C++ save_weights函数代码示例

void train_mnist_distill(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);

    char *backup_directory = "backup";
    int classes = 10;
    int N = 50000;

    int epoch = (*net.seen)/N;

    data train;// = load_all_mnist10();
    matrix soft = csv_to_matrix("results/ensemble.csv");

    float weight = .9;
    scale_matrix(soft, weight);
    scale_matrix(train.y, 1. - weight);
    matrix_add_matrix(soft, train.y);

    while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
        clock_t time=clock();

        float loss = train_network_sgd(net, train, 1);
        if(avg_loss == -1) avg_loss = loss;
        avg_loss = avg_loss*.95 + loss*.05;
        if(get_current_batch(net)%100 == 0)
        {
            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);
        }
        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);

    free_network(net);
    free(base);
    free_data(train);
}

void train_char_rnn(char *cfgfile, char *weightfile, char *filename)
{
    FILE *fp = fopen(filename, "r");
    //FILE *fp = fopen("data/ab.txt", "r");
    //FILE *fp = fopen("data/grrm/asoiaf.txt", "r");

    fseek(fp, 0, SEEK_END); 
    size_t size = ftell(fp);
    fseek(fp, 0, SEEK_SET); 

    char *text = calloc(size, sizeof(char));
    fread(text, 1, size, fp);
    fclose(fp);

    char *backup_directory = "/home/pjreddie/backup/";
    srand(time(0));
    data_seed = time(0);
    char *base = basecfg(cfgfile);
    printf("%s\n", base);
    float avg_loss = -1;
    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 batch = net.batch;
    int steps = net.time_steps;
    int i = (*net.seen)/net.batch;

    clock_t time;
    while(get_current_batch(net) < net.max_batches){
        i += 1;
        time=clock();
        float_pair p = get_rnn_data(text, size, batch/steps, steps);

        float loss = train_network_datum(net, p.x, p.y) / (batch);
        free(p.x);
        free(p.y);
        if (avg_loss < 0) avg_loss = loss;
        avg_loss = avg_loss*.9 + loss*.1;

        printf("%d: %f, %f avg, %f rate, %lf seconds\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time));
        if(i%100==0){
            char buff[256];
            sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
            save_weights(net, buff);
        }
        if(i%10==0){
            char buff[256];
            sprintf(buff, "%s/%s.backup", backup_directory, base);
            save_weights(net, buff);
        }
    }
    char buff[256];
    sprintf(buff, "%s/%s_final.weights", backup_directory, base);
    save_weights(net, buff);
}

void train_go(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);

    char *backup_directory = "/home/pjreddie/backup/";

    char buff[256];
    float *board = calloc(19*19*net.batch, sizeof(float));
    float *move = calloc(19*19*net.batch, sizeof(float));
    moves m = load_go_moves("/home/pjreddie/go.train");
    //moves m = load_go_moves("games.txt");

    int N = m.n;
    int epoch = (*net.seen)/N;
    while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
        clock_t time=clock();

        random_go_moves(m, board, move, net.batch);
        float loss = train_network_datum(net, board, move) / net.batch;
        if(avg_loss == -1) avg_loss = loss;
        avg_loss = avg_loss*.95 + loss*.05;
        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);
        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);
        }
        if(get_current_batch(net)%10000 == 0){
            char buff[256];
            sprintf(buff, "%s/%s_%d.backup",backup_directory,base,get_current_batch(net));
            save_weights(net, buff);
        }
    }
    sprintf(buff, "%s/%s.weights", backup_directory, base);
    save_weights(net, buff);

    free_network(net);
    free(base);
}

void normalize_net(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 0);
    int i;
    for(i = 0; i < net->n; ++i){
        layer l = net->layers[i];
        if(l.type == CONVOLUTIONAL && !l.batch_normalize){
            net->layers[i] = normalize_layer(l, l.n);
        }
        if (l.type == CONNECTED && !l.batch_normalize) {
            net->layers[i] = normalize_layer(l, l.outputs);
        }
        if (l.type == GRU && l.batch_normalize) {
            *l.input_z_layer = normalize_layer(*l.input_z_layer, l.input_z_layer->outputs);
            *l.input_r_layer = normalize_layer(*l.input_r_layer, l.input_r_layer->outputs);
            *l.input_h_layer = normalize_layer(*l.input_h_layer, l.input_h_layer->outputs);
            *l.state_z_layer = normalize_layer(*l.state_z_layer, l.state_z_layer->outputs);
            *l.state_r_layer = normalize_layer(*l.state_r_layer, l.state_r_layer->outputs);
            *l.state_h_layer = normalize_layer(*l.state_h_layer, l.state_h_layer->outputs);
            net->layers[i].batch_normalize=1;
        }
    }
    save_weights(net, outfile);
    free_network(net);
}

