--- Log opened Wed Apr 30 00:00:28 2014 | ||
-!- x4i [~A2o@unaffiliated/x4i] has joined #shogun | 01:16 | |
-!- x4i [~A2o@unaffiliated/x4i] has quit [Quit: irc] | 01:23 | |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has joined #shogun | 02:32 | |
-!- mode/#shogun [+o HeikoS] by ChanServ | 02:33 | |
-!- khalednasr [~k.nasr92@196.221.64.143] has quit [Quit: Leaving] | 02:45 | |
shogun-buildbot | build #696 of nightly_none is complete: Failure [failed compile] Build details are at http://buildbot.shogun-toolbox.org/builders/nightly_none/builds/696 blamelist: Heiko Strathmann <heiko.strathmann@gmail.com>, lambday <heavensdevil6909@gmail.com> | 03:08 |
---|---|---|
shogun-buildbot | build #689 of nightly_all is complete: Failure [failed compile test] Build details are at http://buildbot.shogun-toolbox.org/builders/nightly_all/builds/689 blamelist: Heiko Strathmann <heiko.strathmann@gmail.com>, lambday <heavensdevil6909@gmail.com> | 03:14 |
-!- abinash_panda [0e8b2998@gateway/web/freenode/ip.14.139.41.152] has joined #shogun | 04:21 | |
-!- abinash_panda [0e8b2998@gateway/web/freenode/ip.14.139.41.152] has quit [Ping timeout: 240 seconds] | 04:28 | |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has quit [Ping timeout: 240 seconds] | 04:46 | |
-!- soumyaC [uid15286@gateway/web/irccloud.com/x-rfdbvlwfgtssyfwl] has quit [Quit: Connection closed for inactivity] | 05:06 | |
-!- abinash_panda [d2d43d97@gateway/web/cgi-irc/kiwiirc.com/ip.210.212.61.151] has joined #shogun | 06:20 | |
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has joined #shogun | 06:37 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 06:37 | |
-!- shogun-buildbot [~shogun-bu@7nn.de] has quit [Ping timeout: 252 seconds] | 06:37 | |
-!- shogun-buildbot_ [~shogun-bu@7nn.de] has joined #shogun | 06:37 | |
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has quit [Quit: Leaving] | 07:09 | |
-!- abinash_panda [d2d43d97@gateway/web/cgi-irc/kiwiirc.com/ip.210.212.61.151] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client] | 09:38 | |
-!- lisitsyn [~qdrgsm@80.252.20.67] has left #shogun [] | 10:53 | |
-!- thoralf [~thoralf@91-65-219-80-dynip.superkabel.de] has joined #shogun | 10:58 | |
thoralf | Funny facts about code on github: http://sideeffect.kr/popularconvention/ | 10:58 |
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has joined #shogun | 11:39 | |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has joined #shogun | 11:48 | |
-!- soumyaC [uid15286@gateway/web/irccloud.com/x-ymokqiijtxjdzofv] has joined #shogun | 12:13 | |
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has quit [] | 13:08 | |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has joined #shogun | 13:30 | |
-!- mode/#shogun [+o HeikoS] by ChanServ | 13:30 | |
-!- khalednasr [~k.nasr92@41.69.174.89] has joined #shogun | 14:04 | |
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has joined #shogun | 14:16 | |
lambday | HeikoS: there?? | 14:42 |
@HeikoS | lambday: hi | 14:46 |
lambday | HeikoS: hey! | 14:46 |
lambday | HeikoS: just upgraded my RAM and did the benchmark with vectorized Eigen3 sum calls | 14:46 |
lambday | HeikoS: sent a PR - results are remarkable | 14:46 |
@HeikoS | lambday: cool! | 14:47 |
@HeikoS | checking | 14:47 |
lambday | HeikoS: according to this - we should definitely override these sum methods in CCustomKernel | 14:47 |
@HeikoS | lambday: I see | 14:47 |
@HeikoS | lambday: how does it do the magic? | 14:47 |
lambday | HeikoS: I'm not sure! Eigen3 says its operations are vectorized | 14:48 |
lambday | so that could be it | 14:48 |
lambday | HeikoS: compiled the benchmark with " g++ -std=c++0x -O3 -fopenmp benchmark.cpp -I/usr/include/eigen3 -lshogun" | 14:49 |
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun | 14:49 | |
shogun-notifier- | shogun: lambday :develop * dd56776 / benchmarks/kernel_matrix_sum_benchmark.cpp: https://github.com/shogun-toolbox/shogun/commit/dd567760a3c1a31a202c62c4807fd172b75eaf38 | 14:49 |
shogun-notifier- | shogun: added kernel matrix sum benchmark - CKernel::kernel calls vs Eigen3::sum | 14:49 |
