--- Log opened Wed Jun 05 00:00:03 2013 | ||
--- Day changed Wed Jun 05 2013 | ||
-!- van51 [~van51@athedsl-408350.home.otenet.gr] has joined #shogun | 00:00 | |
-!- gsomix [~gsomix@188.168.3.7] has quit [Ping timeout: 245 seconds] | 00:05 | |
-!- gsomix [~gsomix@188.168.3.7] has joined #shogun | 00:06 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has joined #shogun | 01:46 | |
-!- van51 [~van51@athedsl-408350.home.otenet.gr] has left #shogun ["QUIT :Leaving."] | 01:53 | |
-!- gsomix [~gsomix@188.168.3.7] has quit [Ping timeout: 256 seconds] | 02:58 | |
-!- gsomix [~gsomix@188.168.3.7] has joined #shogun | 02:58 | |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has quit [Read error: No route to host] | 03:00 | |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has joined #shogun | 03:03 | |
-!- nube [~rho@49.244.20.247] has quit [Ping timeout: 256 seconds] | 03:05 | |
-!- hushell [~hushell@c-67-189-100-116.hsd1.or.comcast.net] has joined #shogun | 04:31 | |
-!- gsomix [~gsomix@188.168.3.7] has quit [Ping timeout: 245 seconds] | 04:54 | |
-!- nube [~rho@36.253.65.127] has joined #shogun | 04:54 | |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has quit [Ping timeout: 248 seconds] | 05:04 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client] | 05:15 | |
-!- nube1 [~rho@36.253.65.127] has joined #shogun | 05:26 | |
-!- nube [~rho@36.253.65.127] has quit [Ping timeout: 248 seconds] | 05:27 | |
-!- nube [~rho@116.90.228.137] has joined #shogun | 05:33 | |
-!- nube1 [~rho@36.253.65.127] has quit [Ping timeout: 248 seconds] | 05:36 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has joined #shogun | 05:52 | |
lambday | sonney2k: good morning :) | 05:52 |
---|---|---|
@sonney2k | lambday, hey! | 05:54 |
@sonney2k | lambday, if you have time please fix the build :) I mean the rng init might help... | 06:07 |
lambday | sonney2k: there is another problem.. in the Complex unittest (which just checks for abs and do not have any permutation before that) also fails for 1e-15.. | 06:07 |
lambday | what could be the reason for that one? :( | 06:07 |
-!- gsomix [~gsomix@83.234.169.64] has joined #shogun | 06:09 | |
@sonney2k | lambday, that should not happen | 06:11 |
lambday | sonney2k: I checked buildbot logs and it shows failure for that test too :( | 06:13 |
-!- gsomix [~gsomix@83.234.169.64] has quit [Ping timeout: 248 seconds] | 06:16 | |
-!- gsomix [~gsomix@83.234.169.64] has joined #shogun | 06:16 | |
@sonney2k | lambday, who is computing abs(a) | 06:18 |
@sonney2k | for a being a complex type? | 06:18 |
gsomix | good morning | 06:18 |
@sonney2k | is this in std:: ? | 06:19 |
lambday | oh.. its the std::abs... I should have used CMath::abs() for complex, but that also currently calls std::abs() only | 06:19 |
@sonney2k | lambday, then you found in a bug in std:: | 06:19 |
@sonney2k | the result is just wrong on bsd | 06:20 |
@sonney2k | lambday, using an arbitrary precision calculator the result should be | 06:20 |
@sonney2k | 7.81024967590665439413 | 06:20 |
@sonney2k | ; (5**2+6**2)^0.5 - 7.81024967590665397665 | 06:21 |
@sonney2k | 0.00000000000000041748 | 06:21 |
@sonney2k | ; (5**2+6**2)^0.5 - 7.8102496759066558 | 06:21 |
@sonney2k | -0.00000000000000140587 | 06:21 |
@sonney2k | is what we see otherwise | 06:21 |
@sonney2k | so <1e-15 is what you have with the number you gave as reference | 06:21 |
@sonney2k | but the other is really off | 06:21 |
@sonney2k | gsomix, morning! today is test day right? | 06:22 |
lambday | sonney2k: okay.. I should change the reference too then.. | 06:22 |
lambday | but what to do with this bsd? I am not sure :( | 06:22 |
@sonney2k | there is no fix | 06:22 |
@sonney2k | we can only go to 1e-14 | 06:23 |
@sonney2k | precision | 06:23 |
lambday | :( | 06:23 |
lambday | okay | 06:23 |
gsomix | sonney2k, yep. | 06:23 |
@sonney2k | and then ask wiking to install newer std stuff | 06:23 |
@sonney2k | gtg, cu | 06:23 |
lambday | sonney2k: okies | 06:23 |
lambday | ciao :) | 06:23 |
lambday | I'll submit the PR soon | 06:23 |
-!- nube [~rho@116.90.228.137] has quit [Ping timeout: 248 seconds] | 06:25 | |
-!- foulwall_ [~foulwall@2001:da8:215:503:8c13:264:5b04:37a7] has joined #shogun | 06:26 | |
-!- nube [~rho@36.253.65.127] has joined #shogun | 06:41 | |
-!- nube1 [~rho@116.90.228.137] has joined #shogun | 06:53 | |
-!- nube [~rho@36.253.65.127] has quit [Ping timeout: 248 seconds] | 06:54 | |
-!- gsomix [~gsomix@83.234.169.64] has quit [Ping timeout: 248 seconds] | 07:37 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client] | 07:47 | |
-!- lambday [67157f4c@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.76] has joined #shogun | 08:17 | |
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun | 08:18 | |
shogun-notifier- | shogun: van51 :develop * d4115d5 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/d4115d5512d5899abb983b3b428a4346d708785b | 08:18 |
shogun-notifier- | shogun: Changed CList to CDynamicObjectArray in CCombinedDotFeatures (WIP) | 08:18 |
shogun-notifier- | shogun: Soeren Sonnenburg :develop * 2eb8ee7 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/2eb8ee78c046490ec87ce2b64d92c3f66743f637 | 08:18 |
shogun-notifier- | shogun: Merge pull request #1138 from van51/feature/dotfeats | 08:18 |
shogun-notifier- | shogun: | 08:18 |
shogun-notifier- | shogun: Changed CList to CDynamicObjectArray in CCombinedDotFeatures | 08:18 |
-!- lambday [67157f4c@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.76] has quit [Client Quit] | 08:21 | |
shogun-buildbot | build #1071 of bsd1 - libshogun is complete: Failure [failed test] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1071 blamelist: Soeren Sonnenburg <sonne@debian.org> | 08:35 |
shogun-buildbot | build #903 of cyg1 - libshogun is complete: Failure [failed compile] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/903 blamelist: Soeren Sonnenburg <sonne@debian.org> | 08:40 |
shogun-buildbot | build #904 of cyg1 - libshogun is complete: Failure [failed configure] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/904 blamelist: van51 <vangelis_51@hotmail.com> | 08:40 |
shogun-buildbot | build #1072 of bsd1 - libshogun is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1072 | 08:42 |
-!- gsomix [~Miranda@r206-10.smr.ru] has joined #shogun | 08:43 | |
-!- lisitsyn [~blackburn@37.61.181.124] has joined #shogun | 08:44 | |
-!- sonne|work [~sonnenbu@sams-office-nat.tomtomgroup.com] has quit [Quit: Leaving.] | 08:48 | |
-!- sonne|work [~sonnenbu@sams-office-nat.tomtomgroup.com] has joined #shogun | 08:48 | |
gsomix | lisitsyn: hey, listing. do you want me to do fourier transformation of your cat? do you have a cat? | 08:49 |
lisitsyn | no I don't | 08:50 |
lisitsyn | :( | 08:50 |
gsomix | sonne|work: and you? have a cat? | 08:50 |
-!- foulwall_ [~foulwall@2001:da8:215:503:8c13:264:5b04:37a7] has quit [Remote host closed the connection] | 08:54 | |
-!- hushell [~hushell@c-67-189-100-116.hsd1.or.comcast.net] has quit [Ping timeout: 260 seconds] | 08:59 | |
-!- lisitsyn [~blackburn@37.61.181.124] has left #shogun [] | 09:09 | |
sonne|work | gsomix: no but feel free to transform my fish :D | 09:10 |
-!- iglesiasg [~iglesiasg@193.147.77.22] has joined #shogun | 09:15 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 09:15 | |
shogun-buildbot | build #1196 of deb3 - modular_interfaces is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/deb3%20-%20modular_interfaces/builds/1196 | 09:18 |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has joined #shogun | 09:36 | |
