mlpack IRC logs, 2018-04-06

Logs for the day 2018-04-06 (starts at 0:00 UTC) are shown below.

April 2018
Sun
Mon
Tue
Wed
Thu
Fri
Sat
1
2
3
4
5
6
7
8
9
10
11
12
13
28
29
30
--- Log opened Fri Apr 06 00:00:24 2018
00:32 -!- witness [uid10044@gateway/web/irccloud.com/x-acoxuvgrqlwvvdqq] has quit [Quit: Connection closed for inactivity]
03:57 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 256 seconds]
04:00 -!- thepro [~thepro@117.239.115.118] has joined #mlpack
04:32 -!- thepro [~thepro@117.239.115.118] has quit [Ping timeout: 240 seconds]
04:33 -!- thepro [~thepro@117.239.115.118] has joined #mlpack
04:42 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
04:52 -!- thepro [~thepro@117.239.115.118] has quit [Ping timeout: 256 seconds]
05:04 -!- thepro [~thepro@117.239.115.118] has joined #mlpack
05:27 -!- thepro [~thepro@117.239.115.118] has quit [Ping timeout: 240 seconds]
05:41 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 264 seconds]
05:46 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
07:09 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
07:14 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
08:11 -!- manthan [6725c94b@gateway/web/freenode/ip.103.37.201.75] has joined #mlpack
08:44 -!- manthan [6725c94b@gateway/web/freenode/ip.103.37.201.75] has quit [Ping timeout: 260 seconds]
09:20 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 260 seconds]
09:26 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
09:37 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 260 seconds]
09:39 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
10:23 -!- rajiv_ [6a3313d8@gateway/web/freenode/ip.106.51.19.216] has joined #mlpack
10:33 -!- rajiv_ [6a3313d8@gateway/web/freenode/ip.106.51.19.216] has quit [Ping timeout: 260 seconds]
10:43 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
10:43 -!- sumedhghaisas2 [~yaaic@host-92-8-33-72.as43234.net] has quit [Read error: Connection reset by peer]
10:46 -!- sumedhghaisas2 [~yaaic@185.69.144.251] has joined #mlpack
10:48 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Ping timeout: 256 seconds]
10:52 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
10:53 -!- sumedhghaisas2 [~yaaic@185.69.144.251] has quit [Ping timeout: 260 seconds]
10:57 -!- manthan [6725c94b@gateway/web/freenode/ip.103.37.201.75] has joined #mlpack
10:58 < manthan> zoq : you there?
11:00 < manthan> i explicitly printed costPlus, costMinus, orgGradient and estGradient for the test and found that for both cases (full module and specific module), costPlus = costMinus, but still in full module test, estGradient comes to be equal to orgGradient but in specific test it comes to be 0.
11:00 < manthan> might be due to any precision loss issues?
11:05 < zoq> possible
11:07 < zoq> Checked the backward and gradient step and I don't think there is an issue.
11:10 < manthan> ya then why could the checkgradient be failing?
11:38 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Read error: Connection reset by peer]
11:39 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
11:41 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Read error: Connection reset by peer]
11:42 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
12:06 -!- sumedhghaisas2 [~yaaic@185.69.144.254] has joined #mlpack
12:08 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Ping timeout: 245 seconds]
12:38 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 240 seconds]
12:39 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
12:45 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 245 seconds]
12:48 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
12:53 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 255 seconds]
12:56 -!- sumedhghaisas2 [~yaaic@185.69.144.254] has quit [Ping timeout: 240 seconds]
12:57 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
12:58 -!- sumedhghaisas [~yaaic@185.69.144.254] has joined #mlpack
13:03 -!- dmatt [~quassel@91.140.124.33] has joined #mlpack
13:09 -!- robertohueso [~root@217.216.127.162.dyn.user.ono.com] has joined #mlpack
13:18 -!- dmatt [~quassel@91.140.124.33] has quit [Remote host closed the connection]
13:20 -!- sumedhghaisas2 [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
13:22 -!- sumedhghaisas [~yaaic@185.69.144.254] has quit [Ping timeout: 240 seconds]
13:22 -!- sumedhghaisas3 [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
13:25 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has joined #mlpack
13:25 -!- sumedhghaisas2 [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Ping timeout: 276 seconds]
13:27 -!- sumedhghaisas3 [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Ping timeout: 265 seconds]
13:45 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Quit: Leaving]
13:56 -!- Trion [~trion@117.215.246.12] has joined #mlpack
14:02 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Read error: Connection reset by peer]
14:03 -!- daivik [7d10a738@gateway/web/cgi-irc/kiwiirc.com/ip.125.16.167.56] has joined #mlpack
14:05 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
14:16 < daivik> rcurtin: zoq: I opened PR #12 on the models repo which implements a CNN for the digit recognition Kaggle challenge. Unfortunately, there was already an open PR for implementing LeNet for the same - I apologize, I completely overlooked this. As of now, my model performs slightly better than the one on PR #9 (the LeNet PR) - giving a 94.485% accuracy
14:16 < daivik> on the hidden test data on Kaggle in 40 epochs of training. Also, I think that PR#9 is going to use the original MNIST dataset now (instead of the Kaggle dataset)? I'm hesitant to close my PR right away because I think that I can push the performance a bit more with parameter tuning.. What do you suggest?
