mlpack IRC logs, 2018-05-29

Logs for the day 2018-05-29 (starts at 0:00 UTC) are shown below.

May 2018
Sun
Mon
Tue
Wed
Thu
Fri
Sat
 
 
1
2
3
4
5
6
7
8
9
10
11
26
27
28
29
30
31
--- Log opened Tue May 29 00:00:40 2018
02:24 < zoq> Thanks for all the status updates, really interesting.
02:25 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 256 seconds]
02:25 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
02:41 -!- prakhar_code[m] [prakharcod@gateway/shell/matrix.org/x-ajpmphlmipdmxcpr] has quit [Ping timeout: 245 seconds]
02:41 -!- killer_bee[m] [killerbeem@gateway/shell/matrix.org/x-pogpkmrlsxhubkyg] has quit [Ping timeout: 260 seconds]
02:45 -!- Netsplit *.net <-> *.split quits: xa0, Atharva
02:45 -!- Netsplit over, joins: Atharva, xa0
02:47 -!- Netsplit *.net <-> *.split quits: jenkins-mlpack, zoq
02:47 -!- Netsplit over, joins: zoq, jenkins-mlpack
02:49 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 260 seconds]
02:50 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
03:18 -!- prakhar_code[m] [prakharcod@gateway/shell/matrix.org/x-wdnmwemdecusxyac] has joined #mlpack
03:59 -!- killer_bee[m] [killerbeem@gateway/shell/matrix.org/x-ypbcytcezxolxbau] has joined #mlpack
04:11 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 256 seconds]
05:14 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
08:06 -!- haritha1313 [0e8bf0fb@gateway/web/freenode/ip.14.139.240.251] has joined #mlpack
08:19 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
08:33 -!- sumedhghaisas [~yaaic@2405:204:386:8ada:716a:845e:4645:9f6f] has joined #mlpack
08:49 < haritha1313> zoq: You mentioned writing another class for merging two networks, similar to FAN. I am unable to find any such class. Could you please give some reference to it?
09:07 < ShikharJ> haritha1313: I guess it is Identity Layer, but again better to get confirmation from zoq!
09:17 < haritha1313> ShikharJ: Actually, I need to merge two networks (sequential/FNN) using add/multiply merge.
09:17 < haritha1313> By identity layer, you mean base layer, right?
09:20 < ShikharJ> I'm not sure if you can do this, but maybe you can try doing this (https://github.com/mlpack/mlpack/pull/1204/files#diff-73a3e2abae16e9a84a96856b191900e4R50)?
09:22 < haritha1313> Thanks for your help. I'll take a look at it :)
09:45 -!- Trion [~trion@122.173.56.178] has joined #mlpack
09:48 < jenkins-mlpack> Project docker mlpack nightly build build #333: SUCCESS in 2 hr 34 min: http://masterblaster.mlpack.org/job/docker%20mlpack%20nightly%20build/333/
09:53 -!- sumedhghaisas [~yaaic@2405:204:386:8ada:716a:845e:4645:9f6f] has quit [Remote host closed the connection]
10:21 -!- Trion [~trion@122.173.56.178] has quit [Quit: Entering a wormhole]
10:30 -!- haritha1313 [0e8bf0fb@gateway/web/freenode/ip.14.139.240.251] has quit [Ping timeout: 260 seconds]
11:01 -!- sumedhghaisas [~yaaic@2402:3a80:662:49:716a:845e:4645:9f6f] has joined #mlpack
11:06 -!- sumedhghaisas [~yaaic@2402:3a80:662:49:716a:845e:4645:9f6f] has quit [Ping timeout: 276 seconds]
12:03 -!- sumedhghaisas [~yaaic@223.189.12.253] has joined #mlpack
13:17 -!- sumedhghaisas2 [~yaaic@2402:3a80:66b:d1d0:5293:e8d7:7406:fdf9] has joined #mlpack
13:20 -!- sumedhghaisas [~yaaic@223.189.12.253] has quit [Ping timeout: 260 seconds]
14:03 -!- sumedhghaisas2 [~yaaic@2402:3a80:66b:d1d0:5293:e8d7:7406:fdf9] has quit [Ping timeout: 276 seconds]
14:03 -!- sumedhghaisas [~yaaic@2402:3a80:662:22ae:d79:198b:fbd2:fd10] has joined #mlpack
14:09 < Atharva> Is it okay to initialise helper matrices while implementing functions for a class, inside the function?