shogun-notifier- | shogun: Heiko Strathmann :develop * 6c71771 / benchmarks/kernel_matrix_sum_benchmark.cpp: https://github.com/shogun-toolbox/shogun/commit/6c717713913a8a32f50f180c0d3a640f82735648 | 14:49 |
shogun-notifier- | shogun: Merge pull request #2196 from lambday/feature/quadratic_time_mmd | 14:49 |
shogun-notifier- | shogun: | 14:49 |
shogun-notifier- | shogun: added kernel matrix sum benchmark - CKernel::kernel calls vs Eigen3::sum | 14:49 |
@HeikoS | lambday: I see, so thats vector operations on hardware level | 14:49 |
lambday | HeikoS: yep! | 14:50 |
@HeikoS | lambday: super cool | 14:50 |
lambday | yooo! | 14:50 |
@HeikoS | lambday: ah man, we need linear algebra framework to be working | 14:50 |
@HeikoS | lambday: can you push that a bit? | 14:50 |
lambday | HeikoS: sunil is having exams | 14:50 |
@HeikoS | at least for basic things such as summing up matrix values, factorisations etc | 14:50 |
@HeikoS | lambday: yeah | 14:50 |
@HeikoS | ah I mean ok, it will come :) | 14:50 |
lambday | HeikoS: khaled wanted to work on that CPU/GPU stuff | 14:50 |
@HeikoS | lambday: in the mean time, feel free to override the CCusotmKernel things | 14:50 |
@HeikoS | lambday: but could you already put summing over matrices in the linear algebra backend? | 14:51 |
@HeikoS | so that the stuff you are adding there is available for others | 14:51 |
lambday | HeikoS: he wanted to replace current SGVector with GPUVector instead - although I don't think that its a good diea | 14:51 |
@HeikoS | lambday: should be straight forward not? | 14:51 |
lambday | HeikoS: absolutely | 14:51 |
@HeikoS | lambday: no, no replacement | 14:51 |
lambday | HeikoS: umm do we need summing in the linear algebra backend? | 14:52 |
@HeikoS | lambday: why not? | 14:52 |
@HeikoS | lambday: why should it rely on eigen? | 14:52 |
lambday | umm yeah it would be cool! | 14:52 |
lambday | yeah you're right | 14:52 |
@HeikoS | lambday: if we change the linalg lib then we have to change everything again | 14:52 |
@HeikoS | that should not be the case | 14:52 |
lambday | seeing how it performs with GPU would be actually interesting | 14:52 |
@HeikoS | would in fact like to get rid of most eigen3 calls in algorithms and rather call shogun classes that do the eigen3 stuff inside (or any other lib) | 14:53 |
@HeikoS | lambday: I gotta go now, out for a hiking trip | 14:53 |
@HeikoS | so see you later today | 14:53 |
lambday | HeikoS: yo man! have fun! :D | 14:53 |
lambday | HeikoS: see you! | 14:53 |
lambday | I'll send a PR with overridden CCustomKernel calls soon and then start the backend stuff | 14:54 |
@HeikoS | cool! | 14:54 |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has quit [Quit: Leaving.] | 14:56 | |
khalednasr | lambday, I didn't want to replace SGVector, I meant handling both GPU and CPU memory inside SGVector | 14:57 |
lambday | khalednasr: ah sorry man I didn't get you completely | 14:57 |
lambday | wanted to talk to you regarding this | 14:57 |
lambday | khalednasr: what's wrong with having 2 different classes for 2 different implementations? | 14:58 |
khalednasr | If you have an algorithm that can run on both cpu or gpu, you'd have to have instances of both SGVector and GPUVector for every vector you have | 14:59 |
lambday | khalednasr: we can always manage that using templates, right? | 15:00 |
khalednasr | possible, but it might be complicated if you wanted more control on what data is stored on the gpu and what data is stored on the gpu | 15:03 |
lambday | khalednasr: I am not getting the problem properly - may be we can discuss this in more details when heiko is here? | 15:04 |
shogun-buildbot_ | build #624 of FCRH - libshogun is complete: Success [build successful] Build details are at http://buildbot.shogun-toolbox.org/builders/FCRH%20-%20libshogun/builds/624 | 15:04 |
khalednasr | lambday, yeah sure | 15:05 |
lambday | khalednasr: but if you think that its problematic for some specific instance, could you please post an example on that thread? it would be really helpful | 15:05 |
khalednasr | lambday, ok, I'll see what I can do | 15:06 |
lambday | khalednasr: thanks man! | 15:06 |
