From 0305fb4d99cf1efc7d4aa4d2ee2d65d54500d437 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 26 Nov 2015 19:48:01 +0000
Subject: [PATCH] Some changes
---
src/parser.c | 233 ++++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 176 insertions(+), 57 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 242a83c..277c6e2 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -14,8 +14,8 @@
#include "softmax_layer.h"
#include "dropout_layer.h"
#include "detection_layer.h"
-#include "region_layer.h"
#include "avgpool_layer.h"
+#include "local_layer.h"
#include "route_layer.h"
#include "list.h"
#include "option_list.h"
@@ -28,6 +28,7 @@
int is_network(section *s);
int is_convolutional(section *s);
+int is_local(section *s);
int is_deconvolutional(section *s);
int is_connected(section *s);
int is_maxpool(section *s);
@@ -38,7 +39,6 @@
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);
@@ -109,6 +109,27 @@
return layer;
}
+local_layer parse_local(list *options, size_params params)
+{
+ int n = option_find_int(options, "filters",1);
+ 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", "logistic");
+ ACTIVATION activation = get_activation(activation_s);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before local layer must output image.");
+
+ local_layer layer = make_local_layer(batch,h,w,c,n,size,stride,pad,activation);
+
+ return layer;
+}
+
convolutional_layer parse_convolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
@@ -124,8 +145,9 @@
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before convolutional layer must output image.");
+ int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
- convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation);
+ convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation, batch_normalize);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
@@ -167,20 +189,19 @@
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 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);
- region_layer layer = make_region_layer(params.batch, params.inputs, num, classes, coords, rescore);
+ int side = option_find_int(options, "side", 7);
+ detection_layer layer = make_detection_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
+
+ layer.softmax = option_find_int(options, "softmax", 0);
+ layer.sqrt = option_find_int(options, "sqrt", 0);
+
+ layer.coord_scale = option_find_float(options, "coord_scale", 1);
+ layer.forced = option_find_int(options, "forced", 0);
+ layer.object_scale = option_find_float(options, "object_scale", 1);
+ layer.noobject_scale = option_find_float(options, "noobject_scale", 1);
+ layer.class_scale = option_find_float(options, "class_scale", 1);
+ layer.jitter = option_find_float(options, "jitter", .2);
return layer;
}
@@ -188,7 +209,8 @@
{
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);
+ float scale = option_find_float_quiet(options, "scale",1);
+ cost_layer layer = make_cost_layer(params.batch, params.inputs, type, scale);
return layer;
}
@@ -211,6 +233,7 @@
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);
+ l.shift = option_find_float(options, "shift", 0);
l.noadjust = noadjust;
return l;
}
@@ -304,6 +327,18 @@
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;
+ if (strcmp(s, "sigmoid")==0) return SIG;
+ if (strcmp(s, "steps")==0) return STEPS;
+ 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);
@@ -318,7 +353,47 @@
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");
+
+ 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->scale = option_find_float(options, "scale", 1);
+ } else if (net->policy == STEPS){
+ char *l = option_find(options, "steps");
+ char *p = option_find(options, "scales");
+ if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
+
+ int len = strlen(l);
+ int n = 1;
+ int i;
+ for(i = 0; i < len; ++i){
+ if (l[i] == ',') ++n;
+ }
+ int *steps = calloc(n, sizeof(int));
+ float *scales = calloc(n, sizeof(float));
+ for(i = 0; i < n; ++i){
+ int step = atoi(l);
+ float scale = atof(p);
+ l = strchr(l, ',')+1;
+ p = strchr(p, ',')+1;
+ steps[i] = step;
+ scales[i] = scale;
+ }
+ net->scales = scales;
