윈도우 버전 YOLO v3 설치

2021. 8. 16. 00:22

Visual Studio 2019
NVIDIA CUDA (cuda-toolkit-archive)
NVIDIA cuDNN (cudnn-archive)
OpenCV 2.4 이상 (4.1)

Darknet project

GitHub - AlexeyAB/darknet: YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Da

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet ) - GitHub - AlexeyAB/darknet: YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object ...

github.com

Visual Studio 설정

darknet-master\build\darknet\darknet.vcxproj 파일 수정

     :
    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
    :
    <PlatformToolset>v142</PlatformToolset>
    :
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
    <ImportGroup Label="ExtensionSettings">
    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.props" />
  </ImportGroup>
    :
    <AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
    :
    <AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
    :
    <PostBuildEvent>
      <Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
</Command>
    </PostBuildEvent>
    :
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.targets" />
  </ImportGroup>
    :

 <?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <ItemGroup Label="ProjectConfigurations">
    <ProjectConfiguration Include="Debug|x64">
      <Configuration>Debug</Configuration>
      <Platform>x64</Platform>
    </ProjectConfiguration>
    <ProjectConfiguration Include="Release|x64">
      <Configuration>Release</Configuration>
      <Platform>x64</Platform>
    </ProjectConfiguration>
  </ItemGroup>
  <PropertyGroup Label="Globals">
    <ProjectGuid>{4CF5694F-12A5-4012-8D94-9A0915E9FEB5}</ProjectGuid>
    <RootNamespace>darknet</RootNamespace>
    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
    <ConfigurationType>Application</ConfigurationType>
    <UseDebugLibraries>true</UseDebugLibraries>
    <PlatformToolset>v142</PlatformToolset>
    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
    <ConfigurationType>Application</ConfigurationType>
    <UseDebugLibraries>false</UseDebugLibraries>
    <PlatformToolset>v142</PlatformToolset>
    <WholeProgramOptimization>true</WholeProgramOptimization>
    <CharacterSet>MultiByte</CharacterSet>
  </PropertyGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
  <ImportGroup Label="ExtensionSettings">
    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.props" />
  </ImportGroup>
  <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="PropertySheets">
    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
  </ImportGroup>
  <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="PropertySheets">
    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
  </ImportGroup>
  <PropertyGroup Label="UserMacros" />
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
    <OutDir>$(SolutionDir)$(Platform)\</OutDir>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
    <OutDir>$(SolutionDir)$(Platform)\</OutDir>
  </PropertyGroup>
  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
    <ClCompile>
      <WarningLevel>Level3</WarningLevel>
      <Optimization>Disabled</Optimization>
      <SDLCheck>true</SDLCheck>
      <AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
