darknet/src/darknet.c

#include <time.h>
#include <stdlib.h>
#include <stdio.h>

#include "parser.h"
#include "utils.h"
#include "cuda.h"
#include "blas.h"
#include "connected_layer.h"

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

extern void run_voxel(int argc, char **argv);
extern void run_yolo(int argc, char **argv);
extern void run_detector(int argc, char **argv);
extern void run_coco(int argc, char **argv);
extern void run_writing(int argc, char **argv);
extern void run_captcha(int argc, char **argv);
extern void run_nightmare(int argc, char **argv);
extern void run_dice(int argc, char **argv);
extern void run_compare(int argc, char **argv);
extern void run_classifier(int argc, char **argv);
extern void run_char_rnn(int argc, char **argv);
extern void run_vid_rnn(int argc, char **argv);
extern void run_tag(int argc, char **argv);
extern void run_cifar(int argc, char **argv);
extern void run_go(int argc, char **argv);
extern void run_art(int argc, char **argv);
extern void run_super(int argc, char **argv);

void change_rate(char *filename, float scale, float add)
{
    // Ready for some weird shit??
    FILE *fp = fopen(filename, "r+b");
    if(!fp) file_error(filename);
    float rate = 0;
    fread(&rate, sizeof(float), 1, fp);
    printf("Scaling learning rate from %f to %f\n", rate, rate*scale+add);
    rate = rate*scale + add;
    fseek(fp, 0, SEEK_SET);
    fwrite(&rate, sizeof(float), 1, fp);
    fclose(fp);
}

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.filters, 1, out.filters, 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.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);
}

void speed(char *cfgfile, int tics)
{
    if (tics == 0) tics = 1000;
    network net = parse_network_cfg(cfgfile);
    set_batch_network(&net, 1);
    int i;
    time_t start = time(0);
    image im = make_image(net.w, net.h, net.c);
    for(i = 0; i < tics; ++i){
        network_predict(net, im.data);
    }
    double t = difftime(time(0), start);
    printf("\n%d evals, %f Seconds\n", tics, t);
    printf("Speed: %f sec/eval\n", t/tics);
    printf("Speed: %f Hz\n", tics/t);
}

void operations(char *cfgfile)
{
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    int i;
    long ops = 0;
    for(i = 0; i < net.n; ++i){
        layer l = net.layers[i];
        if(l.type == CONVOLUTIONAL){
            ops += 2l * l.n * l.size*l.size*l.c * l.out_h*l.out_w;
        } else if(l.type == CONNECTED){
            ops += 2l * l.inputs * l.outputs;
        }
    }
    printf("Floating Point Operations: %ld\n", ops);
    printf("Floating Point Operations: %.2f Bn\n", (float)ops/1000000000.);
}

void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights_upto(&net, weightfile, max);
    }
    *net.seen = 0;
    save_weights_upto(net, outfile, max);
}

void stacked(char *cfgfile, char *weightfile, char *outfile)
{
    gpu_index = -1;
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    net.seen = 0;
    save_weights_double(net, outfile);
}

#include "convolutional_layer.h"
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 l = net.layers[i];
        if(l.type == CONVOLUTIONAL){
            rescale_filters(l, 2, -.5);
            break;
        }
    }
    save_weights(net, outfile);
}

void rgbgr_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 l = net.layers[i];
        if(l.type == CONVOLUTIONAL){
            rgbgr_filters(l);
            break;
        }
    }
    save_weights(net, outfile);
}

void reset_normalize_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 l = net.layers[i];
        if (l.type == CONVOLUTIONAL && l.batch_normalize) {
            denormalize_convolutional_layer(l);
        }
        if (l.type == CONNECTED && l.batch_normalize) {
            denormalize_connected_layer(l);
        }
        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);
        }
    }
    save_weights(net, outfile);
}

layer normalize_layer(layer l, int n)
{
    int j;
    l.batch_normalize=1;
    l.scales = calloc(n, sizeof(float));
    for(j = 0; j < n; ++j){
        l.scales[j] = 1;
    }
    l.rolling_mean = calloc(n, sizeof(float));
    l.rolling_variance = calloc(n, sizeof(float));
    return l;
}

void normalize_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 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);
}

