From b5936b499abc94c0efffbcc99b5698574b59d860 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sat, 05 Sep 2015 00:52:44 +0000
Subject: [PATCH] lots of stuff
---
src/parser.c | 181 ++++++++++++++++++++++++++++++++++++++------
1 files changed, 155 insertions(+), 26 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 48567a1..b9f6cb6 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -7,12 +7,15 @@
#include "crop_layer.h"
#include "cost_layer.h"
#include "convolutional_layer.h"
+#include "normalization_layer.h"
#include "deconvolutional_layer.h"
#include "connected_layer.h"
#include "maxpool_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
#include "detection_layer.h"
+#include "region_layer.h"
+#include "avgpool_layer.h"
#include "route_layer.h"
#include "list.h"
#include "option_list.h"
@@ -28,11 +31,14 @@
int is_deconvolutional(section *s);
int is_connected(section *s);
int is_maxpool(section *s);
+int is_avgpool(section *s);
int is_dropout(section *s);
int is_softmax(section *s);
+int is_normalization(section *s);
int is_crop(section *s);
int is_cost(section *s);
int is_detection(section *s);
+int is_region(section *s);
int is_route(section *s);
list *read_cfg(char *filename);
@@ -100,7 +106,6 @@
#ifdef GPU
if(weights || biases) push_deconvolutional_layer(layer);
#endif
- option_unused(options);
return layer;
}
@@ -129,7 +134,6 @@
#ifdef GPU
if(weights || biases) push_convolutional_layer(layer);
#endif
- option_unused(options);
return layer;
}
@@ -148,7 +152,6 @@
#ifdef GPU
if(weights || biases) push_connected_layer(layer);
#endif
- option_unused(options);
return layer;
}
@@ -156,7 +159,6 @@
{
int groups = option_find_int(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
- option_unused(options);
return layer;
}
@@ -164,11 +166,22 @@
{
int coords = option_find_int(options, "coords", 1);
int classes = option_find_int(options, "classes", 1);
- int rescore = option_find_int(options, "rescore", 1);
- int nuisance = option_find_int(options, "nuisance", 0);
- int background = option_find_int(options, "background", 1);
- detection_layer layer = make_detection_layer(params.batch, params.inputs, classes, coords, rescore, background, nuisance);
- option_unused(options);
+ int rescore = option_find_int(options, "rescore", 0);
+ int joint = option_find_int(options, "joint", 0);
+ int objectness = option_find_int(options, "objectness", 0);
+ int background = 0;
+ detection_layer layer = make_detection_layer(params.batch, params.inputs, classes, coords, joint, rescore, background, objectness);
+ return layer;
+}
+
+region_layer parse_region(list *options, size_params params)
+{
+ int coords = option_find_int(options, "coords", 1);
+ int classes = option_find_int(options, "classes", 1);
+ int rescore = option_find_int(options, "rescore", 0);
+ int num = option_find_int(options, "num", 1);
+ int side = option_find_int(options, "side", 7);
+ region_layer layer = make_region_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
return layer;
}
@@ -176,8 +189,8 @@
{
char *type_s = option_find_str(options, "type", "sse");
COST_TYPE type = get_cost_type(type_s);
- cost_layer layer = make_cost_layer(params.batch, params.inputs, type);
- option_unused(options);
+ float scale = option_find_float_quiet(options, "scale",1);
+ cost_layer layer = make_cost_layer(params.batch, params.inputs, type, scale);
return layer;
}
@@ -197,8 +210,10 @@
batch=params.batch;
if(!(h && w && c)) error("Layer before crop layer must output image.");