-!- mode/#shogun [+o lisitsyn] by ChanServ | 09:36 | |
@lisitsyn | sonne|work: I've started on model selection syntax | 09:36 |
sonne|work | nice | 09:37 |
gsomix | ok, signal processing... | 09:39 |
-!- gsomix [~Miranda@r206-10.smr.ru] has quit [Quit: Miranda IM! Smaller, Faster, Easier. http://miranda-im.org] | 09:39 | |
-!- nube1 [~rho@116.90.228.137] has quit [Ping timeout: 264 seconds] | 09:59 | |
-!- nube [~rho@116.90.228.137] has joined #shogun | 10:02 | |
-!- nube [~rho@116.90.228.137] has quit [Ping timeout: 245 seconds] | 10:20 | |
-!- nube [~rho@36.253.75.217] has joined #shogun | 10:41 | |
-!- nube1 [~rho@116.90.228.137] has joined #shogun | 10:51 | |
-!- nube [~rho@36.253.75.217] has quit [Ping timeout: 248 seconds] | 10:55 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has joined #shogun | 10:55 | |
lambday | sonney2k: hi.. I changed our CMath::abs(complex64_t a) to not to make use of std::abs() but rather calculate it | 10:57 |
lambday | sonney2k: I think this should work in bsd.. | 10:57 |
lambday | the SGVector test error also arises from abs()... | 10:57 |
lambday | but I can't check whether it works or not in bsd.. should I keep the tests as 1e-15 and if this time it doesn't work then make it 1e-14? | 10:58 |
lambday | sonne|work: | 10:59 |
sonne|work | lambday: yes makes sense | 11:00 |
lambday | sonne|work: okay.. then sending a PR with just that | 11:02 |
@iglesiasg | lambday, I can merge that now | 11:09 |
@iglesiasg | why did you change the constant in the comparisons? | 11:09 |
lambday | iglesiasg: okay :) thanks | 11:09 |
@iglesiasg | that is the new value you get when you run it with CMath::abs? | 11:09 |
lambday | iglesiasg: no.. this is what I get using bc | 11:09 |
@iglesiasg | bc? | 11:09 |
lambday | similar to what sonne|work: wrote this morning | 11:09 |
lambday | arbitrary precision calculator or something | 11:10 |
@iglesiasg | aham ok | 11:10 |
@iglesiasg | lambday, so did you use another program to get that value? | 11:10 |
lambday | iglesiasg: yes | 11:10 |
lambday | for these two values | 11:10 |
@iglesiasg | lambday, ok, matlab or so? | 11:10 |
lambday | no.. its called bc | 11:11 |
@iglesiasg | and it runs well on your machine | 11:11 |
@iglesiasg | aaah ok, got it now :) | 11:11 |
lambday | http://www.gnu.org/software/bc/manual/html_mono/bc.html | 11:11 |
@iglesiasg | I thought bc was a generic name for arbitrary precision calculators | 11:11 |
@iglesiasg | though I didn't get where the shortform could come from | 11:11 |
lambday | iglesiasg: my mistake :( I should have been more clear with it.. actually I didn't know about this until this morning | 11:12 |
@iglesiasg | lambday, no problem :) | 11:12 |
@iglesiasg | let's just check that the test is fine on travis build | 11:12 |
sonne|work | iglesiasg: matlab just uses double too | 11:12 |
@iglesiasg | and later hope it goes well on bsd | 11:12 |
@iglesiasg | sonne|work, aham | 11:13 |
lambday | yes.. the value that c++ program gives lie within the range 1e-15 of the value that bc gives | 11:13 |
sonne|work | so it suffers the same issues | 11:13 |
@iglesiasg | sonne|work, this arbitrary precision calculator use a list of digits? | 11:13 |
@iglesiasg | or similar idea? | 11:13 |
sonne|work | you tell it how many digits you want | 11:13 |
shogun-notifier- | shogun: lambday :develop * c8cc427 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/c8cc427435b1ab974b66afe409b5f7d4b9803dff | 11:14 |
shogun-notifier- | shogun: CMath::abs(complex64_t) changed to not to use std::abs() | 11:14 |
shogun-notifier- | shogun: Fernando Iglesias :develop * a851de1 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/a851de1f6dd25e4405f34d08edd9451f1f34f9f3 | 11:14 |
shogun-notifier- | shogun: Merge pull request #1148 from lambday/develop | 11:14 |
shogun-notifier- | shogun: | 11:15 |
shogun-notifier- | shogun: CMath::abs(complex64_t) changed to not to make use of std::abs() | 11:15 |
lambday | thanks iglesiasg: hope this works | 11:15 |
* lambday keeping his fingers crossed | 11:15 | |
@iglesiasg | sonne|work, I actually think there is something in matlab to set more precision than double | 11:17 |
sonne|work | iglesiasg: no there is not | 11:17 |
@iglesiasg | ok :) | 11:17 |
sonne|work | iglesiasg: type 1-1.01 | 11:18 |
sonne|work | in matlab | 11:18 |
sonne|work | and set format to the best possible | 11:18 |
sonne|work | then you will see | 11:18 |
@iglesiasg | sonne|work, http://www.mathworks.se/help/symbolic/vpa.html | 11:19 |
sonne|work | IIRC | 11:19 |
sonne|work | format long | 11:19 |
sonne|work | 1-1.01 | 11:19 |
@iglesiasg | I can be wrong | 11:19 |
sonne|work | for some symbolic stuff yeah | 11:20 |
-!- naywhaya1e [~ryan@spoon.lugatgt.org] has joined #shogun | 11:24 | |
-!- Netsplit *.net <-> *.split quits: @sonney2k, thoralf, naywhayare | 11:30 | |
-!- Netsplit over, joins: @sonney2k, thoralf | 11:31 | |
-!- zxtx [~zv@cpe-75-83-151-252.socal.res.rr.com] has joined #shogun | 11:34 | |
@iglesiasg | lambday, it seems the test went fine on BSD | 11:35 |
@iglesiasg | at least this time :) | 11:35 |
lambday | iglesiasg: ah, finally :D | 11:36 |
lambday | yippie :D | 11:36 |
@iglesiasg | mmm although it is building again | 11:36 |
-!- nube1 [~rho@116.90.228.137] has quit [Quit: Leaving.] | 11:36 | |
-!- nube [~rho@116.90.228.137] has joined #shogun | 11:37 | |
lambday | building twice? one for the commit and another for merge? | 11:37 |
@iglesiasg | I think so | 11:38 |
@iglesiasg | lambday, what I find funny is that it seems it first builds the commit with the merge | 11:39 |
lambday | yes.. | 11:39 |
shogun-buildbot | build #905 of cyg1 - libshogun is complete: Failure [failed compile] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/905 blamelist: Fernando Iglesias <fernando.iglesiasg@gmail.com> | 11:39 |
lambday | cyg1 :'( | 11:40 |
* lambday feels like watching last extra 3 mins in a football match | 11:40 | |
@iglesiasg | lambday, cygwin is not your fault | 11:40 |
@iglesiasg | it was already screwed :D | 11:40 |
@iglesiasg | it actually configured well this time | 11:41 |
lambday | sse2 not found or something | 11:41 |
lambday | not enabled | 11:41 |
lambday | yay... bsd works :D | 11:43 |
@lisitsyn | bah | 11:43 |
@lisitsyn | did anyone touch libocas recently? | 11:43 |
@iglesiasg | no idea | 11:44 |
@iglesiasg | nothing that I can remember | 11:44 |
-!- HeikoS [~heiko@nat-173-83.internal.eduroam.ucl.ac.uk] has joined #shogun | 11:49 | |
-!- mode/#shogun [+o HeikoS] by ChanServ | 11:49 | |
thoralf | sonney2k: I put all local changes into a single commit, but I cannot commit them into the remote branch, since it already contains the "old" commits. | 11:49 |
thoralf | sonney2k: Would push --force mess something up? | 11:50 |
shogun-buildbot | build #906 of cyg1 - libshogun is complete: Failure [failed compile] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/906 blamelist: lambday <heavensdevil6909@gmail.com> | 11:50 |
lambday | hi HeikoS | 11:54 |
@HeikoS | hi | 11:54 |
lambday | checking your comments | 11:55 |
@HeikoS | commenting ... :) | 11:55 |
@HeikoS | lambday: done | 11:55 |
lambday | HeikoS: okay.. I'm checking :) | 11:55 |
lambday | HeikoS: alright.. | 11:56 |
lambday | I'm making the changes then | 11:56 |
@iglesiasg | lisitsyn, do you know why the buildbot builds first the merge commit and then the other? | 11:58 |
@iglesiasg | it looks weird to me, since the other one is done first | 11:58 |
sonne|work | thoralf: well not for the PR | 11:58 |
sonne|work | but for the general repository yeah kaboom time :D | 11:58 |