14:17 < daivik> *hyperparameter tuning
14:21 -!- daivik [7d10a738@gateway/web/cgi-irc/kiwiirc.com/ip.125.16.167.56] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client]
14:22 -!- daivik [7d10a738@gateway/web/cgi-irc/kiwiirc.com/ip.125.16.167.56] has joined #mlpack
14:22 < rcurtin> daivik: I agree, I'd prefer to take the model that does better. I hadn't looked into that #9 was going to use the MNIST dataset, I agree that we should stick wtih the Kaggle dataset
14:23 < rcurtin> go ahead and leave it open, I'll try and comment in the next few days to figure out how to reconcile the two PRs, maybe we can take a little from each (but I haven't looked closely at yours, and it's been a few days since I looked at #9)
14:35 -!- Trion [~trion@117.215.246.12] has quit [Quit: Entering a wormhole]
14:39 < daivik> okay, sorry again for not checking the open PRs beforehand
14:40 < rcurtin> no problem at all, there are a lot of open PRs :)
14:59 -!- govg [~govg@unaffiliated/govg] has quit [Quit: leaving]
15:48 -!- daivik [7d10a738@gateway/web/cgi-irc/kiwiirc.com/ip.125.16.167.56] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client]
15:53 -!- Trion [~trion@117.215.246.12] has joined #mlpack
17:04 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Read error: Connection reset by peer]
17:05 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
17:25 -!- sumedhghaisas2 [~yaaic@85.255.233.196] has joined #mlpack
17:27 -!- sumedhghaisas [~yaaic@2a00:79e0:d:fd00:c92e:7497:a91:b02c] has quit [Ping timeout: 245 seconds]
17:43 -!- Trion [~trion@117.215.246.12] has quit [Quit: Entering a wormhole]
17:43 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Read error: Connection reset by peer]
17:45 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
17:47 -!- sumedhghaisas2 [~yaaic@85.255.233.196] has quit [Read error: Connection reset by peer]
17:47 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
18:53 -!- sumedhghaisas2 [~yaaic@85.255.233.219] has joined #mlpack
18:53 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Ping timeout: 240 seconds]
18:54 -!- sumedhghaisas2 [~yaaic@85.255.233.219] has quit [Read error: Connection reset by peer]
18:54 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
18:58 -!- robertohueso [~root@217.216.127.162.dyn.user.ono.com] has quit [Quit: leaving]
18:59 -!- sumedhghaisas2 [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
19:01 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Ping timeout: 260 seconds]
19:02 -!- sumedhghaisas2 [~yaaic@host-92-8-33-72.as43234.net] has quit [Read error: Connection reset by peer]
19:02 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
19:06 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Read error: Connection reset by peer]
19:06 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
19:13 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Read error: Connection reset by peer]
19:14 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
19:15 -!- manthan [6725c94b@gateway/web/freenode/ip.103.37.201.75] has quit [Ping timeout: 260 seconds]
19:24 -!- xa0 [~zeta@unaffiliated/uoy] has joined #mlpack
19:52 -!- dmatt [~quassel@91.140.124.33] has joined #mlpack
20:10 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Quit: Leaving]
20:17 -!- dmatt [~quassel@91.140.124.33] has quit [Remote host closed the connection]
20:25 -!- sumedhghaisas2 [~yaaic@85.255.233.222] has joined #mlpack
20:26 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has quit [Ping timeout: 264 seconds]
20:47 -!- sumedhghaisas2 [~yaaic@85.255.233.222] has quit [Read error: Connection reset by peer]
20:48 -!- sumedhghaisas [~yaaic@host-92-8-33-72.as43234.net] has joined #mlpack
21:19 < rcurtin> alright, I have tested and working PyPI packages for linux that I'll upload once the final rebuild is done
21:19 < rcurtin> nothing for Windows though
22:15 -!- Asfaltaplayas [Asfaltapla@90.85-86-111.dynamic.clientes.euskaltel.es] has joined #mlpack
22:15 -!- Asfaltaplayas [Asfaltapla@90.85-86-111.dynamic.clientes.euskaltel.es] has left #mlpack []
22:49 < xa0> hi all, i'm wondering if mlpack supports multi layer perceptrons?
23:16 < rcurtin> xa0: yeah, you can use the deep learning framework to build one
23:17 < xa0> i've just discovered this :D now to upgrade to version 3.0.0 so the deep learning framework actually even exists
23:17 < xa0> thanks rcurtin
23:17 < rcurtin> you could look in src/mlpack/tests/feedforward_network_test.cpp for an example
23:17 < rcurtin> and also http://mlpack.org/docs/mlpack-3.0.0/doxygen/anntutorial.html
23:17 < rcurtin> sure, happy to help :)
23:18 < xa0> gotcha!
--- Log closed Sat Apr 07 00:00:25 2018