From f88baf4a3a756140cef3ca07be98cabb803d80ae Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 18 Dec 2014 23:46:45 +0000
Subject: [PATCH] 99 problems
---
src/parser.c | 247 ++++++++++++++++++++++++++++++++++++-------------
1 files changed, 182 insertions(+), 65 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 1656346..d53e87c 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -4,12 +4,15 @@
#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"
@@ -23,7 +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);
@@ -43,9 +49,24 @@
free(s);
}
-convolutional_layer *parse_convolutional(list *options, network *net, int count)
+void parse_data(char *data, float *a, int n)
{
int i;
+ if(!data) return;
+ char *curr = data;
+ char *next = data;
+ int done = 0;
+ for(i = 0; i < n && !done; ++i){
+ while(*++next !='\0' && *next != ',');
+ if(*next == '\0') done = 1;
+ *next = '\0';
+ sscanf(curr, "%g", &a[i]);
+ curr = next+1;
+ }
+}
+
+convolutional_layer *parse_convolutional(list *options, network *net, int count)
+{
int h,w,c;
float learning_rate, momentum, decay;
int n = option_find_int(options, "filters",1);
@@ -76,56 +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);
- if(biases){
- char *curr = biases;
- char *next = biases;
- int done = 0;
- for(i = 0; i < n && !done; ++i){
- while(*++next !='\0' && *next != ',');
- if(*next == '\0') done = 1;
- *next = '\0';
- sscanf(curr, "%g", &layer->biases[i]);
- curr = next+1;
- }
- }
- if(weights){
- char *curr = weights;
- char *next = weights;
- int done = 0;
- for(i = 0; i < c*n*size*size && !done; ++i){
- while(*++next !='\0' && *next != ',');
- if(*next == '\0') done = 1;
- *next = '\0';
- sscanf(curr, "%g", &layer->filters[i]);
- curr = next+1;
- }
- }
+ 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);
@@ -147,23 +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 +156,52 @@
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);
+ }
+ char *type_s = option_find_str(options, "type", "sse");
+ COST_TYPE type = get_cost_type(type_s);
+ cost_layer *layer = make_cost_layer(net->batch, input, type);
+ option_unused(options);
+ return layer;
+}
+
+crop_layer *parse_crop(list *options, network *net, int count)
+{
+ float learning_rate, momentum, decay;
+ int h,w,c;
+ int crop_height = option_find_int(options, "crop_height",1);
+ int crop_width = option_find_int(options, "crop_width",1);
+ int flip = option_find_int(options, "flip",0);
+ if(count == 0){
+ 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);
+ learning_rate = option_find_float(options, "learning_rate", .001);
+ momentum = option_find_float(options, "momentum", .9);
+ decay = option_find_float(options, "decay", .0001);
+ net->learning_rate = learning_rate;
+ net->momentum = momentum;
+ net->decay = decay;
+ }else{
+ image m = get_network_image_layer(*net, count-1);
+ h = m.h;
+ w = m.w;
+ c = m.c;
+ if(h == 0) error("Layer before crop layer must output image.");
+ }
+ crop_layer *layer = make_crop_layer(net->batch,h,w,c,crop_height,crop_width,flip);
+ option_unused(options);
+ return layer;
+}
+
maxpool_layer *parse_maxpool(list *options, network *net, int count)
{
int h,w,c;
@@ -204,6 +224,20 @@
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;
@@ -211,6 +245,12 @@
if(count == 0){
net->batch = option_find_int(options, "batch",1);
input = option_find_int(options, "input",1);
+ float learning_rate = option_find_float(options, "learning_rate", .001);
+ float momentum = option_find_float(options, "momentum", .9);
+ float decay = option_find_float(options, "decay", .0001);
+ net->learning_rate = learning_rate;
+ net->momentum = momentum;
+ net->decay = decay;
}else{
input = get_network_output_size_layer(*net, count-1);
}
@@ -261,6 +301,14 @@
connected_layer *layer = parse_connected(options, &net, count);
net.types[count] = CONNECTED;
net.layers[count] = layer;
+ }else if(is_crop(s)){
+ 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;
@@ -277,6 +325,10 @@
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);
}
@@ -290,6 +342,14 @@
return net;
}
+int is_crop(section *s)
+{
+ 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
@@ -309,6 +369,10 @@
{
return (strcmp(s->type, "[dropout]")==0);
}
+int is_freeweight(section *s)
+{
+ return (strcmp(s->type, "[freeweight]")==0);
+}
int is_softmax(section *s)
{
@@ -389,11 +453,11 @@
l->batch,l->h, l->w, l->c, l->learning_rate, l->momentum, l->decay);
} else {
if(l->learning_rate != net.learning_rate)
- fprintf(fp, "learning_rate=%g\n", l->learning_rate);
+ fprintf(fp, "learning_rate=%g\n", l->learning_rate);
if(l->momentum != net.momentum)
- fprintf(fp, "momentum=%g\n", l->momentum);
+ fprintf(fp, "momentum=%g\n", l->momentum);
if(l->decay != net.decay)
- fprintf(fp, "decay=%g\n", l->decay);
+ fprintf(fp, "decay=%g\n", l->decay);
}
fprintf(fp, "filters=%d\n"
"size=%d\n"
@@ -409,6 +473,25 @@
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;
@@ -432,12 +515,30 @@
"activation=%s\n",
l->outputs,
get_activation_string(l->activation));
- fprintf(fp, "data=");
+ fprintf(fp, "biases=");
for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]);
- for(i = 0; i < l->inputs*l->outputs; ++i) fprintf(fp, "%g,", l->weights[i]);
+ fprintf(fp, "\n");
+ fprintf(fp, "weights=");
+ for(i = 0; i < l->outputs*l->inputs; ++i) fprintf(fp, "%g,", l->weights[i]);
fprintf(fp, "\n\n");
}
+void print_crop_cfg(FILE *fp, crop_layer *l, network net, int count)
+{
+ fprintf(fp, "[crop]\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",
+ l->batch,l->h, l->w, l->c, net.learning_rate, net.momentum, net.decay);
+ }
+ fprintf(fp, "crop_height=%d\ncrop_width=%d\nflip=%d\n\n", l->crop_height, l->crop_width, l->flip);
+}
+
void print_maxpool_cfg(FILE *fp, maxpool_layer *l, network net, int count)
{
fprintf(fp, "[maxpool]\n");
@@ -470,6 +571,14 @@
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));
+ 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");
@@ -481,12 +590,20 @@
print_convolutional_cfg(fp, (convolutional_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)
+ 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