yolo源码解析(1):代码逻辑

一. 整体代码逻辑

yolo中源码分为三个部分,example,include,以及src文件夹下都有源代码存在.

结构如下所示

├── examples
│   ├── darknet.c(主程序)
│   │── xxx1.c
│   └── xxx2.c
│
├── include
│   ├── darknet.h
│ 
│ 
├── Makefile
│ 
│ 
└── src
    ├── yyy1.c
    ├── yyy2.h
    └──......

include文件夹中没有.h头文件, 里边的内容算作一个整体, 都是darknet.c中的一部分, 每个文件的内容共darknet.c调用, 除了darknet.c外, include文件夹中的文件不存在互相调用, 各自完成不同的功能,如检测视频, 检测图片, 检测艺术品等, 通过darknet.c中的if条件进行选择调用. 因为这部分算作一个整体, 所以共用darknet.h这个头文件. 如果include需要用到src中的函数, 则在darknet.h中进行声明

在src文件夹中, 每个c文件都对应一个同名的.h头文件; main函数存在于example文件夹下的darknet.c文件中.

include文件夹下的darknet.h的作用是联系example与src两部分, 在这两部分中都需要用的函数则在darknet.h中进行声明, 例如example中有xxx1.c, src中有yyy1.c及yyy1.h, xxx1.c与yyy1.c中都需要用到func()这个函数, 那么func()的声明需要放在darknet.h中, 然后在xxx1.c与yyy1.h分别引入头文件#include "darknet.h"

而如果exampledarknet.c中需要调用examplexxx1.c中的函数, 则需要在exampledarknet.c加extern字段

多文件的实现方式(头文件的使用)

在本项目中, includesdarknet.h是examples中文件的头文件, 而在includesdarknet.h中, 又对部分函数(例如 void forward_network(network *net); )进行了声明, 但是 forward_network 函数的定义是在src etwork.c中, 因为定义是在src中, 所以定义时src中的文件需要引入darknet.h这个头文件; 由此, examples中的文件便可通过darknet.h中的声明调用src中的函数了

举例

对于 ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg 这条命令,首先传送到darknet.c文件, 然后darknet.c文件检测到含有detect字符, 所以进入if语句. 使用srcutils.c中的find_char_arg函数来获取输出文件名等信息, 然后调用detector.c文件中的test_detector函数, 该函数负责检测并进行输出.

二. main函数

 唉唉唉

三. makefile文件

入门见<并行程序设计(第四版)>

以yolo源码中的makefile文件为例

GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0

ARCH= -gencode arch=compute_30,code=sm_30 
      -gencode arch=compute_35,code=sm_35 
      -gencode arch=compute_50,code=[sm_50,compute_50] 
      -gencode arch=compute_52,code=[sm_52,compute_52]
#      -gencode arch=compute_20,code=[sm_20,sm_21]  This one is deprecated?

# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52

VPATH=./src/:./examples
# VTATH用来告诉make,源文件的路径, 参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/

CC=gcc
NVCC=nvcc 
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread       #gcc等编译器会用到的一些优化参数，也可以在里面指定库文件的位置
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC   #指定头文件（.h文件）的路径，如：CFLAGS=-I/usr/include -I/path/include。

ifeq ($(OPENMP), 1) 
CFLAGS+= -fopenmp
endif

ifeq ($(DEBUG), 1) 
OPTS=-O0 -g
endif

CFLAGS+=$(OPTS)

ifeq ($(OPENCV), 1) 
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv` 
COMMON+= `pkg-config --cflags opencv` 
endif

ifeq ($(GPU), 1) 
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif

ifeq ($(CUDNN), 1) 
COMMON+= -DCUDNN 
CFLAGS+= -DCUDNN
LDFLAGS+= -lcudnn
endif

OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o l2norm_layer.o yolo_layer.o
EXECOBJA=my_test.o  captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o darknet.o
ifeq ($(GPU), 1) 
LDFLAGS+= -lstdc++ 
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o avgpool_layer_kernels.o
endif

