win10编译darknet(yolov4)

• https://github.com/AlexeyAB/darknet

系统环境

windows10 x64
GTX 2070 6G
显卡驱动 441.66
cuda_10.2.89_441.22_win10
cudnn-10.2-windows10-x64-v8.1.1.33
vs2019/vs2017
opencv-3.4.0-vc14_vc15

要求

设置环境变量

# 设置系统变量
CUDA_BIN_PATH	%CUDA_PATH%\bin
CUDA_LIB_PATH	%CUDA_PATH%\lib\x64
CUDA_PATH	C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2
CUDA_PATH_V10_2	C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2
CUDA_SDK_BIN_PATH	%CUDA_SDK_PATH%\bin\win64
CUDA_SDK_LIB_PATH	%CUDA_SDK_PATH%\common\lib\x64
CUDA_SDK_PATH	C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2
CUDNN	C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2
NVCUDASAMPLES_ROOT	C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2
NVCUDASAMPLES10_2_ROOT	C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2
NVTOOLSEXT_PATH	C:\Program Files\NVIDIA Corporation\NvToolsExt\
OpenCV_DIR	C:\opencv_3.0\opencv\build

# 更新系统 path
%CUDA_LIB_PATH%
%CUDA_BIN_PATH%
%CUDA_SDK_LIB_PATH%
%CUDA_SDK_BIN_PATH%
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\lib\x64
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\include
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\extras\CUPTI\include
C:\opencv_3.0\opencv\build\x64\vc15\bin
C:\opencv_3.0\opencv\build\x64\vc14\bin
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\libnvvp
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2

编译步骤

测试运行

将darknet\Release\* 复制到darknet\build\darknet\x64

darknet.exe detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -ext_output dog.jpg

执行命令darknet.exe detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -thresh 0.2 出现以下错误

将darknet\build\darknet\x64下的pthreadVC2.dll和pthreadGC2.dll复制到C:\Windows\System32