+ int noadjust = option_find_int_quiet(options, "noadjust",0);
+
crop_layer l = make_crop_layer(batch,h,w,c,crop_height,crop_width,flip, angle, saturation, exposure);
- option_unused(options);
+ l.noadjust = noadjust;
return l;
}
@@ -215,7 +230,19 @@
if(!(h && w && c)) error("Layer before maxpool layer must output image.");
maxpool_layer layer = make_maxpool_layer(batch,h,w,c,size,stride);
- option_unused(options);
+ return layer;
+}
+
+avgpool_layer parse_avgpool(list *options, size_params params)
+{
+ int batch,w,h,c;
+ w = params.w;
+ h = params.h;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before avgpool layer must output image.");
+
+ avgpool_layer layer = make_avgpool_layer(batch,w,h,c);
return layer;
}
@@ -223,10 +250,22 @@
{
float probability = option_find_float(options, "probability", .5);
dropout_layer layer = make_dropout_layer(params.batch, params.inputs, probability);
- option_unused(options);
+ layer.out_w = params.w;
+ layer.out_h = params.h;
+ layer.out_c = params.c;
return layer;
}
+layer parse_normalization(list *options, size_params params)
+{
+ float alpha = option_find_float(options, "alpha", .0001);
+ float beta = option_find_float(options, "beta" , .75);
+ float kappa = option_find_float(options, "kappa", 1);
+ int size = option_find_int(options, "size", 5);
+ layer l = make_normalization_layer(params.batch, params.w, params.h, params.c, size, alpha, beta, kappa);
+ return l;
+}
+
route_layer parse_route(list *options, size_params params, network net)
{
char *l = option_find(options, "layers");
@@ -264,17 +303,25 @@
}
}
- option_unused(options);
return layer;
}
+learning_rate_policy get_policy(char *s)
+{
+ if (strcmp(s, "poly")==0) return POLY;
+ if (strcmp(s, "constant")==0) return CONSTANT;
+ if (strcmp(s, "step")==0) return STEP;
+ if (strcmp(s, "exp")==0) return EXP;
+ fprintf(stderr, "Couldn't find policy %s, going with constant\n", s);
+ return CONSTANT;
+}
+
void parse_net_options(list *options, network *net)
{
net->batch = option_find_int(options, "batch",1);
net->learning_rate = option_find_float(options, "learning_rate", .001);
net->momentum = option_find_float(options, "momentum", .9);
net->decay = option_find_float(options, "decay", .0001);
- net->seen = option_find_int(options, "seen",0);
int subdivs = option_find_int(options, "subdivisions",1);
net->batch /= subdivs;
net->subdivisions = subdivs;
@@ -283,8 +330,20 @@
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);
+
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
- option_unused(options);
+
+ char *policy_s = option_find_str(options, "policy", "constant");
+ net->policy = get_policy(policy_s);
+ if(net->policy == STEP){
+ net->step = option_find_int(options, "step", 1);
+ net->gamma = option_find_float(options, "gamma", 1);
+ } else if (net->policy == EXP){
+ net->gamma = option_find_float(options, "gamma", 1);
+ } else if (net->policy == POLY){
+ net->power = option_find_float(options, "power", 1);
+ }
+ net->max_batches = option_find_int(options, "max_batches", 0);
}
network parse_network_cfg(char *filename)
@@ -308,6 +367,7 @@
n = n->next;
int count = 0;
+ free_section(s);
while(n){
fprintf(stderr, "%d: ", count);
s = (section *)n->val;
@@ -325,10 +385,16 @@
l = parse_cost(options, params);
}else if(is_detection(s)){
l = parse_detection(options, params);
+ }else if(is_region(s)){
+ l = parse_region(options, params);
}else if(is_softmax(s)){
