From 38bd6ae6ba24fc8c14fd61d1238ae94a983434b3 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 20 Jul 2015 23:16:26 +0000
Subject: [PATCH] Better partial function
---
src/parser.c | 818 +++++++++++++++++++++------------------------------------
1 files changed, 302 insertions(+), 516 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 3f94c80..5591dc3 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -7,13 +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 "normalization_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
-#include "freeweight_layer.h"
+#include "detection_layer.h"
+#include "avgpool_layer.h"
+#include "route_layer.h"
#include "list.h"
#include "option_list.h"
#include "utils.h"
@@ -23,16 +25,19 @@
list *options;
}section;
+int is_network(section *s);
int is_convolutional(section *s);
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_freeweight(section *s);
int is_softmax(section *s);
+int is_normalization(section *s);
int is_crop(section *s);
int is_cost(section *s);
-int is_normalization(section *s);
+int is_detection(section *s);
+int is_route(section *s);
list *read_cfg(char *filename);
void free_section(section *s)
@@ -67,333 +72,311 @@
}
}
-deconvolutional_layer *parse_deconvolutional(list *options, network *net, int count)
+typedef struct size_params{
+ int batch;
+ int inputs;
+ int h;
+ int w;
+ int c;
+} size_params;
+
+deconvolutional_layer parse_deconvolutional(list *options, size_params params)
{
- 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", "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);
- 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);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before deconvolutional layer must output image.");
+
+ deconvolutional_layer layer = make_deconvolutional_layer(batch,h,w,c,n,size,stride,activation);
+
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);
+ parse_data(weights, layer.filters, c*n*size*size);
+ parse_data(biases, layer.biases, n);
#ifdef GPU
- if(weights || biases) push_deconvolutional_layer(*layer);
+ if(weights || biases) push_deconvolutional_layer(layer);
#endif
- option_unused(options);
return layer;
}
-convolutional_layer *parse_convolutional(list *options, network *net, int count)
+convolutional_layer parse_convolutional(list *options, size_params params)
{
- 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);
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);
- 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 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);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before convolutional layer must output image.");
+
+ convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation);
+
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);
+ parse_data(weights, layer.filters, c*n*size*size);
+ parse_data(biases, layer.biases, n);
#ifdef GPU
- if(weights || biases) push_convolutional_layer(*layer);
+ if(weights || biases) push_convolutional_layer(layer);
#endif
- option_unused(options);
return layer;
}
-connected_layer *parse_connected(list *options, network *net, int count)
+connected_layer parse_connected(list *options, size_params params)
{
- 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);
- 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{
- 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);
- input = get_network_output_size_layer(*net, count-1);
- }
- connected_layer *layer = make_connected_layer(net->batch, input, output, activation,learning_rate,momentum,decay);
+
+ connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation);
+
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);
+ parse_data(biases, layer.biases, output);
+ parse_data(weights, layer.weights, params.inputs*output);
#ifdef GPU
- if(weights || biases) push_connected_layer(*layer);
+ if(weights || biases) push_connected_layer(layer);
#endif
- option_unused(options);
return layer;
}
-softmax_layer *parse_softmax(list *options, network *net, int count)
+softmax_layer parse_softmax(list *options, size_params params)
{
- 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);
- }
- softmax_layer *layer = make_softmax_layer(net->batch, input);
- option_unused(options);
+ int groups = option_find_int(options, "groups",1);
+ softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
return layer;
}
-cost_layer *parse_cost(list *options, network *net, int count)
+detection_layer parse_detection(list *options, size_params params)
{
- 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", 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;
+}
+
+cost_layer parse_cost(list *options, size_params params)
+{
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);