thoralf | sonne|work: So you don't know other ways than 1. a new PR or 2. push --force? | 12:00 |
thoralf | sonne|work: "but for the general repository yeah kaboom time" <-- parse error ;) | 12:00 |
sonne|work | thoralf: push --force is what we usually do | 12:01 |
sonne|work | (for PRs!) | 12:01 |
@lisitsyn | iglesiasg: no don't know why that | 12:02 |
sonne|work | iglesiasg: I think it is building the master branch for some reason | 12:02 |
@iglesiasg | sonne|work, mmm but it seems to build the changes were are pushing these days, that go to develop branch | 12:03 |
sonne|work | iglesiasg: well you can see what it built http://shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun | 12:04 |
@iglesiasg | sonne|work, yep, that is develop | 12:05 |
sonne|work | no idea then | 12:05 |
wiking | lisitsyn: not that i know of | 12:16 |
wiking | (libocas) | 12:16 |
@iglesiasg | wiking, any idea why shogun buildbot builds the commit in that order? | 12:19 |
@iglesiasg | say there is a PR with a commit then someones merge it | 12:20 |
@iglesiasg | it builts first the merge, then the original commit | 12:20 |
lambday | HeikoS: could please have a look at : https://github.com/shogun-toolbox/shogun/pull/1140/files#L19R508 | 12:23 |
wiking | iglesiasg: lol... sorry no idea | 12:28 |
@iglesiasg | then we leave it as x-file :D | 12:29 |
@HeikoS | lambday: good that you found that one! | 12:34 |
lambday | HeikoS: more unit-tests? :( | 12:35 |
lambday | okay adding | 12:35 |
@HeikoS | lambday: not your fault, but this nicely illustrates why one should always add at least one per method that makes sure no nonsense is produced | 12:35 |
@HeikoS | if you could add one for this, this would be very helpful | 12:36 |
lambday | HeikoS: yes.. | 12:37 |
lambday | even I missed a few for complex and SGVector.. I'll make sure that each method is called at least once.. (may not need a separate test case for each method then) | 12:38 |
lambday | or a separate one for each one is better? | 12:38 |
-!- Netsplit *.net <-> *.split quits: @sonney2k, thoralf | 12:40 | |
@HeikoS | seperate is better | 12:41 |
lambday | alright | 12:41 |
@HeikoS | lambday: but depends on how much work you want to invest | 12:41 |
@HeikoS | if its separated, its way easier to track errors | 12:41 |
@HeikoS | tests should be as simple as possible | 12:42 |
@HeikoS | have alook at the SGObject tests I recently added | 12:42 |
lambday | okay | 12:42 |
@HeikoS | 20 of them or so, since it allows to quickly see whats wrong | 12:42 |
lambday | and for the parameters, I should add test cases too in the TParameter tests, right? | 12:43 |
lambday | for complex64_t I mean | 12:43 |
@HeikoS | lambday: question is what to test there | 12:43 |
@HeikoS | but actually, yes that would be helpful | 12:43 |
lambday | compare_ptype | 12:43 |
@HeikoS | since then we have a fine grid of whats going on | 12:43 |
@HeikoS | rather than "serialization doesnt work" | 12:43 |
lambday | okay.. I'll check it | 12:44 |
lambday | will add that too in the PR then? including the edits for error msgs? | 12:44 |
-!- Netsplit over, joins: @sonney2k, thoralf | 12:45 | |
@HeikoS | lambday: yes please do | 12:48 |
lambday | HeikoS: alright :) | 12:48 |
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has joined #shogun | 12:55 | |
-!- nube [~rho@116.90.228.137] has quit [Remote host closed the connection] | 12:58 | |
-!- iglesiasg [~iglesiasg@193.147.77.22] has quit [Quit: Leaving] | 13:14 | |
-!- gsomix [~Miranda@83.234.54.93] has joined #shogun | 13:15 | |
gsomix | passed | 13:15 |
@lisitsyn | away? teacher passed away? :D | 13:16 |
gsomix | lisitsyn: huh, no. then I'd have failed the exam! | 13:20 |
thoralf | gsomix: Dying teacher implies failed exam? | 13:21 |
thoralf | gsomix: Drivers license? :) | 13:21 |
gsomix | thoralf: no, just exam at university. | 13:22 |
thoralf | gsomix: I wasn't serious. ;) | 13:23 |
thoralf | gsomix: I was just wondering, which kind of exam fails if the teacher passes away... :) | 13:23 |
gsomix | thoralf: ok. I'm a little inadequate now. >:3 | 13:24 |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has joined #shogun | 13:26 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 13:28 | |
-!- gsomix [~Miranda@83.234.54.93] has quit [Quit: Miranda IM! Smaller, Faster, Easier. http://miranda-im.org] | 13:48 | |
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has quit [Quit: Leaving] | 13:52 | |
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has joined #shogun | 14:12 | |
@lisitsyn | votjakovr: hey, when do you have exams? | 14:13 |
-!- naywhaya1e is now known as naywhayare | 14:14 | |
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout] | 14:15 | |
votjakovr | lisitsyn: hi, in june, but i'm already free | 14:18 |
@HeikoS | votjakovr: hi! | 14:20 |
@HeikoS | how is it going with the GPs? | 14:20 |
votjakovr | HeikoS: hi, please wait a minute, i'd like to send a PR with moving of latent features to fitc | 14:22 |
@lisitsyn | votjakovr: no exams? | 14:26 |
votjakovr | lisitsyn: almost :) | 14:28 |
-!- Netsplit *.net <-> *.split quits: @sonney2k, thoralf | 14:30 | |
votjakovr | HeikoS: mmm... sorry, integration tests are failed, i'm finding the reason | 14:31 |
@HeikoS | votjakovr: did you change any class members? variables? or any implementation details? | 14:31 |
votjakovr | HeikoS: yep, but diff is empty | 14:32 |
-!- nube [~rho@116.90.228.137] has joined #shogun | 14:33 | |
-!- Netsplit over, joins: @sonney2k, thoralf | 14:34 | |
-!- HeikoS [~heiko@nat-173-83.internal.eduroam.ucl.ac.uk] has quit [Quit: Leaving.] | 14:46 | |
-!- HeikoS [~heiko@nat-173-83.internal.eduroam.ucl.ac.uk] has joined #shogun | 15:16 | |
-!- mode/#shogun [+o HeikoS] by ChanServ | 15:16 | |
-!- lisitsyn1 [~lisitsin@mxs.kg.ru] has joined #shogun | 15:19 | |
lambday | HeikoS: unit-test for float64_t seems okay? | 15:21 |
@HeikoS | lambday: traivs fails | 15:21 |
@HeikoS | CMath::sinh(a) evaluates to 162.07812441272409,162.07812441272406545067 evaluates to 162.07812441272407, and1E-15 evaluates to 1.0000000000000001e-15. | 15:21 |
lambday | err | 15:22 |
lambday | no idea why this happens! | 15:22 |
lambday | it passed all the tests here :( | 15:23 |
@HeikoS | dont know, maybe some library issues? | 15:23 |
@HeikoS | I will get some lunch now, be back in an hour | 15:23 |
lambday | I think so | 15:23 |
lambday | HeikoS: okay, even I'm leaving.. be back in an hour too | 15:23 |
lambday | will fix it then | 15:23 |
@HeikoS | ok, see you then! | 15:24 |
lambday | see you :) | 15:24 |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has quit [Quit: Page closed] | 15:27 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has quit [Quit: lambday] | 15:28 | |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has quit [Read error: Connection reset by peer] | 15:34 | |
-!- nube [~rho@116.90.228.137] has quit [Quit: Leaving.] | 15:36 | |
-!- vgorbati [~vgorbati@212.2.159.34] has joined #shogun | 16:05 | |
-!- vgorbati [~vgorbati@212.2.159.34] has quit [Read error: Operation timed out] | 16:08 | |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has joined #shogun | 16:15 | |
-!- vgorbati [~vgorbati@212.2.159.34] has joined #shogun | 16:17 | |
votjakovr | HeikoS: there is something strange: one of two python integration tests reports about an error and diff is empty, but another one is OK. | 16:20 |
@HeikoS | votjakovr: indeed strange | 16:20 |
@HeikoS | is this related to an example where you changed things? | 16:20 |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 16:20 | |
