Yolo v2 multi-version installation

yolo v2 install

First, using Windows 7 to achieve

1. vs2015+opencv3.2+GeForce GT 1030 (c++ compilation)

Github：https://github.com/pjreddie/darknet

1. vs2015 installation

2. OpenCV3.2 configuration

3. Driver installation, download the corresponding version from NVIDIA's official website

4. cuda choose 9.0, cudnn package

   configure and compile

5. Double-click \darknet-master\build\darknet\darknet.sln (if there is no GPU, use the darknet_no_gpu.sln project) to open the project

6. Modify the words related to the cuda version in darknet.vcxproj
7. In the darknet property page, modify the OpenCV section in the c/c++ and additional include directories in the linker
8. compile

Second, using Ubuntu 16.04 to achieve

Github：https://github.com/pjreddie/darknet

1. Download and install directly

   git clone https://github.com/pjreddie/darknet
cd darknet/

   make

   Modify the MakeFile file GPU/CUDNN/OPENCV, etc. as needed

3. Both Ubuntu16.04 and Windows can be used

1 hard+tebsorflow-gpu 版

Github:https://github.com/allanzelener/YAD2K

1. install anaconda3

2. Install keras and TensorFlow-gpu

   pip install tensorflow-gpu

   pip install keras

3. install yad2k

   git clone https://github.com/allanzelener/yad2k.git
   cd yad2k
   
   conda env create -f environment.yml
   source activate yad2k
   
   pip install numpy h5py pillow

2、TensorFlow

Github:https://github.com/thtrieu/darkflow

1. Compile and install

   git clone https://github.com/thtrieu/darkflow
cd darknet/

   python3 setup.py build_ext --inplace

   pip install .