From e36182cd8c5dd5c6d0aa1f77cf5cdca87e8bb1f0 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 21 Nov 2014 23:35:19 +0000
Subject: [PATCH] cleaned up data parsing a lot. probably nothing broken?
---
src/parser.c | 125 +++++++++++++++++++++++++++++------------
1 files changed, 88 insertions(+), 37 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 5c991a5..79d4a3a 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -5,12 +5,14 @@
#include "parser.h"
#include "activations.h"
#include "crop_layer.h"
+#include "cost_layer.h"
#include "convolutional_layer.h"
#include "connected_layer.h"
#include "maxpool_layer.h"
#include "normalization_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
+#include "freeweight_layer.h"
#include "list.h"
#include "option_list.h"
#include "utils.h"
@@ -24,8 +26,10 @@
int is_connected(section *s);
int is_maxpool(section *s);
int is_dropout(section *s);
+int is_freeweight(section *s);
int is_softmax(section *s);
int is_crop(section *s);
+int is_cost(section *s);
int is_normalization(section *s);
list *read_cfg(char *filename);
@@ -63,7 +67,6 @@
convolutional_layer *parse_convolutional(list *options, network *net, int count)
{
- int i;
int h,w,c;
float learning_rate, momentum, decay;
int n = option_find_int(options, "filters",1);
@@ -94,34 +97,19 @@
if(h == 0) error("Layer before convolutional layer must output image.");
}
convolutional_layer *layer = make_convolutional_layer(net->batch,h,w,c,n,size,stride,pad,activation,learning_rate,momentum,decay);
- char *data = option_find_str(options, "data", 0);
- if(data){
- char *curr = data;
- char *next = data;
- for(i = 0; i < n; ++i){
- while(*++next !='\0' && *next != ',');
- *next = '\0';
- sscanf(curr, "%g", &layer->biases[i]);
- curr = next+1;
- }
- for(i = 0; i < c*n*size*size; ++i){
- while(*++next !='\0' && *next != ',');
- *next = '\0';
- sscanf(curr, "%g", &layer->filters[i]);
- curr = next+1;
- }
- }
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
- parse_data(biases, layer->biases, n);
parse_data(weights, layer->filters, c*n*size*size);
+ parse_data(biases, layer->biases, n);
+ #ifdef GPU
+ push_convolutional_layer(*layer);
+ #endif
option_unused(options);
return layer;
}
connected_layer *parse_connected(list *options, network *net, int count)
{
- int i;
int input;
float learning_rate, momentum, decay;
int output = option_find_int(options, "output",1);
@@ -143,27 +131,13 @@
input = get_network_output_size_layer(*net, count-1);
}
connected_layer *layer = make_connected_layer(net->batch, input, output, activation,learning_rate,momentum,decay);
- char *data = option_find_str(options, "data", 0);
- if(data){
- char *curr = data;
- char *next = data;
- for(i = 0; i < output; ++i){
- while(*++next !='\0' && *next != ',');
- *next = '\0';
- sscanf(curr, "%g", &layer->biases[i]);
- curr = next+1;
- }
- for(i = 0; i < input*output; ++i){
- while(*++next !='\0' && *next != ',');
- *next = '\0';
- sscanf(curr, "%g", &layer->weights[i]);
- curr = next+1;
- }
- }
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, input*output);
+ #ifdef GPU
+ push_connected_layer(*layer);
+ #endif
option_unused(options);
return layer;
}
@@ -182,6 +156,20 @@
return layer;
}
+cost_layer *parse_cost(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);
+ }else{
+ input = get_network_output_size_layer(*net, count-1);
+ }
+ cost_layer *layer = make_cost_layer(net->batch, input);
+ option_unused(options);
+ return layer;
+}
+
crop_layer *parse_crop(list *options, network *net, int count)
{
float learning_rate, momentum, decay;
@@ -234,6 +222,20 @@
return layer;
}
+freeweight_layer *parse_freeweight(list *options, network *net, int count)
+{
+ int input;
+ if(count == 0){
+ net->batch = option_find_int(options, "batch",1);
+ input = option_find_int(options, "input",1);
+ }else{
+ input = get_network_output_size_layer(*net, count-1);
+ }
+ freeweight_layer *layer = make_freeweight_layer(net->batch,input);
+ option_unused(options);
+ return layer;
+}
+
dropout_layer *parse_dropout(list *options, network *net, int count)
{
int input;
@@ -295,6 +297,10 @@
crop_layer *layer = parse_crop(options, &net, count);
net.types[count] = CROP;
net.layers[count] = layer;
+ }else if(is_cost(s)){
+ cost_layer *layer = parse_cost(options, &net, count);
+ net.types[count] = COST;
+ net.layers[count] = layer;
}else if(is_softmax(s)){
softmax_layer *layer = parse_softmax(options, &net, count);
net.types[count] = SOFTMAX;
@@ -311,6 +317,10 @@
dropout_layer *layer = parse_dropout(options, &net, count);
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;
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
@@ -328,6 +338,10 @@
{
return (strcmp(s->type, "[crop]")==0);
}
+int is_cost(section *s)
+{
+ return (strcmp(s->type, "[cost]")==0);
+}
int is_convolutional(section *s)
{
return (strcmp(s->type, "[conv]")==0
@@ -347,6 +361,10 @@
{
return (strcmp(s->type, "[dropout]")==0);
}
+int is_freeweight(section *s)
+{
+ return (strcmp(s->type, "[freeweight]")==0);
+}
int is_softmax(section *s)
{
@@ -447,6 +465,25 @@
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");
+ if(count == 0){
+ fprintf(fp, "batch=%d\ninput=%d\n",l->batch, l->inputs);
+ }
+ fprintf(fp, "\n");
+}
+
+void print_dropout_cfg(FILE *fp, dropout_layer *l, network net, int count)
+{
+ fprintf(fp, "[dropout]\n");
+ if(count == 0){
+ fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs);
+ }
+ fprintf(fp, "probability=%g\n\n", l->probability);
+}
+
void print_connected_cfg(FILE *fp, connected_layer *l, network net, int count)
{
int i;
@@ -526,6 +563,14 @@
fprintf(fp, "\n");
}
+void print_cost_cfg(FILE *fp, cost_layer *l, network net, int count)
+{
+ fprintf(fp, "[cost]\n");
+ if(count == 0) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs);
+ fprintf(fp, "\n");
+}
+
+
void save_network(network net, char *filename)
{
FILE *fp = fopen(filename, "w");
@@ -541,10 +586,16 @@
print_crop_cfg(fp, (crop_layer *)net.layers[i], net, i);
else if(net.types[i] == MAXPOOL)
print_maxpool_cfg(fp, (maxpool_layer *)net.layers[i], net, i);
+ else if(net.types[i] == FREEWEIGHT)
+ print_freeweight_cfg(fp, (freeweight_layer *)net.layers[i], net, i);
+ else if(net.types[i] == DROPOUT)
+ print_dropout_cfg(fp, (dropout_layer *)net.layers[i], net, i);
else if(net.types[i] == NORMALIZATION)
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] == COST)
+ print_cost_cfg(fp, (cost_layer *)net.layers[i], net, i);
}
fclose(fp);
}
--
Gitblit v1.10.0