From f047cfff99e00e28c02eb59b6d32386c122f9af6 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 08 Mar 2015 18:31:12 +0000
Subject: [PATCH] renamed sigmoid to logistic
---
src/parser.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 files changed, 168 insertions(+), 8 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 6a107cc..7b1057e 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -7,11 +7,13 @@
#include "crop_layer.h"
#include "cost_layer.h"
#include "convolutional_layer.h"
+#include "deconvolutional_layer.h"
#include "connected_layer.h"
#include "maxpool_layer.h"
#include "normalization_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
+#include "detection_layer.h"
#include "freeweight_layer.h"
#include "list.h"
#include "option_list.h"
@@ -23,6 +25,7 @@
}section;
int is_convolutional(section *s);
+int is_deconvolutional(section *s);
int is_connected(section *s);
int is_maxpool(section *s);
int is_dropout(section *s);
@@ -30,6 +33,7 @@
int is_softmax(section *s);
int is_crop(section *s);
int is_cost(section *s);
+int is_detection(section *s);
int is_normalization(section *s);
list *read_cfg(char *filename);
@@ -65,6 +69,49 @@
}
}
+deconvolutional_layer *parse_deconvolutional(list *options, network *net, int count)
+{
+ int h,w,c;
+ float learning_rate, momentum, decay;
+ 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);
+ if(count == 0){
+ learning_rate = option_find_float(options, "learning_rate", .001);
+ momentum = option_find_float(options, "momentum", .9);
+ decay = option_find_float(options, "decay", .0001);
+ h = option_find_int(options, "height",1);
+ w = option_find_int(options, "width",1);
+ c = option_find_int(options, "channels",1);
+ net->batch = option_find_int(options, "batch",1);
+ 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);
+ decay = option_find_float_quiet(options, "decay", net->decay);
+ image m = get_network_image_layer(*net, count-1);
+ h = m.h;
+ w = m.w;
+ c = m.c;
+ if(h == 0) error("Layer before deconvolutional layer must output image.");
+ }
+ deconvolutional_layer *layer = make_deconvolutional_layer(net->batch,h,w,c,n,size,stride,activation,learning_rate,momentum,decay);
+ 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_deconvolutional_layer(*layer);
+ #endif
+ option_unused(options);
+ return layer;
+}
+
convolutional_layer *parse_convolutional(list *options, network *net, int count)
{
int h,w,c;
@@ -73,7 +120,7 @@
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", "sigmoid");
+ char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
if(count == 0){
learning_rate = option_find_float(options, "learning_rate", .001);
@@ -114,7 +161,7 @@
int input;
float learning_rate, momentum, decay;
int output = option_find_int(options, "output",1);
- char *activation_s = option_find_str(options, "activation", "sigmoid");
+ char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
if(count == 0){
input = option_find_int(options, "input",1);
@@ -146,6 +193,7 @@
softmax_layer *parse_softmax(list *options, network *net, int count)
{
int input;
+ int groups = option_find_int(options, "groups",1);
if(count == 0){
input = option_find_int(options, "input",1);
net->batch = option_find_int(options, "batch",1);
@@ -153,7 +201,25 @@
}else{
input = get_network_output_size_layer(*net, count-1);
}
- softmax_layer *layer = make_softmax_layer(net->batch, input);
+ softmax_layer *layer = make_softmax_layer(net->batch, groups, input);
+ option_unused(options);
+ return layer;
+}
+
+detection_layer *parse_detection(list *options, network *net, int count)
+{
+ int input;
+ 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);
+ }
+ int coords = option_find_int(options, "coords", 1);
+ int classes = option_find_int(options, "classes", 1);
+ int rescore = option_find_int(options, "rescore", 1);
+ detection_layer *layer = make_detection_layer(net->batch, input, classes, coords, rescore);
option_unused(options);
return layer;
}
@@ -306,6 +372,10 @@
convolutional_layer *layer = parse_convolutional(options, &net, count);
net.types[count] = CONVOLUTIONAL;
net.layers[count] = layer;
+ }else if(is_deconvolutional(s)){
+ deconvolutional_layer *layer = parse_deconvolutional(options, &net, count);
+ net.types[count] = DECONVOLUTIONAL;
+ net.layers[count] = layer;
}else if(is_connected(s)){
connected_layer *layer = parse_connected(options, &net, count);
net.types[count] = CONNECTED;
@@ -318,6 +388,10 @@
cost_layer *layer = parse_cost(options, &net, count);
net.types[count] = COST;
net.layers[count] = layer;
+ }else if(is_detection(s)){
+ detection_layer *layer = parse_detection(options, &net, count);
+ net.types[count] = DETECTION;
+ net.layers[count] = layer;
}else if(is_softmax(s)){
softmax_layer *layer = parse_softmax(options, &net, count);
