Results consistently differ from the C++ library

[ag-tcm]

I did some testing comparing the results from this library and the C++ library and they are consistently different. I needed to get it to work so I went through line by line in a debugger comparing the two and fixed the java code on my local copy. Let me know if you'd like me to push it here so others can use it. Oh, also I added support for the Manhattan distance.

[Dawien]

I did some testing comparing the results from this library and the C++ library and they are consistently different. I needed to get it to work so I went through line by line in a debugger comparing the two and fixed the java code on my local copy. Let me know if you'd like me to push it here so others can use it. Oh, also I added support for the Manhattan distance.

I also encountered the same problem when I was using it. Can you open source the modified code for reference? Thank you very much！

[ag-tcm]

No problem, I put my modified code here: https://github.com/ag-tcm/annoy-java.

[Dawien]

No problem, I put my modified code here: https://github.com/ag-tcm/annoy-java.

Great!! Thanks for sharing!