darknet/src/classifier.c

#include "network.h"
#include "utils.h"
#include "parser.h"
#include "option_list.h"
#include "blas.h"
#include "assert.h"
#include "classifier.h"
#include <sys/time.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, int clear)
{
    int nthreads = 2;
    int i;

    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);
    }
    if(clear) *net.seen = 0;
    printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
    int imgs = net.batch*net.subdivisions/nthreads;
    assert(net.batch*net.subdivisions % nthreads == 0);

    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_threads = calloc(nthreads, sizeof(pthread_t));
    data *trains  = calloc(nthreads, sizeof(data));
    data *buffers = calloc(nthreads, sizeof(data));

    load_args args = {0};
    args.w = net.w;
    args.h = net.h;

    args.min = net.min_crop;
    args.max = net.max_crop;
    args.size = net.w;

    args.paths = paths;
    args.classes = classes;
    args.n = imgs;
    args.m = N;
    args.labels = labels;
    args.type = CLASSIFICATION_DATA;

    for(i = 0; i < nthreads; ++i){
        args.d = buffers + i;
        load_threads[i] = load_data_in_thread(args);
    }

    int epoch = (*net.seen)/N;
    while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
        time=clock();
        for(i = 0; i < nthreads; ++i){
            pthread_join(load_threads[i], 0);
            trains[i] = buffers[i];
        }
        data train = concat_datas(trains, nthreads);

        for(i = 0; i < nthreads; ++i){
            args.d = buffers + i;
            load_threads[i] = load_data_in_thread(args);
        }

        printf("Loaded: %lf seconds\n", sec(clock()-time));
        time=clock();

        /*
           int u;
           for(u = 0; u < net.batch; ++u){
           image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
           show_image(im, "loaded");
           cvWaitKey(0);
           }
         */

        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);
        for(i = 0; i < nthreads; ++i){
            free_data(trains[i]);
        }
        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(get_current_batch(net)%100 == 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);

    for(i = 0; i < nthreads; ++i){
        pthread_join(load_threads[i], 0);
        free_data(buffers[i]);
    }
    free(buffers);
    free(trains);
    free(load_threads);

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

void validate_classifier_crop(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 = OLD_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;
            }
        }
        int w = net.w;
        int h = net.h;
        int shift = 32;
        image im = load_image_color(paths[i], w+shift, h+shift);
        image images[10];
        images[0] = crop_image(im, -shift, -shift, w, h);
        images[1] = crop_image(im, shift, -shift, w, h);
        images[2] = crop_image(im, 0, 0, w, h);
        images[3] = crop_image(im, -shift, shift, w, h);
        images[4] = crop_image(im, shift, shift, w, h);
        flip_image(im);
        images[5] = crop_image(im, -shift, -shift, w, h);
        images[6] = crop_image(im, shift, -shift, w, h);
        images[7] = crop_image(im, 0, 0, w, h);
        images[8] = crop_image(im, -shift, shift, w, h);
        images[9] = crop_image(im, shift, shift, w, h);
        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_full(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));

    int size = net.w;
    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], 0, 0);
        image resized = resize_min(im, size);
        resize_network(&net, resized.w, resized.h);
        //show_image(im, "orig");
        //show_image(crop, "cropped");
        //cvWaitKey(0);
        float *pred = network_predict(net, resized.data);

        free_image(im);
        free_image(resized);
        top_k(pred, classes, topk, indexes);

        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_single(char *datacfg, char *filename, char *weightfile)
{
    int i, j;
    network net = parse_network_cfg(filename);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    set_batch_network(&net, 1);
    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], 0, 0);
        image resized = resize_min(im, net.w);
        image crop = crop_image(resized, (resized.w - net.w)/2, (resized.h - net.h)/2, net.w, net.h);
        //show_image(im, "orig");
        //show_image(crop, "cropped");
        //cvWaitKey(0);
        float *pred = network_predict(net, crop.data);

        if(resized.data != im.data) free_image(resized);
        free_image(im);
        free_image(crop);
        top_k(pred, classes, topk, indexes);

