mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

stuff

Browse Source
This commit is contained in:
Joseph Redmon
2016-02-29 13:54:12 -08:00
parent 23955b9fa0
commit 16d06ec0db
30 changed files with 1453 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
src/parser.c
View File

@ -12,6 +12,7 @@
#include "deconvolutional_layer.h"
#include "connected_layer.h"
#include "rnn_layer.h"
#include "crnn_layer.h"
#include "maxpool_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
@ -36,6 +37,7 @@ int is_local(section *s);
int is_deconvolutional(section *s);
int is_connected(section *s);
int is_rnn(section *s);
int is_crnn(section *s);
int is_maxpool(section *s);
int is_avgpool(section *s);
int is_dropout(section *s);
@ -169,6 +171,21 @@ convolutional_layer parse_convolutional(list *options, size_params params)
return layer;
}
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_rnn(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
@ -419,6 +436,7 @@ void parse_net_options(list *options, network *net)
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);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
@ -501,6 +519,8 @@ network parse_network_cfg(char *filename)
l = parse_deconvolutional(options, params);
}else if(is_rnn(s)){
l = parse_rnn(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)){
@ -591,6 +611,10 @@ int is_network(section *s)
return (strcmp(s->type, "[net]")==0
|| strcmp(s->type, "[network]")==0);
}
int is_crnn(section *s)
{
return (strcmp(s->type, "[crnn]")==0);
}
int is_rnn(section *s)
{
return (strcmp(s->type, "[rnn]")==0);
@ -705,6 +729,23 @@ void save_weights_double(network net, char *filename)
fclose(fp);
}
void save_convolutional_weights(layer l, FILE *fp)
{
#ifdef GPU
if(gpu_index >= 0){
pull_convolutional_layer(l);
}
#endif
int num = l.n*l.c*l.size*l.size;
fwrite(l.biases, sizeof(float), l.n, fp);
if (l.batch_normalize){
fwrite(l.scales, sizeof(float), l.n, fp);
fwrite(l.rolling_mean, sizeof(float), l.n, fp);
fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
fwrite(l.filters, sizeof(float), num, fp);
}
void save_connected_weights(layer l, FILE *fp)
{
#ifdef GPU
@ -739,25 +780,17 @@ void save_weights_upto(network net, char *filename, int cutoff)
for(i = 0; i < net.n && i < cutoff; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
#ifdef GPU
if(gpu_index >= 0){
pull_convolutional_layer(l);
}
#endif
int num = l.n*l.c*l.size*l.size;
fwrite(l.biases, sizeof(float), l.n, fp);
if (l.batch_normalize){
fwrite(l.scales, sizeof(float), l.n, fp);
fwrite(l.rolling_mean, sizeof(float), l.n, fp);
fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
fwrite(l.filters, sizeof(float), num, fp);
save_convolutional_weights(l, fp);
} if(l.type == CONNECTED){
save_connected_weights(l, fp);
} if(l.type == RNN){
save_connected_weights(*(l.input_layer), fp);
save_connected_weights(*(l.self_layer), fp);
save_connected_weights(*(l.output_layer), fp);
} if(l.type == CRNN){
save_convolutional_weights(*(l.input_layer), fp);
save_convolutional_weights(*(l.self_layer), fp);
save_convolutional_weights(*(l.output_layer), fp);
} if(l.type == LOCAL){
#ifdef GPU
if(gpu_index >= 0){
@ -809,6 +842,27 @@ void load_connected_weights(layer l, FILE *fp, int transpose)
#endif
}
void load_convolutional_weights(layer l, FILE *fp)
{
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
if (l.batch_normalize && (!l.dontloadscales)){
fread(l.scales, sizeof(float), l.n, fp);
fread(l.rolling_mean, sizeof(float), l.n, fp);
fread(l.rolling_variance, sizeof(float), l.n, fp);
}
fread(l.filters, sizeof(float), num, fp);
if (l.flipped) {
transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
}
#ifdef GPU
if(gpu_index >= 0){
push_convolutional_layer(l);
}
#endif
}
void load_weights_upto(network *net, char *filename, int cutoff)
{
fprintf(stderr, "Loading weights from %s...", filename);
@ -830,22 +884,7 @@ void load_weights_upto(network *net, char *filename, int cutoff)
layer l = net->layers[i];
if (l.dontload) continue;
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
if (l.batch_normalize && (!l.dontloadscales)){
fread(l.scales, sizeof(float), l.n, fp);
fread(l.rolling_mean, sizeof(float), l.n, fp);
fread(l.rolling_variance, sizeof(float), l.n, fp);
}
fread(l.filters, sizeof(float), num, fp);
if (l.flipped) {
transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
}
#ifdef GPU
if(gpu_index >= 0){
push_convolutional_layer(l);
}
#endif
load_convolutional_weights(l, fp);
}
if(l.type == DECONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
@ -860,6 +899,11 @@ void load_weights_upto(network *net, char *filename, int cutoff)
if(l.type == CONNECTED){
load_connected_weights(l, fp, transpose);
}
if(l.type == CRNN){
load_convolutional_weights(*(l.input_layer), fp);
load_convolutional_weights(*(l.self_layer), fp);
load_convolutional_weights(*(l.output_layer), fp);
}
if(l.type == RNN){
load_connected_weights(*(l.input_layer), fp, transpose);
load_connected_weights(*(l.self_layer), fp, transpose);