      <PreprocessorDefinitions>CUDNN_HALF;CUDNN;_CRTDBG_MAP_ALLOC;_MBCS;_TIMESPEC_DEFINED;_SCL_SECURE_NO_WARNINGS;_CRT_SECURE_NO_WARNINGS;_CRT_RAND_S;GPU;WIN32;DEBUG;_CONSOLE;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <UndefinePreprocessorDefinitions>OPENCV;</UndefinePreprocessorDefinitions>
      <MultiProcessorCompilation>true</MultiProcessorCompilation>
      <ForcedIncludeFiles>stdlib.h;crtdbg.h;%(ForcedIncludeFiles)</ForcedIncludeFiles>
    </ClCompile>
    <Link>
      <GenerateDebugInformation>true</GenerateDebugInformation>
      <AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
      <OutputFile>$(OutDir)\$(TargetName)$(TargetExt)</OutputFile>
      <AdditionalDependencies>pthreadVC2.lib;cublas.lib;curand.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
      <AssemblyDebug>true</AssemblyDebug>
    </Link>
    <CudaCompile>
      <CodeGeneration>compute_30,sm_30;compute_75,sm_75</CodeGeneration>
      <TargetMachinePlatform>64</TargetMachinePlatform>
    </CudaCompile>
    <PostBuildEvent>
      <Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
</Command>
    </PostBuildEvent>
  </ItemDefinitionGroup>
  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
    <ClCompile>
      <WarningLevel>Level3</WarningLevel>
      <Optimization>MaxSpeed</Optimization>
      <FunctionLevelLinking>true</FunctionLevelLinking>
      <IntrinsicFunctions>true</IntrinsicFunctions>
      <SDLCheck>true</SDLCheck>
      <AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
      <PreprocessorDefinitions>OPENCV;CUDNN_HALF;CUDNN;_TIMESPEC_DEFINED;_SCL_SECURE_NO_WARNINGS;_CRT_SECURE_NO_WARNINGS;_CRT_RAND_S;GPU;WIN32;_CONSOLE;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
      <CLanguageStandard>c11</CLanguageStandard>
      <CppLanguageStandard>c++1y</CppLanguageStandard>
      <PrecompiledHeaderCompileAs>CompileAsCpp</PrecompiledHeaderCompileAs>
      <CompileAs>Default</CompileAs>
      <UndefinePreprocessorDefinitions>NDEBUG</UndefinePreprocessorDefinitions>
      </AdditionalUsingDirectories>
    </ClCompile>
    <Link>
      <GenerateDebugInformation>true</GenerateDebugInformation>
      <EnableCOMDATFolding>true</EnableCOMDATFolding>
      <OptimizeReferences>true</OptimizeReferences>
      <AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
      <AdditionalDependencies>pthreadVC2.lib;cublas.lib;curand.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
      <OutputFile>$(OutDir)\$(TargetName)$(TargetExt)</OutputFile>
    </Link>
    <CudaCompile>
      <TargetMachinePlatform>64</TargetMachinePlatform>
      <CodeGeneration>compute_30,sm_30;compute_75,sm_75</CodeGeneration>
    </CudaCompile>
    <PostBuildEvent>
      <Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
</Command>
    </PostBuildEvent>
  </ItemDefinitionGroup>
  <ItemGroup>
    <CudaCompile Include="..\..\src\activation_kernels.cu" />
    <CudaCompile Include="..\..\src\avgpool_layer_kernels.cu" />
    <CudaCompile Include="..\..\src\blas_kernels.cu" />
    <CudaCompile Include="..\..\src\col2im_kernels.cu" />
    <ClInclude Include="..\..\src\upsample_layer.h" />
    <ClInclude Include="..\..\src\utils.h" />
    <ClInclude Include="..\..\src\yolo_layer.h" />
  </ItemGroup>
  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
  <ImportGroup Label="ExtensionTargets">
    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.targets" />
  </ImportGroup>
</Project>

