From 2f62fe33c913cd9484fe7f2486889d12292c66e0 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sat, 07 Feb 2015 02:53:53 +0000
Subject: [PATCH] saving weight files as binaries, hell yeah
---
src/parser.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++++++------
1 files changed, 101 insertions(+), 13 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 768f48b..6a107cc 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -16,7 +16,6 @@
#include "list.h"
#include "option_list.h"
#include "utils.h"
-#include "opencl.h"
typedef struct{
char *type;
@@ -87,6 +86,7 @@
net->learning_rate = learning_rate;
net->momentum = momentum;
net->decay = decay;
+ net->seen = option_find_int(options, "seen",0);
}else{
learning_rate = option_find_float_quiet(options, "learning_rate", net->learning_rate);
momentum = option_find_float_quiet(options, "momentum", net->momentum);
@@ -103,7 +103,7 @@
parse_data(weights, layer->filters, c*n*size*size);
parse_data(biases, layer->biases, n);
#ifdef GPU
- push_convolutional_layer(*layer);
+ if(weights || biases) push_convolutional_layer(*layer);
#endif
option_unused(options);
return layer;
@@ -137,7 +137,7 @@
parse_data(biases, layer->biases, output);
parse_data(weights, layer->weights, input*output);
#ifdef GPU
- push_connected_layer(*layer);
+ if(weights || biases) push_connected_layer(*layer);
#endif
option_unused(options);
return layer;
@@ -149,6 +149,7 @@
if(count == 0){
input = option_find_int(options, "input",1);
net->batch = option_find_int(options, "batch",1);
+ net->seen = option_find_int(options, "seen",0);
}else{
input = get_network_output_size_layer(*net, count-1);
}
@@ -163,6 +164,7 @@
if(count == 0){
input = option_find_int(options, "input",1);
net->batch = option_find_int(options, "batch",1);
+ net->seen = option_find_int(options, "seen",0);
}else{
input = get_network_output_size_layer(*net, count-1);
}
@@ -191,6 +193,7 @@
net->learning_rate = learning_rate;
net->momentum = momentum;
net->decay = decay;
+ net->seen = option_find_int(options, "seen",0);
}else{
image m = get_network_image_layer(*net, count-1);
h = m.h;
@@ -213,6 +216,7 @@
w = option_find_int(options, "width",1);
c = option_find_int(options, "channels",1);
net->batch = option_find_int(options, "batch",1);
+ net->seen = option_find_int(options, "seen",0);
}else{
image m = get_network_image_layer(*net, count-1);
h = m.h;
@@ -225,6 +229,7 @@
return layer;
}
+/*
freeweight_layer *parse_freeweight(list *options, network *net, int count)
{
int input;
@@ -238,6 +243,7 @@
option_unused(options);
return layer;
}
+*/
dropout_layer *parse_dropout(list *options, network *net, int count)
{
@@ -252,6 +258,7 @@
net->learning_rate = learning_rate;
net->momentum = momentum;
net->decay = decay;
+ net->seen = option_find_int(options, "seen",0);
}else{
input = get_network_output_size_layer(*net, count-1);
}
@@ -272,6 +279,7 @@
w = option_find_int(options, "width",1);
c = option_find_int(options, "channels",1);
net->batch = option_find_int(options, "batch",1);
+ net->seen = option_find_int(options, "seen",0);
}else{
image m = get_network_image_layer(*net, count-1);
h = m.h;
@@ -327,9 +335,10 @@
net.types[count] = DROPOUT;
net.layers[count] = layer;
}else if(is_freeweight(s)){
- freeweight_layer *layer = parse_freeweight(options, &net, count);
- net.types[count] = FREEWEIGHT;
- net.layers[count] = layer;
+ //freeweight_layer *layer = parse_freeweight(options, &net, count);
+ //net.types[count] = FREEWEIGHT;
+ //net.layers[count] = layer;
+ fprintf(stderr, "Type not recognized: %s\n", s->type);
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
@@ -442,7 +451,7 @@
