--- Log opened Wed Jun 27 00:00:17 2012 | ||
n4nd0 | good night! | 00:18 |
---|---|---|
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 00:19 | |
CIA-18 | shogun: Soeren Sonnenburg master * rc9ae118 / src/interfaces/modular/Transfer.i : fix compile error on java modular - http://git.io/1ja-Rw | 00:47 |
-!- av3ngr [~av3ngr@60-241-222-244.static.tpgi.com.au] has joined #shogun | 01:15 | |
-!- av3ngr [~av3ngr@60-241-222-244.static.tpgi.com.au] has quit [Client Quit] | 01:15 | |
-!- ipondering [~iponderin@58.194.224.104] has joined #shogun | 04:35 | |
-!- ipondering [~iponderin@58.194.224.104] has left #shogun [] | 04:35 | |
-!- ipondering [~iponderin@58.194.224.104] has joined #shogun | 04:36 | |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has joined #shogun | 05:18 | |
-!- cheng [80fa500f@gateway/web/freenode/ip.128.250.80.15] has joined #shogun | 06:14 | |
-!- Marina [55b3252a@gateway/web/freenode/ip.85.179.37.42] has joined #shogun | 07:24 | |
Marina | hello everyone, i have the following question: | 07:25 |
Marina | after training a svm with a weighted degree kernel | 07:25 |
Marina | is it possible to get the w vector ? | 07:26 |
Marina | i know that i can get the weight of the support vecotrs - the alphas - or is it possible to reonstruct the w by the alphas? | 07:27 |
-!- cheng [80fa500f@gateway/web/freenode/ip.128.250.80.15] has quit [Quit: Page closed] | 07:59 | |
@sonney2k | Marina, the w is 10^20 dimensional or so but sparse - so it is stored in a tree - so no not really | 08:04 |
Marina | @sonney2k thanks!! | 08:44 |
-!- Marina [55b3252a@gateway/web/freenode/ip.85.179.37.42] has quit [Quit: Page closed] | 08:46 | |
-!- uricamic [~uricamic@2001:718:2:1634:a5ac:d325:440c:2bf2] has joined #shogun | 08:51 | |
CIA-18 | shogun: Soeren Sonnenburg master * r60e54ed / (51 files in 7 dirs): Merge pull request #603 from puffin444/master (+11 more commits...) - http://git.io/QX5xqw | 09:01 |
-!- Netsplit *.net <-> *.split quits: ipondering | 09:06 | |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has quit [Ping timeout: 245 seconds] | 09:07 | |
-!- Netsplit over, joins: ipondering | 09:08 | |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 09:42 | |
-!- ipondering_ [~iponderin@210.25.133.27] has joined #shogun | 09:44 | |
CIA-18 | shogun: Soeren Sonnenburg master * rbd0fd92 / (2 files): remove german umlaut from code -> ascii only - http://git.io/zD-Y-Q | 09:47 |
-!- ipondering [~iponderin@58.194.224.104] has quit [Ping timeout: 264 seconds] | 09:48 | |
-!- ipondering_ is now known as ipondering | 09:48 | |
CIA-18 | shogun: Soeren Sonnenburg master * r4a337b8 / src/shogun/evaluation/MachineEvaluation.h : fix typo - http://git.io/hE-c8w | 09:57 |
CIA-18 | shogun: Soeren Sonnenburg master * rd74ef69 / (3 files): fix warnings in modular interfaces - http://git.io/Z0W_-A | 09:57 |
-!- gsomix [~gsomix@80.234.26.82] has joined #shogun | 10:21 | |
gsomix | good morning | 10:21 |
-!- ipondering [~iponderin@210.25.133.27] has quit [Quit: ipondering] | 10:24 | |
n4nd0 | good morning gsomix | 10:30 |
-!- heiko [~heiko@host86-180-159-152.range86-180.btcentralplus.com] has joined #shogun | 11:25 | |
-!- cheng [~cheng@115-64-111-17.tpgi.com.au] has joined #shogun | 11:42 | |
-!- blackburn [~blackburn@31.28.43.76] has joined #shogun | 11:46 | |
-!- blackburn [~blackburn@31.28.43.76] has quit [Read error: Operation timed out] | 12:34 | |
