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/
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid1 has joined #mlpack
mentekid has quit [Read error: Connection reset by peer]
mentekid1 has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
sumedhghaisas has quit [Ping timeout: 260 seconds]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid1 has joined #mlpack
mentekid1 has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid1 has joined #mlpack
mentekid1 has quit [Client Quit]
mentekid1 has joined #mlpack
mentekid1 has quit [Client Quit]
mentekid1 has joined #mlpack
mentekid1 has quit [Client Quit]
mentekid has quit [Ping timeout: 260 seconds]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mentekid has joined #mlpack
mentekid has quit [Client Quit]
mikeling has joined #mlpack
sumedhghaisas has joined #mlpack
partobs-mdp has joined #mlpack
sumedhghaisas has quit [Ping timeout: 260 seconds]
kris1 has joined #mlpack
< ironstark> Hi getting the following error while running the matlab scripts on slake
< ironstark> can you please help with how to rectify it
andrzejku has joined #mlpack
andrzejku has quit [Quit: Textual IRC Client: www.textualapp.com]
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
shikhar has joined #mlpack
shikhar_ has joined #mlpack
shikhar has quit [Ping timeout: 240 seconds]
shikhar has joined #mlpack
shikhar_ has quit [Ping timeout: 255 seconds]
shikhar has quit [Ping timeout: 260 seconds]
shikhar has joined #mlpack
< zoq> ironstark: Hello, have you resolved the issue?
< ironstark> zoq: No
< ironstark> I am not able to test the scripts locally
< ironstark> so creating PR's and testing them
< ironstark> but that slows down the speed so can you please help me in solving it
< zoq> ironstark: let me take a look
< zoq> ironstark: export MATLAB_BIN=/opt/matlab/bin/ should solve the issue
< zoq> I guess, we could include this step somehow in the Makefile.
< partobs-mdp> zoq: Fixed maxiter bug @rcurtin pointed out. Getting a really nice performance on CopyTask (95% on maxLen = 8). I'll run it a bit more and push it into my fork.
< partobs-mdp> rcurtin: Could you rerun the shell scripts then?
< zoq> partobs-mdp: Nice, I think the result for the copy task are fine.
< ironstark> zoq: It worked thanks a lot :)
< ironstark> but the latest jenkins build failed because of that error too
shikhar_ has joined #mlpack
shikhar has quit [Ping timeout: 248 seconds]
< zoq> ironstark: It should be fixed now.
< ironstark> yes that is the one I have been getting since morning
< ironstark> Now that things are working locally
< ironstark> I should be able to check it
< zoq> okay, not sure that is helpful, you could start matlab from the console and manually test each line
< ironstark> yes that would be nice. Thanks for the suggestion
shikhar has joined #mlpack
shikhar_ has quit [Ping timeout: 276 seconds]
kris1 has quit [Quit: kris1]
< zoq> partobs-mdp: What do you think about the comments I made in #1005.
kris1 has joined #mlpack
rcurtin has joined #mlpack
rcurtin has joined #mlpack
rcurtin has left #mlpack []
kris1 has joined #mlpack
kris1 has quit [Ping timeout: 276 seconds]
kris1 has joined #mlpack
shikhar has quit [Quit: WeeChat 1.7]
kris1 has quit [Quit: kris1]
shikhar has joined #mlpack
kris1 has joined #mlpack
sumedhghaisas has joined #mlpack
mentekid has joined #mlpack
shikhar has quit [Quit: WeeChat 1.7]
andrzejk_ has joined #mlpack
partobs-mdp has quit [Remote host closed the connection]
andrzejk_ has quit [Quit: Textual IRC Client: www.textualapp.com]
sumedhghaisas has quit [Ping timeout: 260 seconds]
< kris1> Any way to free the parameters of the layer of a network?
< kris1> When training the nework via a sgd optmizer
< zoq> kris1: I'm not sure I get what you mean with free the parameters.
< kris1> sorry i mean freeze
sumedhghaisas has joined #mlpack
< kris1> Where you train only a part of the netwokr and free other weights/biases of the network
< zoq> So you like to train a network but like to end up with the same parameter?
< kris1> So suppose i want to train only some layers in the network
< kris1> and not every layer.
< kris1> suppose i just want to train the last layer in cnn for finetuning.
< zoq> hm, currently there is no option to do that, I think if you use the FFN class you could modify the Gradient function to take only a specific layer into account.
< zoq> I guess you could also store the parameters before the training and reset the parameter afterwards for each layer, but that's probably slow.
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
< kris1> Hmmm, well i am little confused as what does the Backward() and Gradient() function do. I do understand the GradientVisitor() function would call the gradient function of all the layer gradient of each layer and the BackwardVisitor call the error at each layer propogate it backwards i guess.
< kris1> Would this be correct ?/
< zoq> yes, I could show you how to modify the Gradient function, for the FFN class, if that is helpful?
< kris1> That would be great. :)
vivekp has quit [Ping timeout: 251 seconds]
vivekp has joined #mlpack
< kris1> Ahhhh got it…. thanks.
< kris1> okay so for training a gan i need to free the discrminator and then trian the generator. So my question is i would be calling the backward() and gradient() function of the discriminator to the the error and gradient for all the layer in the discrminator network and then i would set the error of the outputlayer of the generator to the backward() function from the 1st layer of the discriminator and then call the optimizer on the generator.
< kris1> Does this make sense to you. I can elaborate if you want.
< zoq> Makes sense, yes.