net.types[count] = SOFTMAX;
@@ -360,6 +434,15 @@
{
return (strcmp(s->type, "[cost]")==0);
}
+int is_detection(section *s)
+{
+ return (strcmp(s->type, "[detection]")==0);
+}
+int is_deconvolutional(section *s)
+{
+ return (strcmp(s->type, "[deconv]")==0
+ || strcmp(s->type, "[deconvolutional]")==0);
+}
int is_convolutional(section *s)
{
return (strcmp(s->type, "[conv]")==0
@@ -438,7 +521,7 @@
break;
default:
if(!read_option(line, current->options)){
- printf("Config file error line %d, could parse: %s\n", nu, line);
+ fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
free(line);
}
break;
@@ -488,6 +571,45 @@
fprintf(fp, "\n\n");
}
+void print_deconvolutional_cfg(FILE *fp, deconvolutional_layer *l, network net, int count)
+{
+ #ifdef GPU
+ if(gpu_index >= 0) pull_deconvolutional_layer(*l);
+ #endif
+ int i;
+ fprintf(fp, "[deconvolutional]\n");
+ if(count == 0) {
+ fprintf(fp, "batch=%d\n"
+ "height=%d\n"
+ "width=%d\n"
+ "channels=%d\n"
+ "learning_rate=%g\n"
+ "momentum=%g\n"
+ "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);
+ if(l->momentum != net.momentum)
+ fprintf(fp, "momentum=%g\n", l->momentum);
+ if(l->decay != net.decay)
+ fprintf(fp, "decay=%g\n", l->decay);
+ }
+ fprintf(fp, "filters=%d\n"
+ "size=%d\n"
+ "stride=%d\n"
+ "activation=%s\n",
+ l->n, l->size, l->stride,
+ get_activation_string(l->activation));
+ fprintf(fp, "biases=");
+ for(i = 0; i < l->n; ++i) fprintf(fp, "%g,", l->biases[i]);
+ fprintf(fp, "\n");
+ fprintf(fp, "weights=");
+ for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]);
+ fprintf(fp, "\n\n");
+}
+
void print_freeweight_cfg(FILE *fp, freeweight_layer *l, network net, int count)
{
fprintf(fp, "[freeweight]\n");
@@ -590,6 +712,13 @@
fprintf(fp, "\n");
}
+void print_detection_cfg(FILE *fp, detection_layer *l, network net, int count)
+{
+ fprintf(fp, "[detection]\n");
+ fprintf(fp, "classes=%d\ncoords=%d\nrescore=%d\n", l->classes, l->coords, l->rescore);
+ fprintf(fp, "\n");
+}
+
void print_cost_cfg(FILE *fp, cost_layer *l, network net, int count)
{
fprintf(fp, "[cost]\ntype=%s\n", get_cost_string(l->type));
@@ -599,7 +728,7 @@
void save_weights(network net, char *filename)
{
- printf("Saving weights to %s\n", filename);
+ fprintf(stderr, "Saving weights to %s\n", filename);
FILE *fp = fopen(filename, "w");
if(!fp) file_error(filename);
@@ -621,6 +750,17 @@
fwrite(layer.biases, sizeof(float), layer.n, fp);
fwrite(layer.filters, sizeof(float), num, fp);
}
+ if(net.types[i] == DECONVOLUTIONAL){
+ deconvolutional_layer layer = *(deconvolutional_layer *) net.layers[i];
+ #ifdef GPU
+ if(gpu_index >= 0){
+ pull_deconvolutional_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
@@ -635,9 +775,9 @@
fclose(fp);
}
-void load_weights(network *net, char *filename)
+void load_weights_upto(network *net, char *filename, int cutoff)
{
- printf("Loading weights from %s\n", filename);
+ fprintf(stderr, "Loading weights from %s\n", filename);
FILE *fp = fopen(filename, "r");
if(!fp) file_error(filename);
@@ -648,7 +788,7 @@
set_learning_network(net, net->learning_rate, net->momentum, net->decay);
int i;
- for(i = 0; i < net->n; ++i){
+ for(i = 0; i < net->n && i < cutoff; ++i){
if(net->types[i] == CONVOLUTIONAL){
convolutional_layer layer = *(convolutional_layer *) net->layers[i];
int num = layer.n*layer.c*layer.size*layer.size;
@@ -660,6 +800,17 @@
}
#endif
}
+ if(net->types[i] == DECONVOLUTIONAL){
+ deconvolutional_layer layer = *(deconvolutional_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_deconvolutional_layer(layer);
+ }
+ #endif
+ }
if(net->types[i] == CONNECTED){
connected_layer layer = *(connected_layer *) net->layers[i];
fread(layer.biases, sizeof(float), layer.outputs, fp);
@@ -674,6 +825,11 @@
fclose(fp);
}
+void load_weights(network *net, char *filename)
+{
+ load_weights_upto(net, filename, net->n);
+}
+
void save_network(network net, char *filename)
{
FILE *fp = fopen(filename, "w");
@@ -683,6 +839,8 @@
{
if(net.types[i] == CONVOLUTIONAL)
print_convolutional_cfg(fp, (convolutional_layer *)net.layers[i], net, i);
+ else if(net.types[i] == DECONVOLUTIONAL)
+ print_deconvolutional_cfg(fp, (deconvolutional_layer *)net.layers[i], net, i);
else if(net.types[i] == CONNECTED)
print_connected_cfg(fp, (connected_layer *)net.layers[i], net, i);
else if(net.types[i] == CROP)
@@ -697,6 +855,8 @@
print_normalization_cfg(fp, (normalization_layer *)net.layers[i], net, i);
else if(net.types[i] == SOFTMAX)
print_softmax_cfg(fp, (softmax_layer *)net.layers[i], net, i);
+ else if(net.types[i] == DETECTION)
+ print_detection_cfg(fp, (detection_layer *)net.layers[i], net, i);
else if(net.types[i] == COST)
print_cost_cfg(fp, (cost_layer *)net.layers[i], net, i);
}
--
Gitblit v1.10.0