-!- pluskid [~pluskid@111.120.44.88] has joined #shogun | 12:43 | |
-!- cheng [~cheng@115-64-111-17.tpgi.com.au] has quit [Quit: Leaving.] | 12:53 | |
-!- cheng [~cheng@115-64-111-17.tpgi.com.au] has joined #shogun | 13:30 | |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Ping timeout: 246 seconds] | 13:31 | |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 14:01 | |
-!- cheng [~cheng@115-64-111-17.tpgi.com.au] has quit [Quit: Leaving.] | 14:42 | |
-!- heiko [~heiko@host86-180-159-152.range86-180.btcentralplus.com] has quit [Ping timeout: 264 seconds] | 14:53 | |
-!- pluskid [~pluskid@111.120.44.88] has quit [Ping timeout: 246 seconds] | 15:37 | |
-!- pluskid [~pluskid@202.130.113.141] has joined #shogun | 15:37 | |
-!- alexlovesdata_ [82955843@gateway/web/freenode/ip.130.149.88.67] has joined #shogun | 16:13 | |
-!- heiko [~heiko@host86-180-159-152.range86-180.btcentralplus.com] has joined #shogun | 16:16 | |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 16:24 | |
-!- blackburn [5f43cee3@gateway/web/freenode/ip.95.67.206.227] has joined #shogun | 16:35 | |
-!- pluskid [~pluskid@202.130.113.141] has quit [Quit: Leaving] | 16:37 | |
-!- zxtx [~zv@cpe-75-83-151-252.socal.res.rr.com] has quit [Ping timeout: 248 seconds] | 16:52 | |
-!- uricamic [~uricamic@2001:718:2:1634:a5ac:d325:440c:2bf2] has quit [Quit: Leaving.] | 16:53 | |
-!- blackburn [5f43cee3@gateway/web/freenode/ip.95.67.206.227] has quit [Ping timeout: 245 seconds] | 16:58 | |
-!- alexlovesdata_ [82955843@gateway/web/freenode/ip.130.149.88.67] has quit [Quit: Page closed] | 17:15 | |
-!- blackburn [5f43cee3@gateway/web/freenode/ip.95.67.206.227] has joined #shogun | 17:18 | |
@sonney2k | hmmhh whenever I need n4nd0 he is not there :D | 17:57 |
@sonney2k | must be that we live in different timezones ;) | 17:57 |
blackburn | sonney2k: I just got first publication ever :D | 18:02 |
blackburn | http://computeroptics.smr.ru/KO/KO36-2og.html | 18:02 |
@sonney2k | blackburn, congrats | 18:02 |
@sonney2k | now a 100 more and you will be professor :D | 18:02 |
blackburn | hahah lol | 18:03 |
@sonney2k | and don't forget to do shogun coding practicals then :D | 18:03 |
heiko | blackburn, congrats :) | 18:03 |
blackburn | sonney2k: n4nd0 is usually here nights | 18:03 |
blackburn | thanks | 18:03 |
blackburn | I hope JMLR paper could be accepted too - we will do an attempt | 18:03 |
@sonney2k | the dimred stuff | 18:03 |
@sonney2k | sure | 18:03 |
@sonney2k | blackburn, can you please fix the libshogun example? | 18:07 |
blackburn | sonney2k: didn't I? | 18:07 |
@sonney2k | I'd like to get things back to normal | 18:07 |
@sonney2k | did you? | 18:07 |
* sonney2k checks | 18:07 | |
blackburn | ahhh | 18:07 |
blackburn | sparse | 18:08 |
blackburn | sonney2k: ok I'll fix | 18:08 |
@sonney2k | hmmhh puffin is no longer here - we also have a problem with nlopt | 18:08 |
@sonney2k | blackburn, it is not yet in debian/ubuntu right? | 18:08 |
blackburn | I have to get home (will be here in 35 mins) | 18:08 |
blackburn | what? | 18:09 |
blackburn | sonney2k: what is not yet in debian? | 18:09 |
@sonney2k | nlopt | 18:09 |
blackburn | ahh | 18:09 |
@sonney2k | ? | 18:09 |
@sonney2k | or is it? | 18:09 |
blackburn | no idea let me check | 18:09 |
blackburn | it is very easy to install | 18:09 |