OpenCV, cuDNN, GPU architecture 설정

 $(OPENCV_DIR)\include
$(SolutionDir)..\..\include
$(SolutionDir)..\..\3rdparty\stb\include
$(SolutionDir)..\..\3rdparty\pthreads\include
$(CUDA_PATH_V10_1)\include

 $(OPENCV_DIR)\x64\vc15\lib
$(CUDA_PATH)\lib\$(PlatformName)
$(CUDNN)\lib\x64;$(cudnn)\lib\x64
$(SolutionDir)..\..\3rdparty\pthreads\lib;

테스트 실행

미리 훈련된 weight 값 다운로드

yolov3-openimages.cfg (247 MB COCO Yolo v3) - requires 4 GB GPU-RAM:
https://pjreddie.com/media/files/yolov3-openimages.weights
yolov3-spp.cfg (240 MB COCO Yolo v3) - requires 4 GB GPU-RAM:
https://pjreddie.com/media/files/yolov3-spp.weights
yolov3.cfg (236 MB COCO Yolo v3) - requires 4 GB GPU-RAM:
https://pjreddie.com/media/files/yolov3.weights
yolov3-tiny.cfg (34 MB COCO Yolo v3 tiny) - requires 1 GB GPU-RAM:
https://pjreddie.com/media/files/yolov3-tiny.weights
yolov2.cfg (194 MB COCO Yolo v2) - requires 4 GB GPU-RAM:
https://pjreddie.com/media/files/yolov2.weights
yolo-voc.cfg (194 MB VOC Yolo v2) - requires 4 GB GPU-RAM:
http://pjreddie.com/media/files/yolo-voc.weights
yolov2-tiny.cfg (43 MB COCO Yolo v2) - requires 1 GB GPU-RAM:
https://pjreddie.com/media/files/yolov2-tiny.weights
yolov2-tiny-voc.cfg (60 MB VOC Yolo v2) - requires 1 GB GPU-RAM:
http://pjreddie.com/media/files/yolov2-tiny-voc.weights
yolo9000.cfg (186 MB Yolo9000-model) - requires 4 GB GPU-RAM:
http://pjreddie.com/media/files/yolo9000.weights

...\build\darknet\x64>darknet detector test ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weights ./data/dog.jpg

