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 forward_network(network *net); )进行了声明, 但是 forward_network 函数的定义是在\src\network.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\src\utils.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\n"); 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\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