@sonney2k | blackburn, how did you add support for nlopt then? | 18:09 |
blackburn | sonney2k: installed from sources | 18:10 |
blackburn | it is as easy to install as shogun | 18:10 |
blackburn | well if one have no nlopt he would not have some great stuff from puffin | 18:11 |
blackburn | sounds fair, isn't it? | 18:11 |
@sonney2k | blackburn, well examples crash currently with nlopt not beinga vailable it seems | 18:11 |
blackburn | ahh | 18:11 |
blackburn | different issue then | 18:11 |
blackburn | :D | 18:11 |
@sonney2k | http://shogun-toolbox.org/buildbot/builders/cmdline_static/builds/1006/steps/test_1/logs/stdio | 18:13 |
blackburn | ok give me 30-35 mins for a bike ride | 18:16 |
blackburn | brb :D | 18:16 |
-!- blackburn [5f43cee3@gateway/web/freenode/ip.95.67.206.227] has quit [Quit: Page closed] | 18:16 | |
heiko | sonney2k I read a bit about how German Vereine work | 18:16 |
heiko | some open-source project are registered as one | 18:16 |
heiko | I think that has some nice benefits | 18:16 |
heiko | however, quite some effort is needed to start this off | 18:17 |
heiko | But these money problems wouldnt be there since the Verein has the right to collect/gain money, as long as it is used for purposes of its manifest | 18:17 |
heiko | Ill check if there is like an internet-version of it | 18:18 |
heiko | http://ta7.de/txt/anleitun/anle0023.htm | 18:18 |
CIA-18 | shogun: Soeren Sonnenburg master * r9d3c1a1 / (5 files): fix compile errors in java and csharp modular - http://git.io/PAglCQ | 18:22 |
heiko | http://suite101.de/article/wann-ist-eine-organisation-gemeinnuetzig-a132192 | 18:27 |
-!- gsomix [~gsomix@80.234.26.82] has quit [Ping timeout: 246 seconds] | 18:32 | |
@sonney2k | heiko, any idea why modelselection_parameter_tree.cpp fails? | 18:32 |
heiko | Ill check | 18:33 |
@sonney2k | sonney2k, how many people do we need to sign the manifest? | 18:33 |
heiko | 7 | 18:33 |
heiko | which is a lot for us :) | 18:33 |
@sonney2k | heiko, all Germans? | 18:33 |
heiko | I think so, yes, but let me checlk | 18:33 |
@sonney2k | well, Gunnar, Chris, Heiko, Nico, Alex, Soeren | 18:34 |
@sonney2k | one missing | 18:34 |
heiko | members can be non-german | 18:36 |
@sonney2k | and founders? | 18:37 |
heiko | but I cannot find anything for the founders | 18:37 |
heiko | seems to be allowed | 18:39 |
heiko | Ill ask my parents later, my father knows about that stuff | 18:39 |
@sonney2k | heiko, cool | 18:40 |
@sonney2k | I think this really is the best option for us | 18:40 |
-!- zxtx [~zv@216.239.55.154] has joined #shogun | 18:40 | |
heiko | There is another alternative without notar, but I think then we would have to pay taxes, so e.V. would be best | 18:41 |
-!- gsomix [~gsomix@95.67.148.119] has joined #shogun | 18:42 | |
@sonney2k | heiko, so we would have to create sth along these lines http://www.ccc.de/en/satzung | 18:44 |
heiko | exactly | 18:44 |
@sonney2k | then pay ~100 EUR for notar/ 'Gericht; | 18:44 |
@sonney2k | and done | 18:44 |
heiko | which is fine for shogun | 18:44 |
CIA-18 | shogun: Soeren Sonnenburg master * rcd63a59 / examples/undocumented/libshogun/regression_gaussian_process.cpp : disable example when NLOPT is not available - http://git.io/lchKfg | 18:47 |
-!- zxtx [~zv@216.239.55.154] has quit [Ping timeout: 240 seconds] | 18:48 | |
