mlpack IRC logs, 2018-03-04

Logs for the day 2018-03-04 (starts at 0:00 UTC) are shown below.

March 2018
Sun
Mon
Tue
Wed
Thu
Fri
Sat
 
 
 
 
1
2
3
4
5
6
7
8
9
31
--- Log opened Sun Mar 04 00:00:37 2018
00:23 -!- zoq [~marcus_zo@urgs.org] has joined #mlpack
03:19 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
05:27 -!- bdd_ [67144133@gateway/web/freenode/ip.103.20.65.51] has joined #mlpack
06:21 -!- bdd_ [67144133@gateway/web/freenode/ip.103.20.65.51] has quit [Quit: Page closed]
06:56 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 265 seconds]
07:11 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
07:15 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
08:07 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 240 seconds]
08:28 -!- witness [uid10044@gateway/web/irccloud.com/x-hhzlmgrbayiixxcs] has quit [Quit: Connection closed for inactivity]
09:10 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
09:10 -!- Trion [~trion@61.2.247.63] has joined #mlpack
10:01 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 245 seconds]
10:04 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
10:44 -!- sumedhghaisas [~yaaic@host-92-24-109-143.ppp.as43234.net] has joined #mlpack
11:27 -!- satyam_2401 [0e8bc409@gateway/web/freenode/ip.14.139.196.9] has joined #mlpack
11:31 -!- satyam_2401_ [uid282868@gateway/web/irccloud.com/x-itueofjeqsorpzps] has joined #mlpack
11:32 -!- satyam_2401 [0e8bc409@gateway/web/freenode/ip.14.139.196.9] has quit [Client Quit]
11:32 -!- satyam_2401_ is now known as satyam_2401
12:39 -!- Trion [~trion@61.2.247.63] has quit [Quit: Entering a wormhole]
13:20 < dk97[m]> zoq: I have added the loss functions folder along with the KL Divergence loss.
13:21 < dk97[m]> MSE and Cross-entropy are already implemented in the ann_layers folder, should I shift them to the loss_functions folder?
13:21 < dk97[m]> Also, I found some errors in the MSE implementation.
13:26 -!- apoorv_ [9d25f945@gateway/web/freenode/ip.157.37.249.69] has joined #mlpack
13:29 < apoorv_> Hi i am new to mlpack and follpw up the tutorials i want to contribute to the reinforcement leaening project can anyone give w the suggeations what is the most effective way to do that project..
13:30 -!- apoorv_ [9d25f945@gateway/web/freenode/ip.157.37.249.69] has quit [Client Quit]
13:34 -!- sshkhrnwbie [0e8b800f@gateway/web/freenode/ip.14.139.128.15] has joined #mlpack
13:35 < sshkhrnwbie> @zoq I finished up with the variance scaling initializer PR #1241 (from my end, yet to merge). I was going to get started on the randomized leaky relu as we discussed on 14/2
13:35 -!- prashanthd [uid283531@gateway/web/irccloud.com/x-uomhjjaozakvxyrd] has joined #mlpack
13:35 -!- raivaibhav [0e8bf052@gateway/web/freenode/ip.14.139.240.82] has joined #mlpack
13:35 -!- raivaibhav [0e8bf052@gateway/web/freenode/ip.14.139.240.82] has quit [Client Quit]
13:36 < sshkhrnwbie> @zoq I am going to implement it similar to dropout with a deterministic flag for randomising the activations during train time and fixing them during test. Does this sound right.
13:37 < sshkhrnwbie> @zoq Here is the link to the paper on arxiv for your reference https://arxiv.org/pdf/1505.00853.pdf
13:41 -!- sshkhrnwbie [0e8b800f@gateway/web/freenode/ip.14.139.128.15] has quit [Ping timeout: 260 seconds]
13:44 -!- satyam_2401 [uid282868@gateway/web/irccloud.com/x-itueofjeqsorpzps] has quit [Quit: Connection closed for inactivity]
13:58 -!- daivik [6adbb428@gateway/web/cgi-irc/kiwiirc.com/ip.106.219.180.40] has joined #mlpack
14:09 -!- daivik [6adbb428@gateway/web/cgi-irc/kiwiirc.com/ip.106.219.180.40] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client]
14:47 -!- ImQ009_ [~ImQ009@unaffiliated/imq009] has joined #mlpack
14:50 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Ping timeout: 256 seconds]
15:40 -!- satyam_2401 [uid282868@gateway/web/irccloud.com/x-tsvbkjsjttbigxsu] has joined #mlpack
16:05 -!- prashanthd [uid283531@gateway/web/irccloud.com/x-uomhjjaozakvxyrd] has quit [Quit: Connection closed for inactivity]
17:26 -!- sumedhghaisas2 [~yaaic@85.255.234.13] has joined #mlpack