  CUDA-version: 10010 (10020), cuDNN: 7.6.1, CUDNN_HALF=1, GPU count: 1
 OpenCV version: 4.1.0
 compute_capability = 610, cudnn_half = 0
net.optimized_memory = 0
batch = 1, time_steps = 1, train = 0
   layer   filters  size/strd(dil)      input                output
   0 conv     32       3 x 3/ 1    416 x 416 x   3 ->  416 x 416 x  32 0.299 BF
   1 conv     64       3 x 3/ 2    416 x 416 x  32 ->  208 x 208 x  64 1.595 BF
   2 conv     32       1 x 1/ 1    208 x 208 x  64 ->  208 x 208 x  32 0.177 BF
   3 conv     64       3 x 3/ 1    208 x 208 x  32 ->  208 x 208 x  64 1.595 BF
   4 Shortcut Layer: 1,  wt = 0, wn = 0, outputs: 208 x 208 x  64 0.003 BF
   5 conv    128       3 x 3/ 2    208 x 208 x  64 ->  104 x 104 x 128 1.595 BF
   6 conv     64       1 x 1/ 1    104 x 104 x 128 ->  104 x 104 x  64 0.177 BF
   7 conv    128       3 x 3/ 1    104 x 104 x  64 ->  104 x 104 x 128 1.595 BF
   8 Shortcut Layer: 5,  wt = 0, wn = 0, outputs: 104 x 104 x 128 0.001 BF
   9 conv     64       1 x 1/ 1    104 x 104 x 128 ->  104 x 104 x  64 0.177 BF
  10 conv    128       3 x 3/ 1    104 x 104 x  64 ->  104 x 104 x 128 1.595 BF
  11 Shortcut Layer: 8,  wt = 0, wn = 0, outputs: 104 x 104 x 128 0.001 BF
  12 conv    256       3 x 3/ 2    104 x 104 x 128 ->   52 x  52 x 256 1.595 BF
  13 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  14 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  15 Shortcut Layer: 12,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  16 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  17 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  18 Shortcut Layer: 15,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  19 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  20 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  21 Shortcut Layer: 18,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  22 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  23 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  24 Shortcut Layer: 21,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  25 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  26 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  27 Shortcut Layer: 24,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  28 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  29 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  30 Shortcut Layer: 27,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  31 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  32 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  33 Shortcut Layer: 30,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  34 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
  35 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
  36 Shortcut Layer: 33,  wt = 0, wn = 0, outputs:  52 x  52 x 256 0.001 BF
  37 conv    512       3 x 3/ 2     52 x  52 x 256 ->   26 x  26 x 512 1.595 BF
  38 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  39 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  40 Shortcut Layer: 37,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  41 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  42 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  43 Shortcut Layer: 40,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  44 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  45 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  46 Shortcut Layer: 43,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  47 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  48 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  49 Shortcut Layer: 46,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  50 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  51 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  52 Shortcut Layer: 49,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  53 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  54 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  55 Shortcut Layer: 52,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  56 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  57 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  58 Shortcut Layer: 55,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  59 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  60 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  61 Shortcut Layer: 58,  wt = 0, wn = 0, outputs:  26 x  26 x 512 0.000 BF