void oneoff(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    int oldn = net->layers[net->n - 2].n;
    int c = net->layers[net->n - 2].c;
    scal_cpu(oldn*c, .1, net->layers[net->n - 2].weights, 1);
    scal_cpu(oldn, 0, net->layers[net->n - 2].biases, 1);
    net->layers[net->n - 2].n = 11921;
    net->layers[net->n - 2].biases += 5;
    net->layers[net->n - 2].weights += 5*c;
    if(weightfile){
        load_weights(net, weightfile);
    }
    net->layers[net->n - 2].biases -= 5;
    net->layers[net->n - 2].weights -= 5*c;
    net->layers[net->n - 2].n = oldn;
    printf("%d\n", oldn);
    layer l = net->layers[net->n - 2];
    copy_cpu(l.n/3, l.biases, 1, l.biases +   l.n/3, 1);
    copy_cpu(l.n/3, l.biases, 1, l.biases + 2*l.n/3, 1);
    copy_cpu(l.n/3*l.c, l.weights, 1, l.weights +   l.n/3*l.c, 1);
    copy_cpu(l.n/3*l.c, l.weights, 1, l.weights + 2*l.n/3*l.c, 1);
    *net->seen = 0;
    save_weights(net, outfile);
    free_network(net);
}

void denormalize_net(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 0);
    int i;
    for (i = 0; i < net->n; ++i) {
        layer l = net->layers[i];
        if ((l.type == DECONVOLUTIONAL || l.type == CONVOLUTIONAL) && l.batch_normalize) {
            denormalize_convolutional_layer(l);
            net->layers[i].batch_normalize=0;
        }
        if (l.type == CONNECTED && l.batch_normalize) {
            denormalize_connected_layer(l);
            net->layers[i].batch_normalize=0;
        }
        if (l.type == GRU && l.batch_normalize) {
            denormalize_connected_layer(*l.input_z_layer);
            denormalize_connected_layer(*l.input_r_layer);
            denormalize_connected_layer(*l.input_h_layer);
            denormalize_connected_layer(*l.state_z_layer);
            denormalize_connected_layer(*l.state_r_layer);
            denormalize_connected_layer(*l.state_h_layer);
            l.input_z_layer->batch_normalize = 0;
            l.input_r_layer->batch_normalize = 0;
            l.input_h_layer->batch_normalize = 0;
            l.state_z_layer->batch_normalize = 0;
            l.state_r_layer->batch_normalize = 0;
            l.state_h_layer->batch_normalize = 0;
            net->layers[i].batch_normalize=0;
        }
    }
    save_weights(net, outfile);
    free_network(net);
}

void train_cifar(char *cfgfile, char *weightfile)
{
    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);

    char *backup_directory = "/home/pjreddie/backup/";
    int classes = 10;
    int N = 50000;

    char **labels = get_labels("data/cifar/labels.txt");
    int epoch = (*net.seen)/N;
    data train = load_all_cifar10();
    while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
        clock_t time=clock();

        float loss = train_network_sgd(net, train, 1);
        if(avg_loss == -1) avg_loss = loss;
        avg_loss = avg_loss*.95 + loss*.05;
        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);
        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);

    free_network(net);
    free_ptrs((void**)labels, classes);
    free(base);
    free_data(train);
}

void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights_upto(&net, weightfile, max);
    }
    net.seen = 0;
    save_weights(net, outfile);
}

void average(int argc, char *argv[])
{
    char *cfgfile = argv[2];
    char *outfile = argv[3];
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    network *sum = parse_network_cfg(cfgfile);

    char *weightfile = argv[4];
    load_weights(sum, weightfile);

    int i, j;
    int n = argc - 5;
    for(i = 0; i < n; ++i){
        weightfile = argv[i+5];
        load_weights(net, weightfile);
        for(j = 0; j < net->n; ++j){
            layer l = net->layers[j];
            layer out = sum->layers[j];
            if(l.type == CONVOLUTIONAL){
                int num = l.n*l.c*l.size*l.size;
                axpy_cpu(l.n, 1, l.biases, 1, out.biases, 1);
                axpy_cpu(num, 1, l.weights, 1, out.weights, 1);
                if(l.batch_normalize){
                    axpy_cpu(l.n, 1, l.scales, 1, out.scales, 1);
                    axpy_cpu(l.n, 1, l.rolling_mean, 1, out.rolling_mean, 1);
                    axpy_cpu(l.n, 1, l.rolling_variance, 1, out.rolling_variance, 1);
                }
            }
            if(l.type == CONNECTED){
                axpy_cpu(l.outputs, 1, l.biases, 1, out.biases, 1);
                axpy_cpu(l.outputs*l.inputs, 1, l.weights, 1, out.weights, 1);
            }
        }
    }
    n = n+1;
    for(j = 0; j < net->n; ++j){
        layer l = sum->layers[j];
        if(l.type == CONVOLUTIONAL){
            int num = l.n*l.c*l.size*l.size;
            scal_cpu(l.n, 1./n, l.biases, 1);
            scal_cpu(num, 1./n, l.weights, 1);
                if(l.batch_normalize){
                    scal_cpu(l.n, 1./n, l.scales, 1);
                    scal_cpu(l.n, 1./n, l.rolling_mean, 1);
                    scal_cpu(l.n, 1./n, l.rolling_variance, 1);
                }
        }
        if(l.type == CONNECTED){
            scal_cpu(l.outputs, 1./n, l.biases, 1);
            scal_cpu(l.outputs*l.inputs, 1./n, l.weights, 1);
        }
    }
    save_weights(sum, outfile);
}