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 l = net.layers[i];
        if (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);
}

void visualize(char *cfgfile, char *weightfile)
{
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    visualize_network(net);
#ifdef OPENCV
    cvWaitKey(0);
#endif
}

int main(int argc, char **argv)
{
    //test_resize("data/bad.jpg");
    //test_box();
    //test_convolutional_layer();
    if(argc < 2){
        fprintf(stderr, "usage: %s <function>\n", argv[0]);
        return 0;
    }
    gpu_index = find_int_arg(argc, argv, "-i", 0);
    if(find_arg(argc, argv, "-nogpu")) {
        gpu_index = -1;
    }

#ifndef GPU
    gpu_index = -1;
#else
    if(gpu_index >= 0){
        cudaError_t status = cudaSetDevice(gpu_index);
        check_error(status);
    }
#endif

    if (0 == strcmp(argv[1], "average")){
        average(argc, argv);
    } else if (0 == strcmp(argv[1], "yolo")){
        run_yolo(argc, argv);
    } else if (0 == strcmp(argv[1], "voxel")){
        run_voxel(argc, argv);
    } else if (0 == strcmp(argv[1], "super")){
        run_super(argc, argv);
    } else if (0 == strcmp(argv[1], "detector")){
        run_detector(argc, argv);
    } else if (0 == strcmp(argv[1], "cifar")){
        run_cifar(argc, argv);
    } else if (0 == strcmp(argv[1], "go")){
        run_go(argc, argv);
    } else if (0 == strcmp(argv[1], "rnn")){
        run_char_rnn(argc, argv);
    } else if (0 == strcmp(argv[1], "vid")){
        run_vid_rnn(argc, argv);
    } else if (0 == strcmp(argv[1], "coco")){
        run_coco(argc, argv);
    } else if (0 == strcmp(argv[1], "classifier")){
        run_classifier(argc, argv);
    } else if (0 == strcmp(argv[1], "art")){
        run_art(argc, argv);
    } else if (0 == strcmp(argv[1], "tag")){
        run_tag(argc, argv);
    } else if (0 == strcmp(argv[1], "compare")){
        run_compare(argc, argv);
    } else if (0 == strcmp(argv[1], "dice")){
        run_dice(argc, argv);
    } else if (0 == strcmp(argv[1], "writing")){
        run_writing(argc, argv);
    } else if (0 == strcmp(argv[1], "3d")){
        composite_3d(argv[2], argv[3], argv[4], (argc > 5) ? atof(argv[5]) : 0);
    } else if (0 == strcmp(argv[1], "test")){
        test_resize(argv[2]);
    } else if (0 == strcmp(argv[1], "captcha")){
        run_captcha(argc, argv);
    } else if (0 == strcmp(argv[1], "nightmare")){
        run_nightmare(argc, argv);
    } else if (0 == strcmp(argv[1], "change")){
        change_rate(argv[2], atof(argv[3]), (argc > 4) ? atof(argv[4]) : 0);
    } else if (0 == strcmp(argv[1], "rgbgr")){
        rgbgr_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "reset")){
        reset_normalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "denormalize")){
        denormalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "normalize")){
        normalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "rescale")){
        rescale_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "ops")){
        operations(argv[2]);
    } else if (0 == strcmp(argv[1], "speed")){
        speed(argv[2], (argc > 3) ? atoi(argv[3]) : 0);
    } else if (0 == strcmp(argv[1], "partial")){
        partial(argv[2], argv[3], argv[4], atoi(argv[5]));
    } else if (0 == strcmp(argv[1], "average")){
        average(argc, argv);
    } else if (0 == strcmp(argv[1], "stacked")){
        stacked(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "visualize")){
        visualize(argv[2], (argc > 3) ? argv[3] : 0);
    } else if (0 == strcmp(argv[1], "imtest")){
        test_resize(argv[2]);
    } else {
        fprintf(stderr, "Not an option: %s\n", argv[1]);
    }
    return 0;
}