  62 conv   1024       3 x 3/ 2     26 x  26 x 512 ->   13 x  13 x1024 1.595 BF
  63 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  64 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  65 Shortcut Layer: 62,  wt = 0, wn = 0, outputs:  13 x  13 x1024 0.000 BF
  66 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  67 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  68 Shortcut Layer: 65,  wt = 0, wn = 0, outputs:  13 x  13 x1024 0.000 BF
  69 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  70 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  71 Shortcut Layer: 68,  wt = 0, wn = 0, outputs:  13 x  13 x1024 0.000 BF
  72 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  73 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  74 Shortcut Layer: 71,  wt = 0, wn = 0, outputs:  13 x  13 x1024 0.000 BF
  75 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  76 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  77 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  78 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  79 conv    512       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 512 0.177 BF
  80 conv   1024       3 x 3/ 1     13 x  13 x 512 ->   13 x  13 x1024 1.595 BF
  81 conv    255       1 x 1/ 1     13 x  13 x1024 ->   13 x  13 x 255 0.088 BF
  82 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
  83 route  79                                     ->   13 x  13 x 512
  84 conv    256       1 x 1/ 1     13 x  13 x 512 ->   13 x  13 x 256 0.044 BF
  85 upsample                 2x    13 x  13 x 256 ->   26 x  26 x 256
  86 route  85 61                                  ->   26 x  26 x 768
  87 conv    256       1 x 1/ 1     26 x  26 x 768 ->   26 x  26 x 256 0.266 BF
  88 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  89 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  90 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  91 conv    256       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 256 0.177 BF
  92 conv    512       3 x 3/ 1     26 x  26 x 256 ->   26 x  26 x 512 1.595 BF
  93 conv    255       1 x 1/ 1     26 x  26 x 512 ->   26 x  26 x 255 0.177 BF
  94 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
  95 route  91                                     ->   26 x  26 x 256
  96 conv    128       1 x 1/ 1     26 x  26 x 256 ->   26 x  26 x 128 0.044 BF
  97 upsample                 2x    26 x  26 x 128 ->   52 x  52 x 128
  98 route  97 36                                  ->   52 x  52 x 384
  99 conv    128       1 x 1/ 1     52 x  52 x 384 ->   52 x  52 x 128 0.266 BF
 100 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
 101 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
 102 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
 103 conv    128       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 128 0.177 BF
 104 conv    256       3 x 3/ 1     52 x  52 x 128 ->   52 x  52 x 256 1.595 BF
 105 conv    255       1 x 1/ 1     52 x  52 x 256 ->   52 x  52 x 255 0.353 BF
 106 yolo
[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
Total BFLOPS 65.879
avg_outputs = 532444
 Allocate additional workspace_size = 52.43 MB
Loading weights from ./yolov3.weights...
 seen 64, trained: 32013 K-images (500 Kilo-batches_64)
Done! Loaded 107 layers from weights-file
./data/dog.jpg: Predicted in 57.593000 milli-seconds.
bicycle: 99%
dog: 100%
truck: 94%

Docker 사용하기

$ docker pull votiethuy/tensorflow1.12-base

 $ docker run -it --rm -v /c/TensorFlow/DW2TF:/dw2tf votiethuy/tensorflow1.12-base
# python main.py --cfg 'data/yolov3.cfg' --weights 'data/yolov3.weights' --output 'data/'

'ML' 카테고리의 다른 글

COCO Dataset (0)	2023.08.16
Pascal VOC(Visual Object Classes) Challenges (0)	2023.08.15
분류 모델의 성능평가지표 Accuracy, Recall, Precision, F1-score (0)	2022.12.19