CIA-18 | shogun: puffin444 master * rf4b4c8f / examples/undocumented/libshogun/regression_gaussian_process.cpp : Allowed the Gaussian Process Regression example to behave gracefully - http://git.io/J5f4EQ | 18:50 |
CIA-18 | shogun: Soeren Sonnenburg master * r6e9cc41 / examples/undocumented/libshogun/regression_gaussian_process.cpp : Merge pull request #606 from puffin444/master - http://git.io/WFlBpw | 18:50 |
CIA-18 | shogun: Chiyuan Zhang master * r48af5bd / (2 files): added subset features to modular interface. - http://git.io/TEmtDA | 18:52 |
CIA-18 | shogun: Chiyuan Zhang master * rf5ef596 / (3 files in 2 dirs): Added ShareBoost python modular interface and example - http://git.io/s2eaTg | 18:52 |
CIA-18 | shogun: Chiyuan Zhang master * r21fbe11 / (3 files): slight improvements to some other MC py-modular examples - http://git.io/_G8H_A | 18:52 |
CIA-18 | shogun: Soeren Sonnenburg master * reade5bd / (7 files in 2 dirs): Merge pull request #605 from pluskid/multiclass - http://git.io/nyQjWg | 18:52 |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has joined #shogun | 18:53 | |
puffin444 | hey heiko | 18:54 |
heiko | hey puffin444 | 18:54 |
puffin444 | looks like I broke the build. | 18:54 |
heiko | yeah :) I was just about checking ... | 18:54 |
puffin444 | I just sent in a fix. | 18:54 |
heiko | or do you already know the problem? | 18:54 |
heiko | soeren already merged it | 18:55 |
puffin444 | Yes. In the example I forgot to handle the case when NLOPT is not available. | 18:55 |
puffin444 | Oh good. | 18:55 |
@sonney2k | puffin444, I will revert my fix | 18:55 |
heiko | there also was an error in another test | 18:55 |
@sonney2k | but there is one more problem in the other example | 18:55 |
heiko | sonney2k, is this parameter tree example still failing? | 18:55 |
puffin444 | Which one? | 18:55 |
@sonney2k | heiko, yes | 18:55 |
heiko | k let me check it now | 18:55 |
@sonney2k | sparse subset stuff is what blackburn will fix | 18:56 |
-!- blackburn [~blackburn@31.28.43.76] has joined #shogun | 18:57 | |
@sonney2k | ...who just logged in :D | 18:57 |
blackburn | heh | 18:57 |
blackburn | what's up? | 18:57 |
heiko | puffin444 modelselection_parameter_tree.cpp | 18:57 |
puffin444 | Oh I see what's wrong. The parameter is called "Likelihood Model," not "model" | 18:58 |
CIA-18 | shogun: Soeren Sonnenburg master * r7bac16a / examples/undocumented/libshogun/regression_gaussian_process.cpp : Revert "disable example when NLOPT is not available" - http://git.io/Ysb7Dw | 18:58 |
heiko | sonney2k, I just checked modelselection_parameter_tree.cpp. it doesnt fail here | 18:59 |
heiko | ah wrong file sorry | 18:59 |
blackburn | sonney2k: why did you revert it? | 19:00 |
@sonney2k | blackburn, https://github.com/shogun-toolbox/shogun/commit/7bac16aa78eced5f7d53191a41e69c142a002e6a | 19:00 |
blackburn | so | 19:01 |
blackburn | what is wrong? | 19:01 |
heiko | puffin444, sonney2k, I spotted the problem | 19:01 |
heiko | puffin444, you renamed he parameters | 19:01 |
heiko | "model" -> "Likelihood Model" | 19:01 |
heiko | please dont do that, always use lower case single words, or if needed underscores | 19:02 |
puffin444 | okay | 19:02 |
blackburn | puffin444: I can share some experience on SSD | 19:02 |
-!- zxtx [~zv@216.239.55.154] has joined #shogun | 19:02 | |
puffin444 | blackburn, how is it? | 19:02 |
blackburn | puffin444: ok I can say word 'awesome' or say win7 fully reboots in 20s | 19:03 |
