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/
trapz has quit [Quit: trapz]
trapz has joined #mlpack
thyrix has joined #mlpack
chenzhe has joined #mlpack
chenzhe has quit [Ping timeout: 246 seconds]
kris1 has joined #mlpack
< kris1>
zoq: Did you see my comments on NAG PR. What do you think
chenzhe has joined #mlpack
trapz has quit [Quit: trapz]
kris1 has left #mlpack []
thyrix has quit [Ping timeout: 260 seconds]
mikeling has joined #mlpack
< rcurtin>
kris1: I am sure he got the email, it may be a little while until he can respond
ShangtongZhang has joined #mlpack
ShangtongZhang has left #mlpack []
chenzhe has quit [Ping timeout: 260 seconds]
sumedhghaisas has joined #mlpack
etotientz has joined #mlpack
< etotientz>
Hello world!
etotientz has quit [Ping timeout: 246 seconds]
pvskand has joined #mlpack
etotientz has joined #mlpack
< etotientz>
i am a newcomer here and am finding template metaprogramming a bit complicated.Any easy way to go through it in mlpack?
< pvskand>
Why is this error being shown when I make and run the tests? "/mlpack/src/mlpack/tests/krann_search_test.cpp(713): fatal error in "RAModelTest": critical check numQueriesFail < maxNumQueriesFail failed [28 >= 25]"
govg has quit [Ping timeout: 240 seconds]
chenzhe has joined #mlpack
ironstark has quit [Ping timeout: 240 seconds]
pvskand has quit [Ping timeout: 260 seconds]
etotientz has quit [Ping timeout: 246 seconds]
ironstark has joined #mlpack
vivekp has quit [Ping timeout: 260 seconds]
vivekp has joined #mlpack
sumedhghaisas has quit [Ping timeout: 268 seconds]
vivekp has quit [Ping timeout: 268 seconds]
vivekp has joined #mlpack
thyrix has joined #mlpack
thyrix has quit [Ping timeout: 260 seconds]
tanisha has quit [Quit: Connection closed for inactivity]
ironstark has quit [Read error: Connection reset by peer]
ironstark has joined #mlpack
saumya has joined #mlpack
saumya has left #mlpack []
shikhar has joined #mlpack
< vivekp>
zoq: I saw your comment on AdaGrad policy class PR regarding the SGD<DecomposableFunctionType, AdaGradUpdate> optimizer;
< vivekp>
Actually, since that PR was updated after I had pushed some changes to SMORMS3 PR after your review including that change, I think it's better if I answer to your question. The reason is that basically it expects 6 arguments as specified by the SGD constructor
< zoq>
vivekp: The arguments provided aren't necessary to define the type; as I said in the comment 'SGD<DecomposableFunctionType, AdaGradUpdate> optimizer;' is just fine.
Nauman_ has quit [Ping timeout: 260 seconds]
< vivekp>
I'm not sure what's wrong then but compiler always complaints about the arguments. I'll see if there's another issue with the code that causing that
< zoq>
I can see at least one more issue that I haven't seen the last time, but maybe it's already fixed it. Can you update the PR?
< vivekp>
Okay, I'll push the changes shortly
< zoq>
okay, sounds good
accel has joined #mlpack
accel has quit [Client Quit]
trapz has joined #mlpack
trapz has quit [Quit: trapz]
trapz has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
trapz has quit [Client Quit]
trapz has joined #mlpack
trapz has quit [Client Quit]
govg has joined #mlpack
Nax has joined #mlpack
ironstark has quit [Ping timeout: 260 seconds]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
ironstark has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 258 seconds]
govg has joined #mlpack
trapz has joined #mlpack
govg has quit [Ping timeout: 256 seconds]
govg has joined #mlpack
ironstark has quit [Ping timeout: 264 seconds]
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
Nauman has joined #mlpack
Nax has quit [Ping timeout: 240 seconds]
Nax has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
Nauman has quit [Ping timeout: 240 seconds]
etotientz has joined #mlpack
sumedhghaisas has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
pvskand has joined #mlpack
govg has quit [Ping timeout: 258 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
pengpeng has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 256 seconds]
govg has joined #mlpack
trapz has quit [Quit: trapz]
pengpeng has quit [Quit: pengpeng]
witness_ has joined #mlpack
ironstark has joined #mlpack
govg has quit [Ping timeout: 258 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 258 seconds]
govg has joined #mlpack
Nax has quit [Ping timeout: 260 seconds]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 258 seconds]
mikeling has quit [Quit: Connection closed for inactivity]
witness_ has quit [Quit: Connection closed for inactivity]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
trapz has quit [Quit: trapz]
govg has joined #mlpack
trapz has joined #mlpack
trapz has quit [Client Quit]
trapz has joined #mlpack
trapz has quit [Client Quit]
sumedhghaisas has quit [Ping timeout: 268 seconds]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 268 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 260 seconds]
kris1 has joined #mlpack
< kris1>
I am trying to train the nn with SGD<decltype(model), MomentumUpdate, NoDecay> opt(model, 0.01, maxEpochs * trainData.n_cols, 1e-5 , true, momentumUpdate, noDecay);
< kris1>
But this doesn't seem to work. There is problem with model.Train(std::move(trainData), std::move(trainLabels), opt);
< kris1>
Also one more thing i am writing test for decay learning rates. But the learning rates and the sgd function is not suited for that task.
< zoq>
kris1: hm, maybe if you provide the error message we can figure it out?
< zoq>
kris1: You can test it on LogisticRegression or write a simple network, if the simple SGD test function isn't going to work.
< kris1>
zoq : Have look here.
< kris1>
Also one more question. If we are implementing the new policy class can we just not inherit from the base Vanilla SGD and if we have to reuse some function from vanilla sgd it can be called there.
< zoq>
kris1: We could create an SGD object an use that instead of inherit from SGD if we like to use functions from SGD, that's what we do here: https://github.com/mlpack/mlpack/pull/899
< zoq>
kris1: Maybe your last message got cut off; all I can see is "Have look here."