l = parse_softmax(options, params);
+ }else if(is_normalization(s)){
+ l = parse_normalization(options, params);
}else if(is_maxpool(s)){
l = parse_maxpool(options, params);
+ }else if(is_avgpool(s)){
+ l = parse_avgpool(options, params);
}else if(is_route(s)){
l = parse_route(options, params, net);
}else if(is_dropout(s)){
@@ -342,6 +408,8 @@
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
+ l.dontload = option_find_int_quiet(options, "dontload", 0);
+ option_unused(options);
net.layers[count] = l;
free_section(s);
n = n->next;
@@ -371,6 +439,10 @@
{
return (strcmp(s->type, "[detection]")==0);
}
+int is_region(section *s)
+{
+ return (strcmp(s->type, "[region]")==0);
+}
int is_deconvolutional(section *s)
{
return (strcmp(s->type, "[deconv]")==0
@@ -396,11 +468,22 @@
return (strcmp(s->type, "[max]")==0
|| strcmp(s->type, "[maxpool]")==0);
}
+int is_avgpool(section *s)
+{
+ return (strcmp(s->type, "[avg]")==0
+ || strcmp(s->type, "[avgpool]")==0);
+}
int is_dropout(section *s)
{
return (strcmp(s->type, "[dropout]")==0);
}
+int is_normalization(section *s)
+{
+ return (strcmp(s->type, "[lrn]")==0
+ || strcmp(s->type, "[normalization]")==0);
+}
+
int is_softmax(section *s)
{
return (strcmp(s->type, "[soft]")==0
@@ -464,7 +547,46 @@
return sections;
}
-void save_weights(network net, char *filename)
+void save_weights_double(network net, char *filename)
+{
+ fprintf(stderr, "Saving doubled 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,j,k;
+ for(i = 0; i < net.n; ++i){
+ layer l = net.layers[i];
+ if(l.type == CONVOLUTIONAL){
+#ifdef GPU
+ if(gpu_index >= 0){
+ pull_convolutional_layer(l);
+ }
+#endif
+ float zero = 0;
+ fwrite(l.biases, sizeof(float), l.n, fp);
+ fwrite(l.biases, sizeof(float), l.n, fp);
+
+ for (j = 0; j < l.n; ++j){
+ int index = j*l.c*l.size*l.size;
+ fwrite(l.filters+index, sizeof(float), l.c*l.size*l.size, fp);
+ for (k = 0; k < l.c*l.size*l.size; ++k) fwrite(&zero, sizeof(float), 1, fp);
+ }
+ for (j = 0; j < l.n; ++j){
+ int index = j*l.c*l.size*l.size;
+ for (k = 0; k < l.c*l.size*l.size; ++k) fwrite(&zero, sizeof(float), 1, fp);
+ fwrite(l.filters+index, sizeof(float), l.c*l.size*l.size, fp);
+ }
+ }
+ }
+ fclose(fp);
+}
+
+void save_weights_upto(network net, char *filename, int cutoff)
{
fprintf(stderr, "Saving weights to %s\n", filename);
FILE *fp = fopen(filename, "w");
@@ -473,10 +595,10 @@
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);
+ fwrite(net.seen, sizeof(int), 1, fp);
int i;
- for(i = 0; i < net.n; ++i){
+ for(i = 0; i < net.n && i < cutoff; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
#ifdef GPU
@@ -510,22 +632,28 @@
}
fclose(fp);
}
+void save_weights(network net, char *filename)
+{
+ save_weights_upto(net, filename, net.n);
+}
void load_weights_upto(network *net, char *filename, int cutoff)
{
- fprintf(stderr, "Loading weights from %s\n", filename);
+ fprintf(stderr, "Loading weights from %s...", filename);
+ fflush(stdout);
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);
- fprintf(stderr, "%f %f %f %d\n", net->learning_rate, net->momentum, net->decay, net->seen);
+ float garbage;
+ fread(&garbage, sizeof(float), 1, fp);
+ fread(&garbage, sizeof(float), 1, fp);
+ fread(&garbage, sizeof(float), 1, fp);
+ fread(net->seen, sizeof(int), 1, fp);
int i;
for(i = 0; i < net->n && i < cutoff; ++i){
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);
@@ -556,6 +684,7 @@
#endif
}
}
+ fprintf(stderr, "Done!\n");
fclose(fp);
}
--
Gitblit v1.10.0