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(options, "pad",0);
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,size,stride,pad,activation, batch_normalize, binary, xnor);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(weights, layer.filters, c*n*size*size);
parse_data(biases, layer.biases, n);
#ifdef GPU
if(weights || biases) push_convolutional_layer(layer);
#endif
return layer;
}
void parse_net_options(list *options, network *net)
{
net->batch = option_find_int(options, "batch",1);
net->learning_rate = option_find_float(options, "learning_rate", .001);
net->momentum = option_find_float(options, "momentum", .9);
net->decay = option_find_float(options, "decay", .0001);
int subdivs = option_find_int(options, "subdivisions",1);
net->batch /= subdivs;
net->subdivisions = subdivs;
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
} else if (net->policy == STEPS){
char *l = option_find(options, "steps");
char *p = option_find(options, "scales");
if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
int len = strlen(l);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (l[i] == ',') ++n;
}
int *steps = calloc(n, sizeof(int));
float *scales = calloc(n, sizeof(float));
for(i = 0; i < n; ++i){
int step = atoi(l);
float scale = atof(p);
l = strchr(l, ',')+1;
p = strchr(p, ',')+1;
steps[i] = step;
scales[i] = scale;
}
net->scales = scales;
net->steps = steps;
net->num_steps = n;
} else if (net->policy == EXP){
net->gamma = option_find_float(options, "gamma", 1);
} else if (net->policy == SIG){
net->gamma = option_find_float(options, "gamma", 1);
net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY){
net->power = option_find_float(options, "power", 1);
}
net->max_batches = option_find_int(options, "max_batches", 0);
}
layer parse_gru(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
layer l = make_gru_layer(params.batch, params.inputs, output, params.time_steps, batch_normalize, params.net->adam);
l.tanh = option_find_int_quiet(options, "tanh", 0);
return l;
}
layer parse_rnn(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
layer l = make_rnn_layer(params.batch, params.inputs, output, params.time_steps, activation, batch_normalize, params.net->adam);
l.shortcut = option_find_int_quiet(options, "shortcut", 0);
return l;
}
layer parse_crnn(list *options, size_params params)
{
int output_filters = option_find_int(options, "output_filters",1);
int hidden_filters = option_find_int(options, "hidden_filters",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
layer l = make_crnn_layer(params.batch, params.w, params.h, params.c, hidden_filters, output_filters, params.time_steps, activation, batch_normalize);
l.shortcut = option_find_int_quiet(options, "shortcut", 0);
return l;
}
layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
layer l = make_softmax_layer(params.batch, params.inputs, groups);
l.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
l.w = params.w;
l.h = params.h;
l.c = params.c;
l.spatial = option_find_float_quiet(options, "spatial", 0);
l.noloss = option_find_int_quiet(options, "noloss", 0);
return l;
}
void parse_net_options(list *options, network *net)
{
net->batch = option_find_int(options, "batch",1);
net->learning_rate = option_find_float(options, "learning_rate", .001);
net->momentum = option_find_float(options, "momentum", .9);
net->decay = option_find_float(options, "decay", .0001);
int subdivs = option_find_int(options, "subdivisions",1);
net->batch /= subdivs;
net->subdivisions = subdivs;
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
}
softmax_layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
return layer;
}
layer parse_reorg(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
int reverse = option_find_int_quiet(options, "reverse",0);
int flatten = option_find_int_quiet(options, "flatten",0);
int extra = option_find_int_quiet(options, "extra",0);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before reorg layer must output image.");
layer layer = make_reorg_layer(batch,w,h,c,stride,reverse, flatten, extra);
return layer;
}
layer parse_region(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 4);
int classes = option_find_int(options, "classes", 20);
int num = option_find_int(options, "num", 1);
layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
assert(l.outputs == params.inputs);
l.log = option_find_int_quiet(options, "log", 0);
l.sqrt = option_find_int_quiet(options, "sqrt", 0);
l.softmax = option_find_int(options, "softmax", 0);
l.background = option_find_int_quiet(options, "background", 0);
l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0);
l.thresh = option_find_float(options, "thresh", .5);
l.classfix = option_find_int_quiet(options, "classfix", 0);
l.absolute = option_find_int_quiet(options, "absolute", 0);
l.random = option_find_int_quiet(options, "random", 0);
l.coord_scale = option_find_float(options, "coord_scale", 1);
l.object_scale = option_find_float(options, "object_scale", 1);
l.noobject_scale = option_find_float(options, "noobject_scale", 1);
l.mask_scale = option_find_float(options, "mask_scale", 1);
l.class_scale = option_find_float(options, "class_scale", 1);
l.bias_match = option_find_int_quiet(options, "bias_match",0);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
char *map_file = option_find_str(options, "map", 0);
if (map_file) l.map = read_map(map_file);
char *a = option_find_str(options, "anchors", 0);
if(a){
int len = strlen(a);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
for(i = 0; i < n; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
}
}
return l;
}
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;