17:27 -!- sumedhghaisas [~yaaic@host-92-24-109-143.ppp.as43234.net] has quit [Ping timeout: 248 seconds]
17:44 -!- sumedhghaisas2 [~yaaic@85.255.234.13] has quit [Ping timeout: 256 seconds]
17:56 -!- csoni [~chintan@103.81.36.189] has joined #mlpack
17:58 -!- sumedhghaisas [~yaaic@85.255.234.13] has joined #mlpack
18:03 -!- sumedhghaisas [~yaaic@85.255.234.13] has quit [Ping timeout: 268 seconds]
18:06 -!- sumedhghaisas [~yaaic@185.69.144.107] has joined #mlpack
18:25 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 256 seconds]
18:39 -!- satyam_2401 [uid282868@gateway/web/irccloud.com/x-tsvbkjsjttbigxsu] has quit [Quit: Connection closed for inactivity]
18:43 -!- sumedhghaisas [~yaaic@185.69.144.107] has quit [Ping timeout: 268 seconds]
18:45 -!- daivik [9d31f0ab@gateway/web/cgi-irc/kiwiirc.com/ip.157.49.240.171] has joined #mlpack
19:39 < luffy1996> zoq: Hey I am pretty free from hectic examination schedule. I would like to know if you went through my PR request. I would like to know whether I should proceed with implementing policy gradient methods on mlpack .
20:00 -!- sumedhghaisas [~yaaic@148.252.129.98] has joined #mlpack
20:09 -!- sumedhghaisas [~yaaic@148.252.129.98] has quit [Ping timeout: 240 seconds]
20:36 -!- witness [uid10044@gateway/web/irccloud.com/x-gjetrqovtjkhhfoy] has joined #mlpack
20:45 -!- csoni [~chintan@103.81.36.189] has quit [Remote host closed the connection]
20:56 < daivik> rcurtin: Please forgive me if this is a stupid question, but is there a reason why there are two separate template params for each VecType in mlpack/core/metrics/lmetric.hpp:Evaluate() function? I mean, wouldn't we only want the distance between two arma::vecs or two arma::sp_vecs. I dont see where we would need to find the distance between an arma
20:56 < daivik> ::vec and an arma::sp_vec.. Moreover, attempting to do that results in a segfault (as it should). Isn't VecTypeB redundant?
20:57 < rcurtin> daivik: don't forget armadillo subview types; that's the real reason
20:58 < rcurtin> finding the distance between an arma::vec and arma::sp_vec should not cause a segfault, by the way
21:01 -!- sumedhghaisas [~yaaic@148.252.129.98] has joined #mlpack
21:03 < daivik> https://thepasteb.in/p/lOhOKBYZ379SB --> this causes segfault for me - I assume this is an issue then?
21:07 < daivik> rcurtin: Also about the subview types -- do you mean something like distance between arma::vec and (some arma::mat).col(0) ?
21:09 < rcurtin> the code looks fine to me, it is strange that it causes a segfault. I looked in Evaluate(), I see little reason why what you have there shouldn't work, unless the vec and the sp_vec are not the same dimensions
21:09 < rcurtin> and yes, for the subview types, mat.col() returns a different type
21:11 < daivik> In the code, both the vec and the sp_vec are the same vector (and hence have same dimensions) - this can be seen by adding cout statements.
21:17 -!- sumedhghaisas [~yaaic@148.252.129.98] has quit [Read error: Connection reset by peer]
21:17 -!- sumedhghaisas [~yaaic@host-92-24-110-29.ppp.as43234.net] has joined #mlpack
21:18 -!- nirajgoel [a55b0d9c@gateway/web/freenode/ip.165.91.13.156] has joined #mlpack
21:22 -!- zoq [~marcus_zo@urgs.org] has quit [Remote host closed the connection]
21:23 -!- zoq [~marcus_zo@urgs.org] has joined #mlpack
21:26 -!- ImQ009_ [~ImQ009@unaffiliated/imq009] has quit [Quit: Leaving]
21:28 -!- sumedhghaisas2 [~yaaic@host-92-24-109-143.ppp.as43234.net] has joined #mlpack
21:29 -!- sumedhghaisas [~yaaic@host-92-24-110-29.ppp.as43234.net] has quit [Ping timeout: 240 seconds]
21:45 < daivik> rcurtin: I'll look into this a bit more tomorrow morning and let you know what I find.. Thanks for your help :)
21:49 -!- sumedhghaisas2 [~yaaic@host-92-24-109-143.ppp.as43234.net] has quit [Read error: Connection reset by peer]
21:49 -!- sumedhghaisas [~yaaic@host-92-24-109-143.ppp.as43234.net] has joined #mlpack
21:50 -!- nirajgoel [a55b0d9c@gateway/web/freenode/ip.165.91.13.156] has quit [Quit: Page closed]
22:02 -!- daivik [9d31f0ab@gateway/web/cgi-irc/kiwiirc.com/ip.157.49.240.171] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client]
--- Log closed Mon Mar 05 00:00:39 2018