How to build the library and use it to train, predict, and get feature from image

[cia1099]

Hello,
I clone this library and use cmake to build, but there are much error.

Can you instruct how to build the code and use this code function example?

I am sincerely grateful if any help of your providing.

[belltailjp]

Unfortunately I haven't been using this code long time, thus I can provide no support anymore.

My general advice is that you'd better report at least following information. (Please be noted that this doesn't mean I can promise you some answers by responding to these items)

• In which environment you have tried to build
• How you ran build process
• What exact error you've got.

[cia1099]

Hi,

• I use Visual Studio2012 to complier with OpenCV320 in Win32 environment.

• I use cmake gui to include CMakeLists folder path to configuration the generation the project, I ran the building process.
  e.g.

1. I git clone this code on my D:/Project/CoHOG/libcohog/, in this path there is a CMakeLists.txt, I create a folder D:/Project/CoHOG/libcohog/build/ for generation target destination. I canceled the WITH_CUDA and WITH_OMP selection due to make it simplest.
   
   

While the cmake generated done, I open the project with VS2012 to build ALL_BUILD.vcxproj, then there are the error as follow figure: (these underline are error)

[cia1099]

Hello
I have successfully build the code and run it to get feature.
But I have a problem on how to stack these feature to train.

My development environment is OpenCV320, I want to train INRIA dataset there are 2716 and 12180 for positive and negative respectively. Every data is 64x128 pixels, I divide the size into 4x8 regions. Thus the dimension of feature is 63488 on the INRIA dataset, if I stack the feature with total training data, there are 63488x(2716+12180) size of Mat. Of cause, it is out of memory to stack at such a large Mat.

Can you reply me how CoHog do train data? Thanks

Best regards