--- Log opened Fri Apr 26 00:00:29 2013 | ||
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout] | 00:14 | |
-!- Netsplit *.net <-> *.split quits: @HeikoS | 00:15 | |
-!- Netsplit over, joins: @HeikoS | 00:15 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: Lost terminal] | 00:17 | |
-!- lisitsyn [~blackburn@188.168.13.211] has quit [Ping timeout: 245 seconds] | 00:27 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Quit: Page closed] | 00:44 | |
-!- makokal [~bokal@pD9EF09DC.dip0.t-ipconnect.de] has quit [Quit: makokal] | 00:45 | |
-!- sijin [~smuxi@144.214.222.109] has joined #shogun | 02:22 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has left #shogun ["PING 1366939949"] | 03:32 | |
-!- sids_aquarius [~sidi_@li400-124.members.linode.com] has quit [Remote host closed the connection] | 03:44 | |
-!- sids_aquarius [~sidi_@li400-124.members.linode.com] has joined #shogun | 03:52 | |
-!- Yanglittle [deb20af0@gateway/web/freenode/ip.222.178.10.240] has joined #shogun | 06:07 | |
Yanglittle | hey, does any examples output the testdat's posterior probability in python_modular? | 06:13 |
---|---|---|
-!- gsomix [~Miranda@188.168.13.211] has quit [Quit: Miranda IM! Smaller, Faster, Easier. http://miranda-im.org] | 06:58 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has joined #shogun | 08:23 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has quit [Quit: Leaving.] | 08:24 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 08:28 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 08:28 | |
-!- lisitsyn [~blackburn@46.20.65.122] has joined #shogun | 08:32 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has joined #shogun | 08:36 | |
-!- makokal [~bokal@pD9EF09DC.dip0.t-ipconnect.de] has joined #shogun | 08:44 | |
-!- foulwall [~foulwall@li379-21.members.linode.com] has joined #shogun | 08:58 | |
foulwall | Hi sonney2k | 08:58 |
foulwall | I saw the idea "mloss.org and mldata.org integration" is also available. I think I can do some work on that after I finish the demos. | 09:02 |
sonne|work | foulwall: I think demos is more work than you expect :) | 09:06 |
sonne|work | But sure we could also allow uploads of *small* data sets for the demo | 09:07 |
-!- lisitsyn [~blackburn@46.20.65.122] has quit [Quit: Leaving.] | 09:08 | |
foulwall | sonne|work: Maybe after the GSoC I'll help that. | 09:08 |
foulwall | sonne|work: yeah, some demos will need bigger data set | 09:09 |
sonne|work | foulwall: cheng and me would be happy if you do... | 09:10 |
foulwall | sonne|work: I love shogun, so just at you service, meanwhile I can get myself trained in developing them. | 09:13 |
-!- foulwall [~foulwall@li379-21.members.linode.com] has left #shogun [] | 09:19 | |
-!- erlenda [~erlenda@fw-oslo.intelcom.no] has joined #shogun | 09:40 | |
Yanglittle | hey, LibSVM can map the distance-from-margin into probalilities, does shogun do ? | 09:52 |
-!- makokal [~bokal@pD9EF09DC.dip0.t-ipconnect.de] has quit [Quit: makokal] | 09:58 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has left #shogun ["PING 1366963177"] | 09:59 | |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has joined #shogun | 10:09 | |
-!- mode/#shogun [+o lisitsyn] by ChanServ | 10:09 | |
@HeikoS | Yanglittle, hi, yes we can do this | 10:51 |
@HeikoS | check scores_to_probabilities of BinaryLabels | 10:52 |
@HeikoS | there is also an example in libshogun | 10:52 |
@wiking | HeikoS: what bug? | 10:57 |
@wiking | #948 | 10:57 |