puffin444 | Wow! | 19:03 |
@sonney2k | read speed is really impressive | 19:04 |
blackburn | I am going to install 4 gb ram more | 19:04 |
@sonney2k | though write speed at least for mine is not | 19:04 |
blackburn | and start to switch | 19:04 |
@sonney2k | at least not when compiling | 19:04 |
blackburn | to new one | 19:04 |
blackburn | sonney2k: hmm can we set up compilation to separate dir? | 19:04 |
blackburn | sonney2k: these files are pretty small | 19:05 |
blackburn | well okay actually I'll test compilation on ssd tomorrow | 19:05 |
blackburn | maybe modern ssds are better with it | 19:05 |
heiko | blackburn whats the problem with ssds? | 19:07 |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has quit [Ping timeout: 245 seconds] | 19:07 | |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has joined #shogun | 19:08 | |
@sonney2k | yeah I think newer ssd's don't have these stallation problems | 19:09 |
blackburn | heiko: is there any problem? | 19:09 |
heiko | blackburn, what problem is there with ssd's? | 19:09 |
blackburn | heiko: I don't know any :) | 19:09 |
heiko | I got one and everything compiles ultra fast | 19:09 |
blackburn | but Soeren said compilation is a little slow | 19:09 |
blackburn | hah | 19:09 |
blackburn | okay nice | 19:09 |
heiko | I got one of the ibm ones, think most recent one | 19:10 |
heiko | without any problems | 19:10 |
blackburn | I have samsung (just like notebook vendor) | 19:10 |
blackburn | but I didn't manage to install good os here yet | 19:10 |
@sonney2k | APPLE SSD TS256A here | 19:11 |
@sonney2k | whatever that means :D | 19:11 |
@sonney2k | heiko, so do you fix the bug? | 19:12 |
@sonney2k | and blackburn are you working on it? | 19:12 |
heiko | puffin444 did you change any other names? | 19:12 |
blackburn | yes | 19:12 |
@sonney2k | which reminds me - wiking - how is it going? | 19:12 |
heiko | if not I will change these back to nold values | 19:12 |
blackburn | kick ass time? sonney2k | 19:13 |
@sonney2k | wiking, you can send small patches already now | 19:13 |
blackburn | :D | 19:13 |
@sonney2k | no need to wait until tomorrow | 19:13 |
@sonney2k | blackburn, well wiking promised the PR with everything until tomorrow... | 19:13 |
@sonney2k | so better ask :D | 19:13 |
@sonney2k | blackburn, have you seen the movie 'kick-ass' ? | 19:14 |
blackburn | hmm let me google it | 19:14 |
@sonney2k | blackburn, you should :D | 19:14 |
blackburn | probably no | 19:14 |
blackburn | will do | 19:15 |
@sonney2k | ...but fix the bug before | 19:15 |
@sonney2k | :P | 19:15 |
puffin444 | heiko, a few. I am fixing this now. | 19:15 |
heiko | ok | 19:16 |
puffin444 | If you don't mind I'd like to use the name "likelihood_model" | 19:17 |
heiko | puffin444 sure, could you change that in the example that failed? | 19:18 |
puffin444 | Yes, I will | 19:18 |
heiko | sonney2k, do you remember the problem of appending features? | 19:23 |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 19:23 | |
heiko | we discussed that and agreed on adding a convienience method that appends two given features | 19:24 |
n4nd0 | sonney2k: I see in the logs you were looking for me? | 19:24 |
blackburn | Okay sparse transposed is a little buggy | 19:24 |
heiko | is there anyway of appending features from the CFeatures interface? | 19:24 |
heiko | copying is ok | 19:24 |