EXECOBJ = $(addprefix $(OBJDIR), $(EXECOBJA))   #加前缀函数: $(addprefix <prefix>,<names...>),OBJDIR是obj存放的地址
OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

#all: obj backup results $(SLIB) $(ALIB) $(EXEC)
all: obj  results $(SLIB) $(ALIB) $(EXEC)


$(EXEC): $(EXECOBJ) $(ALIB)
    $(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS) $(ALIB)

$(ALIB): $(OBJS)
    $(AR) $(ARFLAGS) $@ $^

$(SLIB): $(OBJS)
    $(CC) $(CFLAGS) -shared $^ -o $@ $(LDFLAGS)

$(OBJDIR)%.o: %.c $(DEPS)
    $(CC) $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cu $(DEPS)
    $(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@

obj:
    mkdir -p obj
backup:
    mkdir -p backup
results:
    mkdir -p results

.PHONY: clean

clean:
    rm -rf $(OBJS) $(SLIB) $(ALIB) $(EXEC) $(EXECOBJ) $(OBJDIR)/*

关于vpath,参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139

(1)修改代码的第一次尝试

在examples文件夹下新建my_test.c文件, 内容如下

#include "darknet.h"

void output_to_file()
{
    FILE *fp;
    fp=fopen("output.txt","w");
    fprintf(fp,"adfsss");
    printf("test
");
    fclose(fp);
}

在darknet.c中进行调用, 如下

#include "darknet.h"

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

extern void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top);     // 在examplesclassifier.c中
extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen);     // 在examplesdetector.c中
extern void run_yolo(int argc, char **argv);     // 在examplesyolo.c中
extern void run_detector(int argc, char **argv);     // 在examplesdetector.c中
extern void run_coco(int argc, char **argv);         // 在examplescoco.c中
extern void run_captcha(int argc, char **argv);      // 在examplescaptcha.c中
extern void run_nightmare(int argc, char **argv);        // 在examples
ightmare.c中
extern void run_classifier(int argc, char **argv);       // 在examplesclassifier.c中
extern void run_regressor(int argc, char **argv);        // 在examples
egressor.c中
extern void run_segmenter(int argc, char **argv);        // 在examplessegmenter.c中
extern void run_char_rnn(int argc, char **argv);         // 在examples
nn.c中
extern void run_tag(int argc, char **argv);              // 在examples	ag.c中
extern void run_cifar(int argc, char **argv);            // 在examplesfun_cifar.c中
extern void run_go(int argc, char **argv);               // 在examplesgo.c中
extern void run_art(int argc, char **argv);              // 在examplesart.c中
extern void run_super(int argc, char **argv);            // 在examplessuper.c中
extern void run_lsd(int argc, char **argv);              // 在examples
ightmare.c中
extern void output_to_file();              // 在examplesmy_test.c中

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);
}

long numops(network *net)
{
    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.groups * l.out_h*l.out_w;
        } else if(l.type == CONNECTED){
            ops += 2l * l.inputs * l.outputs;
        } else if (l.type == RNN){
            ops += 2l * l.input_layer->inputs * l.input_layer->outputs;
            ops += 2l * l.self_layer->inputs * l.self_layer->outputs;
            ops += 2l * l.output_layer->inputs * l.output_layer->outputs;
        } else if (l.type == GRU){
            ops += 2l * l.uz->inputs * l.uz->outputs;
            ops += 2l * l.uh->inputs * l.uh->outputs;
            ops += 2l * l.ur->inputs * l.ur->outputs;
            ops += 2l * l.wz->inputs * l.wz->outputs;
            ops += 2l * l.wh->inputs * l.wh->outputs;
            ops += 2l * l.wr->inputs * l.wr->outputs;
        } else if (l.type == LSTM){
            ops += 2l * l.uf->inputs * l.uf->outputs;
            ops += 2l * l.ui->inputs * l.ui->outputs;
            ops += 2l * l.ug->inputs * l.ug->outputs;
            ops += 2l * l.uo->inputs * l.uo->outputs;
            ops += 2l * l.wf->inputs * l.wf->outputs;
            ops += 2l * l.wi->inputs * l.wi->outputs;
            ops += 2l * l.wg->inputs * l.wg->outputs;
            ops += 2l * l.wo->inputs * l.wo->outputs;
        }
    }
    return ops;
}