}
softmax_layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) layer.softmax_tree = read_tree(tree_file);
return layer;
}
connected_layer parse_connected(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation, batch_normalize);
return layer;
}
detection_layer parse_detection(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 1);
int classes = option_find_int(options, "classes", 1);
int rescore = option_find_int(options, "rescore", 0);
int num = option_find_int(options, "num", 1);
int side = option_find_int(options, "side", 7);
detection_layer layer = make_detection_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
layer.softmax = option_find_int(options, "softmax", 0);
layer.sqrt = option_find_int(options, "sqrt", 0);
layer.max_boxes = option_find_int_quiet(options, "max",30);
layer.coord_scale = option_find_float(options, "coord_scale", 1);
layer.forced = option_find_int(options, "forced", 0);
layer.object_scale = option_find_float(options, "object_scale", 1);
layer.noobject_scale = option_find_float(options, "noobject_scale", 1);
layer.class_scale = option_find_float(options, "class_scale", 1);
layer.jitter = option_find_float(options, "jitter", .2);
layer.random = option_find_int_quiet(options, "random", 0);
layer.reorg = option_find_int_quiet(options, "reorg", 0);
return layer;
}
layer parse_yolo(list *options, size_params params)
{
int classes = option_find_int(options, "classes", 20);
int total = option_find_int(options, "num", 1);
int num = total;
char *a = option_find_str(options, "mask", 0);
int *mask = parse_yolo_mask(a, &num);
layer l = make_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes);
assert(l.outputs == params.inputs);
l.max_boxes = option_find_int_quiet(options, "max",90);
l.jitter = option_find_float(options, "jitter", .2);
l.ignore_thresh = option_find_float(options, "ignore_thresh", .5);
l.truth_thresh = option_find_float(options, "truth_thresh", 1);
l.random = option_find_int_quiet(options, "random", 0);
char *map_file = option_find_str(options, "map", 0);
if (map_file) l.map = read_map(map_file);
a = option_find_str(options, "anchors", 0);
if(a){
int len = strlen(a);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
for(i = 0; i < n; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
}
}
return l;
}
layer parse_deconvolutional(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);
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 deconvolutional layer must output image.");
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
int pad = option_find_int_quiet(options, "pad",0);
int padding = option_find_int_quiet(options, "padding",0);
if(pad) padding = size/2;
layer l = make_deconvolutional_layer(batch,h,w,c,n,size,stride,padding, activation, batch_normalize, params.net->adam);
return l;
}
maxpool_layer parse_maxpool(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
int size = option_find_int(options, "size",stride);
int padding = option_find_int_quiet(options, "padding", (size-1)/2);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before maxpool layer must output image.");
maxpool_layer layer = make_maxpool_layer(batch,h,w,c,size,stride,padding);
return layer;
}
connected_layer parse_connected(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation, batch_normalize);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(biases, layer.biases, output);
parse_data(weights, layer.weights, params.inputs*output);
#ifdef GPU
if(weights || biases) push_connected_layer(layer);
#endif
return layer;
}
crop_layer parse_crop(list *options, size_params params)
{
int crop_height = option_find_int(options, "crop_height",1);
int crop_width = option_find_int(options, "crop_width",1);
int flip = option_find_int(options, "flip",0);
float angle = option_find_float(options, "angle",0);
float saturation = option_find_float(options, "saturation",1);
float exposure = option_find_float(options, "exposure",1);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before crop layer must output image.");
int noadjust = option_find_int_quiet(options, "noadjust",0);
crop_layer l = make_crop_layer(batch,h,w,c,crop_height,crop_width,flip, angle, saturation, exposure);
l.noadjust = noadjust;
return l;
}
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);
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;
size_t workspace_size = 0;
n = n->next;
int count = 0;
free_section(s);
while(n){
params.index = count;
fprintf(stderr, "%d: ", count);
s = (section *)n->val;
options = s->options;
layer l = {0};
if(is_convolutional(s)){
l = parse_convolutional(options, params);
}else if(is_local(s)){
l = parse_local(options, params);
}else if(is_activation(s)){
l = parse_activation(options, params);
}else if(is_deconvolutional(s)){
l = parse_deconvolutional(options, params);
}else if(is_rnn(s)){
l = parse_rnn(options, params);
}else if(is_gru(s)){
l = parse_gru(options, params);
}else if(is_crnn(s)){
l = parse_crnn(options, params);
}else if(is_connected(s)){
l = parse_connected(options, params);
}else if(is_crop(s)){
l = parse_crop(options, params);
}else if(is_cost(s)){
l = parse_cost(options, params);
}else if(is_detection(s)){
l = parse_detection(options, params);
}else if(is_softmax(s)){
l = parse_softmax(options, params);
}else if(is_normalization(s)){
l = parse_normalization(options, params);
}else if(is_batchnorm(s)){
l = parse_batchnorm(options, params);
}else if(is_maxpool(s)){
l = parse_maxpool(options, params);
}else if(is_avgpool(s)){
l = parse_avgpool(options, params);
}else if(is_route(s)){
l = parse_route(options, params, net);
}else if(is_shortcut(s)){
l = parse_shortcut(options, params, net);