+ cost_layer layer = make_cost_layer(params.batch, params.inputs, type);
return layer;
}
-crop_layer *parse_crop(list *options, network *net, int count)
+crop_layer parse_crop(list *options, size_params params)
{
- 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;
- net->seen = option_find_int(options, "seen",0);
- }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;
+ float angle = option_find_float(options, "angle",0);
+ float saturation = option_find_float(options, "saturation",1);
+ float exposure = option_find_float(options, "exposure",1);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ 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);
+ l.noadjust = noadjust;
+ return l;
}
-maxpool_layer *parse_maxpool(list *options, network *net, int count)
+maxpool_layer parse_maxpool(list *options, size_params params)
{
- int h,w,c;
int stride = option_find_int(options, "stride",1);
int size = option_find_int(options, "size",stride);
- 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);
- net->seen = option_find_int(options, "seen",0);
- }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 convolutional layer must output image.");
- }
- maxpool_layer *layer = make_maxpool_layer(net->batch,h,w,c,size,stride);
- option_unused(options);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before maxpool layer must output image.");
+
+ maxpool_layer layer = make_maxpool_layer(batch,h,w,c,size,stride);
return layer;
}
-/*
-freeweight_layer *parse_freeweight(list *options, network *net, int count)
+avgpool_layer parse_avgpool(list *options, size_params params)
{
- 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);
+ 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;
}
-*/
-dropout_layer *parse_dropout(list *options, network *net, int count)
+dropout_layer parse_dropout(list *options, size_params params)
{
- int input;
float probability = option_find_float(options, "probability", .5);
- 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;
- net->seen = option_find_int(options, "seen",0);
- }else{
- input = get_network_output_size_layer(*net, count-1);
- }
- dropout_layer *layer = make_dropout_layer(net->batch,input,probability);
- option_unused(options);
+ dropout_layer layer = make_dropout_layer(params.batch, params.inputs, probability);
return layer;
}
-normalization_layer *parse_normalization(list *options, network *net, int count)
+layer parse_normalization(list *options, size_params params)
{
- int h,w,c;
- int size = option_find_int(options, "size",1);
- float alpha = option_find_float(options, "alpha", 0.);
- float beta = option_find_float(options, "beta", 1.);
- float kappa = option_find_float(options, "kappa", 1.);
- 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);
- net->seen = option_find_int(options, "seen",0);
- }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 convolutional layer must output image.");
+ 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");
+ int len = strlen(l);
+ if(!l) error("Route Layer must specify input layers");
+ int n = 1;
+ int i;
+ for(i = 0; i < len; ++i){
+ if (l[i] == ',') ++n;
}
- normalization_layer *layer = make_normalization_layer(net->batch,h,w,c,size, alpha, beta, kappa);
- option_unused(options);
+
+ int *layers = calloc(n, sizeof(int));
+ int *sizes = calloc(n, sizeof(int));
+ for(i = 0; i < n; ++i){
+ int index = atoi(l);
+ l = strchr(l, ',')+1;
+ layers[i] = index;
+ sizes[i] = net.layers[index].outputs;
+ }
+ int batch = params.batch;
+
+ route_layer layer = make_route_layer(batch, n, layers, sizes);
+
+ convolutional_layer first = net.layers[layers[0]];
+ layer.out_w = first.out_w;
+ layer.out_h = first.out_h;
+ layer.out_c = first.out_c;
+ for(i = 1; i < n; ++i){
+ int index = layers[i];
+ convolutional_layer next = net.layers[index];
+ if(next.out_w == first.out_w && next.out_h == first.out_h){
+ layer.out_c += next.out_c;
+ }else{
+ layer.out_h = layer.out_w = layer.out_c = 0;
+ }
+ }
+
return layer;
}
+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);
+ int subdivs = option_find_int(options, "subdivisions",1);
+ net->batch /= subdivs;
+ net->subdivisions = subdivs;
+
+ net->h = option_find_int_quiet(options, "height",0);
+ 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");
+}
+
network parse_network_cfg(char *filename)
{
list *sections = read_cfg(filename);
- network net = make_network(sections->size, 0);
-
node *n = sections->front;
+ if(!n) error("Config file has no sections");
+ network net = make_network(sections->size - 1);
+ size_params params;
+
+ section *s = (section *)n->val;
+ list *options = s->options;
+ if(!is_network(s)) error("First section must be [net] or [network]");
+ parse_net_options(options, &net);
+