void speed(char *cfgfile, int tics)
{
    if (tics == 0) tics = 1000;
    network *net = parse_network_cfg(cfgfile);
    set_batch_network(net, 1);
    int i;
    double time=what_time_is_it_now();
    image im = make_image(net->w, net->h, net->c*net->batch);
    for(i = 0; i < tics; ++i){
        network_predict(net, im.data);
    }
    double t = what_time_is_it_now() - time;
    long ops = numops(net);
    printf("
%d evals, %f Seconds
", tics, t);
    printf("Floating Point Operations: %.2f Bn
", (float)ops/1000000000.);
    printf("FLOPS: %.2f Bn
", (float)ops/1000000000.*tics/t);
    printf("Speed: %f sec/eval
", t/tics);
    printf("Speed: %f Hz
", tics/t);
}

void operations(char *cfgfile)
{
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    long ops = numops(net);
    printf("Floating Point Operations: %ld
", ops);
    printf("Floating Point Operations: %.2f Bn
", (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;
    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
", 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 oneoff2(char *cfgfile, char *weightfile, char *outfile, int l)
{
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights_upto(net, weightfile, 0, net->n);
        load_weights_upto(net, weightfile, l, net->n);
    }
    *net->seen = 0;
    save_weights_upto(net, outfile, net->n);
}

void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 1);
    save_weights_upto(net, outfile, max);
}

void print_weights(char *cfgfile, char *weightfile, int n)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 1);
    layer l = net->layers[n];
    int i, j;
    //printf("[");
    for(i = 0; i < l.n; ++i){
        //printf("[");
        for(j = 0; j < l.size*l.size*l.c; ++j){
            //if(j > 0) printf(",");
            printf("%g ", l.weights[i*l.size*l.size*l.c + j]);
        }
        printf("
");
        //printf("]%s
", (i == l.n-1)?"":",");
    }
    //printf("]");
}

void rescale_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){
            rescale_weights(l, 2, -.5);
            break;
        }
    }
    save_weights(net, outfile);
}

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);
}

void reset_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) {
            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 = 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);
}

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

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);
}

void mkimg(char *cfgfile, char *weightfile, int h, int w, int num, char *prefix)
{
    network *net = load_network(cfgfile, weightfile, 0);
    image *ims = get_weights(net->layers[0]);
    int n = net->layers[0].n;
    int z;
    for(z = 0; z < num; ++z){
        image im = make_image(h, w, 3);
        fill_image(im, .5);
        int i;
        for(i = 0; i < 100; ++i){
            image r = copy_image(ims[rand()%n]);
            rotate_image_cw(r, rand()%4);
            random_distort_image(r, 1, 1.5, 1.5);
            int dx = rand()%(w-r.w);
            int dy = rand()%(h-r.h);
            ghost_image(r, im, dx, dy);
            free_image(r);
        }
        char buff[256];
        sprintf(buff, "%s/gen_%d", prefix, z);
        save_image(im, buff);
        free_image(im);
    }
}

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

int main(int argc, char **argv)
{
    // argv[0] 指向程序运行的全路径名;argv[1] 指向在DOS命令行中执行程序名后的第一个字符串;argv[2]第二个
    //test_resize("data/bad.jpg");
    //test_box();
    //test_convolutional_layer();
    if(argc < 2){
        fprintf(stderr, "usage: %s <function>
", 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

