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\example\darknet.c中需要调用\example\xxx1.c中的函数, 则需要在\example\darknet.c加extern字段
多文件的实现方式(头文件的使用)
在本项目中, \includes\darknet.h是\examples中文件的头文件, 而在\includes\darknet.h中, 又对部分函数(例如 void )进行了声明, 但是 forward_network
举例
对于 ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
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)/*View Code
关于vpath,参考
(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\n");
fclose(fp);
}View Code
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\examples\classifier.c中
extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen); // 在\examples\detector.c中
extern void run_yolo(int argc, char **argv); // 在\examples\yolo.c中
extern void run_detector(int argc, char **argv); // 在\examples\detector.c中
extern void run_coco(int argc, char **argv); // 在\examples\coco.c中
extern void run_captcha(int argc, char **argv); // 在\examples\captcha.c中
extern void run_nightmare(int argc, char **argv); // 在\examples\nightmare.c中
extern void run_classifier(int argc, char **argv); // 在\examples\classifier.c中
extern void run_regressor(int argc, char **argv); // 在\examples\regressor.c中
extern void run_segmenter(int argc, char **argv); // 在\examples\segmenter.c中
extern void run_char_rnn(int argc, char **argv); // 在\examples\rnn.c中
extern void run_tag(int argc, char **argv); // 在\examples\tag.c中
extern void run_cifar(int argc, char **argv); // 在\examples\fun_cifar.c中
extern void run_go(int argc, char **argv); // 在\examples\go.c中
extern void run_art(int argc, char **argv); // 在\examples\art.c中
extern void run_super(int argc, char **argv); // 在\examples\super.c中
extern void run_lsd(int argc, char **argv); // 在\examples\nightmare.c中
extern void output_to_file(); // 在\examples\my_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("\n%d evals, %f Seconds\n", tics, t);
printf("Floating Point Operations: %.2f Bn\n", (float)ops/1000000000.);
printf("FLOPS: %.2f Bn\n", (float)ops/1000000000.*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);
long ops = numops(net);
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;
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);
}
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("\n");
//printf("]%s\n", (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\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 = 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>\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
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\src\utils.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\n", argv[1]);
}
return 0;
}View Code
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) $(OBJDIR)/*View Code
编译并可成功运行.
(2)修改代码的第二次尝试
在\src目录下新建my_testinsrc.c以及my_testinsrc.h, 内容如下
// my_testinsrc.h
#include "darknet.h"
// my_testinsrc.c
#include <stdio.h>
void my_testinsrc(){
printf("test in src\n");
}View Code
修改Makefile, 在最后声明新加的函数
修改后内容如下
GPU=0
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0
ARCH= -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=[sm_50,compute_50] \
-gencode arch=compute_52,code=[sm_52,compute_52]
# -gencode arch=compute_20,code=[sm_20,sm_21] \ This one is deprecated?
# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52
VPATH=./src/:./examples
# VTATH用来告诉make,源文件的路径, 参考https://blog.csdn.net/mcgrady_tracy/article/details/27240139
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/
CC=gcc
NVCC=nvcc
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread #gcc等编译器会用到的一些优化参数，也可以在里面指定库文件的位置
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC #指定头文件（.h文件）的路径，如：CFLAGS=-I/usr/include -I/path/include。
ifeq ($(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)/*View Code
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\examples\classifier.c中
extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen); // 在\examples\detector.c中
extern void run_yolo(int argc, char **argv); // 在\examples\yolo.c中
extern void run_detector(int argc, char **argv); // 在\examples\detector.c中
extern void run_coco(int argc, char **argv); // 在\examples\coco.c中
extern void run_captcha(int argc, char **argv); // 在\examples\captcha.c中
extern void run_nightmare(int argc, char **argv); // 在\examples\nightmare.c中
extern void run_classifier(int argc, char **argv); // 在\examples\classifier.c中
extern void run_regressor(int argc, char **argv); // 在\examples\regressor.c中
extern void run_segmenter(int argc, char **argv); // 在\examples\segmenter.c中
extern void run_char_rnn(int argc, char **argv); // 在\examples\rnn.c中
extern void run_tag(int argc, char **argv); // 在\examples\tag.c中
extern void run_cifar(int argc, char **argv); // 在\examples\fun_cifar.c中
extern void run_go(int argc, char **argv); // 在\examples\go.c中
extern void run_art(int argc, char **argv); // 在\examples\art.c中
extern void run_super(int argc, char **argv); // 在\examples\super.c中
extern void run_lsd(int argc, char **argv); // 在\examples\nightmare.c中
extern void output_to_file(); // 在\examples\my_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("\n%d evals, %f Seconds\n", tics, t);
printf("Floating Point Operations: %.2f Bn\n", (float)ops/1000000000.);
printf("FLOPS: %.2f Bn\n", (float)ops/1000000000.*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);
long ops = numops(net);
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;
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);
}
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("\n");
//printf("]%s\n", (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\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 = 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>\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
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\src\utils.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\n", argv[1]);
}
return 0;
}View Code
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\n");
}View Code
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
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)/*View Code
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
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
