detection layer fixed

Joseph Redmon

2015-03-08 655f636a42d6e1d4518b712cfac6d973424de693

 src/parser.c

@@ -7,11 +7,13 @@
#include "crop_layer.h"
#include "cost_layer.h"
#include "convolutional_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 "detection_layer.h"
#include "freeweight_layer.h"
#include "list.h"
#include "option_list.h"
@@ -23,6 +25,7 @@
}section;

int is_convolutional(section *s);
int is_deconvolutional(section *s);
int is_connected(section *s);
int is_maxpool(section *s);
int is_dropout(section *s);
@@ -30,6 +33,7 @@
int is_softmax(section *s);
int is_crop(section *s);
int is_cost(section *s);
int is_detection(section *s);
int is_normalization(section *s);
list *read_cfg(char *filename);

@@ -65,6 +69,49 @@
    }
}

deconvolutional_layer *parse_deconvolutional(list *options, network *net, int count)
{
    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");
    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);
    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);
    #ifdef GPU
    if(weights || biases) push_deconvolutional_layer(*layer);
    #endif
    option_unused(options);
    return layer;
}

convolutional_layer *parse_convolutional(list *options, network *net, int count)
{
    int h,w,c;
@@ -146,6 +193,7 @@
softmax_layer *parse_softmax(list *options, network *net, int count)
{
    int input;
    int groups = option_find_int(options, "groups",1);
    if(count == 0){
        input = option_find_int(options, "input",1);
        net->batch = option_find_int(options, "batch",1);
@@ -153,7 +201,25 @@
    }else{
        input =  get_network_output_size_layer(*net, count-1);
    }
    softmax_layer *layer = make_softmax_layer(net->batch, input);
    softmax_layer *layer = make_softmax_layer(net->batch, groups, input);
    option_unused(options);
    return layer;
}

detection_layer *parse_detection(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);
        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", 1);
    detection_layer *layer = make_detection_layer(net->batch, input, classes, coords, rescore);
    option_unused(options);
    return layer;
}
@@ -306,6 +372,10 @@
            convolutional_layer *layer = parse_convolutional(options, &net, count);
            net.types[count] = CONVOLUTIONAL;
            net.layers[count] = layer;
        }else if(is_deconvolutional(s)){
            deconvolutional_layer *layer = parse_deconvolutional(options, &net, count);
            net.types[count] = DECONVOLUTIONAL;
            net.layers[count] = layer;
        }else if(is_connected(s)){
            connected_layer *layer = parse_connected(options, &net, count);
            net.types[count] = CONNECTED;
@@ -318,6 +388,10 @@
            cost_layer *layer = parse_cost(options, &net, count);
            net.types[count] = COST;
            net.layers[count] = layer;
        }else if(is_detection(s)){
            detection_layer *layer = parse_detection(options, &net, count);
            net.types[count] = DETECTION;
            net.layers[count] = layer;
        }else if(is_softmax(s)){
            softmax_layer *layer = parse_softmax(options, &net, count);
            net.types[count] = SOFTMAX;
@@ -360,6 +434,15 @@
{
    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
            || strcmp(s->type, "[deconvolutional]")==0);
}
int is_convolutional(section *s)
{
    return (strcmp(s->type, "[conv]")==0
@@ -438,7 +521,7 @@
                break;
            default:
                if(!read_option(line, current->options)){
                    printf("Config file error line %d, could parse: %s\n", nu, line);
                    fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
                    free(line);
                }
                break;
@@ -488,6 +571,45 @@
    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");
@@ -590,6 +712,13 @@
    fprintf(fp, "\n");
}

void print_detection_cfg(FILE *fp, detection_layer *l, network net, int count)
{
    fprintf(fp, "[detection]\n");
    fprintf(fp, "classes=%d\ncoords=%d\nrescore=%d\n", l->classes, l->coords, l->rescore);
    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));
@@ -599,7 +728,7 @@

void save_weights(network net, char *filename)
{
    printf("Saving weights to %s\n", filename);
    fprintf(stderr, "Saving weights to %s\n", filename);
    FILE *fp = fopen(filename, "w");
    if(!fp) file_error(filename);

@@ -621,6 +750,17 @@
            fwrite(layer.biases, sizeof(float), layer.n, fp);
            fwrite(layer.filters, sizeof(float), num, fp);
        }
        if(net.types[i] == DECONVOLUTIONAL){
            deconvolutional_layer layer = *(deconvolutional_layer *) net.layers[i];
            #ifdef GPU
            if(gpu_index >= 0){
                pull_deconvolutional_layer(layer);
            }
            #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);
        }
        if(net.types[i] == CONNECTED){
            connected_layer layer = *(connected_layer *) net.layers[i];
            #ifdef GPU
@@ -635,9 +775,9 @@
    fclose(fp);
}

void load_weights(network *net, char *filename)
void load_weights_upto(network *net, char *filename, int cutoff)
{
    printf("Loading weights from %s\n", filename);
    fprintf(stderr, "Loading weights from %s\n", filename);
    FILE *fp = fopen(filename, "r");
    if(!fp) file_error(filename);

@@ -648,7 +788,7 @@
    set_learning_network(net, net->learning_rate, net->momentum, net->decay);
    
    int i;
    for(i = 0; i < net->n; ++i){
    for(i = 0; i < net->n && i < cutoff; ++i){
        if(net->types[i] == CONVOLUTIONAL){
            convolutional_layer layer = *(convolutional_layer *) net->layers[i];
            int num = layer.n*layer.c*layer.size*layer.size;
@@ -660,6 +800,17 @@
            }
            #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(gpu_index >= 0){
                push_deconvolutional_layer(layer);
            }
            #endif
        }
        if(net->types[i] == CONNECTED){
            connected_layer layer = *(connected_layer *) net->layers[i];
            fread(layer.biases, sizeof(float), layer.outputs, fp);
@@ -674,6 +825,11 @@
    fclose(fp);
}

void load_weights(network *net, char *filename)
{
    load_weights_upto(net, filename, net->n);
}

void save_network(network net, char *filename)
{
    FILE *fp = fopen(filename, "w");
@@ -683,6 +839,8 @@
    {
        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)
@@ -697,6 +855,8 @@
            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] == DETECTION)
            print_detection_cfg(fp, (detection_layer *)net.layers[i], net, i);
        else if(net.types[i] == COST)
            print_cost_cfg(fp, (cost_layer *)net.layers[i], net, i);
    }