lambday | :) | 15:06 |
* lambday afk | 15:06 | |
-!- travis-ci [~travis-ci@ec2-54-221-8-80.compute-1.amazonaws.com] has joined #shogun | 15:49 | |
travis-ci | [travis-ci] it's Heiko Strathmann's turn to pay the next round of drinks for the massacre he caused in shogun-toolbox/shogun: http://travis-ci.org/shogun-toolbox/shogun/builds/24099440 | 15:49 |
-!- travis-ci [~travis-ci@ec2-54-221-8-80.compute-1.amazonaws.com] has left #shogun [] | 15:49 | |
-!- thoralf [~thoralf@91-65-219-80-dynip.superkabel.de] has quit [Ping timeout: 265 seconds] | 16:31 | |
-!- thoralf [~thoralf@91-65-219-80-dynip.superkabel.de] has joined #shogun | 16:32 | |
shogun-buildbot_ | build #282 of debian wheezy - memcheck is complete: Failure [failed memory check] Build details are at http://buildbot.shogun-toolbox.org/builders/debian%20wheezy%20-%20memcheck/builds/282 blamelist: Heiko Strathmann <heiko.strathmann@gmail.com>, lambday <heavensdevil6909@gmail.com> | 17:13 |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has quit [Quit: Leaving.] | 17:22 | |
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout] | 17:49 | |
-!- abinash_panda [0126158c@gateway/web/cgi-irc/kiwiirc.com/ip.1.38.21.140] has joined #shogun | 18:09 | |
abinash_panda | thoralf: Hi ! | 18:10 |
thoralf | Hey abinash_panda | 18:12 |
abinash_panda | thoralf:So finally my exams are over :) | 18:12 |
abinash_panda | thoralf:I can now devote my full time for shogun | 18:12 |
thoralf | abinash_panda: That's great :) | 18:13 |
thoralf | abinash_panda: I guess you already have ideas on this, right? | 18:13 |
abinash_panda | thoralf: You mean ideas regarding my project, right? | 18:14 |
thoralf | Yes. | 18:14 |
abinash_panda | thoralf: Yeah, I have been going through various papers and tutorials | 18:14 |
abinash_panda | thoralf: There is an implementation of multi-label learning in scikit-learn. I was playing with it to get an idea | 18:15 |
-!- abinash_panda [0126158c@gateway/web/cgi-irc/kiwiirc.com/ip.1.38.21.140] has quit [Quit: http://www.kiwiirc.com/ - A hand crafted IRC client] | 18:53 | |
-!- abinash_panda [0126158c@gateway/web/cgi-irc/kiwiirc.com/ip.1.38.21.140] has joined #shogun | 18:56 | |
-!- jd_tx [80538d58@gateway/web/freenode/ip.128.83.141.88] has joined #shogun | 19:36 | |
jd_tx | hi, I'm using LibSVM through the python swig interface. I've trained a classifier, and I'd like to now get margins(decision values) for my task. apply() only returns the hard +1/-1 outputs. How can I access the decision values? | 19:38 |
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has joined #shogun | 19:41 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 19:41 | |
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has quit [Ping timeout: 240 seconds] | 19:50 | |
-!- thor|alf [~thoralf@91-66-34-47-dynip.superkabel.de] has joined #shogun | 20:08 | |
thor|alf | Hey | 20:09 |
thor|alf | abinash_panda: Sorry, had to leave... | 20:09 |
thor|alf | abinash_panda: I played with scikit-learn's multilabel stuff as well, but back then it implemented intractable methods like label-combination. | 20:10 |
thor|alf | abinash_panda: I checked and it changed a bit... | 20:14 |
-!- thor|alf [~thoralf@91-66-34-47-dynip.superkabel.de] has quit [Ping timeout: 265 seconds] | 20:45 | |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has joined #shogun | 21:29 | |
-!- mode/#shogun [+o HeikoS] by ChanServ | 21:29 | |
-!- soumyaC [uid15286@gateway/web/irccloud.com/x-ymokqiijtxjdzofv] has quit [Quit: Connection closed for inactivity] | 21:46 | |
-!- HeikoS [~heiko@85-220-3-15.dsl.dynamic.simnet.is] has quit [Ping timeout: 240 seconds] | 21:51 | |
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has quit [Quit: Leaving] | 21:51 | |
-!- khalednasr [~k.nasr92@41.69.174.89] has quit [Quit: Leaving] | 22:11 | |
-!- lambday [67157f4f@gateway/web/freenode/ip.103.21.127.79] has joined #shogun | 22:47 | |
-!- jd_tx [80538d58@gateway/web/freenode/ip.128.83.141.88] has quit [Quit: Page closed] | 22:57 | |
--- Log closed Thu May 01 00:00:29 2014 |
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!