    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], "super")){
        run_super(argc, argv);
    } else if (0 == strcmp(argv[1], "lsd")){
        run_lsd(argc, argv);
    } else if (0 == strcmp(argv[1], "detector")){
        run_detector(argc, argv);
    } else if (0 == strcmp(argv[1], "detect")){
        float thresh = find_float_arg(argc, argv, "-thresh", .5);       //thresh用来控制检测的阈值
        char *filename = (argc > 4) ? argv[4]: 0;
        char *outfile = find_char_arg(argc, argv, "-out", 0);           // 定义在srcutils.c中
        int fullscreen = find_arg(argc, argv, "-fullscreen");
        test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, .5, outfile, fullscreen);      // 函数定义位于detector.c中
        // 命令举例./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

        //*修改//
        output_to_file();
        //*//

    } 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], "coco")){
        run_coco(argc, argv);
    } else if (0 == strcmp(argv[1], "classify")){
        predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
    } else if (0 == strcmp(argv[1], "classifier")){
        run_classifier(argc, argv);
    } else if (0 == strcmp(argv[1], "regressor")){
        run_regressor(argc, argv);
    } else if (0 == strcmp(argv[1], "segmenter")){
        run_segmenter(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], "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], "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], "statistics")){
        statistics_net(argv[2], argv[3]);
    } 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 && argv[3]) ? atoi(argv[3]) : 0);
    } else if (0 == strcmp(argv[1], "oneoff")){
        oneoff(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "oneoff2")){
        oneoff2(argv[2], argv[3], argv[4], atoi(argv[5]));
    } else if (0 == strcmp(argv[1], "print")){
        print_weights(argv[2], argv[3], atoi(argv[4]));
    } 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], "visualize")){
        visualize(argv[2], (argc > 3) ? argv[3] : 0);
    } else if (0 == strcmp(argv[1], "mkimg")){
        mkimg(argv[2], argv[3], atoi(argv[4]), atoi(argv[5]), atoi(argv[6]), argv[7]);
    } else if (0 == strcmp(argv[1], "imtest")){
        test_resize(argv[2]);
    } else {
        fprintf(stderr, "Not an option: %s
", argv[1]);
    }
    return 0;
}

然后修改Makefile文件, 在EXECOBJA=后追加my_test.o字段. 注意不可将该字段放在EXECOBJA=的最后, 否则编译不通过. 内容如下

GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0

ARCH= -gencode arch=compute_30,code=sm_30 
      -gencode arch=compute_35,code=sm_35 
      -gencode arch=compute_50,code=[sm_50,compute_50] 
      -gencode arch=compute_52,code=[sm_52,compute_52]
#      -gencode arch=compute_20,code=[sm_20,sm_21]  This one is deprecated?

# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52

VPATH=./src/:./examples
# VTATH用来告诉make,源文件的路径, 参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/

CC=gcc
NVCC=nvcc 
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread       #gcc等编译器会用到的一些优化参数，也可以在里面指定库文件的位置
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC   #指定头文件（.h文件）的路径，如：CFLAGS=-I/usr/include -I/path/include。

ifeq ($(OPENMP), 1) 
CFLAGS+= -fopenmp
endif

ifeq ($(DEBUG), 1) 
OPTS=-O0 -g
endif

CFLAGS+=$(OPTS)

ifeq ($(OPENCV), 1) 
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv` 
COMMON+= `pkg-config --cflags opencv` 
endif

ifeq ($(GPU), 1) 
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif

ifeq ($(CUDNN), 1) 
COMMON+= -DCUDNN 
CFLAGS+= -DCUDNN
LDFLAGS+= -lcudnn
endif

OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o l2norm_layer.o yolo_layer.o
EXECOBJA=my_test.o  captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o darknet.o
ifeq ($(GPU), 1) 
LDFLAGS+= -lstdc++ 
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o avgpool_layer_kernels.o
endif

EXECOBJ = $(addprefix $(OBJDIR), $(EXECOBJA))   #加前缀函数: $(addprefix <prefix>,<names...>),OBJDIR是obj存放的地址
OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

#all: obj backup results $(SLIB) $(ALIB) $(EXEC)
all: obj  results $(SLIB) $(ALIB) $(EXEC)


$(EXEC): $(EXECOBJ) $(ALIB)
    $(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS) $(ALIB)