votjakovr | HeikoS: yep | 16:21 |
@HeikoS | votjakovr: then maybe rewind your changes a bit to see which part borke it? | 16:22 |
@HeikoS | broke | 16:22 |
votjakovr | HeikoS: huh... Ok, I'll try to do so... | 16:23 |
@HeikoS | votjakovr: maybe also show the full error message to me or sonney2k first | 16:24 |
votjakovr | Detailled failures: | 16:26 |
votjakovr | regression_gaussian_process_modular.py setting 1/2 | 16:26 |
votjakovr | ====DIFF================ | 16:26 |
votjakovr | ====EOT================ | 16:26 |
votjakovr | That's all | 16:27 |
@HeikoS | thats weird indeeed | 16:27 |
@HeikoS | no idea what can cause this | 16:27 |
votjakovr | btw i when run this test manually and plot some stuff, everything is OK | 16:28 |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has joined #shogun | 16:29 | |
@HeikoS | I see | 16:29 |
@HeikoS | so then try to find out when this occured | 16:29 |
@HeikoS | this usually solves such problems | 16:29 |
lambday | HeikoS: hi | 16:33 |
lisitsyn1 | votjakovr: HeikoS: looks like a crash for me | 16:36 |
lisitsyn1 | could be that I mean | 16:36 |
-!- Netsplit *.net <-> *.split quits: @sonney2k, thoralf | 16:36 | |
votjakovr | lisitsyn1: I think so, but I when run this test manually and it doesn't report anything | 16:38 |
votjakovr | lisitsyn1: I mean segfaults, etc | 16:39 |
-!- Netsplit over, joins: @sonney2k, thoralf | 16:49 | |
@HeikoS | lisitsyn1: do we have group lasso in shogun? | 16:50 |
@HeikoS | and in particular, group lasso for logistic regression (aka classification) ? | 16:50 |
@HeikoS | sonne|work, sonney2k ^ | 16:50 |
sonne|work | HeikoS: IIRC lisitsyn added that last year | 16:51 |
-!- sonney2k [~shogun@7nn.de] has quit [Ping timeout: 270 seconds] | 16:51 | |
-!- sonney2k [~shogun@7nn.de] has joined #shogun | 16:52 | |
lisitsyn1 | HeikoS: yes multiclass group lasso is here | 16:52 |
@HeikoS | lisitsyn1: which class? | 16:52 |
@HeikoS | and: does it work? :D | 16:52 |
lisitsyn1 | HeikoS: https://github.com/shogun-toolbox/shogun/blob/develop/src/shogun/multiclass/MulticlassTreeGuidedLogisticRegression.cpp | 16:52 |
lisitsyn1 | HeikoS: in general it is tree group lasso | 16:53 |
lisitsyn1 | HeikoS: well I hope it works | 16:53 |
@HeikoS | no documentation .... | 16:53 |
@HeikoS | which algorithm is implemented in there? | 16:53 |
lisitsyn1 | HeikoS: algorithm of learning? | 16:54 |
@HeikoS | so is it based on the multiclass framework and does OvO ? | 16:54 |
lisitsyn1 | HeikoS: OvR | 16:54 |
@HeikoS | and how is the lasso problem solved | 16:54 |
@HeikoS | okay so its core is logistic regression I guess? | 16:54 |
lisitsyn1 | HeikoS: euclidean projection | 16:54 |
lisitsyn1 | IIRC it is called that | 16:54 |
@HeikoS | where did you take this from? | 16:55 |
@HeikoS | where is the algorithm described? | 16:55 |
lisitsyn1 | HeikoS: http://www.public.asu.edu/~jye02/Software/SLEP/ | 16:55 |
lisitsyn1 | HeikoS: http://www.public.asu.edu/~jye02/Software/SLEP/manual.pdf | 16:55 |
lisitsyn1 | HeikoS: tree_mcLogisticR | 16:55 |
@HeikoS | cool thanks! | 16:56 |
@HeikoS | maybe this should be noted in the shogun documentation | 16:56 |
@HeikoS | otherwise no-one will ever use it | 16:56 |
lisitsyn1 | HeikoS: optimization wise it is some moreau-yosida proximal stuff | 16:56 |
@HeikoS | especially in case you suddenly die ;) | 16:57 |
lisitsyn1 | implemented in the 'altra' function | 16:57 |
lisitsyn1 | HeikoS: so basically accelerated projected gradient descend or so | 16:57 |
@HeikoS | lisitsyn1: is there an example how to use it? | 16:57 |
lisitsyn1 | HeikoS: let me check | 16:58 |
lisitsyn1 | HeikoS: https://github.com/shogun-toolbox/shogun/blob/develop/examples/undocumented/python_modular/classifier_featureblock_logistic_regression.py | 16:59 |
lisitsyn1 | like that | 16:59 |
@HeikoS | cool thanks! | 16:59 |
lisitsyn1 | HeikoS: the group stuff is the same | 16:59 |
@HeikoS | so this block stuff defines the groups? | 16:59 |
lisitsyn1 | yes | 16:59 |
@HeikoS | I in fact never used such methods, so forgive me my stupid questions | 16:59 |
lisitsyn1 | HeikoS: haha no that's good question because API is stupid | 17:00 |
lisitsyn1 | HeikoS: you want to regularize groups of features right? | 17:00 |
@HeikoS | yes | 17:01 |
@HeikoS | Let me explain the problem: | 17:01 |
lisitsyn1 | like L1 of (L2 of (1,2,3)) + (L2 of (4,5,6)) | 17:01 |
@HeikoS | maybe you have an idea | 17:01 |
@HeikoS | I have a dataset | 17:01 |
lisitsyn1 | HeikoS: ah wait | 17:01 |
@HeikoS | it consists of frequency measurements of the brain - with a few hundred sensors | 17:01 |
lisitsyn1 | do you need multiclass | 17:02 |
@HeikoS | yes | 17:02 |
lisitsyn1 | or binary? | 17:02 |
lisitsyn1 | alright | 17:02 |
@HeikoS | the sensors are place on the head of a guy | 17:02 |
lisitsyn1 | HeikoS: unfortunately I'd have to ask you to try and let me know if it produces something unreasonable | 17:02 |
@HeikoS | haha ok | 17:02 |
lisitsyn1 | ok lets continue | 17:02 |
lisitsyn1 | so each feature is | 17:03 |
-!- lisitsyn1 is now known as lisitsyn | 17:03 | |
lisitsyn | ampl of some frequency | 17:03 |
lisitsyn | ? | 17:03 |
@HeikoS | yes, its preprocessed I have the FFt coefficients | 17:03 |
@HeikoS | I want to group sensors | 17:03 |
lisitsyn | do you have groups of sensors? | 17:04 |
lisitsyn | or do you want to group them? | 17:04 |
@HeikoS | makes sense to group them | 17:04 |
@HeikoS | the resulting weights are probably sparse | 17:04 |
@HeikoS | but the sparsity structure depends on the sensor positions | 17:04 |
@HeikoS | so I want to try to learn this | 17:04 |
lisitsyn | hmm can you group sensors into some hierarchy? | 17:05 |
lisitsyn | HeikoS: it is important to have these groups already | 17:06 |
lisitsyn | it can't learn the groups itself | 17:06 |
@HeikoS | i know thats fine | 17:06 |
lisitsyn | HeikoS: so the simplest way to go is | 17:07 |
lisitsyn | let me check | 17:07 |
lisitsyn | HeikoS: root is all features | 17:07 |
lisitsyn | HeikoS: tree = IndexBlockTree(IndexBlock(0,n_features)) | 17:08 |
lisitsyn | then if you want no L2 of all features do tree.get_root_block.set_weight(0.0) | 17:08 |
lisitsyn | and then | 17:09 |
@HeikoS | whats the difference between IndexBlockGroup and tree? | 17:09 |
lisitsyn | HeikoS: just how they treat the IndexBlock | 17:09 |
lisitsyn | HeikoS: I mean Tree uses subblocks as childs | 17:09 |
lisitsyn | Group is just a set of blocks | 17:09 |
@HeikoS | so if I have indices | 17:10 |
@HeikoS | [0,1,2,3,4,5,6,7,8,9] | 17:10 |
@HeikoS | and I want groups | 17:10 |
@HeikoS | [0,1,2], [3,4,5], [6,7,8,9] | 17:10 |
lisitsyn | the code will be | 17:10 |
lisitsyn | tree = IndexBlockTree(IndexBlock(0,10)) | 17:10 |
lisitsyn | tree.get_root_block().add_subblock(IndexBlock(0,3)) | 17:11 |
lisitsyn | tree.get_root_block().add_subblock(IndexBlock(3,6)) | 17:11 |
lisitsyn | tree.get_root_block().add_subblock(IndexBlock(6,10)) | 17:11 |
lisitsyn | that's tree | 17:11 |
lisitsyn | root [0,1,2,3,4,5,6,7,8,9] | 17:11 |
lisitsyn | children [0,1,2], [3,4,5], [6,7,8,9] | 17:11 |
@HeikoS | and I want the regulariser to be \lambda \sum ||groups||_2 | 17:11 |
lisitsyn | HeikoS: I didn't implement pure group lasso but tree lasso | 17:12 |
lisitsyn | so you have to put weights here | 17:12 |
@HeikoS | ok, can I simulate this? | 17:12 |
@HeikoS | okay | 17:12 |
lisitsyn | yes | 17:12 |
@HeikoS | how? :) | 17:12 |
lisitsyn | just set the weight of root to 0 | 17:12 |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has quit [Ping timeout: 250 seconds] | 17:12 | |
lisitsyn | and you get L1/L2 | 17:12 |
