verne.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
witness_ has quit [Quit: Connection closed for inactivity]
witness_ has joined #mlpack
vivekp has quit [Ping timeout: 256 seconds]
vivekp has joined #mlpack
< ShikharJ>
zoq: Yeah.
vivekp has quit [Ping timeout: 260 seconds]
vivekp has joined #mlpack
caiojcarvalho has joined #mlpack
cjlcarvalho has quit [Ping timeout: 256 seconds]
ImQ009 has joined #mlpack
wenhao has joined #mlpack
caiojcarvalho has quit [Quit: Konversation terminated!]
cjlcarvalho has joined #mlpack
wenhao has quit [Ping timeout: 252 seconds]
< ShikharJ>
zoq: Are you there?
< ShikharJ>
zoq: I was a bit confused about how we should be providing the SSRBM test. Take a look at Kris' gist here: https://gist.github.com/kris-singh/55a4934c463bbddb3c8d321dd889d194 . Most of the code seems to be correct, and only needs some finer tuning, but as you could see, even from the generic CIFAR-10, we'll have to change the shape of the input using the python script he has provided.
< ShikharJ>
zoq: I was wondering whether we should be providing the script with the test or not? If yes, then where? It'd take me a sometime to get everything on the test sorted, depending on how fast it converges.
< zoq>
As for me, it would be reasonable to provide the script as part of a preprocessing step, if someone likes to reconstruct the full pipeline. However, we should provide the preprocessed dataset as well. We can put everything into the models repo.