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/
sumedhghaisas has quit [Ping timeout: 260 seconds]
conrad_ has left #mlpack []
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
govg has joined #mlpack
andrzejku has joined #mlpack
vivekp has quit [Ping timeout: 260 seconds]
vivekp has joined #mlpack
kris1 has joined #mlpack
kris1 has quit [Quit: kris1]
partobs-mdp has joined #mlpack
partobs-mdp has quit [Client Quit]
partobs-mdp has joined #mlpack
shikhar has joined #mlpack
shikhar has quit [Client Quit]
pretorium has joined #mlpack
partobs-mdp has quit [Ping timeout: 260 seconds]
theycallhimkost has joined #mlpack
pretorium has quit [Ping timeout: 240 seconds]
partobs-mdp has joined #mlpack
theycallhimkost has quit [Ping timeout: 240 seconds]
kris1 has joined #mlpack
partobs-mdp has quit [Read error: Connection reset by peer]
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
mentekid has quit [Quit: Leaving.]
partobs-mdp has joined #mlpack
mikeling has joined #mlpack
< partobs-mdp> zoq: rcurtin: implemented the scheme we've discussed yesterday. I get more or less stable 60% precision on the CopyTask setting we've used as a test.
< partobs-mdp> By the way, I'm trying to add --trials option to average the results from several runs inside the program execution. However, I get some weird exception on the second run:
< partobs-mdp> error: Mat::rows(): indices out of bounds or incorrectly used
< partobs-mdp> I seem to have seen that bug before (deja vu?)
< partobs-mdp> Looks like an RNN destructor issue, what do you think?
< partobs-mdp> Can you rerun my code (I've pushed it to my fork) to check the reproducibility?
< partobs-mdp> bin/mlpack_lstm_baseline -t copy -e 500 -b 2 -l 10 -r 1 -s 128 -v --trials 5
< partobs-mdp> 73% on the rerun, but it's still strange - IMHO, looks like it executes less iterations than the previous version (but why?)
partobs-mdp has quit [Remote host closed the connection]
pretorium has joined #mlpack
< pretorium> rcurtin: zoq: Dropped Internet connection. Can't see the logs - did you respond yet?
pretorium has left #mlpack []
partobs-mdp has joined #mlpack
< partobs-mdp> (pretorium is my fallback nickname - no idea why it activated)
shikhar has joined #mlpack
govg has quit [Quit: leaving]
mentekid has joined #mlpack
partobs-mdp has quit [Read error: Connection reset by peer]
kris1 has quit [Quit: kris1]
shikhar has quit [Quit: WeeChat 1.7]
mentekid has quit [Ping timeout: 240 seconds]
kris1 has joined #mlpack
mentekid has joined #mlpack
mentekid has quit [Ping timeout: 240 seconds]
< kris1> Hi zoq, don’t you think there should be a model level forward visitor as well
< kris1> right now there is only a layer level forward function
mentekid has joined #mlpack
< ironstark> https://paste.ubuntu.com/25098575/ This is my shogun SVM implementation. Getting the error : [DEBUG] [ERROR] In file
< ironstark> me/dewang/benchmarks/libraries/shogun/src/shogun/multiclass/MulticlassLibSVM.cpp
< ironstark> line 203: SVM set failed
< ironstark> .E..
< ironstark> cant figure out the reason :(
shikhar has joined #mlpack
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
shikhar has quit [Quit: WeeChat 1.7]
andrzejku has quit [Quit: Textual IRC Client: www.textualapp.com]