}else if(is_dropout(s)){
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.dontload = option_find_int_quiet(options, "dontload", 0);
l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 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);
net.outputs = get_network_output_size(net);
net.output = get_network_output(net);
if(workspace_size){
//printf("%ld\n", workspace_size);
#ifdef GPU
net.workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
#else
net.workspace = calloc(1, workspace_size);
#endif
}
return net;
}
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 == LOCAL){
l = parse_local(options, params);
}else if(lt == ACTIVE){
l = parse_activation(options, params);
}else if(lt == RNN){
l = parse_rnn(options, params);
}else if(lt == GRU){
l = parse_gru(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 == 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 == 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.dontload = option_find_int_quiet(options, "dontload", 0);
l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 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);
net.outputs = get_network_output_size(net);
net.output = get_network_output(net);
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;
}
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 == ISEG){
l = parse_iseg(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.numload = option_find_int_quiet(options, "numload", 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;
}
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);
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;
n = n->next;
int count = 0;
while(n){
fprintf(stderr, "%d: ", count);
s = (section *)n->val;
options = s->options;
layer l = {0};
if(is_convolutional(s)){
l = parse_convolutional(options, params);
}else if(is_deconvolutional(s)){
l = parse_deconvolutional(options, params);
}else if(is_connected(s)){
l = parse_connected(options, params);
}else if(is_crop(s)){
l = parse_crop(options, params);
}else if(is_cost(s)){
l = parse_cost(options, params);
}else if(is_detection(s)){
l = parse_detection(options, params);
}else if(is_softmax(s)){
l = parse_softmax(options, params);
}else if(is_normalization(s)){
l = parse_normalization(options, params);
}else if(is_maxpool(s)){
l = parse_maxpool(options, params);
}else if(is_avgpool(s)){
l = parse_avgpool(options, params);
}else if(is_route(s)){
l = parse_route(options, params, net);
}else if(is_dropout(s)){
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.dontload = option_find_int_quiet(options, "dontload", 0);
option_unused(options);
net.layers[count] = l;
free_section(s);
n = n->next;
if(n){
params.h = l.out_h;
params.w = l.out_w;
params.c = l.out_c;
params.inputs = l.outputs;
}
++count;
}
free_list(sections);
net.outputs = get_network_output_size(net);
net.output = get_network_output(net);
return net;
}
void parse_net_options(list *options, network *net)
{
net->batch = option_find_int(options, "batch",1);
net->learning_rate = option_find_float(options, "learning_rate", .001);
net->momentum = option_find_float(options, "momentum", .9);
net->decay = option_find_float(options, "decay", .0001);
int subdivs = option_find_int(options, "subdivisions",1);
net->time_steps = option_find_int_quiet(options, "time_steps",1);
net->notruth = option_find_int_quiet(options, "notruth",0);
net->batch /= subdivs;
net->batch *= net->time_steps;
net->subdivisions = subdivs;
net->random = option_find_int_quiet(options, "random", 0);
net->adam = option_find_int_quiet(options, "adam", 0);
if(net->adam){
net->B1 = option_find_float(options, "B1", .9);
net->B2 = option_find_float(options, "B2", .999);
net->eps = option_find_float(options, "eps", .0000001);
}
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
net->max_crop = option_find_int_quiet(options, "max_crop",net->w*2);
net->min_crop = option_find_int_quiet(options, "min_crop",net->w);
net->max_ratio = option_find_float_quiet(options, "max_ratio", (float) net->max_crop / net->w);
net->min_ratio = option_find_float_quiet(options, "min_ratio", (float) net->min_crop / net->w);
net->center = option_find_int_quiet(options, "center",0);
net->clip = option_find_float_quiet(options, "clip", 0);
net->angle = option_find_float_quiet(options, "angle", 0);
net->aspect = option_find_float_quiet(options, "aspect", 1);
net->saturation = option_find_float_quiet(options, "saturation", 1);
net->exposure = option_find_float_quiet(options, "exposure", 1);
net->hue = option_find_float_quiet(options, "hue", 0);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
net->burn_in = option_find_int_quiet(options, "burn_in", 0);
net->power = option_find_float_quiet(options, "power", 4);
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
} else if (net->policy == STEPS){
char *l = option_find(options, "steps");
char *p = option_find(options, "scales");
if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
int len = strlen(l);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (l[i] == ',') ++n;
}
int *steps = calloc(n, sizeof(int));
float *scales = calloc(n, sizeof(float));
for(i = 0; i < n; ++i){
int step = atoi(l);
float scale = atof(p);
l = strchr(l, ',')+1;
p = strchr(p, ',')+1;
steps[i] = step;
scales[i] = scale;
}
net->scales = scales;
net->steps = steps;
net->num_steps = n;
} else if (net->policy == EXP){
net->gamma = option_find_float(options, "gamma", 1);
} else if (net->policy == SIG){
net->gamma = option_find_float(options, "gamma", 1);
net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY || net->policy == RANDOM){
}
net->max_batches = option_find_int(options, "max_batches", 0);
}