+ params.h = net.h;
+ params.w = net.w;
+ params.c = net.c;
+ params.inputs = net.inputs;
+ params.batch = net.batch;
+
+ n = n->next;
int count = 0;
while(n){
- section *s = (section *)n->val;
- list *options = s->options;
+ fprintf(stderr, "%d: ", count);
+ s = (section *)n->val;
+ options = s->options;
+ layer l = {0};
if(is_convolutional(s)){
- convolutional_layer *layer = parse_convolutional(options, &net, count);
- net.types[count] = CONVOLUTIONAL;
- net.layers[count] = layer;
+ l = parse_convolutional(options, params);
}else if(is_deconvolutional(s)){
- deconvolutional_layer *layer = parse_deconvolutional(options, &net, count);
- net.types[count] = DECONVOLUTIONAL;
- net.layers[count] = layer;
+ l = parse_deconvolutional(options, params);
}else if(is_connected(s)){
- connected_layer *layer = parse_connected(options, &net, count);
- net.types[count] = CONNECTED;
- net.layers[count] = layer;
+ l = parse_connected(options, params);
}else if(is_crop(s)){
- crop_layer *layer = parse_crop(options, &net, count);
- net.types[count] = CROP;
- net.layers[count] = layer;
+ l = parse_crop(options, params);
}else if(is_cost(s)){
- cost_layer *layer = parse_cost(options, &net, count);
- net.types[count] = COST;
- net.layers[count] = layer;
+ l = parse_cost(options, params);
+ }else if(is_detection(s)){
+ l = parse_detection(options, params);
}else if(is_softmax(s)){
- softmax_layer *layer = parse_softmax(options, &net, count);
- net.types[count] = SOFTMAX;
- net.layers[count] = layer;
- }else if(is_maxpool(s)){
- maxpool_layer *layer = parse_maxpool(options, &net, count);
- net.types[count] = MAXPOOL;
- net.layers[count] = layer;
+ l = parse_softmax(options, params);
}else if(is_normalization(s)){
- normalization_layer *layer = parse_normalization(options, &net, count);
- net.types[count] = NORMALIZATION;
- net.layers[count] = layer;
+ 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)){
- 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;
- fprintf(stderr, "Type not recognized: %s\n", s->type);
+ l = parse_dropout(options, params);
+ l.output = net.layers[count-1].output;
+ l.delta = net.layers[count-1].delta;
+ #ifdef GPU
+ l.output_gpu = net.layers[count-1].output_gpu;
+ l.delta_gpu = net.layers[count-1].delta_gpu;
+ #endif
}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);
- ++count;
n = n->next;
+ if(n){
+ params.h = l.out_h;
+ params.w = l.out_w;
+ params.c = l.out_c;
+ params.inputs = l.outputs;
+ }
+ ++count;
}
free_list(sections);
net.outputs = get_network_output_size(net);
@@ -409,6 +392,10 @@
{
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
@@ -419,6 +406,11 @@
return (strcmp(s->type, "[conv]")==0
|| strcmp(s->type, "[convolutional]")==0);
}
+int is_network(section *s)
+{
+ return (strcmp(s->type, "[net]")==0
+ || strcmp(s->type, "[network]")==0);
+}
int is_connected(section *s)
{
return (strcmp(s->type, "[conn]")==0
@@ -429,13 +421,20 @@
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_freeweight(section *s)
+
+int is_normalization(section *s)
{
- return (strcmp(s->type, "[freeweight]")==0);
+ return (strcmp(s->type, "[lrn]")==0
+ || strcmp(s->type, "[normalization]")==0);
}
int is_softmax(section *s)
@@ -443,10 +442,9 @@
return (strcmp(s->type, "[soft]")==0
|| strcmp(s->type, "[softmax]")==0);
}
-int is_normalization(section *s)
+int is_route(section *s)
{
- return (strcmp(s->type, "[lrnorm]")==0
- || strcmp(s->type, "[localresponsenormalization]")==0);
+ return (strcmp(s->type, "[route]")==0);
}
int read_option(char *s, list *options)
@@ -502,195 +500,7 @@
return sections;
}
-void print_convolutional_cfg(FILE *fp, convolutional_layer *l, network net, int count)
-{
- #ifdef GPU
- if(gpu_index >= 0) pull_convolutional_layer(*l);
- #endif
- int i;
- fprintf(fp, "[convolutional]\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"
- "pad=%d\n"
- "activation=%s\n",
- l->n, l->size, l->stride, l->pad,
- 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_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");
- 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)
-{
- #ifdef GPU
- if(gpu_index >= 0) pull_connected_layer(*l);
- #endif
- int i;
- fprintf(fp, "[connected]\n");
- if(count == 0){
- fprintf(fp, "batch=%d\n"
- "input=%d\n"
- "learning_rate=%g\n"
- "momentum=%g\n"
- "decay=%g\n"
- "seen=%d\n",
- l->batch, l->inputs, 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, "output=%d\n"
- "activation=%s\n",
- l->outputs,
- get_activation_string(l->activation));
- fprintf(fp, "biases=");
- for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[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"
- "seen=%d\n",
- l->batch,l->h, l->w, l->c, net.learning_rate, net.momentum, net.decay, net.seen);
- }
