float *network_predict(network net, float *input)
{
#ifdef GPU
if(gpu_index >= 0) return network_predict_gpu(net, input);
#endif
network_state state;
state.input = input;
state.truth = 0;
state.train = 0;
state.delta = 0;
forward_network(net, state);
float *out = get_network_output(net);
return out;
}
void train_writing(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 256;
int i = net.seen/imgs;
list *plist = get_paths("data/train.list");
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
clock_t time;
while(1){
++i;
time=clock();
data train = load_data_writing(paths, imgs, plist->size, 256, 256, 4);
float loss = train_network(net, train);
#ifdef GPU
float *out = get_network_output_gpu(net);
#else
float *out = get_network_output(net);
#endif
// image pred = float_to_image(32, 32, 1, out);
// print_image(pred);
net.seen += imgs;
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
free_data(train);
if((i % 20000) == 0) net.learning_rate *= .1;
//if(i%100 == 0 && net.learning_rate > .00001) net.learning_rate *= .97;
if(i%250==0){
char buff[256];
sprintf(buff, "/home/pjreddie/writing_backup/%s_%d.weights", base, i);
save_weights(net, buff);
}
}
}
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;
}
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);
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;
}
void top_predictions(network net, int k, int *index)
{
int size = get_network_output_size(net);
float *out = get_network_output(net);
top_k(out, size, k, index);
}
int get_predicted_class_network(network net)
{
float *out = get_network_output(net);
int k = get_network_output_size(net);
return max_index(out, k);
}