$(ALIB): $(OBJS)
    $(AR) $(ARFLAGS) $@ $^

$(SLIB): $(OBJS)
    $(CC) $(CFLAGS) -shared $^ -o $@ $(LDFLAGS)

$(OBJDIR)%.o: %.c $(DEPS)
    $(CC) $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cu $(DEPS)
    $(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@

obj:
    mkdir -p obj
backup:
    mkdir -p backup
results:
    mkdir -p results

.PHONY: clean

clean:
    rm -rf $(OBJS) $(SLIB) $(ALIB) $(EXEC) $(EXECOBJ) $(OBJDIR)/*

编译并可成功运行.

 (2)修改代码的第二次尝试

在src目录下新建my_testinsrc.c以及my_testinsrc.h, 内容如下

// my_testinsrc.h
#include "darknet.h"



// my_testinsrc.c
#include <stdio.h>
void my_testinsrc(){
    printf("test in src
");
}

修改Makefile, 在最后声明新加的函数

修改后内容如下

GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0

ARCH= -gencode arch=compute_30,code=sm_30 
      -gencode arch=compute_35,code=sm_35 
      -gencode arch=compute_50,code=[sm_50,compute_50] 
      -gencode arch=compute_52,code=[sm_52,compute_52]
#      -gencode arch=compute_20,code=[sm_20,sm_21]  This one is deprecated?

# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52

VPATH=./src/:./examples
# VTATH用来告诉make,源文件的路径, 参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/

CC=gcc
NVCC=nvcc 
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread       #gcc等编译器会用到的一些优化参数，也可以在里面指定库文件的位置
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC   #指定头文件（.h文件）的路径，如：CFLAGS=-I/usr/include -I/path/include。

ifeq ($(OPENMP), 1) 
CFLAGS+= -fopenmp
endif

ifeq ($(DEBUG), 1) 
OPTS=-O0 -g
endif

CFLAGS+=$(OPTS)

ifeq ($(OPENCV), 1) 
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv` 
COMMON+= `pkg-config --cflags opencv` 
endif

ifeq ($(GPU), 1) 
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif

ifeq ($(CUDNN), 1) 
COMMON+= -DCUDNN 
CFLAGS+= -DCUDNN
LDFLAGS+= -lcudnn
endif

OBJ=my_testinsrc.o  gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o l2norm_layer.o yolo_layer.o
EXECOBJA=my_test.o  captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o darknet.o
ifeq ($(GPU), 1) 
LDFLAGS+= -lstdc++ 
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o avgpool_layer_kernels.o
endif

EXECOBJ = $(addprefix $(OBJDIR), $(EXECOBJA))   #加前缀函数: $(addprefix <prefix>,<names...>),OBJDIR是obj存放的地址
OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

#all: obj backup results $(SLIB) $(ALIB) $(EXEC)
all: obj  results $(SLIB) $(ALIB) $(EXEC)


$(EXEC): $(EXECOBJ) $(ALIB)
    $(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS) $(ALIB)

$(ALIB): $(OBJS)
    $(AR) $(ARFLAGS) $@ $^

$(SLIB): $(OBJS)
    $(CC) $(CFLAGS) -shared $^ -o $@ $(LDFLAGS)

$(OBJDIR)%.o: %.c $(DEPS)
    $(CC) $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cu $(DEPS)
    $(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@

obj:
    mkdir -p obj
backup:
    mkdir -p backup
results:
    mkdir -p results

.PHONY: clean

clean:
    rm -rf $(OBJS) $(SLIB) $(ALIB) $(EXEC) $(EXECOBJ) $(OBJDIR)/*

在darknet.c中进行调用, 内容如下

#include "darknet.h"

