[学习笔记]darknet的部署和利用darkmark进行训练

今天跟着学长来了解以下darknet的训练过程

首先前置需求就是darknet,darkmark(可视化寻训练工具)，darkhelp

一、编译几个工具

首先修改makefile文件

GPU=1就是用gpu（不用我干嘛费那么大事装CUDA干啥）

CUDNN=1同上（费大劲了）

LIBSO=1是之后的必须项，会生成一些文件

然后make -j8，应该不会报错（记得不要删掉build文件夹）

之后跟着官方的readme文档装依赖编译就行了

Darknet:

    sudo apt-get install build-essential git libopencv-dev
    cd ~/src
    git clone https://github.com/AlexeyAB/darknet.git
    cd darknet
    # edit Makefile to set LIBSO=1, and possibly other flags
    make
    sudo cp libdarknet.so /usr/local/lib/
    sudo cp include/darknet.h /usr/local/include/
    sudo ldconfig

DarkHelp:

    sudo apt-get install cmake build-essential libtclap-dev libmagic-dev libopencv-dev
    cd ~/src
    git clone https://github.com/stephanecharette/DarkHelp.git
    cd DarkHelp
    mkdir build
    cd build
    cmake -DCMAKE_BUILD_TYPE=Release ..
    make
    make package
    sudo dpkg -i darkhelp*.deb

DarkMark:

    sudo apt-get install build-essential cmake libopencv-dev libx11-dev libfreetype6-dev libxrandr-dev libxinerama-dev libxcursor-dev libmagic-dev libpoppler-cpp-dev
    cd ~/src
    git clone https://github.com/stephanecharette/DarkMark.git
    cd DarkMark
    mkdir build
    cd build
    cmake -DCMAKE_BUILD_TYPE=Release ..
    make
    make package
    sudo dpkg -i darkmark*.deb

二、darkmark的使用

在终端里输入DarkMark就能打开darkmark的图形化界面