@wiking | ? | 10:57 |
@iglesiasg | wiking, HeikoS : hey guys, one thing that I don't quite understand regarding the randomness issue with the tests | 11:01 |
@iglesiasg | wiking: it fails across platforms/archs because we are relying too much on the seed right? | 11:02 |
@wiking | not about seed | 11:02 |
@wiking | it's about RNG | 11:02 |
@iglesiasg | wiking: then? | 11:02 |
@wiking | it's not the same accross platforms | 11:02 |
@iglesiasg | wiking: ok but say | 11:02 |
@wiking | hence seeded RNG won't be the same either | 11:02 |
@iglesiasg | if it is because we are relying on the seed I understand | 11:03 |
@iglesiasg | otherwise, I don't | 11:03 |
@iglesiasg | because if we are generating numbers from say an interval [0,1] | 11:03 |
@HeikoS | wiking: ? | 11:03 |
@iglesiasg | why does it make a difference how are they generated as long as they are in that interval? | 11:03 |
@wiking | iglesiasg: because they are not the same exact number? :) | 11:04 |
@HeikoS | iglesiasg: we save results to files, then compare against them | 11:04 |
@HeikoS | to any random stuff will kill us | 11:04 |
@iglesiasg | wiking: then, we are relying too much on the seed | 11:04 |
@HeikoS | iglesiasg: some methods are random | 11:04 |
@wiking | iglesiasg: with seed(x) in the code u suppose that the random will be always the same | 11:04 |
@iglesiasg | wiking: i.e. we are generating "random numbers" that are not random actually | 11:04 |
@HeikoS | no way around that | 11:04 |
@iglesiasg | wiking: ok, I understand | 11:04 |
@HeikoS | data doesnt have to be, but other things have to be | 11:04 |
@wiking | which is true until u r using the same system | 11:04 |
@HeikoS | wiking: what was with the bug? | 11:04 |
@wiking | HeikoS: nada realised | 11:04 |
@iglesiasg | wiking: then it doesn't make sense to me to face problems for that | 11:04 |
@HeikoS | what if we have our own random machine in shogun? | 11:05 |
@HeikoS | would that solve it? | 11:05 |
@iglesiasg | it is just that the tests don't work on random data | 11:05 |
@HeikoS | what about python? | 11:05 |
@HeikoS | iglesiasg: its not only that data | 11:05 |
@wiking | HeikoS: python uses system rng afaik | 11:05 |
@iglesiasg | HeikoS: yeah, it is also internally like in CV you said | 11:05 |
@iglesiasg | right? | 11:05 |
@HeikoS | wiking: so even python is not reproducible? | 11:05 |
@wiking | HeikoS: and anyhow now we are failing exactly with python_modular ;P | 11:05 |
@HeikoS | iglesiasg: exactly | 11:05 |
@HeikoS | wiking: so we need a random machine in shogun that can produce everything | 11:06 |
@HeikoS | as far as i know we mainly use normal and uniform samples from python | 11:06 |
@HeikoS | we have both in shogun | 11:06 |
@HeikoS | just need to use them instead of the numpy methods then | 11:07 |
@HeikoS | or we change our approach | 11:07 |
@lisitsyn | HeikoS: wiking: sonne|work: iglesiasg: please check mail | 11:07 |
@HeikoS | that is, only use fixed data | 11:07 |
@HeikoS | dont test random methods but whether results make sense | 11:07 |
@HeikoS | I did that a while ago but its also problematic | 11:07 |
@HeikoS | like x-val results | 11:07 |
@HeikoS | you can define an interval of what you expect | 11:08 |
@HeikoS | but no guarantee | 11:08 |
@iglesiasg | lisitsyn: it is looking good :) | 11:09 |
@HeikoS | lisitsyn: dito | 11:09 |
@lisitsyn | HeikoS: is it bad or good? | 11:10 |
@lisitsyn | :D | 11:10 |
@iglesiasg | HeikoS: rather than using our random machine | 11:11 |