lisitsyn | otherwise you get L1/L2 of groups | 17:12 |
lisitsyn | plus L2 of all features | 17:13 |
@HeikoS | ok | 17:13 |
@HeikoS | tree.get_root_block.set_weight(0.0) | 17:13 |
@HeikoS | nice | 17:13 |
-!- mode/#shogun [+o sonney2k] by ChanServ | 17:14 | |
@HeikoS | btw, this should really be documented somewhere (sorry to be annoying :) | 17:14 |
lisitsyn | HeikoS: really ugly API | 17:14 |
@HeikoS | why? | 17:14 |
lisitsyn | I want to do something with it but don't know what | 17:14 |
@HeikoS | its fine | 17:14 |
@HeikoS | just one needs to share the knowledge on how to use it | 17:14 |
lisitsyn | HeikoS: about its working capabilities | 17:15 |
lisitsyn | I *know* binary thing works | 17:15 |
lisitsyn | can't say that about multiclass tree thing though | 17:15 |
lisitsyn | but I will be able to find a bug rather quick | 17:15 |
@HeikoS | if binary works and it uses the multoclass framework than it should be fine right? | 17:15 |
@HeikoS | but there are also multinomial formulations of this | 17:16 |
@HeikoS | anyway | 17:16 |
lisitsyn | HeikoS: no that's different solvers | 17:16 |
@HeikoS | I am glad there is something | 17:16 |
@HeikoS | really? | 17:16 |
@HeikoS | I see | 17:16 |
@HeikoS | did you ever test it? | 17:16 |
@HeikoS | like on a toy multiclass problem | 17:16 |
lisitsyn | HeikoS: yes I tried to use it on road signs data | 17:16 |
@sonney2k | lisitsyn, HeikoS - that you are both here. When do we put up a workshop schedule? | 17:16 |
@sonney2k | I mean finalize the schedule! | 17:16 |
lisitsyn | where HoG cells are groups | 17:16 |
@sonney2k | lisitsyn, did it improve anything? | 17:17 |
lisitsyn | HeikoS: it produced reasonable results but worse than SVM | 17:17 |
lisitsyn | sonney2k: no became worse | 17:17 |
@sonney2k | lisitsyn, yeah as expected :D | 17:17 |
@sonney2k | MKL is just crap | 17:17 |
lisitsyn | sonney2k: too many parameters (each group has weight) | 17:17 |
@sonney2k | complex crap | 17:18 |
lisitsyn | haha yes | 17:18 |
@sonney2k | HeikoS, lisitsyn workshop! | 17:18 |
lisitsyn | everything complex sucks it seems | 17:18 |
@sonney2k | 1 month | 17:18 |
lisitsyn | sonney2k: yes yes | 17:18 |
lisitsyn | what's about it? | 17:18 |
@sonney2k | we need to fix the schedule | 17:18 |
@HeikoS | sonney2k: is there a list of people that applied? | 17:18 |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has joined #shogun | 17:18 | |
@sonney2k | as in when & where | 17:18 |
@sonney2k | HeikoS, did you apply? | 17:18 |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 17:18 | |
@HeikoS | sonney2k: no why should I? | 17:18 |
@sonney2k | HeikoS, then do it | 17:19 |
-!- gsomix [~Miranda@85.26.235.51] has joined #shogun | 17:19 | |
@sonney2k | HeikoS, how do we know who will come and what topics we want to see presented/discussed? | 17:19 |
@sonney2k | lisitsyn, did you? | 17:19 |
lisitsyn | sonney2k: applying | 17:20 |
lisitsyn | done | 17:21 |
-!- van51 [~van51@athedsl-408350.home.otenet.gr] has joined #shogun | 17:22 | |
@sonney2k | anyway we need to come up with a fixed workshop program | 17:22 |
@HeikoS | sonney2k: is there a list? | 17:22 |
lisitsyn | HeikoS: list of what? | 17:22 |
@sonney2k | lisitsyn, can you give HeikoS access to the list please | 17:22 |
@sonney2k | workshop document | 17:23 |
@HeikoS | found it | 17:23 |
@HeikoS | didnt know there was this google doc | 17:23 |
@HeikoS | 20 people | 17:23 |
lisitsyn | HeikoS: shared with you :) | 17:23 |
lisitsyn | I'd say 17 | 17:23 |
lisitsyn | ha | 17:23 |
lisitsyn | thoralf: one more :) | 17:24 |
thoralf | :) | 17:24 |
@sonney2k | thoralf, will you come btw? | 17:24 |
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun | 17:24 | |
shogun-notifier- | shogun: Thoralf Klein :develop * 4146e2b / src/shogun/mathematics/Math.h,tests/unit/mathematics/Math_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/4146e2bb6159f01b743c4c6e226714fdda12331f | 17:24 |
shogun-notifier- | shogun: Added test for sorting zero-sized vectors: | 17:24 |
shogun-notifier- | shogun: | 17:24 |
shogun-notifier- | shogun: - CMath::qsort(* T, ...) | 17:24 |
shogun-notifier- | shogun: - CMath::qsort(** T, ...) | 17:24 |
shogun-notifier- | shogun: - CMath::qsort_index(...) | 17:24 |
shogun-notifier- | shogun: Soeren Sonnenburg :develop * 7e999bd / src/shogun/mathematics/Math.h,tests/unit/mathematics/Math_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/7e999bdd3d9c74866e25e3fa628f70fba8b61185 | 17:24 |
shogun-notifier- | shogun: Merge pull request #1145 from tklein23/develop | 17:24 |
shogun-notifier- | shogun: | 17:24 |
@sonney2k | iglesiasg, registered and cheng will also be there | 17:24 |
shogun-notifier- | shogun: Unit tests for CMath::qsort(): Trying to sort empty lists with qsort(*T) and qsort(**T) | 17:24 |
lisitsyn | sonney2k: cheng is already here | 17:25 |
thoralf | sonney2k: I just registered. | 17:25 |
@HeikoS | sonney2k: I suggest we count votes on topics and take the n most voted ideas | 17:26 |
@HeikoS | tree.get_root_block().add_subblock(IndexBlock(0,3)) | 17:27 |
@HeikoS | AttributeError: 'IndexBlock' object has no attribute 'add_subblock' | 17:27 |
@HeikoS | lisitsyn: ^ | 17:28 |
lisitsyn | HeikoS: sub_block may be? | 17:28 |
@HeikoS | yep | 17:29 |
-!- vgorbati [~vgorbati@212.2.159.34] has quit [Quit: vgorbati] | 17:29 | |
lisitsyn | sonney2k: so what should we fix? | 17:30 |
@sonney2k | lisitsyn, the schedule! | 17:30 |
@HeikoS | sonney2k: have we decided on which topics we present? | 17:30 |
@sonney2k | as in who gives a talk about what, what discussions, hands ons thats | 17:30 |
@sonney2k | HeikoS, nope | 17:30 |
@sonney2k | we have to do that | 17:30 |
@HeikoS | sonney2k, lisitsyn so my suggestion on this, just count | 17:30 |
@HeikoS | find volunteers | 17:31 |
@HeikoS | and then assign them the topics | 17:31 |
lisitsyn | yeah lets do that this way | 17:31 |
@HeikoS | I can do that | 17:31 |
@HeikoS | do we have a list of people that want to talk about things? | 17:31 |
lisitsyn | HeikoS: do you want? | 17:31 |
@HeikoS | lisitsyn: maybe we could put names, emails, and topics somewhere | 17:32 |
@sonney2k | oh HeikoS and please don't forget the e.V. thing. the WS is just one month away | 17:32 |
@HeikoS | sonney2k: yes, havent forgot it | 17:32 |
@sonney2k | I don't really want to talk but hey I guess I have to | 17:32 |
@sonney2k | 1 talk only though :) | 17:32 |
@HeikoS | I guess so :D | 17:32 |
shogun-buildbot | build #907 of cyg1 - libshogun is complete: Failure [failed configure] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/907 blamelist: Thoralf Klein <thoralf.klein@zib.de> | 17:33 |
@sonney2k | sry gtg, can we talk about this further in the evening? | 17:33 |
@sonney2k | thoralf, you are famous - | 17:33 |
@HeikoS | sonney2k, lisitsyn so noone has in fact submitted any abstracts | 17:33 |
* sonney2k argh if I only knew why cygwin has problems ... | 17:33 | |
@HeikoS | I guess this means we only have our own talks | 17:34 |
@sonney2k | HeikoS, yes no researchers that need a plane / train ticket | 17:34 |
@sonney2k | in the evening then... cu | 17:34 |
@sonney2k | afk | 17:34 |
-!- shogun-notifier- [~irker@7nn.de] has quit [Ping timeout: 256 seconds] | 17:38 | |
-!- gsomix [~Miranda@85.26.235.51] has quit [Ping timeout: 256 seconds] | 17:41 | |
-!- shogun-toolbox [~shogun@7nn.de] has quit [Ping timeout: 256 seconds] | 17:41 | |
--- Log closed Wed Jun 05 17:41:01 2013 | ||
--- Log opened Wed Jun 05 17:41:12 2013 | ||
-!- shogun-toolbox [~shogun@7nn.de] has joined #shogun | 17:41 | |
