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/
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 248 seconds]
nikhilweee has joined #mlpack
sumedhghaisas_ has quit [Ping timeout: 268 seconds]
sumedhghaisas_ has joined #mlpack
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
chenzhe has joined #mlpack
< chenzhe> Hi! I have a question using git.
< chenzhe> Currently I have code on my own branch for vector problems and matrix problems
< chenzhe> I want to make a new PR with only the vector problems code
< chenzhe> Is there any way that I can hide the matrix problems code some how, and create a new branch with only the vector problem code?
stephentu has joined #mlpack
zoq_ has joined #mlpack
zoq has quit [Read error: Connection reset by peer]
chenzhe has quit [Ping timeout: 246 seconds]
chenzhe has joined #mlpack
govg has joined #mlpack
mikeling has joined #mlpack
chenzhe has quit [Quit: chenzhe]
partobs-mdp has joined #mlpack
sumedhghaisas_ has quit [Quit: Ex-Chat]
sumedhghaisas_ has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
andrzejku has joined #mlpack
vivekp has quit [Ping timeout: 248 seconds]
vivekp has joined #mlpack
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
sumedhghaisas_ has quit [Ping timeout: 268 seconds]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 276 seconds]
zoq_ is now known as zoq
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 248 seconds]
andrzejku has quit [Quit: My iMac has gone to sleep. ZZZzzz…]
kris1 has joined #mlpack
< lozhnikov> kris1: Could you look at the comment? https://github.com/mlpack/mlpack/pull/1066#issuecomment-318034720
< kris1> Yes i did. I actually i got confused about about the train method earlier.
< kris1> I see your point now. That we have to call the optimizer only once
< kris1> I will start think how you could do that.
< kris1> start *thinking
< lozhnikov> Actually, I suggest you to finish the ssRBM first.
< kris1> Ahhhh……yes okay i will get on that.
< lozhnikov> I pointed out some issues here https://github.com/mlpack/mlpack/pull/1046#issuecomment-317401006
< kris1> Yes i did go through them. I will start working on them now and complete them first before Gan PR.
< lozhnikov> Right now the ssRBM passes the classification test, but I still can't get right results on the full MNIST dataset. I mean the test from deeplearning.net
< lozhnikov> maybe I passed incorrect parameters, maybe there is an error somewhere
stephentu has joined #mlpack
< kris1> Hmmm okay. when you result you mean the reconstructed samples right ?
< kris1> Since we do not have an accuracy with deeplearning.net example.
< lozhnikov> yes, I mean the pictures
stephentu has quit [Ping timeout: 240 seconds]
< kris1> The paper test this on cifar dataset. With patches of size 192*1 for every image. I have these patches if you want let me know. They are large in size though each is around 200mb
< kris1> On cifar the accuracy was around 68%
< kris1> Also i think we can test ssRBM implementation by converting it to BinaryRBM. We just have to set the some parameters equal 1.
< kris1> I will dig out the paper that stated how to convert ssRBM to binary rbm.
< lozhnikov> Could you send me the link to the paper?
< lozhnikov> I haven't got an access to the paper
andrzejku has joined #mlpack
< kris1> On another read i don’t think this would be helpful. They came up with mu-pooled rbm and reduced it to ssRBM.
< kris1> I thought we could do something similar with the ssRBM —> binary rbm
< lozhnikov> kris1: thanks for the link, I have downloaded the paper, I think it is better to remove the file from google drive since this is a logged channel
< kris1> Ahh okay…
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
< ironstark> zoq: rcurtin: I am getting the following error while using options in weka:
stephentu has joined #mlpack
< zoq> ironstark: Did you use: J48 cModel = new J48(); instead of Classifier cModel = (Classifier)new J48();?
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
< ironstark> zoq: The issue got resolved. Thanks a lot for the help.
< zoq> ironstark: Glad I could help :)
kris1 has quit [Quit: kris1]
stephentu has quit [Ping timeout: 260 seconds]
kris1 has joined #mlpack
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 258 seconds]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 246 seconds]
andrzejku has quit [Quit: My iMac has gone to sleep. ZZZzzz…]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
andrzejku has joined #mlpack
partobs-mdp has quit [Remote host closed the connection]
kris1 has quit [Quit: kris1]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 258 seconds]
andrzejku has quit [Quit: Textual IRC Client: www.textualapp.com]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 248 seconds]
sumedhghaisas_ has joined #mlpack
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
stephentu has joined #mlpack
stephentu has quit [Ping timeout: 240 seconds]
sumedhghaisas_ has quit [Ping timeout: 268 seconds]