@iglesiasg | HeikoS: I would enable the possibility of setting randomly generated values as the deafult option, but in tests we set that from outsite | 11:11 |
@iglesiasg | outside* | 11:11 |
@iglesiasg | that would be for the parts that use random numbers internally, e.g. CV | 11:12 |
@lisitsyn | wiking: I like your font | 11:12 |
sonne|work | HeikoS, wiking, iglesiasg - we need a portable random number generator | 11:12 |
@wiking | lisitsyn: which? :)))) | 11:12 |
@wiking | lisitsyn: i think i've fixed it | 11:12 |
sonne|work | eigen3? | 11:12 |
@lisitsyn | wiking: in the issue you just created | 11:12 |
@lisitsyn | wiking: I just read a mail and whoa! | 11:13 |
@iglesiasg | sonne|work: I think the solution can be a bigger problem than the original one :) | 11:13 |
@wiking | lisitsyn: hahahah yeah | 11:13 |
@lisitsyn | sonne|work: eigen3 doesn't have great random | 11:13 |
@wiking | lisitsyn: github took it's work seriously with highlighting :)) | 11:13 |
@wiking | sonne|work: afaik openssl/ssh will have one ;) | 11:13 |
@lisitsyn | sonne|work: C++11 has portable random stuff | 11:14 |
@lisitsyn | :D | 11:14 |
@wiking | sonne|work: and those ones are for sure portable | 11:14 |
@wiking | sonne|work: it's now matter of teste | 11:14 |
@wiking | *taste | 11:14 |
@wiking | to depend shogun on openssl | 11:14 |
@wiking | or just cut out the rng from openssl | 11:15 |
@lisitsyn | are we going to use C++11 btw? | 11:15 |
@lisitsyn | :D | 11:15 |
@wiking | i'd rather go with simple dependency, as nowadays a system w/o openssl is pretty weird... unless it's not connected to the network :P | 11:17 |
@HeikoS | true ssl is easy to depend on | 11:21 |
@HeikoS | how about c++11? | 11:21 |
@HeikoS | what would that do to us? | 11:21 |
@lisitsyn | HeikoS: I am not sure it is really portable but I just ask if we are going to use new standard | 11:22 |
@HeikoS | lisitsyn: different question, lets solve the other one first :) | 11:23 |
@HeikoS | if it *is* portable, we could do it | 11:23 |
@HeikoS | but what would it do to us? | 11:23 |
@HeikoS | whats needed to use it? | 11:23 |
@lisitsyn | HeikoS: --std=c++0x IIRC | 11:24 |
@lisitsyn | HeikoS: starting from gcc 4.6 or 4.7 | 11:24 |
@HeikoS | lisitsyn: have you tried what happens then? | 11:24 |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has joined #shogun | 11:29 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 11:29 | |
-!- makokal [~bokal@eduroam-pool3-225.wlan.uni-bremen.de] has joined #shogun | 11:30 | |
@lisitsyn | HeikoS: happens like? | 11:31 |
@lisitsyn | HeikoS: once you use newer standard you can use new headers | 11:32 |
@lisitsyn | like shared_ptr or these rng things | 11:32 |
@lisitsyn | HeikoS: ah and std collections use move semantics | 11:33 |
@HeikoS | lisitsyn: I mean, does it compile? | 11:33 |
@wiking | HeikoS: it does | 11:33 |
@lisitsyn | HeikoS: yes of course, back compatibility is a must | 11:33 |
@HeikoS | then why not use it? | 11:33 |
@wiking | at least with clang yes | 11:33 |
@lisitsyn | HeikoS: it can get into troubles though | 11:34 |
@lisitsyn | HeikoS: as I know shared libraries are not compatible | 11:34 |
@HeikoS | lisitsyn: I see | 11:35 |
@wiking | lisitsyn: do you know an easy way to generate a skeleton of a polygon? | 11:35 |
@lisitsyn | wiking: generate? | 11:35 |
@lisitsyn | wiking: http://upload.wikimedia.org/wikipedia/commons/a/ab/StraightSkeletonDefinition.png like that? | 11:36 |
