darknet 版本yolo v1 - v4 编译及环境配置 Ubuntu18.04

darknet训练自己的数据

一. 电脑环境

1. GPU: 1080TI
2. CUDA:10.0
3. tensorflow:1.14.0
4. keras:2.3.1
5. Ubuntu18.04

CUDA CUDNN等具体安装步骤见: https://blog.csdn.net/qq_28949847/article/details/110122179

二. github网址

https://github.com/AlexeyAB/darknet

三.环境配置

步骤:

1. cd darknet
2. gedit Makefile # 打开makefile文件
3. 修改makefile文件中的内容
'''
#是否需要gpu，如果没有卡就设置为0吧
GPU=1 
CUDNN=1 #同上
CUDNN_HALF=0
OPENCV=1 #如果没有安装opencv>2.4，或者设置为1编译报错，这里设置为0
'''
#编译
4. make -j8

这样如果编译成功，会在当前路径下生成可执行darknet文件.然后会有一个build目录(编译产生的各种结果都在里面，而且我后面的训练数据权重上面的都在build下面，因美味这样把源码隔开了，有好处。官方教程中也建议把制作好的数据集也放到里面)，为了简单的测试一下,先下载好yolov4训练好的权重(看readme)。然找个目录放好。在终端执行:

./darknet detector test cfg/coco.data yolov4.cfg yolov4.weights -ext_output data/dog.jpg
# 注意yolov4.weights 等文件的位置

四.安装过程中踩过的坑:

1. 遇到的报错:
   
   Make总是报错
   Makefile:186:recipe for target ‘obj/network_kernels.o’ failed
   往上看报错信息发现两个error都是network_kernels.o
   cudaStreamCaorureModeGlobal没有定义，function多了一个参数，两句报错都在同一行，在网上查了一圈都没查到有人报这个错，所以直接去obj文件夹里找network_kernels.o看源码
   
   CHECK_CUDA(cudaStreamBeginCapture(stream0,cudaStreamCaptureModeGlobal));
   不知道是不是版本问题，所以函数定义不太一样，我直接把fuction里的cudaStreamCaptureModeGlobal参数删掉之后，就可以正常Make了。

查找问题中,有些博客提到需要修改下面这些内容, 但是自己尝试后问题并没有解决, 也许跟电脑本身的设置有写关系, 后续遇到安装失败,可尝试下面这些方法:
2. 修改makefile
NVCC = /usr/local/cuda-10.0/bin/nvcc
并将makefile中带有cuda的路径都改为自己的cuda版本
参考:https://blog.csdn.net/qq_33869371/article/details/89260056

3. 修改环境变量
   参考: https://blog.csdn.net/zhaoyoulin2016/article/details/81626179

4. 修改makefile中的算力的
   参考: https://blog.csdn.net/weixin_43350700/article/details/109294554

5. $ python darknet_images.py Traceback (most recent call last): File "darknet_images.py", line 5, in <module> import darknet File "/home/wnj/Projects/darknet/darknet.py", line 225, in <module> "libdarknet.so"), RTLD_GLOBAL) File "/home/wnj/anaconda3/lib/python3.7/ctypes/__init__.py", line 356, in __init__ self._handle = _dlopen(self._name, mode) OSError: ./libdarknet.so: cannot open shared object file: No such file or directory
   解决办法：
   在Makefile文件中把LIBSO=0改成LIBSO=1，重新make
   注意： 每次make之前要进行make clean

个人完整的makefile文件

GPU=1
CUDNN=1
CUDNN_HALF=0
OPENCV=1
AVX=0
OPENMP=0
LIBSO=0
ZED_CAMERA=0
ZED_CAMERA_v2_8=0

# set GPU=1 and CUDNN=1 to speedup on GPU
# set CUDNN_HALF=1 to further speedup 3 x times (Mixed-precision on Tensor Cores) GPU: Volta, Xavier, Turing and higher
# set AVX=1 and OPENMP=1 to speedup on CPU (if error occurs then set AVX=0)
# set ZED_CAMERA=1 to enable ZED SDK 3.0 and above
# set ZED_CAMERA_v2_8=1 to enable ZED SDK 2.X

USE_CPP=0
DEBUG=0

ARCH= -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_61,code=[sm_61,compute_61]

OS := $(shell uname)

# GeForce RTX 3070, 3080, 3090
# ARCH= -gencode arch=compute_86,code=[sm_86,compute_86]

# Kepler GeForce GTX 770, GTX 760, GT 740
# ARCH= -gencode arch=compute_30,code=sm_30

# Tesla A100 (GA100), DGX-A100, RTX 3080
# ARCH= -gencode arch=compute_80,code=[sm_80,compute_80]

# Tesla V100
# ARCH= -gencode arch=compute_70,code=[sm_70,compute_70]

# GeForce RTX 2080 Ti, RTX 2080, RTX 2070, Quadro RTX 8000, Quadro RTX 6000, Quadro RTX 5000, Tesla T4, XNOR Tensor Cores
# ARCH= -gencode arch=compute_75,code=[sm_75,compute_75]

# Jetson XAVIER
# ARCH= -gencode arch=compute_72,code=[sm_72,compute_72]

# GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4
# ARCH= -gencode arch=compute_61,code=sm_61 -gencode arch=compute_61,code=compute_61

