcmp(argv[1], "captcha")){
run_captcha(argc, argv);
} else if (0 == strcmp(argv[1], "nightmare")){
run_nightmare(argc, argv);
} else if (0 == strcmp(argv[1], "rgbgr")){
rgbgr_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "reset")){
reset_normalize_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "denormalize")){
denormalize_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "statistics")){
statistics_net(argv[2], argv[3]);
} else if (0 == strcmp(argv[1], "normalize")){
normalize_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "rescale")){
rescale_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "ops")){
operations(argv[2]);
} else if (0 == strcmp(argv[1], "speed")){
speed(argv[2], (argc > 3 && argv[3]) ? atoi(argv[3]) : 0);
} else if (0 == strcmp(argv[1], "oneoff")){
oneoff(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "oneoff2")){
oneoff2(argv[2], argv[3], argv[4], atoi(argv[5]));
} else if (0 == strcmp(argv[1], "partial")){
partial(argv[2], argv[3], argv[4], atoi(argv[5]));
} else if (0 == strcmp(argv[1], "average")){
average(argc, argv);
} else if (0 == strcmp(argv[1], "visualize")){
visualize(argv[2], (argc > 3) ? argv[3] : 0);
} else if (0 == strcmp(argv[1], "mkimg")){
mkimg(argv[2], argv[3], atoi(argv[4]), atoi(argv[5]), atoi(argv[6]), argv[7]);
} else if (0 == strcmp(argv[1], "imtest")){
test_resize(argv[2]);
} else {
fprintf(stderr, "Not an option: %s\n", argv[1]);
}
return 0;
}
很简单可以看出,主函数就是对于参数argv[1]的一个判断,根据argv[1]的内容来启动不同的程序。让我们继续跟着训练命令走argv[1] = detector时,调用的函数是run_detector,而这个函数在examples/detector.c的最后,让我们再来看看这个函数吧:
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);
int avg = find_int_arg(argc, argv, "-avg", 3);
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");
int fullscreen = find_arg(argc, argv, "-fullscreen");
int width = find_int_arg(argc, argv, "-w", 0);
int height = find_int_arg(argc, argv, "-h", 0);
int fps = find_int_arg(argc, argv, "-fps", 0);
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, outfile, fullscreen);
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], "valid2")) validate_detector_flip(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", 2);
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, avg, hier_thresh, width, height, fps, fullscreen);
}
}
在这里 run_detector的主要作用还是在根据argv[]的值执行不同的函数,其他关于gpu啊,threshold啊之类的我们都可以不用管,这里最重要的是argv[2]的值,根据其值的不同,执行不同函数,这里的test_detector,train_detector这些函数在detector.c中都有定义,并且从名字上我们就可以看出这些函数是干什么的。这里我们依旧跟随之前的训练命令,argv[2] = train,这里让我们来看一下train_detector函数(注:这里是我修改过一部分的,不是原来的代码):
void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
list *options = read_data_cfg(datacfg);
char *train_images = option_find_str(options, "train", "scripts/train.txt"); //训练集路径
char *backup_directory = option_find_str(options, "backup", "/backup/"); //备份训练结果路径
srand(time(0));
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
network *nets = calloc(ngpus, sizeof(network));
srand(time(0));
int seed = rand();
int i;
for(i = 0; i < ngpus; ++i){
srand(seed);
#ifdef GPU
cuda_set_device(gpus[i]);
#endif
nets[i] = load_network(cfgfile, weightfile, clear); //载入网络
nets[i].learning_rate *= ngpus;
}
srand(time(0));
network net = nets[0];
int imgs = net.batch * net.subdivisions * ngpus;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
data train, buffer;
layer l = net.layers[net.n - 1];
int classes = l.classes;
float jitter = l.jitter;
list *plist = get_paths(train_images);
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.paths = paths;
args.n = imgs;
args.m = plist->size;
args.classes = classes;
args.jitter = jitter;
args.num_boxes = l.max_boxes;
args.d = &buffer;
args.type = DETECTION_DATA;
args.threads = 8;
args.angle = net.angle;
args.exposure = net.exposure;
args.saturation = net.saturation;