14:10 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
14:21 -!- sumedhghaisas2 [~yaaic@2402:3a80:670:67c8:69f4:3387:a222:fdee] has joined #mlpack
14:22 -!- sumedhghaisas [~yaaic@2402:3a80:662:22ae:d79:198b:fbd2:fd10] has quit [Ping timeout: 260 seconds]
14:38 -!- sumedhghaisas2 [~yaaic@2402:3a80:670:67c8:69f4:3387:a222:fdee] has quit [Ping timeout: 276 seconds]
14:41 -!- sumedhghaisas [~yaaic@2402:3a80:64a:7145:9c0:13c3:e808:7fa1] has joined #mlpack
15:15 -!- sumedhghaisas2 [~yaaic@2402:3a80:654:6a5a:3f45:3a7a:fa4e:44ff] has joined #mlpack
15:15 -!- sumedhghaisas [~yaaic@2402:3a80:64a:7145:9c0:13c3:e808:7fa1] has quit [Ping timeout: 260 seconds]
15:25 < rcurtin> Atharva: I'm not sure I have enough context to say for sure, but I don't see any particular issue with that. I'd say, go ahead and do what you need to do, and if it's an issue it'll probably get brought up during a PR review :)
15:25 < Atharva> I figured it out, so no problem now.
15:40 < rcurtin> sounds good :)
16:06 < zoq> haritha1313: Actually I was talking about writing an extra class similair to the GAN class #1204, the idea is we can construct the GAN with two networks (generator and discriminator). We could do the same for th NCF module. Internally we merge the results. Do you think that could work here, if not let's just use Sequential layer, wich acts as a FFN class, but can be used with the merge/add layer.
16:11 < zoq> haritha1313: About the failing test, since it's just a failing simple test to see if we can retrain, let's use:
16:11 < zoq> arma::mat randomData = arma::zeros(100, 100);
16:11 < zoq> randomData.diag().ones();
16:11 < zoq> instead of
16:11 < zoq> arma::mat randomData(100, 100);
16:11 < zoq> randomData.randu();
16:11 < zoq> which should solve the issue.
16:23 < ShikharJ> zoq: Can I have a review of #1204 please? If I can be sure of its correctness for batchSize=1 case, then I can also run it for batchSize > 1 case and get the code merged.
16:32 -!- sumedhghaisas2 [~yaaic@2402:3a80:654:6a5a:3f45:3a7a:fa4e:44ff] has quit [Ping timeout: 265 seconds]
16:37 -!- sumedhghaisas [~yaaic@2402:3a80:65c:c546:80b3:fd08:8bf2:2dad] has joined #mlpack
16:48 -!- haritha1313 [0e8bf0fb@gateway/web/freenode/ip.14.139.240.251] has joined #mlpack
16:48 < haritha1313> zoq: Wow, that just solved it :D . I still don't understand though why it was giving error for random values.
16:49 < haritha1313> Ah, you meant GAN. A typo then. Actually there wasn't much documentation available even for sequential layer. Thats why I thought of looking into the alternative solution you gave.
16:50 < haritha1313> I'll see how it turns out with sequential itself then.