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

extern void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top);     // 在examplesclassifier.c中
extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen);     // 在examplesdetector.c中
extern void run_yolo(int argc, char **argv);     // 在examplesyolo.c中
extern void run_detector(int argc, char **argv);     // 在examplesdetector.c中
extern void run_coco(int argc, char **argv);         // 在examplescoco.c中
extern void run_captcha(int argc, char **argv);      // 在examplescaptcha.c中
extern void run_nightmare(int argc, char **argv);        // 在examples
ightmare.c中
extern void run_classifier(int argc, char **argv);       // 在examplesclassifier.c中
extern void run_regressor(int argc, char **argv);        // 在examples
egressor.c中
extern void run_segmenter(int argc, char **argv);        // 在examplessegmenter.c中
extern void run_char_rnn(int argc, char **argv);         // 在examples
nn.c中
extern void run_tag(int argc, char **argv);              // 在examples	ag.c中
extern void run_cifar(int argc, char **argv);            // 在examplesfun_cifar.c中
extern void run_go(int argc, char **argv);               // 在examplesgo.c中
extern void run_art(int argc, char **argv);              // 在examplesart.c中
extern void run_super(int argc, char **argv);            // 在examplessuper.c中
extern void run_lsd(int argc, char **argv);              // 在examples
ightmare.c中
extern void output_to_file();              // 在examplesmy_test.c中

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);
}

long numops(network *net)
{
    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.groups * l.out_h*l.out_w;
        } else if(l.type == CONNECTED){
            ops += 2l * l.inputs * l.outputs;
        } else if (l.type == RNN){
            ops += 2l * l.input_layer->inputs * l.input_layer->outputs;
            ops += 2l * l.self_layer->inputs * l.self_layer->outputs;
            ops += 2l * l.output_layer->inputs * l.output_layer->outputs;
        } else if (l.type == GRU){
            ops += 2l * l.uz->inputs * l.uz->outputs;
            ops += 2l * l.uh->inputs * l.uh->outputs;
            ops += 2l * l.ur->inputs * l.ur->outputs;
            ops += 2l * l.wz->inputs * l.wz->outputs;
            ops += 2l * l.wh->inputs * l.wh->outputs;
            ops += 2l * l.wr->inputs * l.wr->outputs;
        } else if (l.type == LSTM){
            ops += 2l * l.uf->inputs * l.uf->outputs;
            ops += 2l * l.ui->inputs * l.ui->outputs;
            ops += 2l * l.ug->inputs * l.ug->outputs;
            ops += 2l * l.uo->inputs * l.uo->outputs;
            ops += 2l * l.wf->inputs * l.wf->outputs;
            ops += 2l * l.wi->inputs * l.wi->outputs;
            ops += 2l * l.wg->inputs * l.wg->outputs;
            ops += 2l * l.wo->inputs * l.wo->outputs;
        }
    }
    return ops;
}

void speed(char *cfgfile, int tics)
{
    if (tics == 0) tics = 1000;
    network *net = parse_network_cfg(cfgfile);
    set_batch_network(net, 1);
    int i;
    double time=what_time_is_it_now();
    image im = make_image(net->w, net->h, net->c*net->batch);
    for(i = 0; i < tics; ++i){
        network_predict(net, im.data);
    }
    double t = what_time_is_it_now() - time;
    long ops = numops(net);
    printf("
%d evals, %f Seconds
", tics, t);
    printf("Floating Point Operations: %.2f Bn
", (float)ops/1000000000.);
    printf("FLOPS: %.2f Bn
", (float)ops/1000000000.*tics/t);
    printf("Speed: %f sec/eval
", t/tics);
    printf("Speed: %f Hz
", tics/t);
}

void operations(char *cfgfile)
{
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    long ops = numops(net);
    printf("Floating Point Operations: %ld
", ops);
    printf("Floating Point Operations: %.2f Bn
", (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;
    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
", 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 oneoff2(char *cfgfile, char *weightfile, char *outfile, int l)
{
    gpu_index = -1;
    network *net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights_upto(net, weightfile, 0, net->n);
        load_weights_upto(net, weightfile, l, net->n);
    }
    *net->seen = 0;
    save_weights_upto(net, outfile, net->n);
}

void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 1);
    save_weights_upto(net, outfile, max);
}

