ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at http://www.mlpack.org/irc/
< ShikharJ> sakshamB: Toshal: Also I hope that you guys would please be regular with the blog-posts so that I can stay updated with your work.
xiaohong has joined #mlpack
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
xiaohong has quit [Remote host closed the connection]
< rcurtin> zoq: awesome, thanks!
k3nz0 has joined #mlpack
xiaohong has joined #mlpack
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
ImQ009 has joined #mlpack
< xiaohong> Hi, anyone know how to use element-wise product in arma::mat ?
< xiaohong> Oh, I find the document. Sorry for bothering.
< jenkins-mlpack2> Project docker mlpack nightly build build #400: STILL UNSTABLE in 3 hr 53 min: http://ci.mlpack.org/job/docker%20mlpack%20nightly%20build/400/
ImQ009 has quit [Read error: Connection reset by peer]
ImQ009 has joined #mlpack
< xiaohong> I have a questions, how to convert to arma::colvec to arma::mat to perform element-wise product?
< xiaohong> Anyone know how to solve this problem?
Yashwants19 has joined #mlpack
< Yashwants19> Hi xiahong: For converting arma::colvec into arma::mat
< Yashwants19> You can use an advanced constructor.
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
< Yashwants19> A .memptr() of colvec.
Yashwants19 has quit [Remote host closed the connection]
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
< zoq> xiaohong: arma::conv_to should help
< zoq> xiaohong Yashwants19: advanced constructor does work as well
< xiaohong> Yashwants19: sorry for missing the message.
< xiaohong> zoq: Yes. I fixed it.
< xiaohong> Yashwants19: The issue was fixed.
< xiaohong> zoq: I have a little difficult on understanding how the backward function work.
< xiaohong> If I use empty loss in the model, I have a problem in performing backward.
< xiaohong> The `currentInput` variable is a [0x0] matrix.
< zoq> xiaohong: The currentInput parameter is set in the Forward step.
< zoq> xiaohong: If it is [0x0] advantages in criticNetwork.Backward(advantages, criticGradients); has to be [0x0]
< xiaohong> zoq: Acctually, the [0x0] currentInput is in the last but one layer.
< zoq> xiaohong: Not sure I can follow.
< xiaohong> Currently, I am debugging the actorNetwork
< xiaohong> No worries, I review the mechanism of fnn again.
< xiaohong> And trying to figure it out.
< zoq> xiaohong: Okay, will run the code later.
< xiaohong> Yeah, I will take a deeper look at it. Thank you~
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
iamprayush has joined #mlpack
iamprayush has quit [Remote host closed the connection]
jeffin143 has joined #mlpack
< jeffin143> lozhnikov : Is there anything I should do with 1814 PR ?
< jeffin143> Also I will try to benchmark the string-cleaning PR today and once Bench-marked We can take that ahead from there :)
< jeffin143> Also I wil try to be more active here from now on, Currently in last year of graduation, so got caught up with some of the placement drives
jeffin143 has quit [Ping timeout: 260 seconds]
xiaohong has quit [Remote host closed the connection]
vivekp has joined #mlpack
vivekp has quit [Ping timeout: 244 seconds]
< lozhnikov> jeffin143: No, I think #1814 is almost done, I'll push the fixes by Monday.
xiaohong has joined #mlpack
xiaohong has quit [Remote host closed the connection]
KimSangYeon-DGU has joined #mlpack
vivekp has joined #mlpack
vivekp has quit [Read error: Connection reset by peer]
vivekp has joined #mlpack
KimSangYeon-DGU has quit [Remote host closed the connection]
< Toshal> sakshamB: Why do you need the dimension of non-bias weight? For using it into the formula or just for setting and intializing them?
< Toshal> ShikharJ: Please review my label smoothing PR. I will need it for LSGANs.
vivekp has quit [Ping timeout: 245 seconds]
ImQ009 has quit [Quit: Leaving]