void print_convolutional_cfg(FILE *fp, convolutional_layer *l, network net, int count)
{
#ifdef GPU
- if(gpu_index >= 0) pull_convolutional_layer(*l);
+ if(gpu_index >= 0) pull_convolutional_layer(*l);
#endif
int i;
fprintf(fp, "[convolutional]\n");
@@ -453,8 +462,9 @@
"channels=%d\n"
"learning_rate=%g\n"
"momentum=%g\n"
- "decay=%g\n",
- l->batch,l->h, l->w, l->c, l->learning_rate, l->momentum, l->decay);
+ "decay=%g\n"
+ "seen=%d\n",
+ l->batch,l->h, l->w, l->c, l->learning_rate, l->momentum, l->decay, net.seen);
} else {
if(l->learning_rate != net.learning_rate)
fprintf(fp, "learning_rate=%g\n", l->learning_rate);
@@ -508,8 +518,9 @@
"input=%d\n"
"learning_rate=%g\n"
"momentum=%g\n"
- "decay=%g\n",
- l->batch, l->inputs, l->learning_rate, l->momentum, l->decay);
+ "decay=%g\n"
+ "seen=%d\n",
+ l->batch, l->inputs, l->learning_rate, l->momentum, l->decay, net.seen);
} else {
if(l->learning_rate != net.learning_rate)
fprintf(fp, "learning_rate=%g\n", l->learning_rate);
@@ -540,8 +551,9 @@
"channels=%d\n"
"learning_rate=%g\n"
"momentum=%g\n"
- "decay=%g\n",
- l->batch,l->h, l->w, l->c, net.learning_rate, net.momentum, net.decay);
+ "decay=%g\n"
+ "seen=%d\n",
+ l->batch,l->h, l->w, l->c, net.learning_rate, net.momentum, net.decay, net.seen);
}
fprintf(fp, "crop_height=%d\ncrop_width=%d\nflip=%d\n\n", l->crop_height, l->crop_width, l->flip);
}
@@ -585,6 +597,82 @@
fprintf(fp, "\n");
}
+void save_weights(network net, char *filename)
+{
+ printf("Saving weights to %s\n", filename);
+ FILE *fp = fopen(filename, "w");
+ if(!fp) file_error(filename);
+
+ fwrite(&net.learning_rate, sizeof(float), 1, fp);
+ fwrite(&net.momentum, sizeof(float), 1, fp);
+ fwrite(&net.decay, sizeof(float), 1, fp);
+ fwrite(&net.seen, sizeof(int), 1, fp);
+
+ int i;
+ for(i = 0; i < net.n; ++i){
+ if(net.types[i] == CONVOLUTIONAL){
+ convolutional_layer layer = *(convolutional_layer *) net.layers[i];
+ #ifdef GPU
+ if(gpu_index >= 0){
+ pull_convolutional_layer(layer);
+ }
+ #endif
+ int num = layer.n*layer.c*layer.size*layer.size;
+ fwrite(layer.biases, sizeof(float), layer.n, fp);
+ fwrite(layer.filters, sizeof(float), num, fp);
+ }
+ if(net.types[i] == CONNECTED){
+ connected_layer layer = *(connected_layer *) net.layers[i];
+ #ifdef GPU
+ if(gpu_index >= 0){
+ pull_connected_layer(layer);
+ }
+ #endif
+ fwrite(layer.biases, sizeof(float), layer.outputs, fp);
+ fwrite(layer.weights, sizeof(float), layer.outputs*layer.inputs, fp);
+ }
+ }
+ fclose(fp);
+}
+
+void load_weights(network *net, char *filename)
+{
+ printf("Loading weights from %s\n", filename);
+ FILE *fp = fopen(filename, "r");
+ if(!fp) file_error(filename);
+
+ fread(&net->learning_rate, sizeof(float), 1, fp);
+ fread(&net->momentum, sizeof(float), 1, fp);
+ fread(&net->decay, sizeof(float), 1, fp);
+ fread(&net->seen, sizeof(int), 1, fp);
+ set_learning_network(net, net->learning_rate, net->momentum, net->decay);
+
+ int i;
+ for(i = 0; i < net->n; ++i){
+ if(net->types[i] == CONVOLUTIONAL){
+ convolutional_layer layer = *(convolutional_layer *) net->layers[i];
+ int num = layer.n*layer.c*layer.size*layer.size;
+ fread(layer.biases, sizeof(float), layer.n, fp);
+ fread(layer.filters, sizeof(float), num, fp);
+ #ifdef GPU
+ if(gpu_index >= 0){
+ push_convolutional_layer(layer);
+ }
+ #endif
+ }
+ if(net->types[i] == CONNECTED){
+ connected_layer layer = *(connected_layer *) net->layers[i];
+ fread(layer.biases, sizeof(float), layer.outputs, fp);
+ fread(layer.weights, sizeof(float), layer.outputs*layer.inputs, fp);
+ #ifdef GPU
+ if(gpu_index >= 0){
+ push_connected_layer(layer);
+ }
+ #endif
+ }
+ }
+ fclose(fp);
+}
void save_network(network net, char *filename)
{
--
Gitblit v1.10.0