-!- Irssi: #shogun: Total of 15 nicks [3 ops, 0 halfops, 0 voices, 12 normal] | 17:41 | |
shogun-buildbot | build #1075 of bsd1 - libshogun is complete: Failure [failed test] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1075 blamelist: Thoralf Klein <thoralf.klein@zib.de> | 17:41 |
-!- gsomix_ [~Miranda@85.26.235.51] has joined #shogun | 17:41 | |
-!- Irssi: Join to #shogun was synced in 6 secs | 17:41 | |
shogun-buildbot | build #1076 of bsd1 - libshogun is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1076 | 17:47 |
-!- gsomix_ [~Miranda@85.26.235.51] has quit [Ping timeout: 264 seconds] | 17:52 | |
-!- sonney2k [~shogun@7nn.de] has quit [Ping timeout: 264 seconds] | 17:52 | |
-!- sonney2k [~shogun@7nn.de] has joined #shogun | 17:53 | |
-!- gsomix [~Miranda@37.61.180.242] has joined #shogun | 17:55 | |
-!- nube1 [~rho@36.253.6.136] has joined #shogun | 17:56 | |
-!- Netsplit *.net <-> *.split quits: lambday, nube, van51 | 17:57 | |
-!- Netsplit over, joins: van51 | 18:05 | |
-!- mode/#shogun [+o sonney2k] by ChanServ | 18:05 | |
-!- iglesiasg [c1934d16@gateway/web/freenode/ip.193.147.77.22] has quit [Quit: Page closed] | 18:08 | |
-!- nube1 [~rho@36.253.6.136] has quit [Ping timeout: 256 seconds] | 18:08 | |
-!- nube [~rho@36.253.6.136] has joined #shogun | 18:08 | |
-!- nube [~rho@36.253.6.136] has quit [Ping timeout: 256 seconds] | 18:13 | |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has joined #shogun | 18:13 | |
-!- nube [~rho@49.244.97.103] has joined #shogun | 18:22 | |
lambday | HeikoS: please take a look at the PR when you're free. | 18:59 |
lambday | I'm taking off for the day.. | 18:59 |
lambday | ciao | 18:59 |
-!- lambday [67157f4e@gateway/web/cgi-irc/kiwiirc.com/ip.103.21.127.78] has quit [Quit: lambday] | 19:00 | |
-!- Netsplit *.net <-> *.split quits: @sonney2k, nube, shogun-buildbot, flxb_, van51 | 19:05 | |
-!- vgorbati [~vgorbati@212.2.159.34] has joined #shogun | 19:05 | |
-!- Netsplit over, joins: nube, van51, @sonney2k, shogun-buildbot, flxb_ | 19:08 | |
-!- zxtx [~zv@cpe-75-83-151-252.socal.res.rr.com] has quit [Ping timeout: 246 seconds] | 19:11 | |
-!- lisitsyn [~blackburn@37.61.180.242] has joined #shogun | 19:13 | |
@sonney2k | lisitsyn, HeikoS so what should be the topics? | 19:25 |
@sonney2k | HeikoS, it looks like lots of people want MMD/HSIC :) | 19:26 |
@HeikoS | sonney2k: can do :) | 19:26 |
@HeikoS | I will do the vote list tomorrow | 19:26 |
@sonney2k | van51, around? | 19:34 |
van51 | sonney2k: yeap | 19:34 |
@sonney2k | van51, could you make sense of what I wrote yesterday about dotfeatures? | 19:35 |
van51 | sonney2k: yea | 19:35 |
van51 | sonney2k: by reading it on the logs | 19:35 |
@sonney2k | and how to do the CHashedDocFeatures / CHashedDocPreprocessor | 19:35 |
@sonney2k | (Doc is not the best word but no idea what else to use) | 19:36 |
@sonney2k | van51, I think this is no more than 1 day of work for you BTW | 19:36 |
van51 | sonney2k: question, the preprocessor can be used offline? | 19:36 |
@sonney2k | van51, offline as in? | 19:36 |
@sonney2k | not sure what you mean | 19:36 |
van51 | I mean use it with a file as input and a file as output | 19:36 |
votjakovr | HeikoS: I've found that difference between a and b in compare function in tester.py approx. 10e-12 on test that gives empty diff | 19:37 |
van51 | and then read that file through a load method | 19:37 |
van51 | or something | 19:37 |
@sonney2k | van51, ohh actually preprocessor won't work - you need a converter | 19:37 |
@HeikoS | votjakovr: say again, I did not get that | 19:37 |
@sonney2k | van51, ok one step back. which interface do you intend to use? | 19:37 |
@sonney2k | pure C++? | 19:37 |
van51 | sonney2k: yea | 19:38 |
@sonney2k | or e.g. python_modular | 19:38 |
@sonney2k | van51, ok then well you can create your stringcharfeatures | 19:38 |
@sonney2k | load some strings from disk | 19:38 |
@sonney2k | and then apply a converter to convert them to DenseFeatures | 19:38 |
@sonney2k | since it is all about wordcounts you can use uint16_t or int32_t | 19:39 |
@sonney2k | for dense features | 19:39 |
@sonney2k | so you would convert StringFeatures<char> -> CDenseFeatures<int32_t> in your converter | 19:40 |
@sonney2k | and then of course you can print the whole matrix | 19:40 |
van51 | sonney2k: ah yea | 19:40 |
votjakovr | HeikoS: I've changed implementation of exact inference method a little bit. Python integration test gives an error and empty diff. I've found that that the difference between a and b in compare function in tester.py approx. 10e-12 | 19:40 |
van51 | sonney2k: this sounds ok to me | 19:40 |
@sonney2k | hmmhh maybe CSparseFeatures<int32_t> is better considering that you use hashes :) | 19:40 |
van51 | sonney2k: I am not sure that the vector will be sparse | 19:41 |
@sonney2k | van51, it will be: look | 19:41 |
@sonney2k | hash(word1) -> some large int | 19:42 |
@sonney2k | and you do this for all words in the docuemnt | 19:42 |
@sonney2k | so depending on the number of bits you use for your hash | 19:42 |
van51 | sonney2k: yes but from what I understand it's for dimensionality reduction and afterwards you mod that number to a specific range 0...d | 19:42 |
@sonney2k | say 20 | 19:42 |
@sonney2k | you have a 1048576 dimensional vector you create of a text document | 19:43 |
@sonney2k | van51, well if you specify number of bits to be say 8 | 19:43 |
@sonney2k | then it will be dense | 19:43 |
@sonney2k | but we the more bits we can afford the better the results | 19:44 |
@sonney2k | so it is usually sparse | 19:44 |
@sonney2k | IIRC spam filters use sth like 32bit | 19:44 |
van51 | sonney2k: ok, got it | 19:44 |
votjakovr | HeikoS: May be it's better to regenerate test data? | 19:44 |
@sonney2k | van51, anyway you should really get started with that | 19:44 |
van51 | sonney2k: I will today | 19:45 |
van51 | sonney2k: btw since we're at it | 19:45 |
van51 | sonney2k: how do I specify the number of bits in the hashes from CHash? | 19:46 |
van51 | hash functions* | 19:46 |
@sonney2k | van51, well just use bitwise & | 19:48 |
@sonney2k | as in x & ((1<<8)-1) | 19:48 |
@sonney2k | would give you an 8 bit hash | 19:48 |
@sonney2k | and btw use murmurhash3 | 19:49 |
van51 | sonney2k: ok I will | 19:50 |
van51 | sonney2k: thanks, you've been really helpful :) | 19:50 |
-!- nube [~rho@49.244.97.103] has quit [Quit: Leaving.] | 19:57 | |
@sonney2k | van51, you just have to do this once. afterwards you will realize how simple this is | 19:59 |
votjakovr | HeikoS: i've just sent a PR, please have a look at it. | 20:02 |
-!- vgorbati [~vgorbati@212.2.159.34] has quit [Quit: vgorbati] | 20:08 | |
@sonney2k | van51, I've found the reason for the crash with the feature iterator | 20:10 |
@sonney2k | van51, bad news is that it is not easy to fix | 20:11 |
van51 | sonney2k: what is it? | 20:11 |
@sonney2k | it is indeed the conversion to SGSparseVector and reference counting | 20:11 |
@sonney2k | the correct patch will be very intrusive | 20:11 |
@sonney2k | no idea what it will break besides that but I suspect serialization and lots of other stuff | 20:12 |
@sonney2k | so I will need HeikoS help then too | 20:12 |
@sonney2k | van51, ok let me try... | 20:12 |
van51 | sonney2k: good luck :) | 20:12 |
-!- vgorbati [~vgorbati@212.2.159.34] has joined #shogun | 20:17 | |
van51 | sonney2k: it's in the get_sparse_feature_vector() method? | 20:18 |
@HeikoS | votjakovr: looking... | 20:24 |
@sonney2k | van51, no it is the whole CSparseFeatureMatrix class | 20:25 |
votjakovr | HeikoS: thanks :) | 20:25 |