void train_imagenet(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);
    //net.seen=0;
    int imgs = 1024;
    int i = net.seen/imgs;
    char **labels = get_labels("data/inet.labels.list");
    list *plist = get_paths("/data/imagenet/cls.train.list");
    char **paths = (char **)list_to_array(plist);
    printf("%d\n", plist->size);
    clock_t time;
    pthread_t load_thread;
    data train;
    data buffer;
    load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
    while(1){
        ++i;
        time=clock();
        pthread_join(load_thread, 0);
        train = buffer;

        /*
        image im = float_to_image(256, 256, 3, train.X.vals[114]);
        show_image(im, "training");
        cvWaitKey(0);
        */

        load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
        printf("Loaded: %lf seconds\n", sec(clock()-time));
        time=clock();
        float loss = train_network(net, train);
        net.seen += imgs;
        if(avg_loss == -1) avg_loss = loss;
        avg_loss = avg_loss*.9 + loss*.1;
        printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
        free_data(train);
        if((i % 20000) == 0) net.learning_rate *= .1;
        //if(i%100 == 0 && net.learning_rate > .00001) net.learning_rate *= .97;
        if(i%1000==0){
            char buff[256];
            sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
            save_weights(net, buff);
        }
    }
}

void rgbgr_net(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 0);
    int i;
    for(i = 0; i < net->n; ++i){
        layer l = net->layers[i];
        if(l.type == CONVOLUTIONAL){
            rgbgr_weights(l);
            break;
        }
    }
    save_weights(net, outfile);
    free_network(net);
}

void rgbgr_net(char *cfgfile, char *weightfile, char *outfile)
{
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    int i;
    for(i = 0; i < net.n; ++i){
        layer l = net.layers[i];
        if(l.type == CONVOLUTIONAL){
            rgbgr_filters(l);
            break;
        }
    }
    save_weights(net, outfile);
}

static void denormalize_net(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    if (weightfile) {
        load_weights(&net, weightfile);
    }
    int i;
    for (i = 0; i < net.n; ++i) {
        layer_t l = net.layers[i];
        if (l.type == CONVOLUTIONAL && l.batch_normalize) {
            denormalize_convolutional_layer(l);
            net.layers[i].batch_normalize=0;
        }
    }
    save_weights(net, outfile);
}

static void rescale_net(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    int i;
    for(i = 0; i < net.n; ++i){
        layer_t l = net.layers[i];
        if(l.type == CONVOLUTIONAL){
            rescale_filters(l, 2, -.5);
            break;
        }
    }
    save_weights(net, outfile);
}

static void average(int argc, char *argv[])
{
    char *cfgfile = argv[2];
    char *outfile = argv[3];
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    network sum = parse_network_cfg(cfgfile);

    char *weightfile = argv[4];   
    load_weights(&sum, weightfile);

    int i, j;
    int n = argc - 5;
    for(i = 0; i < n; ++i){
        weightfile = argv[i+5];   
        load_weights(&net, weightfile);
        for(j = 0; j < net.n; ++j){
            layer_t l = net.layers[j];
            layer_t out = sum.layers[j];
            if(l.type == CONVOLUTIONAL){
                int num = l.n*l.c*l.size*l.size;
                fltadd(out.biases, l.biases, l.n);
                fltadd(out.filters, l.filters, num);
            }
            if(l.type == CONNECTED){
                fltadd(out.biases, l.biases, l.outputs);
                fltadd(out.weights, l.weights, l.outputs * l.inputs);
            }
        }
    }
    n = n+1;
    for(j = 0; j < net.n; ++j){
        layer_t l = sum.layers[j];
        if(l.type == CONVOLUTIONAL){
            int num = l.n*l.c*l.size*l.size;
            scal_cpu(l.n, 1./n, l.biases, 1);
            scal_cpu(num, 1./n, l.filters, 1);
        }
        if(l.type == CONNECTED){
            scal_cpu(l.outputs, 1./n, l.biases, 1);
            scal_cpu(l.outputs*l.inputs, 1./n, l.weights, 1);
        }
    }
    save_weights(sum, outfile);
}