Darknet源码阅读notes
darknet notes
some functions
char *basecfg(char *cfgfile)
{
char *c = cfgfile;
char *next;
while((next = strchr(c, '/')))
{
c = next+1;
}
c = copy_string(c);
next = strchr(c, '.');
if (next) *next = 0;
return c;
}C 库函数 char *strchr(const char *str, int c) 在参数 str 所指向的字符串中搜索第一次出现字符 c（一个无符号字符）的位置。返回的next实际上是指向c的指针，用%s打出来也就是c（包含）之后的字符串。while 当还有斜杠时，继续往后找，没有斜杠就退出，也就是指向最后一个斜杠。与点号匹配去后缀名。
typedef struct network{
int n;
int batch;
size_t *seen;
int *t;
float epoch;
int subdivisions;
layer *layers;
float *output;
learning_rate_policy policy;
float learning_rate;
float momentum;
float decay;
float gamma;
float scale;
float power;
int time_steps;
int step;
int max_batches;
float *scales;
int *steps;
int num_steps;
int burn_in;
int adam;
float B1;
float B2;
float eps;
int inputs;
int outputs;
int truths;
int notruth;
int h, w, c;
int max_crop;
int min_crop;
float max_ratio;
float min_ratio;
int center;
float angle;
float aspect;
float exposure;
float saturation;
float hue;
int random;
int gpu_index;
tree *hierarchy;
float *input;
float *truth;
float *delta;
float *workspace;
int train;
int index;
float *cost;
float clip;
#ifdef GPU
float *input_gpu;
float *truth_gpu;
float *delta_gpu;
float *output_gpu;
#endif
} network;darknet.h中对network的定义。
network *load_network(char *cfg, char *weights, int clear)
{
network *net = parse_network_cfg(cfg);
if(weights && weights[0] != 0){
load_weights(net, weights);
}
if(clear) (*net->seen) = 0;
return net;
}通过cfg文件和已有的权重加载网络模型。从cfg到网络的过程有函数parse_network_cfg实现。首先看如何读入cfg文件到list* 类型。
list *read_cfg(char *filename)
{
FILE *file = fopen(filename, "r");
if(file == 0) file_error(filename);
char *line;
int nu = 0;
list *options = make_list();
section *current = 0;
while((line=fgetl(file)) != 0){
++ nu;
strip(line);
switch(line[0]){
case '[':
current = malloc(sizeof(section));
list_insert(options, current);
current->options = make_list();
current->type = line;
break;
case '\0':
case '#':
case ';':
free(line);
break;
default:
if(!read_option(line, current->options)){
fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
free(line);
}
break;
}
}
fclose(file);
return options;
}可以看出，先判断每一行有没有内容。这里的read_cfg读到一个[ ]中括号，就开一块内存，并且把它加入到现有的options的list中。遇到反斜杠0，#或；都直接break。如果不是按照规则写的则报错。返回options。
下面再看parse_network_cfg
network *parse_network_cfg(char *filename)
{
list *sections = read_cfg(filename);
node *n = sections->front;
if(!n) error("Config file has no sections");
network *net = make_network(sections->size - 1);
net->gpu_index = gpu_index;
size_params params;
section *s = (section *)n->val;
list *options = s->options;
if(!is_network(s)) error("First section must be [net] or [network]");
parse_net_options(options, net);
params.h = net->h;
params.w = net->w;
params.c = net->c;
params.inputs = net->inputs;
params.batch = net->batch;
params.time_steps = net->time_steps;
params.net = net;
size_t workspace_size = 0;
n = n->next;
int count = 0;
free_section(s);
fprintf(stderr, "layer filters size input output\n");
while(n){
params.index = count;
fprintf(stderr, "%5d ", count);
s = (section *)n->val;
options = s->options;
layer l = {0};
LAYER_TYPE lt = string_to_layer_type(s->type);
if(lt == CONVOLUTIONAL){
l = parse_convolutional(options, params);
}else if(lt == DECONVOLUTIONAL){
l = parse_deconvolutional(options, params);
}else if(lt == LOCAL){
l = parse_local(options, params);
}else if(lt == ACTIVE){
l = parse_activation(options, params);
}else if(lt == LOGXENT){
l = parse_logistic(options, params);
}else if(lt == L2NORM){
l = parse_l2norm(options, params);
}else if(lt == RNN){
l = parse_rnn(options, params);
}else if(lt == GRU){
l = parse_gru(options, params);
}else if (lt == LSTM) {
l = parse_lstm(options, params);
}else if(lt == CRNN){
l = parse_crnn(options, params);