@sonney2k | van51, it needs to be converted to internally use SGSparseMatrix | 20:25 |
@HeikoS | sonney2k: reference counting for sparse vectors? | 20:25 |
@sonney2k | van51, otherwise refcounts are kaboom | 20:25 |
@sonney2k | HeikoS, we have that already | 20:25 |
@sonney2k | HeikoS, but SGSparseMatrix is not yet used and I will need help with serialization support for that | 20:26 |
@HeikoS | sonney2k: I see | 20:26 |
@HeikoS | who wnats to have that? | 20:26 |
@sonney2k | HeikoS, sorry what? | 20:28 |
@HeikoS | sonney2k: how come you are working on this? | 20:28 |
@sonney2k | HeikoS, CSparseFeatureMatrix is half-way converted to use our refcounted stuff | 20:28 |
@HeikoS | I see | 20:28 |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has joined #shogun | 20:28 | |
@sonney2k | we have crashers now due to it not being done completely | 20:29 |
@sonney2k | so I am doing it now (or better trying to do it) | 20:29 |
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun | 20:29 | |
shogun-notifier- | shogun: Roman Votyakov :develop * cd27d05 / / (11 files): https://github.com/shogun-toolbox/shogun/commit/cd27d057b1c1a7cd2e5a22741c9b7be1e1d8e896 | 20:29 |
shogun-notifier- | shogun: Redesigned GP framework | 20:29 |
shogun-notifier- | shogun: Heiko Strathmann :develop * 53f4ea1 / / (11 files): https://github.com/shogun-toolbox/shogun/commit/53f4ea1ff26387eb1d85988c3f547c7e8f94676a | 20:29 |
shogun-notifier- | shogun: Merge pull request #1150 from votjakovr/develop | 20:29 |
shogun-notifier- | shogun: | 20:29 |
shogun-notifier- | shogun: Redesigned GP framework | 20:29 |
@HeikoS | sonney2k: I see, sounds like a nasty one | 20:29 |
-!- hushell [~hushell@c-24-21-141-32.hsd1.or.comcast.net] has joined #shogun | 20:29 | |
@HeikoS | at some point we have to fix all these parameter issues and bugs | 20:30 |
@HeikoS | also streaming .... | 20:30 |
@HeikoS | but so much work :( | 20:30 |
@HeikoS | votjakovr: what is the next step? | 20:31 |
@HeikoS | votjakovr: pulling GP class out? | 20:31 |
@sonney2k | votjakovr, woaaah massive patch! | 20:31 |
votjakovr | HeikoS: I'd like to remove check_members methods | 20:31 |
votjakovr | HeikoS: Also solve the problem with recomputing cholesky | 20:32 |
@HeikoS | votjakovr: go ahead ! I agree | 20:32 |
@HeikoS | yep also on that | 20:32 |
@HeikoS | sonney2k: votjakovr is like a steam train :) | 20:32 |
votjakovr | HeikoS: I find that update_parameter_hash() will be very helpful with that | 20:33 |
votjakovr | hehe :D | 20:34 |
@HeikoS | votjakovr: yep :) | 20:34 |
@sonney2k | HeikoS, hehe yeah I would say the same about lambday ;) | 20:34 |
@sonney2k | HeikoS, and you and lisitsyn btw :) | 20:34 |
@HeikoS | yeah lambday rocks totally | 20:34 |
@sonney2k | maybe even more like a start destroyer 'we break for nobody' | 20:35 |
@sonney2k | :D | 20:35 |
lisitsyn | RE! | 20:35 |
@HeikoS | haha :) | 20:35 |
@sonney2k | lisitsyn, I finally understand why you didn't even try to convert sparse featurs to use SGSparseMatrix | 20:35 |
* sonney2k suffers | 20:35 | |
lisitsyn | sonney2k: why? | 20:36 |
lisitsyn | because it is mega pain in the ass you mean? | 20:36 |
lisitsyn | like megaupload | 20:37 |
shogun-buildbot | build #909 of cyg1 - libshogun is complete: Failure [failed configure] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/909 blamelist: Heiko Strathmann <heiko.strathmann@gmail.com> | 20:38 |
@HeikoS | whaaaaaat? | 20:38 |
votjakovr | hmmm | 20:38 |
@HeikoS | votjakovr: its cyg, dont worry :) | 20:38 |
@sonney2k | HeikoS, btw you should ask Olivier if he wants to come to the workshop :) | 20:39 |
@HeikoS | sonney2k: will do | 20:40 |
@HeikoS | he seemed ultra busy though | 20:40 |
@HeikoS | as everyone always seems | 20:40 |
@HeikoS | weird isnt it? | 20:40 |
lisitsyn | what is the magical moment it comes better with our busy deals | 20:41 |
lisitsyn | sonney2k: everything is getting worse with years, right? | 20:41 |
lisitsyn | :D | 20:41 |
@HeikoS | when my evil-nano-robots conquered the planet | 20:42 |
@sonney2k | lisitsyn, yes it is now that you have lots of time | 20:42 |
lisitsyn | sonney2k: haha ok! | 20:42 |
@sonney2k | once you become as old as me you would wish you would have spent your lots and lots of time you had more wisely :D | 20:43 |
lisitsyn | sonney2k: tell me what I should spend it on then! | 20:43 |
@sonney2k | doing cool stuff | 20:43 |
lisitsyn | sonney2k: haha! | 20:43 |
@sonney2k | lisitsyn, so of course working on shogun :D | 20:43 |
@sonney2k | or HeikoS nano robots | 20:44 |
@sonney2k | but powered by shogun | 20:44 |
@HeikoS | of course they are | 20:44 |
@sonney2k | hmmhh | 20:44 |
lisitsyn | sonney2k: let see what you say when you turn 50 | 20:44 |
@HeikoS | they are in fact powered on unit-tests | 20:44 |
@sonney2k | lisitsyn, hey I am not there yet | 20:44 |
lisitsyn | I will turn like 36 | 20:44 |
lisitsyn | :D | 20:44 |
@sonney2k | I first have to survive this decade | 20:45 |
lisitsyn | sonney2k: oh I'll turn your current year when you turn 50 | 20:45 |
@sonney2k | what? | 20:45 |
lisitsyn | sonney2k: when you are 50 I am 36 | 20:45 |
@sonney2k | HeikoS, lisitsyn does anyone use get_feature from our features? and the on-the-fly preprocessors? | 20:45 |
@HeikoS | I dont know | 20:46 |
lisitsyn | sonney2k: I never used on-the-fly thing | 20:46 |
@sonney2k | I used to use them but haven't for a long time | 20:46 |
lisitsyn | well it may be a good thing but | 20:46 |
lisitsyn | something is wrong | 20:46 |
@sonney2k | it was working when I wrote it - I made sure | 20:46 |
@sonney2k | but now with all that refactoring and no tests | 20:47 |
@sonney2k | no idea | 20:47 |
lisitsyn | sonney2k: no it works I think | 20:47 |
lisitsyn | I mean something is wrong with its api and etc | 20:47 |
lisitsyn | it is not attractive to use | 20:47 |
lisitsyn | sonney2k: see a big shot in our list | 20:47 |
@sonney2k | what woudl you do better? | 20:47 |
@sonney2k | it is very easy to do | 20:47 |
lisitsyn | sonney2k: if I had idea I would do that or say :) | 20:47 |
@sonney2k | just attach a list of preprocessors | 20:47 |
@sonney2k | done | 20:47 |
lisitsyn | I usually say I don't like X because I don't know how to improve it | 20:48 |
@sonney2k | no idea how it could be even easier | 20:48 |
@sonney2k | I am a bit worried about the Cache in all this | 20:48 |
lisitsyn | sonney2k: I'd like to drop some code | 20:48 |
lisitsyn | :D | 20:48 |
@sonney2k | lisitsyn, do you know some LRU cache? | 20:49 |
lisitsyn | sonney2k: basics - never implemented | 20:49 |
lisitsyn | you mean implementation? | 20:49 |
@sonney2k | I would rather use some well written thing and drop ours | 20:49 |
shogun-notifier- | shogun: lambday :develop * 23d134a / / (10 files): https://github.com/shogun-toolbox/shogun/commit/23d134aa08d65d5d8df380c46c4140af9ea76398 | 20:49 |
shogun-notifier- | shogun: error msgs fixed for complex64_t, unit-tests added | 20:49 |
shogun-notifier- | shogun: Heiko Strathmann :develop * 6a47272 / / (10 files): https://github.com/shogun-toolbox/shogun/commit/6a47272a5d5982979faddf98d551eef60ee04c60 | 20:49 |
shogun-notifier- | shogun: Merge pull request #1149 from lambday/develop | 20:49 |
shogun-notifier- | shogun: | 20:49 |
shogun-notifier- | shogun: error msgs fixed for complex64_t, unit-tests added | 20:49 |
@sonney2k | yeah something we could use | 20:49 |
lisitsyn | lets google | 20:49 |
@sonney2k | HeikoS, you do that on purpose do you? Just when I branched you mega merge | 20:49 |
@HeikoS | ehm? | 20:50 |
@HeikoS | what? | 20:50 |
lisitsyn | sonney2k: a lot of implementations | 20:50 |