        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[] = {192, 224, 288, 320, 352};
    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){
            image r = resize_min(im, scales[j]);
            resize_network(&net, r.w, r.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);
            if(r.data != im.data) 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;
    int size = net.w;
    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, 0, 0);
        image r = resize_min(im, size);
        resize_network(&net, r.w, r.h);
        printf("%d %d\n", r.w, r.h);

        float *X = r.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]);
        }
        if(r.data != im.data) free_image(r);
        free_image(im);
        if (filename) break;
    }
}


void label_classifier(char *datacfg, char *filename, char *weightfile)
{
    int i;
    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, "names", "data/labels.list");
    char *test_list = option_find_str(options, "test", "data/train.list");
    int classes = option_find_int(options, "classes", 2);

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

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

    for(i = 0; i < m; ++i){
        image im = load_image_color(paths[i], 0, 0);
        image resized = resize_min(im, net.w);
        image crop = crop_image(resized, (resized.w - net.w)/2, (resized.h - net.h)/2, net.w, net.h);
        float *pred = network_predict(net, crop.data);

        if(resized.data != im.data) free_image(resized);
        free_image(im);
        free_image(crop);
        int ind = max_index(pred, classes);

        printf("%s\n", labels[ind]);
    }
}


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 = OLD_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 demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
{
#ifdef OPENCV
    printf("Classifier Demo\n");
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    set_batch_network(&net, 1);
    list *options = read_data_cfg(datacfg);

    srand(2222222);
    CvCapture * cap;

    if(filename){
        cap = cvCaptureFromFile(filename);
    }else{
        cap = cvCaptureFromCAM(cam_index);
    }

    int top = option_find_int(options, "top", 1);

    char *name_list = option_find_str(options, "names", 0);
    char **names = get_labels(name_list);

    int *indexes = calloc(top, sizeof(int));

    if(!cap) error("Couldn't connect to webcam.\n");
    cvNamedWindow("Classifier", CV_WINDOW_NORMAL); 
    cvResizeWindow("Classifier", 512, 512);
    float fps = 0;
    int i;

    while(1){
        struct timeval tval_before, tval_after, tval_result;
        gettimeofday(&tval_before, NULL);

        image in = get_image_from_stream(cap);
        image in_s = resize_image(in, net.w, net.h);
        show_image(in, "Classifier");

        float *predictions = network_predict(net, in_s.data);
        top_predictions(net, top, indexes);

        printf("\033[2J");
        printf("\033[1;1H");
        printf("\nFPS:%.0f\n",fps);

        for(i = 0; i < top; ++i){
            int index = indexes[i];
            printf("%.1f%%: %s\n", predictions[index]*100, names[index]);
        }

        free_image(in_s);
        free_image(in);

        cvWaitKey(10);

        gettimeofday(&tval_after, NULL);
        timersub(&tval_after, &tval_before, &tval_result);
        float curr = 1000000.f/((long int)tval_result.tv_usec);
        fps = .9*fps + .1*curr;
    }
#endif
}


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;
    }

    int cam_index = find_int_arg(argc, argv, "-c", 0);
    int clear = find_arg(argc, argv, "-clear");
    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, clear);
    else if(0==strcmp(argv[2], "demo")) demo_classifier(data, cfg, weights, cam_index, filename);
    else if(0==strcmp(argv[2], "test")) test_classifier(data, cfg, weights, layer);
    else if(0==strcmp(argv[2], "label")) label_classifier(data, cfg, weights);
    else if(0==strcmp(argv[2], "valid")) validate_classifier_single(data, cfg, weights);
    else if(0==strcmp(argv[2], "validmulti")) validate_classifier_multi(data, cfg, weights);
    else if(0==strcmp(argv[2], "valid10")) validate_classifier_10(data, cfg, weights);
    else if(0==strcmp(argv[2], "validcrop")) validate_classifier_crop(data, cfg, weights);
    else if(0==strcmp(argv[2], "validfull")) validate_classifier_full(data, cfg, weights);
}