void print_weights(char *cfgfile, char *weightfile, int n)
{
    gpu_index = -1;
    network *net = load_network(cfgfile, weightfile, 1);
    layer l = net->layers[n];
    int i, j;
    //printf("[");
    for(i = 0; i < l.n; ++i){
        //printf("[");
        for(j = 0; j < l.size*l.size*l.c; ++j){
            //if(j > 0) printf(",");
            printf("%g ", l.weights[i*l.size*l.size*l.c + j]);
        }
        printf("
");
        //printf("]%s
", (i == l.n-1)?"":",");
    }
    //printf("]");
}

void rescale_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){
            rescale_weights(l, 2, -.5);
            break;
        }
    }
    save_weights(net, outfile);
}

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);
}

void reset_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) {
            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 = 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);
}

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

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);
}

void mkimg(char *cfgfile, char *weightfile, int h, int w, int num, char *prefix)
{
    network *net = load_network(cfgfile, weightfile, 0);
    image *ims = get_weights(net->layers[0]);
    int n = net->layers[0].n;
    int z;
    for(z = 0; z < num; ++z){
        image im = make_image(h, w, 3);
        fill_image(im, .5);
        int i;
        for(i = 0; i < 100; ++i){
            image r = copy_image(ims[rand()%n]);
            rotate_image_cw(r, rand()%4);
            random_distort_image(r, 1, 1.5, 1.5);
            int dx = rand()%(w-r.w);
            int dy = rand()%(h-r.h);
            ghost_image(r, im, dx, dy);
            free_image(r);
        }
        char buff[256];
        sprintf(buff, "%s/gen_%d", prefix, z);
        save_image(im, buff);
        free_image(im);
    }
}

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

int main(int argc, char **argv)
{
    // argv[0] 指向程序运行的全路径名;argv[1] 指向在DOS命令行中执行程序名后的第一个字符串;argv[2]第二个
    //test_resize("data/bad.jpg");
    //test_box();
    //test_convolutional_layer();
    if(argc < 2){
        fprintf(stderr, "usage: %s <function>
", 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

    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], "super")){
        run_super(argc, argv);
    } else if (0 == strcmp(argv[1], "lsd")){
        run_lsd(argc, argv);
    } else if (0 == strcmp(argv[1], "detector")){
        run_detector(argc, argv);
    } else if (0 == strcmp(argv[1], "detect")){
        float thresh = find_float_arg(argc, argv, "-thresh", .5);       //thresh用来控制检测的阈值
        char *filename = (argc > 4) ? argv[4]: 0;
        char *outfile = find_char_arg(argc, argv, "-out", 0);           // 定义在srcutils.c中
        int fullscreen = find_arg(argc, argv, "-fullscreen");
        test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, .5, outfile, fullscreen);      // 函数定义位于detector.c中
        // 命令举例./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

        //*修改//
        //output_to_file();
        my_testinsrc();
        //*//

    } 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], "coco")){
        run_coco(argc, argv);
    } else if (0 == strcmp(argv[1], "classify")){
        predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
    } else if (0 == strcmp(argv[1], "classifier")){
        run_classifier(argc, argv);
    } else if (0 == strcmp(argv[1], "regressor")){
        run_regressor(argc, argv);
    } else if (0 == strcmp(argv[1], "segmenter")){
        run_segmenter(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], "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], "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], "statistics")){
        statistics_net(argv[2], argv[3]);
    } 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 && argv[3]) ? atoi(argv[3]) : 0);
    } else if (0 == strcmp(argv[1], "oneoff")){
        oneoff(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "oneoff2")){
        oneoff2(argv[2], argv[3], argv[4], atoi(argv[5]));
    } else if (0 == strcmp(argv[1], "print")){
        print_weights(argv[2], argv[3], atoi(argv[4]));
    } 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], "visualize")){
        visualize(argv[2], (argc > 3) ? argv[3] : 0);
    } else if (0 == strcmp(argv[1], "mkimg")){
        mkimg(argv[2], argv[3], atoi(argv[4]), atoi(argv[5]), atoi(argv[6]), argv[7]);
    } else if (0 == strcmp(argv[1], "imtest")){
        test_resize(argv[2]);
    } else {
        fprintf(stderr, "Not an option: %s
", argv[1]);
    }
    return 0;
}