- 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");
- if(count == 0) fprintf(fp, "batch=%d\n"
- "height=%d\n"
- "width=%d\n"
- "channels=%d\n",
- l->batch,l->h, l->w, l->c);
- fprintf(fp, "size=%d\nstride=%d\n\n", l->size, l->stride);
-}
-
-void print_normalization_cfg(FILE *fp, normalization_layer *l, network net, int count)
-{
- fprintf(fp, "[localresponsenormalization]\n");
- if(count == 0) fprintf(fp, "batch=%d\n"
- "height=%d\n"
- "width=%d\n"
- "channels=%d\n",
- l->batch,l->h, l->w, l->c);
- fprintf(fp, "size=%d\n"
- "alpha=%g\n"
- "beta=%g\n"
- "kappa=%g\n\n", l->size, l->alpha, l->beta, l->kappa);
-}
-
-void print_softmax_cfg(FILE *fp, softmax_layer *l, network net, int count)
-{
- fprintf(fp, "[softmax]\n");
- if(count == 0) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs);
- 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_weights(network net, char *filename)
+void save_weights_upto(network net, char *filename, int cutoff)
{
fprintf(stderr, "Saving weights to %s\n", filename);
FILE *fp = fopen(filename, "w");
@@ -702,46 +512,49 @@
fwrite(&net.seen, sizeof(int), 1, fp);
int i;
- for(i = 0; i < net.n; ++i){
- if(net.types[i] == CONVOLUTIONAL){
- convolutional_layer layer = *(convolutional_layer *) net.layers[i];
- #ifdef GPU
+ for(i = 0; i < net.n && i < cutoff; ++i){
+ layer l = net.layers[i];
+ if(l.type == CONVOLUTIONAL){
+#ifdef GPU
if(gpu_index >= 0){
- pull_convolutional_layer(layer);
+ pull_convolutional_layer(l);
}
- #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);
+#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(net.types[i] == DECONVOLUTIONAL){
- deconvolutional_layer layer = *(deconvolutional_layer *) net.layers[i];
- #ifdef GPU
+ if(l.type == DECONVOLUTIONAL){
+#ifdef GPU
if(gpu_index >= 0){
- pull_deconvolutional_layer(layer);
+ pull_deconvolutional_layer(l);
}
- #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);
+#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(net.types[i] == CONNECTED){
- connected_layer layer = *(connected_layer *) net.layers[i];
- #ifdef GPU
+ if(l.type == CONNECTED){
+#ifdef GPU
if(gpu_index >= 0){
- pull_connected_layer(layer);
+ pull_connected_layer(l);
}
- #endif
- fwrite(layer.biases, sizeof(float), layer.outputs, fp);
- fwrite(layer.weights, sizeof(float), layer.outputs*layer.inputs, fp);
+#endif
+ fwrite(l.biases, sizeof(float), l.outputs, fp);
+ fwrite(l.weights, sizeof(float), l.outputs*l.inputs, fp);
}
}
fclose(fp);
}
-
-void load_weights(network *net, char *filename)
+void save_weights(network net, char *filename)
{
- fprintf(stderr, "Loading weights from %s\n", filename);
+ save_weights_upto(net, filename, net.n);
+}
+
+void load_weights_upto(network *net, char *filename, int cutoff)
+{
+ fprintf(stderr, "Loading weights from %s...", filename);
+ fflush(stdout);
FILE *fp = fopen(filename, "r");
if(!fp) file_error(filename);
@@ -749,74 +562,47 @@
fread(&net->momentum, sizeof(float), 1, fp);
fread(&net->decay, sizeof(float), 1, fp);
fread(&net->seen, sizeof(int), 1, fp);
- set_learning_network(net, net->learning_rate, net->momentum, net->decay);
-
+
int i;
- for(i = 0; i < net->n; ++i){
- if(net->types[i] == CONVOLUTIONAL){
- convolutional_layer layer = *(convolutional_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
+ 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);
+ fread(l.filters, sizeof(float), num, fp);
+#ifdef GPU
if(gpu_index >= 0){
- push_convolutional_layer(layer);
+ push_convolutional_layer(l);
}
- #endif
+#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(l.type == DECONVOLUTIONAL){
+ int num = l.n*l.c*l.size*l.size;
+ fread(l.biases, sizeof(float), l.n, fp);
+ fread(l.filters, sizeof(float), num, fp);
+#ifdef GPU
if(gpu_index >= 0){
- push_deconvolutional_layer(layer);
+ push_deconvolutional_layer(l);
}
- #endif
+#endif
}
- if(net->types[i] == CONNECTED){
- connected_layer layer = *(connected_layer *) net->layers[i];
- fread(layer.biases, sizeof(float), layer.outputs, fp);
- fread(layer.weights, sizeof(float), layer.outputs*layer.inputs, fp);
- #ifdef GPU
+ if(l.type == CONNECTED){
+ fread(l.biases, sizeof(float), l.outputs, fp);
+ fread(l.weights, sizeof(float), l.outputs*l.inputs, fp);
+#ifdef GPU
if(gpu_index >= 0){
- push_connected_layer(layer);
+ push_connected_layer(l);
}
- #endif
+#endif
}
}
+ fprintf(stderr, "Done!\n");
fclose(fp);
}
-void save_network(network net, char *filename)
+void load_weights(network *net, char *filename)
{
- FILE *fp = fopen(filename, "w");
- if(!fp) file_error(filename);
- int i;
- for(i = 0; i < net.n; ++i)
- {
- 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)
- 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);
+ load_weights_upto(net, filename, net->n);
}
--
Gitblit v1.10.0