lisitsyn | sonney2k: what is it for? | 20:50 |
@sonney2k | lisitsyn, our on-the-fly preprocessors use a cache to cache feature vectors | 20:51 |
@sonney2k | preprocessed ones I mean | 20:51 |
lisitsyn | sounds complex! | 20:51 |
@sonney2k | I know you never used it but our DenseFeatures don't have to be in memory | 20:51 |
lisitsyn | haha yes I know | 20:52 |
lisitsyn | but never tried | 20:52 |
@HeikoS | I gotta go now | 20:52 |
@HeikoS | see you guys tomorrow! | 20:52 |
-!- mode/#shogun [+o lisitsyn] by ChanServ | 20:52 | |
-!- HeikoS [~heiko@nat-173-83.internal.eduroam.ucl.ac.uk] has quit [Quit: Leaving.] | 20:52 | |
@sonney2k | to late to say bye | 20:52 |
shogun-buildbot | build #1078 of bsd1 - libshogun is complete: Failure [failed test] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1078 blamelist: Roman Votyakov <votjakovr@gmail.com> | 20:52 |
shogun-buildbot | build #910 of cyg1 - libshogun is complete: Failure [failed compile] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/910 blamelist: Roman Votyakov <votjakovr@gmail.com> | 20:53 |
@sonney2k | lisitsyn, could you please change this to 1e-14 http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1078/steps/test/logs/stdio | 20:53 |
@sonney2k | looks like fabs is b0rken in old libc's | 20:54 |
@lisitsyn | crazy precision | 20:54 |
@sonney2k | lisitsyn, why? | 20:54 |
@lisitsyn | sonney2k: I am scaried what these guys are going to compute | 20:55 |
@lisitsyn | intergalactic spaceships | 20:55 |
@lisitsyn | or what | 20:55 |
@sonney2k | lisitsyn, I was already scared when I read the proposal | 20:55 |
@lisitsyn | sonney2k: I believe they are going to compute 4d space warping to fly away from this planet | 20:55 |
@sonney2k | *yay* it is becoming kind of summer here :D | 20:55 |
@lisitsyn | sonney2k: bayessian theoretical aspects of teleportation | 20:56 |
@lisitsyn | sonney2k: we should ask if nasa uses such a precision | 20:58 |
@lisitsyn | they must be e-3 most of the times | 20:59 |
@lisitsyn | :D | 20:59 |
@sonney2k | lisitsyn, only our SVMs are 1e-3 | 21:00 |
@lisitsyn | sonney2k: what about the others? | 21:00 |
@lisitsyn | oops I am into merging issue | 21:04 |
-!- votjakovr [~votjakovr@host-46-241-3-209.bbcustomer.zsttk.net] has quit [Quit: Leaving] | 21:11 | |
shogun-notifier- | shogun: Sergey Lisitsyn :develop * e496115 / tests/unit/lib/SGVector_unittest.cc,tests/unit/mathematics/Complex_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/e4961157662ed92cac9139fd4eca1913a4548771 | 21:17 |
shogun-notifier- | shogun: Lowered precision of complex unit-tests | 21:17 |
@lisitsyn | finally | 21:17 |
-!- vgorbati [~vgorbati@212.2.159.34] has quit [Quit: vgorbati] | 21:20 | |
-!- shogun-toolbox [~shogun@7nn.de] has quit [Ping timeout: 256 seconds] | 21:21 | |
--- Log closed Wed Jun 05 21:21:27 2013 | ||
--- Log opened Wed Jun 05 21:21:36 2013 | ||
-!- shogun-t1olbox [~shogun@7nn.de] has joined #shogun | 21:21 | |
-!- Irssi: #shogun: Total of 15 nicks [2 ops, 0 halfops, 0 voices, 13 normal] | 21:21 | |
-!- Irssi: Join to #shogun was synced in 9 secs | 21:21 | |
-!- van51 [~van51@athedsl-408350.home.otenet.gr] has left #shogun ["QUIT :Leaving."] | 21:23 | |
-!- shogun-toolbox [~shogun@7nn.de] has quit [Ping timeout: 256 seconds] | 21:28 | |
@sonney2k | argh out of battery | 21:29 |
shogun-notifier- | shogun: van51 :feature/model_selection_syntax * b1b8570 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/b1b85707654bed214973ec65aa8c9742143a31c0 | 21:31 |
shogun-notifier- | shogun: Changed CList to CDynamicObjectArray in CCombinedDotFeatures (WIP) | 21:31 |
shogun-notifier- | shogun: lambday :feature/model_selection_syntax * d453390 / / (3 files): https://github.com/shogun-toolbox/shogun/commit/d453390e7ecd231fea02d4e8259a9279ea30ca7d | 21:31 |
shogun-notifier- | shogun: CMath::abs(complex64_t) changed to not to use std::abs() | 21:31 |
shogun-notifier- | shogun: Thoralf Klein :feature/model_selection_syntax * a361752 / src/shogun/mathematics/Math.h,tests/unit/mathematics/Math_unittest.cc: https://github.com/shogun-toolbox/shogun/commit/a361752210386dec5027ffc84427276b39895b8d | 21:31 |
shogun-notifier- | shogun: Added test for sorting zero-sized vectors: | 21:31 |
shogun-notifier- | shogun: | 21:31 |
shogun-notifier- | shogun: - CMath::qsort(* T, ...) | 21:31 |
shogun-notifier- | shogun: - CMath::qsort(** T, ...) | 21:31 |
shogun-notifier- | shogun: - CMath::qsort_index(...) | 21:31 |
shogun-notifier- | shogun: Roman Votyakov :feature/model_selection_syntax * 5b94f09 / / (11 files): https://github.com/shogun-toolbox/shogun/commit/5b94f09a19731d6dc13160169efdddbf10897df1 | 21:31 |
shogun-notifier- | shogun: Redesigned GP framework | 21:31 |
shogun-notifier- | shogun: Sergey Lisitsyn :feature/model_selection_syntax * f9cdccf / / (4 files): https://github.com/shogun-toolbox/shogun/commit/f9cdccf2cf48cf4168437cbc3741288a209a2727 | 21:31 |
shogun-notifier- | shogun: A prototype of builder-like modelselection syntax | 21:31 |
@lisitsyn | sonney2k: these guys are tiresome | 21:31 |
@lisitsyn | ehmm I get e+180 difference | 21:31 |
@lisitsyn | in FITCInferenceMethod | 21:31 |
@lisitsyn | vgorbati: hey how are ya doin? | 21:31 |
@lisitsyn | sonney2k: here goes a new branch | 21:32 |
-!- iglesiasg [d58f3220@gateway/web/freenode/ip.213.143.50.32] has joined #shogun | 21:34 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 21:34 | |
@lisitsyn | oh shit | 21:35 |
shogun-buildbot | build #911 of cyg1 - libshogun is complete: Failure [failed configure] Build details are at http://www.shogun-toolbox.org/buildbot/builders/cyg1%20-%20libshogun/builds/911 blamelist: Heiko Strathmann <heiko.strathmann@gmail.com>, lambday <heavensdevil6909@gmail.com>, Sergey Lisitsyn <lisitsyn.s.o@gmail.com> | 21:42 |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has quit [Ping timeout: 245 seconds] | 21:47 | |
shogun-buildbot | build #1079 of bsd1 - libshogun is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/bsd1%20-%20libshogun/builds/1079 | 21:49 |
shogun-notifier- | shogun: Sergey Lisitsyn :feature/model_selection_syntax * 8ac4ed7 / src/shogun/modelselection/ModelSelectionParameters.h: https://github.com/shogun-toolbox/shogun/commit/8ac4ed73c9edf590a2b8954b5bda49e49fbfe374 | 21:58 |
shogun-notifier- | shogun: Some documentation for model selection range helper | 21:58 |
-!- Netsplit *.net <-> *.split quits: @lisitsyn, hushell, flxb_, sonne|work, gsomix, shogun-notifier-, shogun-buildbot, @sonney2k, naywhayare, wiking, (+2 more, use /NETSPLIT to show all of them) | 22:02 | |
-!- zxtx [~zv@rrcs-74-62-200-195.west.biz.rr.com] has joined #shogun | 22:28 | |
-!- Netsplit over, joins: @iglesiasg, hushell, shogun-notifier-, @lisitsyn, flxb_, shogun-buildbot, @sonney2k, gsomix, thoralf, naywhayare (+2 more) | 22:28 | |
-!- shogun-t1olbox [~shogun@7nn.de] has quit [Ping timeout: 240 seconds] | 22:39 | |
--- Log closed Wed Jun 05 22:39:25 2013 | ||
--- Log opened Wed Jun 05 22:39:33 2013 | ||
-!- shogun-toolbox [~shogun@7nn.de] has joined #shogun | 22:39 | |
-!- Irssi: #shogun: Total of 16 nicks [4 ops, 0 halfops, 0 voices, 12 normal] | 22:39 | |
-!- Irssi: Join to #shogun was synced in 6 secs | 22:39 | |
-!- shogun-t1olbox [~shogun@7nn.de] has quit [Ping timeout: 240 seconds] | 22:41 | |
-!- HeikoS [~heiko@nat-173-83.internal.eduroam.ucl.ac.uk] has quit [Quit: Leaving.] | 22:50 | |
-!- iglesiasg [d58f3220@gateway/web/freenode/ip.213.143.50.32] has quit [Quit: Page closed] | 22:55 | |
--- Log closed Thu Jun 06 00:00:33 2013 |
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!