@wiking | lisitsyn: yeah similar but my polygon is a simple 2D one | 11:37 |
@lisitsyn | I don't know the algorithm | 11:38 |
@wiking | yeah i'm trying to find one as well atm... | 11:41 |
-!- gsomix [~Miranda@r206-10.smr.ru] has joined #shogun | 11:43 | |
gsomix | hello | 11:43 |
gsomix | sonne|work: sonney2k: there? | 11:43 |
-!- saket [0e8b5206@gateway/web/freenode/ip.14.139.82.6] has joined #shogun | 11:48 | |
@wiking | lisitsyn: anybody is working on RandomizedPCa and fast k-Means? | 11:51 |
@lisitsyn | wiking: no, probably no | 11:51 |
@lisitsyn | wiking: I wanted to but swamped | 11:51 |
@wiking | ok | 11:52 |
@wiking | i took random forest | 11:52 |
@lisitsyn | wiking: want to participate in gsoc? ;) | 11:52 |
@lisitsyn | :D | 11:52 |
@wiking | lisitsyn: heheh can i ? | 11:52 |
@wiking | :) | 11:52 |
@lisitsyn | wiking: are you eligible at all? | 11:53 |
@wiking | lisitsyn: i've realised that yes :) | 11:53 |
@lisitsyn | hah | 11:53 |
-!- saket [0e8b5206@gateway/web/freenode/ip.14.139.82.6] has quit [Ping timeout: 245 seconds] | 11:54 | |
@wiking | btw: for CRF we could use http://www.chokkan.org/software/crfsuite/ | 11:54 |
@wiking | it's bsd license | 11:54 |
* wiking just looking through the development issues on github | 11:55 | |
@wiking | btw isn't #943 fixed? | 11:57 |
@wiking | json serialization ? | 11:57 |
-!- iglesiasg [~nando@n177-p222.kthopen.kth.se] has joined #shogun | 12:24 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 12:24 | |
-!- gsomix [~Miranda@r206-10.smr.ru] has quit [Read error: Connection reset by peer] | 12:56 | |
@wiking | btw opencv has RNG as well http://docs.opencv.org/modules/core/doc/operations_on_arrays.html?highlight=rng#rng | 13:01 |
-!- gsomix [~Miranda@r206-10.smr.ru] has joined #shogun | 13:04 | |
@iglesiasg | interesting | 13:04 |
-!- pranjaldaga [~pranjalda@115.248.50.23] has joined #shogun | 13:13 | |
-!- gsomix [~Miranda@r206-10.smr.ru] has quit [Quit: Miranda IM! Smaller, Faster, Easier. http://miranda-im.org] | 13:18 | |
-!- gsomix [~Miranda@r206-10.smr.ru] has joined #shogun | 13:21 | |
-!- sids_aquarius [~sidi_@li400-124.members.linode.com] has quit [Ping timeout: 264 seconds] | 13:23 | |
-!- pranjaldaga [~pranjalda@115.248.50.23] has quit [Ping timeout: 260 seconds] | 14:02 | |
-!- iglesiasg [~nando@n177-p222.kthopen.kth.se] has quit [Quit: leaving] | 15:13 | |
-!- iglesiasg [~nando@n177-p222.kthopen.kth.se] has joined #shogun | 15:30 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 15:30 | |
-!- kabujinuo [ca288b6b@gateway/web/freenode/ip.202.40.139.107] has joined #shogun | 15:39 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Ping timeout: 245 seconds] | 15:47 | |
-!- erlenda [~erlenda@fw-oslo.intelcom.no] has quit [Quit: Leaving] | 16:00 | |
-!- iglesiasg [~nando@n177-p222.kthopen.kth.se] has quit [Quit: leaving] | 16:06 | |
-!- sonne|work [~sonnenbu@sams-office-nat.tomtomgroup.com] has quit [Quit: Leaving.] | 16:28 | |
-!- lisitsyn [~lisitsin@mxs.kg.ru] has quit [Quit: Leaving.] | 16:28 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has joined #shogun | 16:48 | |
-!- kaushalb09 [~kaushalb0@cpe-74-77-131-130.buffalo.res.rr.com] has joined #shogun | 16:57 | |
-!- kaushalb09 [~kaushalb0@cpe-74-77-131-130.buffalo.res.rr.com] has quit [Client Quit] | 16:58 | |
-!- gsomix [~Miranda@r206-10.smr.ru] has quit [Quit: Miranda IM! Smaller, Faster, Easier. http://miranda-im.org] | 17:07 | |
-!- makokal [~bokal@eduroam-pool3-225.wlan.uni-bremen.de] has quit [Quit: makokal] | 17:20 | |