+ net->steps = steps;
+ net->num_steps = n;
+ } else if (net->policy == EXP){
+ net->gamma = option_find_float(options, "gamma", 1);
+ } else if (net->policy == SIG){
+ net->gamma = option_find_float(options, "gamma", 1);
+ net->step = option_find_int(options, "step", 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)
@@ -342,6 +417,7 @@
n = n->next;
int count = 0;
+ free_section(s);
while(n){
fprintf(stderr, "%d: ", count);
s = (section *)n->val;
@@ -349,6 +425,8 @@
layer l = {0};
if(is_convolutional(s)){
l = parse_convolutional(options, params);
+ }else if(is_local(s)){
+ l = parse_local(options, params);
}else if(is_deconvolutional(s)){
l = parse_deconvolutional(options, params);
}else if(is_connected(s)){
@@ -359,8 +437,6 @@
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)){
@@ -375,14 +451,15 @@
l = parse_dropout(options, params);
l.output = net.layers[count-1].output;
l.delta = net.layers[count-1].delta;
- #ifdef GPU
+#ifdef GPU
l.output_gpu = net.layers[count-1].output_gpu;
l.delta_gpu = net.layers[count-1].delta_gpu;
- #endif
+#endif
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
l.dontload = option_find_int_quiet(options, "dontload", 0);
+ l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
option_unused(options);
net.layers[count] = l;
free_section(s);
@@ -413,9 +490,9 @@
{
return (strcmp(s->type, "[detection]")==0);
}
-int is_region(section *s)
+int is_local(section *s)
{
- return (strcmp(s->type, "[region]")==0);
+ return (strcmp(s->type, "[local]")==0);
}
int is_deconvolutional(section *s)
{
@@ -468,24 +545,6 @@
return (strcmp(s->type, "[route]")==0);
}
-int read_option(char *s, list *options)
-{
- size_t i;
- size_t len = strlen(s);
- char *val = 0;
- for(i = 0; i < len; ++i){
- if(s[i] == '='){
- s[i] = '\0';
- val = s+i+1;
- break;
- }
- }
- if(i == len-1) return 0;
- char *key = s;
- option_insert(options, key, val);
- return 1;
-}
-
list *read_cfg(char *filename)
{
FILE *file = fopen(filename, "r");
@@ -521,6 +580,45 @@
return sections;
}
+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);
@@ -530,7 +628,7 @@
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 < cutoff; ++i){
@@ -543,19 +641,13 @@
#endif
int num = l.n*l.c*l.size*l.size;
fwrite(l.biases, sizeof(float), l.n, fp);
- fwrite(l.filters, sizeof(float), num, fp);
- }
- if(l.type == DECONVOLUTIONAL){
-#ifdef GPU
- if(gpu_index >= 0){
- pull_deconvolutional_layer(l);
+ if (l.batch_normalize){
+ fwrite(l.scales, sizeof(float), l.n, fp);
+ fwrite(l.rolling_mean, sizeof(float), l.n, fp);
+ fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
-#endif
- int num = l.n*l.c*l.size*l.size;
- fwrite(l.biases, sizeof(float), l.n, fp);
fwrite(l.filters, sizeof(float), num, fp);
- }
- if(l.type == CONNECTED){
+ } if(l.type == CONNECTED){
#ifdef GPU
if(gpu_index >= 0){
pull_connected_layer(l);
@@ -563,6 +655,16 @@
#endif
fwrite(l.biases, sizeof(float), l.outputs, fp);
fwrite(l.weights, sizeof(float), l.outputs*l.inputs, fp);
+ } if(l.type == LOCAL){
+#ifdef GPU
+ if(gpu_index >= 0){
+ pull_local_layer(l);
+ }
+#endif
+ int locations = l.out_w*l.out_h;
+ int size = l.size*l.size*l.c*l.n*locations;
+ fwrite(l.biases, sizeof(float), l.outputs, fp);
+ fwrite(l.filters, sizeof(float), size, fp);
}
}
fclose(fp);
@@ -579,10 +681,11 @@
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);
+ 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){
@@ -591,6 +694,11 @@
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
+ if (l.batch_normalize && (!l.dontloadscales)){
+ fread(l.scales, sizeof(float), l.n, fp);
+ fread(l.rolling_mean, sizeof(float), l.n, fp);
+ fread(l.rolling_variance, sizeof(float), l.n, fp);
+ }
fread(l.filters, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
@@ -617,6 +725,17 @@
}
#endif
}
+ if(l.type == LOCAL){
+ int locations = l.out_w*l.out_h;
+ int size = l.size*l.size*l.c*l.n*locations;
+ fread(l.biases, sizeof(float), l.outputs, fp);
+ fread(l.filters, sizeof(float), size, fp);
+#ifdef GPU
+ if(gpu_index >= 0){
+ push_local_layer(l);
+ }
+#endif
+ }
}
fprintf(stderr, "Done!\n");
fclose(fp);
--
Gitblit v1.10.0