내 블로그 - 관리자 홈 전환	`Q` `Q`
새 글 쓰기	`W` `W`

글 수정 (권한 있는 경우)	`E` `E`
댓글 영역으로 이동	`C` `C`

이 페이지의 URL 복사	`S` `S`
맨 위로 이동	`T` `T`
티스토리 홈 이동	`H` `H`
단축키 안내	`Shift` + `/` `⇧` + `/`

dozob

윈도우 버전 YOLO v3 설치

Darknet project

Visual Studio 설정

OpenCV, cuDNN, GPU architecture 설정

관련 DLL 복사

테스트 실행

'ML' 카테고리의 다른 글

+ Recent posts

티스토리툴바

단축키

내 블로그

블로그 게시글

모든 영역

	:
	<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
	:
	<PlatformToolset>v142</PlatformToolset>
	:
	<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
	<ImportGroup Label="ExtensionSettings">
	<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.props" />
	</ImportGroup>
	:
	<AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
	:
	<AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
	:
	<PostBuildEvent>
	<Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
	xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
	</Command>
	</PostBuildEvent>
	:
	<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
	<ImportGroup Label="ExtensionTargets">
	<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.targets" />
	</ImportGroup>
	:

	<?xml version="1.0" encoding="utf-8"?>
	<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
	<ItemGroup Label="ProjectConfigurations">
	<ProjectConfiguration Include="Debug\|x64">
	<Configuration>Debug</Configuration>
	<Platform>x64</Platform>
	</ProjectConfiguration>
	<ProjectConfiguration Include="Release\|x64">
	<Configuration>Release</Configuration>
	<Platform>x64</Platform>
	</ProjectConfiguration>
	</ItemGroup>
	<PropertyGroup Label="Globals">
	<ProjectGuid>{4CF5694F-12A5-4012-8D94-9A0915E9FEB5}</ProjectGuid>
	<RootNamespace>darknet</RootNamespace>
	<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
	</PropertyGroup>
	<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
	<PropertyGroup Condition="'$(Configuration)\|$(Platform)'=='Debug\|x64'" Label="Configuration">
	<ConfigurationType>Application</ConfigurationType>
	<UseDebugLibraries>true</UseDebugLibraries>
	<PlatformToolset>v142</PlatformToolset>
	<CharacterSet>MultiByte</CharacterSet>
	</PropertyGroup>
	<PropertyGroup Condition="'$(Configuration)\|$(Platform)'=='Release\|x64'" Label="Configuration">
	<ConfigurationType>Application</ConfigurationType>
	<UseDebugLibraries>false</UseDebugLibraries>
	<PlatformToolset>v142</PlatformToolset>
	<WholeProgramOptimization>true</WholeProgramOptimization>
	<CharacterSet>MultiByte</CharacterSet>
	</PropertyGroup>
	<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
	<ImportGroup Label="ExtensionSettings">
	<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.props" />
	</ImportGroup>
	<ImportGroup Condition="'$(Configuration)\|$(Platform)'=='Debug\|x64'" Label="PropertySheets">
	<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
	</ImportGroup>
	<ImportGroup Condition="'$(Configuration)\|$(Platform)'=='Release\|x64'" Label="PropertySheets">
	<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
	</ImportGroup>
	<PropertyGroup Label="UserMacros" />
	<PropertyGroup Condition="'$(Configuration)\|$(Platform)'=='Debug\|x64'">
	<OutDir>$(SolutionDir)$(Platform)\</OutDir>
	</PropertyGroup>
	<PropertyGroup Condition="'$(Configuration)\|$(Platform)'=='Release\|x64'">
	<OutDir>$(SolutionDir)$(Platform)\</OutDir>
	</PropertyGroup>
	<ItemDefinitionGroup Condition="'$(Configuration)\|$(Platform)'=='Debug\|x64'">
	<ClCompile>
	<WarningLevel>Level3</WarningLevel>
	<Optimization>Disabled</Optimization>
	<SDLCheck>true</SDLCheck>
	<AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
	<PreprocessorDefinitions>CUDNN_HALF;CUDNN;_CRTDBG_MAP_ALLOC;_MBCS;_TIMESPEC_DEFINED;_SCL_SECURE_NO_WARNINGS;_CRT_SECURE_NO_WARNINGS;_CRT_RAND_S;GPU;WIN32;DEBUG;_CONSOLE;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