16:51 -!- sumedhghaisas2 [~yaaic@2402:3a80:670:918f:7cb3:6722:9299:c4f6] has joined #mlpack
16:52 -!- sumedhghaisas [~yaaic@2402:3a80:65c:c546:80b3:fd08:8bf2:2dad] has quit [Ping timeout: 276 seconds]
17:10 -!- sumedhghaisas2 [~yaaic@2402:3a80:670:918f:7cb3:6722:9299:c4f6] has quit [Ping timeout: 240 seconds]
17:11 -!- sumedhghaisas [~yaaic@2402:3a80:64a:71b0:100e:8413:ffa9:3240] has joined #mlpack
17:32 -!- haritha1313 [0e8bf0fb@gateway/web/freenode/ip.14.139.240.251] has quit [Ping timeout: 260 seconds]
17:41 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 260 seconds]
18:06 -!- sumedhghaisas [~yaaic@2402:3a80:64a:71b0:100e:8413:ffa9:3240] has quit [Ping timeout: 265 seconds]
18:07 -!- sumedhghaisas [~yaaic@2402:3a80:64a:71b0:100e:8413:ffa9:3240] has joined #mlpack
18:13 -!- sumedhghaisas [~yaaic@2402:3a80:64a:71b0:100e:8413:ffa9:3240] has quit [Ping timeout: 260 seconds]
18:13 -!- sumedhghaisas2 [~yaaic@2402:3a80:679:4227:7db3:e12c:2f46:c7f6] has joined #mlpack
18:18 -!- __sulan__ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
18:22 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Ping timeout: 264 seconds]
19:08 -!- sulan_itk [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
19:11 -!- __sulan__ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Ping timeout: 268 seconds]
19:12 -!- sulan_itk is now known as sulan_
19:22 -!- sumedhghaisas [~yaaic@2402:3a80:667:1208:4f84:caf4:2f2d:f554] has joined #mlpack
19:26 -!- sumedhghaisas2 [~yaaic@2402:3a80:679:4227:7db3:e12c:2f46:c7f6] has quit [Ping timeout: 260 seconds]
19:35 -!- sumedhghaisas [~yaaic@2402:3a80:667:1208:4f84:caf4:2f2d:f554] has quit [Ping timeout: 276 seconds]
19:35 -!- sumedhghaisas [~yaaic@2402:3a80:650:71f7:1102:3fca:ef03:7852] has joined #mlpack
19:41 -!- sumedhghaisas2 [~yaaic@2402:3a80:675:31e0:3f0f:f093:dc56:774f] has joined #mlpack
19:42 -!- sumedhghaisas [~yaaic@2402:3a80:650:71f7:1102:3fca:ef03:7852] has quit [Ping timeout: 265 seconds]
19:47 < ShikharJ> zoq: Could you tell me how I could visualize or plot .arm data?
19:53 < zoq> one way ist to save the matrix as csv and to use pyplot or maplot
19:53 < rcurtin> if you were lazy, you could use the preprocessing utilities as a format converter:
19:54 < rcurtin> mlpack_preprocess_split -i data.arm -t train.csv -T test.csv; cat train.csv test.csv > data.csv
19:54 < rcurtin> (but that will shuffle the data too, if that matters)
19:54 < zoq> waht about using armadillo and save as pgm
20:02 < rcurtin> oh, yeah, that could work also
20:03 < rcurtin> but I think Armadillo will only do 8-bit PGM, which I guess will work if it's MNIST data or something
20:09 -!- sumedhghaisas [~yaaic@27.4.20.166] has joined #mlpack
20:10 -!- sumedhghaisas2 [~yaaic@2402:3a80:675:31e0:3f0f:f093:dc56:774f] has quit [Ping timeout: 265 seconds]
20:17 < Atharva> I am sorry if it's a very basic doubt, but what do delta matrices signify in the layer objects? When I studied backpropogation, I don't remember encountering it.
20:29 < Atharva> Isn't delta and error the same thing?
20:30 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Quit: Leaving]
21:11 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Quit: Leaving]
--- Log closed Wed May 30 00:00:41 2018