darknet/src/classifier.c

#include "network.h"
#include "utils.h"
#include "parser.h"
#include "option_list.h"
#include "blas.h"

#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#endif

list *read_data_cfg(char *filename)
{
    FILE *file = fopen(filename, "r");
    if(file == 0) file_error(filename);
    char *line;
    int nu = 0;
    list *options = make_list();
    while((line=fgetl(file)) != 0){
        ++ nu;
        strip(line);
        switch(line[0]){
            case '\0':
            case '#':
            case ';':
                free(line);
                break;
            default:
                if(!read_option(line, options)){
                    fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
                    free(line);
                }
                break;
        }
    }
    fclose(file);
    return options;
}

void train_classifier(char *datacfg, char *cfgfile, char *weightfile)
{
    data_seed = time(0);
    srand(time(0));
    float avg_loss = -1;
    char *base = basecfg(cfgfile);
    printf("%s\n", base);
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
    int imgs = 1024;

    list *options = read_data_cfg(datacfg);

    char *backup_directory = option_find_str(options, "backup", "/backup/");
    char *label_list = option_find_str(options, "labels", "data/labels.list");
    char *train_list = option_find_str(options, "train", "data/train.list");
    int classes = option_find_int(options, "classes", 2);

    char **labels = get_labels(label_list);
    list *plist = get_paths(train_list);
    char **paths = (char **)list_to_array(plist);
    printf("%d\n", plist->size);
    int N = plist->size;
    clock_t time;
    pthread_t load_thread;
    data train;
    data buffer;

    load_args args = {0};
    args.w = net.w;
    args.h = net.h;
    args.paths = paths;
    args.classes = classes;
    args.n = imgs;
    args.m = N;
    args.labels = labels;
    args.d = &buffer;
    args.type = CLASSIFICATION_DATA;

    load_thread = load_data_in_thread(args);
    int epoch = (*net.seen)/N;
    while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
        time=clock();
        pthread_join(load_thread, 0);
        train = buffer;

        load_thread = load_data_in_thread(args);
        printf("Loaded: %lf seconds\n", sec(clock()-time));
        time=clock();
        float loss = train_network(net, train);
        if(avg_loss == -1) avg_loss = loss;
        avg_loss = avg_loss*.9 + loss*.1;
        printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
        free_data(train);
        if(*net.seen/N > epoch){
            epoch = *net.seen/N;
            char buff[256];
            sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
            save_weights(net, buff);
        }
        if(*net.seen%1000 == 0){
            char buff[256];
            sprintf(buff, "%s/%s.backup",backup_directory,base);
            save_weights(net, buff);
        }
    }
    char buff[256];
    sprintf(buff, "%s/%s.weights", backup_directory, base);
    save_weights(net, buff);

    pthread_join(load_thread, 0);
    free_data(buffer);
    free_network(net);
    free_ptrs((void**)labels, classes);
    free_ptrs((void**)paths, plist->size);
    free_list(plist);
    free(base);
}

void validate_classifier(char *datacfg, char *filename, char *weightfile)
{
    int i = 0;
    network net = parse_network_cfg(filename);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    srand(time(0));

    list *options = read_data_cfg(datacfg);

    char *label_list = option_find_str(options, "labels", "data/labels.list");
    char *valid_list = option_find_str(options, "valid", "data/train.list");
    int classes = option_find_int(options, "classes", 2);
    int topk = option_find_int(options, "top", 1);

    char **labels = get_labels(label_list);
    list *plist = get_paths(valid_list);

    char **paths = (char **)list_to_array(plist);
    int m = plist->size;
    free_list(plist);

    clock_t time;
    float avg_acc = 0;
    float avg_topk = 0;
    int splits = m/1000;
    int num = (i+1)*m/splits - i*m/splits;

    data val, buffer;

    load_args args = {0};
    args.w = net.w;
    args.h = net.h;
    args.paths = paths;
    args.classes = classes;
    args.n = num;
    args.m = 0;
    args.labels = labels;
    args.d = &buffer;
    args.type = CLASSIFICATION_DATA;

    pthread_t load_thread = load_data_in_thread(args);
    for(i = 1; i <= splits; ++i){
        time=clock();

        pthread_join(load_thread, 0);
        val = buffer;