	<UndefinePreprocessorDefinitions>OPENCV;</UndefinePreprocessorDefinitions>
	<MultiProcessorCompilation>true</MultiProcessorCompilation>
	<ForcedIncludeFiles>stdlib.h;crtdbg.h;%(ForcedIncludeFiles)</ForcedIncludeFiles>
	</ClCompile>
	<Link>
	<GenerateDebugInformation>true</GenerateDebugInformation>
	<AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
	<OutputFile>$(OutDir)\$(TargetName)$(TargetExt)</OutputFile>
	<AdditionalDependencies>pthreadVC2.lib;cublas.lib;curand.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
	<AssemblyDebug>true</AssemblyDebug>
	</Link>
	<CudaCompile>
	<CodeGeneration>compute_30,sm_30;compute_75,sm_75</CodeGeneration>
	<TargetMachinePlatform>64</TargetMachinePlatform>
	</CudaCompile>
	<PostBuildEvent>
	<Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
	xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
	</Command>
	</PostBuildEvent>
	</ItemDefinitionGroup>
	<ItemDefinitionGroup Condition="'$(Configuration)\|$(Platform)'=='Release\|x64'">
	<ClCompile>
	<WarningLevel>Level3</WarningLevel>
	<Optimization>MaxSpeed</Optimization>
	<FunctionLevelLinking>true</FunctionLevelLinking>
	<IntrinsicFunctions>true</IntrinsicFunctions>
	<SDLCheck>true</SDLCheck>
	<AdditionalIncludeDirectories>$(OPENCV_DIR)\include;$(SolutionDir)..\..\include;$(SolutionDir)..\..\3rdparty\stb\include;$(SolutionDir)..\..\3rdparty\pthreads\include;$(CUDA_PATH_V10_1)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
	<PreprocessorDefinitions>OPENCV;CUDNN_HALF;CUDNN;_TIMESPEC_DEFINED;_SCL_SECURE_NO_WARNINGS;_CRT_SECURE_NO_WARNINGS;_CRT_RAND_S;GPU;WIN32;_CONSOLE;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
	<CLanguageStandard>c11</CLanguageStandard>
	<CppLanguageStandard>c++1y</CppLanguageStandard>
	<PrecompiledHeaderCompileAs>CompileAsCpp</PrecompiledHeaderCompileAs>
	<CompileAs>Default</CompileAs>
	<UndefinePreprocessorDefinitions>NDEBUG</UndefinePreprocessorDefinitions>
	</AdditionalUsingDirectories>
	</ClCompile>
	<Link>
	<GenerateDebugInformation>true</GenerateDebugInformation>
	<EnableCOMDATFolding>true</EnableCOMDATFolding>
	<OptimizeReferences>true</OptimizeReferences>
	<AdditionalLibraryDirectories>$(OPENCV_DIR)\x64\vc15\lib;$(CUDA_PATH)\lib\$(PlatformName);$(CUDNN)\lib\x64;$(cudnn)\lib\x64;..\..\3rdparty\pthreads\lib;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
	<AdditionalDependencies>pthreadVC2.lib;cublas.lib;curand.lib;cudart.lib;%(AdditionalDependencies)</AdditionalDependencies>
	<OutputFile>$(OutDir)\$(TargetName)$(TargetExt)</OutputFile>
	</Link>
	<CudaCompile>
	<TargetMachinePlatform>64</TargetMachinePlatform>
	<CodeGeneration>compute_30,sm_30;compute_75,sm_75</CodeGeneration>
	</CudaCompile>
	<PostBuildEvent>
	<Command>xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_ffmpeg???_64.dll" "$(OutDir)"
	xcopy /d /y "$(OpenCV_DIR)\x64\vc15\opencv_world???.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cublas64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cudart64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\cusolver64_*.dll" "$(OutDir)"
	xcopy /d /y "$(CUDA_PATH_V10_1)\bin\curand64_*.dll" "$(OutDir)"
	</Command>
	</PostBuildEvent>
	</ItemDefinitionGroup>
	<ItemGroup>
	<CudaCompile Include="..\..\src\activation_kernels.cu" />
	<CudaCompile Include="..\..\src\avgpool_layer_kernels.cu" />
	<CudaCompile Include="..\..\src\blas_kernels.cu" />
	<CudaCompile Include="..\..\src\col2im_kernels.cu" />
	<ClInclude Include="..\..\src\upsample_layer.h" />
	<ClInclude Include="..\..\src\utils.h" />
	<ClInclude Include="..\..\src\yolo_layer.h" />
	</ItemGroup>
	<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
	<ImportGroup Label="ExtensionTargets">
	<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 10.1.targets" />
	</ImportGroup>
	</Project>

