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/
< rcurtin> alsc: the basic idea looks good to me, we can definitely work that into a PR and merge it
vivekp has quit [Ping timeout: 264 seconds]
vivekp has joined #mlpack
kaushik_ has joined #mlpack
< rcurtin> dan_dan: not sure if you check the logs at all, but if so here is the PR with the Python3 fixes: https://github.com/mlpack/mlpack/pull/1182
jas__ has quit [Ping timeout: 256 seconds]
jas__ has joined #mlpack
alsc has joined #mlpack
alsc has quit [Quit: alsc]
kaushik_ has quit [Quit: Connection closed for inactivity]
jas__ has quit [Ping timeout: 248 seconds]
alsc has joined #mlpack
< alsc> zoq: it's a bit blurry how to input labels to FNN:Train
< alsc> I'd expect a one-hot vector, but it's not like that. looks like it's 1-based position in a vector of unique-labels?
< alsc> while the results matrix is 0-based.. I don't get it
alsc has quit [Quit: alsc]
deepanshu_ has joined #mlpack
alsc has joined #mlpack
alsc has quit [Client Quit]
alsc has joined #mlpack
< zoq> alsc: Ah right, the NegativeLogLikelihood is 1 based, I'll adjust that later today.
< alsc> thanks
< alsc> I have checked the source code yeah, got it. why not accepting one-hot?
< zoq> the data I used for testing was just like that ...
< alsc> oki :)
alsc has quit [Quit: alsc]
jas__ has joined #mlpack
jas__ is now known as preet
preet has quit [Ping timeout: 248 seconds]
preet has joined #mlpack
preet has quit [Ping timeout: 256 seconds]
rits has joined #mlpack
rits has quit [Client Quit]
rits has joined #mlpack
rits has quit [Client Quit]
deepanshu_ has quit [Quit: Connection closed for inactivity]
dany has joined #mlpack
< dany> rcurtin: hey! I do check the logs, saw the pull request
dany has quit [Client Quit]
dany has joined #mlpack
dany has quit [Client Quit]
< rcurtin> dany: great, hopefully it should fix your issue---if not (or if you find more) just let me know