args.hue = net.hue;
pthread_t load_thread = load_data(args);
clock_t time;
int count = 0;
//while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
if(l.random && count++%10 == 0){
printf("Resizing\n");
int dim = (rand() % 10 + 10) * 32;
if (get_current_batch(net)+200 > net.max_batches) dim = 608;
//int dim = (rand() % 4 + 16) * 32;
printf("%d\n", dim);
args.w = dim;
args.h = dim;
pthread_join(load_thread, 0);
train = buffer;
free_data(train);
load_thread = load_data(args);
for(i = 0; i < ngpus; ++i){
resize_network(nets + i, dim, dim);
}
net = nets[0];
}
time=clock();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data(args);
/*
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
if(!b.x) break;
printf("loaded: %f %f %f %f\n", b.x, b.y, b.w, b.h);
}
*/
/*
int zz;
for(zz = 0; zz < train.X.cols; ++zz){
image im = float_to_image(net.w, net.h, 3, train.X.vals[zz]);
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[zz] + k*5);
printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
draw_bbox(im, b, 1, 1,0,0);
}
show_image(im, "truth11");
cvWaitKey(0);
save_image(im, "truth11");
}
*/
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = 0;
#ifdef GPU
if(ngpus == 1){
loss = train_network(net, train);
} else {
loss = train_networks(nets, ngpus, train, 4);
}
#else
loss = train_network(net, train);
#endif
if (avg_loss < 0) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
i = get_current_batch(net);
printf("%ld: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
if(i%1000==0){
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s.backup", backup_directory, base);
save_weights(net, buff);
}
if(i%10000==0 || (i < 1000 && i%100 == 0)){
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
}
free_data(train);
}
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
}
这里我们主要重视的函数是第7行的read_data_cfg,第8行的train_images,第9行的backup_directory和第25行的load_network函数:
read_data_cfg中的参数datacfg在run_detector中可以看出就是arg[3],在本例中对应的就是voc.data
train_images是用来指定所要训练的图片集的路径的。
backup_directory是用来指定训练出来的权值的路劲的。
而load_network是用来载入所要训练的网络结构和参数的,这里run_detector中可以看出load_network的参数之一cfgfile就是argv[4],在我们这个例子中也便就是yolo-voc.cfg
这里我们先看一下cfg/voc.data(注:这里是我修改过了的,不是原来的)
classes= 2 train = /home/iair339-04/darknet/scripts/train.txt valid = /home/iair339-04/darknet/scripts/2007_test.txt names = data/kitti.names backup = backup
这里可以看出voc.data是用来指定类别数classes,训练集路径train,测试集路径valid和类别名称names和备份文件路径backup的(so easy)。
接下来我们来看一下yolo-voc.cfg文件(注:修改过)
[net] # Testing #batch=1 #subdivisions=1 # Training batch=64 subdivisions=8 height=416 width=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 = 80200 policy=steps steps=40000,60000 scales=.1,.1 [convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky [maxpool] size=2 stride=2 [convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky [maxpool] size=2 stride=2 [convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky [maxpool] size=2 stride=2 [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [maxpool] size=2 stride=2 [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [maxpool] size=2 stride=2 [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky ####### [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [route] layers=-9 [convolutional] batch_normalize=1 size=1 stride=1 pad=1 filters=64 activation=leaky [reorg] stride=2 [route] layers=-1,-4 [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [convolutional] size=1 stride=1 pad=1 filters=35 #此处修改 activation=linear [region] anchors = 1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071 bias_match=1 classes=2 #此处修改种类 coords=4 num=5 softmax=1 jitter=.3 rescore=1 object_scale=5 noobject_scale=1 class_scale=1 coord_scale=1 absolute=1 thresh = .6 random=1
这里[net]里面是网络的超参数的设置,而之后的便是yolo v2的网络结构了。