-!- pranjaldaga [~pranjalda@115.248.50.23] has joined #shogun | 17:25 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Ping timeout: 245 seconds] | 17:38 | |
-!- kabujinuo [ca288b6b@gateway/web/freenode/ip.202.40.139.107] has quit [Quit: Page closed] | 17:48 | |
-!- lisitsyn [~blackburn@46.20.65.63] has joined #shogun | 17:51 | |
-!- Yanglittle [deb20af0@gateway/web/freenode/ip.222.178.10.240] has quit [Ping timeout: 245 seconds] | 17:51 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has joined #shogun | 17:57 | |
-!- gsomix [~Miranda@46.20.65.63] has joined #shogun | 18:01 | |
-!- lisitsyn [~blackburn@46.20.65.63] has quit [Quit: Leaving.] | 18:13 | |
-!- makokal [~bokal@212.201.44.246] has joined #shogun | 18:39 | |
-!- mikhailBelous [~towelenee@109.205.249.161] has joined #shogun | 18:44 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 18:54 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 18:54 | |
-!- sids_aquarius [~sidi_@li400-124.members.linode.com] has joined #shogun | 19:15 | |
-!- makokal [~bokal@212.201.44.246] has quit [Quit: makokal] | 19:19 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has joined #shogun | 19:24 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: Lost terminal] | 19:37 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 19:39 | |
-!- mode/#shogun [+o iglesiasg] by ChanServ | 19:39 | |
-!- pranjaldaga [~pranjalda@115.248.50.23] has quit [Ping timeout: 260 seconds] | 19:51 | |
-!- pranjaldaga [~pranjalda@115.248.50.23] has joined #shogun | 19:52 | |
-!- naywhaya1e is now known as naywhayare | 20:14 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Quit: Page closed] | 20:20 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has joined #shogun | 20:20 | |
-!- van51 [~van51@athedsl-397303.home.otenet.gr] has left #shogun ["QUIT :Leaving."] | 20:28 | |
gsomix | sonney2k: are you there? | 20:32 |
-!- lisitsyn [~blackburn@109-226-120-160.clients.tlt.100megabit.ru] has joined #shogun | 21:12 | |
-!- mode/#shogun [+o lisitsyn] by ChanServ | 21:12 | |
-!- pranjaldaga [~pranjalda@115.248.50.23] has quit [Ping timeout: 258 seconds] | 21:13 | |
-!- gsomix [~Miranda@46.20.65.63] has quit [Read error: Connection reset by peer] | 21:53 | |
-!- vgorbati [d4029f22@gateway/web/freenode/ip.212.2.159.34] has quit [Ping timeout: 245 seconds] | 22:07 | |
-!- gsomix [~Miranda@46.20.65.63] has joined #shogun | 22:09 | |
-!- poojits [75d35d4a@gateway/web/freenode/ip.117.211.93.74] has joined #shogun | 22:26 | |
poojits | I am interested in "Interface and develop the general quadratic solver library libqp" project for GSOC, but there is no preliminary task for this in the issue list on github. Should I get in touch with mentor Vojtech Franc directly? | 22:28 |
@lisitsyn | poojits: yes | 22:29 |
poojits | xfrancv@cmp.felk.cvut.cz is his university email address. Is this okay? | 22:30 |
@lisitsyn | poojits: yes totally | 22:30 |
poojits | thanks alot. | 22:31 |
-!- gsomix [~Miranda@46.20.65.63] has quit [Read error: Connection reset by peer] | 23:15 | |
-!- gsomix [~Miranda@46.20.65.63] has joined #shogun | 23:26 | |
-!- HeikoS [~heiko@nat-160-69.internal.eduroam.ucl.ac.uk] has left #shogun [] | 23:46 | |
-!- iglesiasg [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 23:49 | |
-!- mikhailBelous [~towelenee@109.205.249.161] has quit [Ping timeout: 264 seconds] | 23:55 | |
--- Log closed Sat Apr 27 00:00:29 2013 |
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!