# GP100/Tesla P100 - DGX-1
# ARCH= -gencode arch=compute_60,code=sm_60

# For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment:
# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]

# For Jetson Tx2 or Drive-PX2 uncomment:
# ARCH= -gencode arch=compute_62,code=[sm_62,compute_62]

# For Tesla GA10x cards, RTX 3090, RTX 3080, RTX 3070, RTX A6000, RTX A40 uncomment:
# ARCH= -gencode arch=compute_86,code=[sm_86,compute_86]


VPATH=./src/
EXEC=darknet
OBJDIR=./obj/

ifeq ($(LIBSO), 1)
LIBNAMESO=libdarknet.so
APPNAMESO=uselib
endif

ifeq ($(USE_CPP), 1)
CC=g++
else
CC=gcc
endif

CPP=g++ -std=c++11
NVCC=/usr/local/cuda-10.0/bin/nvcc
OPTS=-Ofast
LDFLAGS= -lm -pthread
COMMON= -Iinclude/ -I3rdparty/stb/include
CFLAGS=-Wall -Wfatal-errors -Wno-unused-result -Wno-unknown-pragmas -fPIC

ifeq ($(DEBUG), 1)
#OPTS= -O0 -g
#OPTS= -Og -g
COMMON+= -DDEBUG
CFLAGS+= -DDEBUG
else
ifeq ($(AVX), 1)
CFLAGS+= -ffp-contract=fast -mavx -mavx2 -msse3 -msse4.1 -msse4.2 -msse4a
endif
endif

CFLAGS+=$(OPTS)

ifneq (,$(findstring MSYS_NT,$(OS)))
LDFLAGS+=-lws2_32
endif

ifeq ($(OPENCV), 1)
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv4 2> /dev/null || pkg-config --libs opencv`
COMMON+= `pkg-config --cflags opencv4 2> /dev/null || pkg-config --cflags opencv`
endif

ifeq ($(OPENMP), 1)
    ifeq ($(OS),Darwin) #MAC
	    CFLAGS+= -Xpreprocessor -fopenmp
	else
		CFLAGS+= -fopenmp
	endif
LDFLAGS+= -lgomp
endif

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

ifeq ($(CUDNN), 1)
COMMON+= -DCUDNN
ifeq ($(OS),Darwin) #MAC
CFLAGS+= -DCUDNN -I/usr/local/cuda/include
LDFLAGS+= -L/usr/local/cuda/lib -lcudnn
else
CFLAGS+= -DCUDNN -I/usr/local/cudnn/include
LDFLAGS+= -L/usr/local/cudnn/lib64 -lcudnn
endif
endif

ifeq ($(CUDNN_HALF), 1)
COMMON+= -DCUDNN_HALF
CFLAGS+= -DCUDNN_HALF
ARCH+= -gencode arch=compute_70,code=[sm_70,compute_70]
endif

ifeq ($(ZED_CAMERA), 1)
CFLAGS+= -DZED_STEREO -I/usr/local/zed/include
ifeq ($(ZED_CAMERA_v2_8), 1)
LDFLAGS+= -L/usr/local/zed/lib -lsl_core -lsl_input -lsl_zed
#-lstdc++ -D_GLIBCXX_USE_CXX11_ABI=0
else
LDFLAGS+= -L/usr/local/zed/lib -lsl_zed
#-lstdc++ -D_GLIBCXX_USE_CXX11_ABI=0
endif
endif

OBJ=image_opencv.o http_stream.o gemm.o utils.o dark_cuda.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 darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o representation_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o reorg_old_layer.o super.o voxel.o tree.o yolo_layer.o gaussian_yolo_layer.o upsample_layer.o lstm_layer.o conv_lstm_layer.o scale_channels_layer.o sam_layer.o
ifeq ($(GPU), 1)
LDFLAGS+= -lstdc++
OBJ+=convolutional_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 network_kernels.o avgpool_layer_kernels.o
endif

OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

all: $(OBJDIR) backup results setchmod $(EXEC) $(LIBNAMESO) $(APPNAMESO)

ifeq ($(LIBSO), 1)
CFLAGS+= -fPIC

$(LIBNAMESO): $(OBJDIR) $(OBJS) include/yolo_v2_class.hpp src/yolo_v2_class.cpp
	$(CPP) -shared -std=c++11 -fvisibility=hidden -DLIB_EXPORTS $(COMMON) $(CFLAGS) $(OBJS) src/yolo_v2_class.cpp -o $@ $(LDFLAGS)

$(APPNAMESO): $(LIBNAMESO) include/yolo_v2_class.hpp src/yolo_console_dll.cpp
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) -o $@ src/yolo_console_dll.cpp $(LDFLAGS) -L ./ -l:$(LIBNAMESO)
endif

$(EXEC): $(OBJS)
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS)

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

$(OBJDIR)%.o: %.cpp $(DEPS)
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) -c $< -o $@

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

$(OBJDIR):
	mkdir -p $(OBJDIR)
backup:
	mkdir -p backup
results:
	mkdir -p results
setchmod:
	chmod +x *.sh

.PHONY: clean

clean:
	rm -rf $(OBJS) $(EXEC) $(LIBNAMESO) $(APPNAMESO)