        num = (i+1)*m/splits - i*m/splits;
        char **part = paths+(i*m/splits);
        if(i != splits){
            args.paths = part;
            load_thread = load_data_in_thread(args);
        }
        printf("Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));

        time=clock();
        float *acc = network_accuracies(net, val, topk);
        avg_acc += acc[0];
        avg_topk += acc[1];
        printf("%d: top 1: %f, top %d: %f, %lf seconds, %d images\n", i, avg_acc/i, topk, avg_topk/i, sec(clock()-time), val.X.rows);
        free_data(val);
    }
}

void validate_classifier_10(char *datacfg, char *filename, char *weightfile)
{
    int i, j;
    network net = parse_network_cfg(filename);
    set_batch_network(&net, 1);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    srand(time(0));

    list *options = read_data_cfg(datacfg);

    char *label_list = option_find_str(options, "labels", "data/labels.list");
    char *valid_list = option_find_str(options, "valid", "data/train.list");
    int classes = option_find_int(options, "classes", 2);
    int topk = option_find_int(options, "top", 1);

    char **labels = get_labels(label_list);
    list *plist = get_paths(valid_list);

    char **paths = (char **)list_to_array(plist);
    int m = plist->size;
    free_list(plist);

    float avg_acc = 0;
    float avg_topk = 0;
    int *indexes = calloc(topk, sizeof(int));

    for(i = 0; i < m; ++i){
        int class = -1;
        char *path = paths[i];
        for(j = 0; j < classes; ++j){
            if(strstr(path, labels[j])){
                class = j;
                break;
            }
        }
        image im = load_image_color(paths[i], 256, 256);
        image images[10];
        images[0] = crop_image(im, -16, -16, 256, 256);
        images[1] = crop_image(im, 16, -16, 256, 256);
        images[2] = crop_image(im, 0, 0, 256, 256);
        images[3] = crop_image(im, -16, 16, 256, 256);
        images[4] = crop_image(im, 16, 16, 256, 256);
        flip_image(im);
        images[5] = crop_image(im, -16, -16, 256, 256);
        images[6] = crop_image(im, 16, -16, 256, 256);
        images[7] = crop_image(im, 0, 0, 256, 256);
        images[8] = crop_image(im, -16, 16, 256, 256);
        images[9] = crop_image(im, 16, 16, 256, 256);
        float *pred = calloc(classes, sizeof(float));
        for(j = 0; j < 10; ++j){
            float *p = network_predict(net, images[j].data);
            axpy_cpu(classes, 1, p, 1, pred, 1);
            free_image(images[j]);
        }
        free_image(im);
        top_k(pred, classes, topk, indexes);
        free(pred);
        if(indexes[0] == class) avg_acc += 1;
        for(j = 0; j < topk; ++j){
            if(indexes[j] == class) avg_topk += 1;
        }

        printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
    }
}

void validate_classifier_multi(char *datacfg, char *filename, char *weightfile)
{
    int i, j;
    network net = parse_network_cfg(filename);
    set_batch_network(&net, 1);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    srand(time(0));

    list *options = read_data_cfg(datacfg);

    char *label_list = option_find_str(options, "labels", "data/labels.list");
    char *valid_list = option_find_str(options, "valid", "data/train.list");
    int classes = option_find_int(options, "classes", 2);
    int topk = option_find_int(options, "top", 1);

    char **labels = get_labels(label_list);
    list *plist = get_paths(valid_list);
    int scales[] = {224, 256, 384, 480, 640};
    int nscales = sizeof(scales)/sizeof(scales[0]);

    char **paths = (char **)list_to_array(plist);
    int m = plist->size;
    free_list(plist);

    float avg_acc = 0;
    float avg_topk = 0;
    int *indexes = calloc(topk, sizeof(int));

    for(i = 0; i < m; ++i){
        int class = -1;
        char *path = paths[i];
        for(j = 0; j < classes; ++j){
            if(strstr(path, labels[j])){
                class = j;
                break;
            }
        }
        float *pred = calloc(classes, sizeof(float));
        image im = load_image_color(paths[i], 0, 0);
        for(j = 0; j < nscales; ++j){
            int w, h;
            if(im.w < im.h){
                w = scales[j];
                h = (im.h*w)/im.w;
            } else {
                h = scales[j];
                w = (im.w * h) / im.h;
            }
            resize_network(&net, w, h);
            image r = resize_image(im, w, h);
            float *p = network_predict(net, r.data);
            axpy_cpu(classes, 1, p, 1, pred, 1);
            flip_image(r);
            p = network_predict(net, r.data);
            axpy_cpu(classes, 1, p, 1, pred, 1);
            free_image(r);
        }
        free_image(im);
        top_k(pred, classes, topk, indexes);
        free(pred);
        if(indexes[0] == class) avg_acc += 1;
        for(j = 0; j < topk; ++j){
            if(indexes[j] == class) avg_topk += 1;
        }

        printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
    }
}

void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename)
{
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    set_batch_network(&net, 1);
    srand(2222222);

    list *options = read_data_cfg(datacfg);

    char *name_list = option_find_str(options, "names", 0);
    if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
    int top = option_find_int(options, "top", 1);

    int i = 0;
    char **names = get_labels(name_list);
    clock_t time;
    int *indexes = calloc(top, sizeof(int));
    char buff[256];
    char *input = buff;
    while(1){
        if(filename){
            strncpy(input, filename, 256);
        }else{
            printf("Enter Image Path: ");
            fflush(stdout);
            input = fgets(input, 256, stdin);
            if(!input) return;
            strtok(input, "\n");
        }
        image im = load_image_color(input, net.w, net.h);
        float *X = im.data;
        time=clock();
        float *predictions = network_predict(net, X);
        top_predictions(net, top, indexes);
        printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
        for(i = 0; i < top; ++i){
            int index = indexes[i];
            printf("%s: %f\n", names[index], predictions[index]);
        }
        free_image(im);
        if (filename) break;
    }
}

void test_classifier(char *datacfg, char *cfgfile, char *weightfile, int target_layer)
{
    int curr = 0;
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    srand(time(0));

    list *options = read_data_cfg(datacfg);

    char *test_list = option_find_str(options, "test", "data/test.list");
    int classes = option_find_int(options, "classes", 2);

    list *plist = get_paths(test_list);

    char **paths = (char **)list_to_array(plist);
    int m = plist->size;
    free_list(plist);

    clock_t time;

    data val, buffer;

    load_args args = {0};
    args.w = net.w;
    args.h = net.h;
    args.paths = paths;
    args.classes = classes;
    args.n = net.batch;
    args.m = 0;
    args.labels = 0;
    args.d = &buffer;
    args.type = CLASSIFICATION_DATA;

    pthread_t load_thread = load_data_in_thread(args);
    for(curr = net.batch; curr < m; curr += net.batch){
        time=clock();

        pthread_join(load_thread, 0);
        val = buffer;

        if(curr < m){
            args.paths = paths + curr;
            if (curr + net.batch > m) args.n = m - curr;
            load_thread = load_data_in_thread(args);
        }
        fprintf(stderr, "Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));

        time=clock();
        matrix pred = network_predict_data(net, val);
        
        int i, j;
        if (target_layer >= 0){
            //layer l = net.layers[target_layer];
        }

        for(i = 0; i < pred.rows; ++i){
            printf("%s", paths[curr-net.batch+i]);
            for(j = 0; j < pred.cols; ++j){
                printf("\t%g", pred.vals[i][j]);
            }
            printf("\n");
        }

        free_matrix(pred);

        fprintf(stderr, "%lf seconds, %d images, %d total\n", sec(clock()-time), val.X.rows, curr);
        free_data(val);
    }
}


void run_classifier(int argc, char **argv)
{
    if(argc < 4){
        fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
        return;
    }

    char *data = argv[3];
    char *cfg = argv[4];
    char *weights = (argc > 5) ? argv[5] : 0;
    char *filename = (argc > 6) ? argv[6]: 0;
    char *layer_s = (argc > 7) ? argv[7]: 0;
    int layer = layer_s ? atoi(layer_s) : -1;
    if(0==strcmp(argv[2], "predict")) predict_classifier(data, cfg, weights, filename);
    else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights);
    else if(0==strcmp(argv[2], "test")) test_classifier(data, cfg, weights, layer);
    else if(0==strcmp(argv[2], "valid")) validate_classifier(data, cfg, weights);
    else if(0==strcmp(argv[2], "valid10")) validate_classifier_10(data, cfg, weights);
    else if(0==strcmp(argv[2], "validmulti")) validate_classifier_multi(data, cfg, weights);
}