[mlpack-git] [mlpack/mlpack] Multiprobe LSH Implementation (#657)

[Yannis Mentekidis]

Thanks for the comments :)
I'll get right on to fixing some stuff!

I think we can merge both changes together, it doesn't really make a difference to me.

Something related to testing: I am running tests on the Corel Color Histogram dataset but I can't get recall over 50-60%. Have you had similar results? I though I might have broken something but I ran the master branch code too and got the same... For example, 4 projections, 64 tables and 15 additional probes couldn't get over 70%.
I thought I might be computing recall wrong but I ran my matlab code as well and had the same results.


---
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/657#issuecomment-222641004
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160531/65303afb/attachment.html>