}else if(lt == CONNECTED){
l = parse_connected(options, params);
}else if(lt == CROP){
l = parse_crop(options, params);
}else if(lt == COST){
l = parse_cost(options, params);
}else if(lt == REGION){
l = parse_region(options, params);
}else if(lt == YOLO){
l = parse_yolo(options, params);
}else if(lt == DETECTION){
l = parse_detection(options, params);
}else if(lt == SOFTMAX){
l = parse_softmax(options, params);
net->hierarchy = l.softmax_tree;
}else if(lt == NORMALIZATION){
l = parse_normalization(options, params);
}else if(lt == BATCHNORM){
l = parse_batchnorm(options, params);
}else if(lt == MAXPOOL){
l = parse_maxpool(options, params);
}else if(lt == REORG){
l = parse_reorg(options, params);
}else if(lt == AVGPOOL){
l = parse_avgpool(options, params);
}else if(lt == ROUTE){
l = parse_route(options, params, net);
}else if(lt == UPSAMPLE){
l = parse_upsample(options, params, net);
}else if(lt == SHORTCUT){
l = parse_shortcut(options, params, net);
}else if(lt == DROPOUT){
l = parse_dropout(options, params);
l.output = net->layers[count-1].output;
l.delta = net->layers[count-1].delta;
#ifdef GPU
l.output_gpu = net->layers[count-1].output_gpu;
l.delta_gpu = net->layers[count-1].delta_gpu;
#endif
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
l.clip = net->clip;
l.truth = option_find_int_quiet(options, "truth", 0);
l.onlyforward = option_find_int_quiet(options, "onlyforward", 0);
l.stopbackward = option_find_int_quiet(options, "stopbackward", 0);
l.dontsave = option_find_int_quiet(options, "dontsave", 0);
l.dontload = option_find_int_quiet(options, "dontload", 0);
l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
l.learning_rate_scale = option_find_float_quiet(options, "learning_rate", 1);
l.smooth = option_find_float_quiet(options, "smooth", 0);
option_unused(options);
net->layers[count] = l;
if (l.workspace_size > workspace_size) workspace_size = l.workspace_size;
free_section(s);
n = n->next;
++count;
if(n){
params.h = l.out_h;
params.w = l.out_w;
params.c = l.out_c;
params.inputs = l.outputs;
}
}
free_list(sections);
layer out = get_network_output_layer(net);
net->outputs = out.outputs;
net->truths = out.outputs;
if(net->layers[net->n-1].truths) net->truths = net->layers[net->n-1].truths;
net->output = out.output;
net->input = calloc(net->inputs*net->batch, sizeof(float));
net->truth = calloc(net->truths*net->batch, sizeof(float));
#ifdef GPU
net->output_gpu = out.output_gpu;
net->input_gpu = cuda_make_array(net->input, net->inputs*net->batch);
net->truth_gpu = cuda_make_array(net->truth, net->truths*net->batch);
#endif
if(workspace_size){
//printf("%ld\n", workspace_size);
#ifdef GPU
if(gpu_index >= 0){
net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
}else {
net->workspace = calloc(1, workspace_size);
}
#else
net->workspace = calloc(1, workspace_size);
#endif
}
return net;
}
主要内容就是通过读出来的每个LAYERTYPE调用不同的parse某种layer 的函数，生成网络结构，并且把参数如batch等传进net。举栗子：parse_convolutional如下：
convolutional_layer parse_convolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
int pad = option_find_int_quiet(options, "pad",0);
int padding = option_find_int_quiet(options, "padding",0);
int groups = option_find_int_quiet(options, "groups", 1);
if(pad) padding = size/2;
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before convolutional layer must output image.");
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
int binary = option_find_int_quiet(options, "binary", 0);
int xnor = option_find_int_quiet(options, "xnor", 0);
convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,groups,size,stride,padding,activation, batch_normalize, binary, xnor, params.net->adam);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
return layer;
}
（to be continued）
2018年7月11日17:49:57