可成功编译并运行

(3)修改代码的第三次尝试

在darknet下新建目录my, 用于存放自己新写的代码. 新建两个文件my_tofile.c与my_file.h, 其内容如下

//my_tofile.h

#ifndef TOFILE
#define TOFLIE
#include "darknet.h"

void my_output_to_file();


#endif


// my_tofile.c
#include "my_tofile.h"

void my_output_to_file()
{
    FILE *fp;
    fp=fopen("output.txt","w");
    fprintf(fp,"adfsss");
    fclose(fp);
    printf("test in \my
");
}

修改Makefile文件, 在最后对函数进行声明, 在VPATH处添加路径 VPATH=./src/:./examples:./my , 修改完后内容如下

GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0

ARCH= -gencode arch=compute_30,code=sm_30 
      -gencode arch=compute_35,code=sm_35 
      -gencode arch=compute_50,code=[sm_50,compute_50] 
      -gencode arch=compute_52,code=[sm_52,compute_52]
#      -gencode arch=compute_20,code=[sm_20,sm_21]  This one is deprecated?

# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52

VPATH=./src/:./examples:./my
# VTATH用来告诉make,源文件的路径, 参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/

CC=gcc
NVCC=nvcc 
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread       #gcc等编译器会用到的一些优化参数，也可以在里面指定库文件的位置
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC   #指定头文件（.h文件）的路径，如：CFLAGS=-I/usr/include -I/path/include。

ifeq ($(OPENMP), 1) 
CFLAGS+= -fopenmp
endif

ifeq ($(DEBUG), 1) 
OPTS=-O0 -g
endif

CFLAGS+=$(OPTS)

ifeq ($(OPENCV), 1) 
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv` 
COMMON+= `pkg-config --cflags opencv` 
endif

ifeq ($(GPU), 1) 
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif

ifeq ($(CUDNN), 1) 
COMMON+= -DCUDNN 
CFLAGS+= -DCUDNN
LDFLAGS+= -lcudnn
endif

OBJ=my_tofile.o    my_testinsrc.o  gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o l2norm_layer.o yolo_layer.o
EXECOBJA=my_test.o  captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o darknet.o
ifeq ($(GPU), 1) 
LDFLAGS+= -lstdc++ 
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o avgpool_layer_kernels.o
endif

EXECOBJ = $(addprefix $(OBJDIR), $(EXECOBJA))   #加前缀函数: $(addprefix <prefix>,<names...>),OBJDIR是obj存放的地址
OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

#all: obj backup results $(SLIB) $(ALIB) $(EXEC)
all: obj  results $(SLIB) $(ALIB) $(EXEC)


$(EXEC): $(EXECOBJ) $(ALIB)
    $(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS) $(ALIB)

$(ALIB): $(OBJS)
    $(AR) $(ARFLAGS) $@ $^

$(SLIB): $(OBJS)
    $(CC) $(CFLAGS) -shared $^ -o $@ $(LDFLAGS)

$(OBJDIR)%.o: %.c $(DEPS)
    $(CC) $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cu $(DEPS)
    $(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@

obj:
    mkdir -p obj
backup:
    mkdir -p backup
results:
    mkdir -p results

.PHONY: clean

clean:
    rm -rf $(OBJS) $(SLIB) $(ALIB) $(EXEC) $(EXECOBJ) $(OBJDIR)/*

最后在exampes中的文件中进行调用, 可顺利编译并运行

├── examples
│   ├── darknet.c(主程序)
│   │── xxx1.c
│   └── xxx2.c
│
├── include
│   ├── darknet.h
│ 
│ 
├── Makefile
│
├── my
│   ├── my_zzz1.c
│   │── my_zzz1.h
│   └── ......
│ 
└── src
    ├── yyy1.c
    ├── yyy2.h
    └──......

最终代码结构会如下所示