	$(OPENCV_DIR)\include
	$(SolutionDir)..\..\include
	$(SolutionDir)..\..\3rdparty\stb\include
	$(SolutionDir)..\..\3rdparty\pthreads\include
	$(CUDA_PATH_V10_1)\include

	$(OPENCV_DIR)\x64\vc15\lib
	$(CUDA_PATH)\lib\$(PlatformName)
	$(CUDNN)\lib\x64;$(cudnn)\lib\x64
	$(SolutionDir)..\..\3rdparty\pthreads\lib;

	CUDA-version: 10010 (10020), cuDNN: 7.6.1, CUDNN_HALF=1, GPU count: 1
	OpenCV version: 4.1.0
	compute_capability = 610, cudnn_half = 0
	net.optimized_memory = 0
	batch = 1, time_steps = 1, train = 0
	layer filters size/strd(dil) input output
	0 conv 32 3 x 3/ 1 416 x 416 x 3 -> 416 x 416 x 32 0.299 BF
	1 conv 64 3 x 3/ 2 416 x 416 x 32 -> 208 x 208 x 64 1.595 BF
	2 conv 32 1 x 1/ 1 208 x 208 x 64 -> 208 x 208 x 32 0.177 BF
	3 conv 64 3 x 3/ 1 208 x 208 x 32 -> 208 x 208 x 64 1.595 BF
	4 Shortcut Layer: 1, wt = 0, wn = 0, outputs: 208 x 208 x 64 0.003 BF
	5 conv 128 3 x 3/ 2 208 x 208 x 64 -> 104 x 104 x 128 1.595 BF
	6 conv 64 1 x 1/ 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BF
	7 conv 128 3 x 3/ 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BF
	8 Shortcut Layer: 5, wt = 0, wn = 0, outputs: 104 x 104 x 128 0.001 BF
	9 conv 64 1 x 1/ 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BF
	10 conv 128 3 x 3/ 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BF
	11 Shortcut Layer: 8, wt = 0, wn = 0, outputs: 104 x 104 x 128 0.001 BF
	12 conv 256 3 x 3/ 2 104 x 104 x 128 -> 52 x 52 x 256 1.595 BF
	13 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	14 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	15 Shortcut Layer: 12, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	16 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	17 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	18 Shortcut Layer: 15, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	19 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	20 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	21 Shortcut Layer: 18, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	22 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	23 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	24 Shortcut Layer: 21, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	25 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	26 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	27 Shortcut Layer: 24, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	28 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	29 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	30 Shortcut Layer: 27, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	31 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	32 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	33 Shortcut Layer: 30, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	34 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	35 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	36 Shortcut Layer: 33, wt = 0, wn = 0, outputs: 52 x 52 x 256 0.001 BF
	37 conv 512 3 x 3/ 2 52 x 52 x 256 -> 26 x 26 x 512 1.595 BF
	38 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	39 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	40 Shortcut Layer: 37, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	41 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	42 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	43 Shortcut Layer: 40, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	44 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	45 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	46 Shortcut Layer: 43, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	47 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	48 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	49 Shortcut Layer: 46, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	50 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	51 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	52 Shortcut Layer: 49, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	53 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	54 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	55 Shortcut Layer: 52, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	56 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	57 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	58 Shortcut Layer: 55, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	59 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	60 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	61 Shortcut Layer: 58, wt = 0, wn = 0, outputs: 26 x 26 x 512 0.000 BF
	62 conv 1024 3 x 3/ 2 26 x 26 x 512 -> 13 x 13 x1024 1.595 BF
	63 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	64 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	65 Shortcut Layer: 62, wt = 0, wn = 0, outputs: 13 x 13 x1024 0.000 BF
	66 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	67 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	68 Shortcut Layer: 65, wt = 0, wn = 0, outputs: 13 x 13 x1024 0.000 BF
	69 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	70 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	71 Shortcut Layer: 68, wt = 0, wn = 0, outputs: 13 x 13 x1024 0.000 BF
	72 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	73 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	74 Shortcut Layer: 71, wt = 0, wn = 0, outputs: 13 x 13 x1024 0.000 BF
	75 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	76 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	77 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	78 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	79 conv 512 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BF
	80 conv 1024 3 x 3/ 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BF
	81 conv 255 1 x 1/ 1 13 x 13 x1024 -> 13 x 13 x 255 0.088 BF
	82 yolo
	[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
	83 route 79 -> 13 x 13 x 512
	84 conv 256 1 x 1/ 1 13 x 13 x 512 -> 13 x 13 x 256 0.044 BF
	85 upsample 2x 13 x 13 x 256 -> 26 x 26 x 256
	86 route 85 61 -> 26 x 26 x 768
	87 conv 256 1 x 1/ 1 26 x 26 x 768 -> 26 x 26 x 256 0.266 BF
	88 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	89 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	90 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	91 conv 256 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BF
	92 conv 512 3 x 3/ 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BF
	93 conv 255 1 x 1/ 1 26 x 26 x 512 -> 26 x 26 x 255 0.177 BF
	94 yolo
	[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
	95 route 91 -> 26 x 26 x 256
	96 conv 128 1 x 1/ 1 26 x 26 x 256 -> 26 x 26 x 128 0.044 BF
	97 upsample 2x 26 x 26 x 128 -> 52 x 52 x 128
	98 route 97 36 -> 52 x 52 x 384
	99 conv 128 1 x 1/ 1 52 x 52 x 384 -> 52 x 52 x 128 0.266 BF
	100 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	101 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	102 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	103 conv 128 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BF
	104 conv 256 3 x 3/ 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BF
	105 conv 255 1 x 1/ 1 52 x 52 x 256 -> 52 x 52 x 255 0.353 BF
	106 yolo
	[yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00
	Total BFLOPS 65.879
	avg_outputs = 532444
	Allocate additional workspace_size = 52.43 MB
	Loading weights from ./yolov3.weights...
	seen 64, trained: 32013 K-images (500 Kilo-batches_64)
	Done! Loaded 107 layers from weights-file
	./data/dog.jpg: Predicted in 57.593000 milli-seconds.
	bicycle: 99%
	dog: 100%
	truck: 94%

	$ docker run -it --rm -v /c/TensorFlow/DW2TF:/dw2tf votiethuy/tensorflow1.12-base
	# python main.py --cfg 'data/yolov3.cfg' --weights 'data/yolov3.weights' --output 'data/'