darknet.c

Go to the documentation of this file.

#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 predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top);
extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh);
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 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 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 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;
    net.layers[net.n - 2].n = 9372;
    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);
}

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);
}

#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_weights(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_weights(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 statistics_net(char *cfgfile, char *weightfile)
{
    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 == CONNECTED && l.batch_normalize) {
            printf("Connected Layer %d\n", i);
            statistics_connected_layer(l);
        }
        if (l.type == GRU && l.batch_normalize) {
            printf("GRU Layer %d\n", i);
            printf("Input Z\n");
            statistics_connected_layer(*l.input_z_layer);
            printf("Input R\n");
            statistics_connected_layer(*l.input_r_layer);
            printf("Input H\n");
            statistics_connected_layer(*l.input_h_layer);
            printf("State Z\n");
            statistics_connected_layer(*l.state_z_layer);
            printf("State R\n");
            statistics_connected_layer(*l.state_r_layer);
            printf("State H\n");
            statistics_connected_layer(*l.state_h_layer);
        }
        printf("\n");
    }
}

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){
        cuda_set_device(gpu_index);
    }
#endif
    float thresh = find_float_arg(argc, argv, "-thresh", .25);
    char *filename = (argc > 1) ? argv[1]: 0;
    test_detector("cfg/coco.data", "cfg/yolo.cfg", "yolo.weights", filename, thresh);
    return 0;
}