puffin444 | heiko, I have a pull request that should fix it. | 19:26 |
CIA-18 | shogun: puffin444 master * rc34d4bd / (7 files in 5 dirs): Fixed some parameter names and examples. - http://git.io/sRgiPQ | 19:27 |
CIA-18 | shogun: Heiko Strathmann master * rdb17b24 / (7 files in 5 dirs): Merge pull request #607 from puffin444/master - http://git.io/_AzCiw | 19:27 |
heiko | puffin444, thanks :) | 19:27 |
puffin444 | Your welcome. I am leaving, but I should be back later today. | 19:27 |
heiko | same here | 19:28 |
heiko | bye | 19:28 |
puffin444 | To get some of those kernel derivatives up and running. | 19:28 |
puffin444 | bye | 19:28 |
-!- puffin444 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has quit [Quit: Page closed] | 19:28 | |
-!- heiko [~heiko@host86-180-159-152.range86-180.btcentralplus.com] has quit [Ping timeout: 264 seconds] | 19:37 | |
n4nd0 | sonney2k: tell me what was it if so and I will check it later :) | 19:46 |
@sonney2k | n4nd0, fixed it already | 19:50 |
@sonney2k | n4nd0, some compile error in modular java interfaces | 19:51 |
@sonney2k | heiko, I do remember - did any problems appear | 19:52 |
@sonney2k | n4nd0, so you want spain to win tonight? | 20:12 |
blackburn | hah | 20:12 |
blackburn | sonney2k: you were pretty inactive about football | 20:12 |
n4nd0 | sonney2k: of course | 20:19 |
n4nd0 | sonney2k: btw, coming back to the discussion of the features | 20:22 |
n4nd0 | what I told you about yesterday, the MatrixFeatures | 20:23 |
blackburn | matrix features? | 20:23 |
n4nd0 | yes | 20:23 |
n4nd0 | for the HMSVM | 20:23 |
n4nd0 | each example is represented with a "matrix" | 20:23 |
n4nd0 | so each of the features of an example is a sequence | 20:24 |
n4nd0 | BUT it is not compulsory that all the features have the same length | 20:24 |
n4nd0 | blackburn: do you see what I mean? | 20:25 |
blackburn | so variable size matrix? | 20:25 |
n4nd0 | yeah, maybe | 20:25 |
n4nd0 | blackburn: what type of shogun features do you think I should use? | 20:26 |
n4nd0 | I think I need to create something new | 20:26 |
blackburn | hmm well some new one I think | 20:26 |
n4nd0 | let me show you | 20:27 |
n4nd0 | https://github.com/iglesias/shogun/blob/so/src/shogun/features/MatrixFeatures.h | 20:27 |
n4nd0 | I sketched them a bit | 20:28 |
n4nd0 | although now this needs to be changed | 20:28 |
blackburn | I actually though about it | 20:28 |
n4nd0 | since Nico has told me that each of the features can have different length | 20:28 |
blackburn | for images | 20:28 |
blackburn | so I second this idea | 20:28 |
n4nd0 | what do you think I should use to handle this? | 20:29 |
n4nd0 | that the length of the features may change | 20:29 |
n4nd0 | I have not thought about it yet (I just got the mail) | 20:29 |
n4nd0 | brain storm :D | 20:29 |
blackburn | hmm | 20:29 |
n4nd0 | I think I can use directly the dynamic object array | 20:30 |
n4nd0 | https://github.com/iglesias/shogun/blob/so/src/shogun/lib/DynamicObjectArray.h | 20:30 |
n4nd0 | mmmm although I don't want to store objects but something simple as integers | 20:31 |
blackburn | well some array of matrices | 20:31 |
n4nd0 | not exactly matrices though | 20:31 |
n4nd0 | since one of the dimensions is not fixed | 20:32 |
n4nd0 | I think it should be something like an array of StringFeatures | 20:36 |
blackburn | n4nd0: I am sorry but I want portugal to win :D | 20:37 |
@sonney2k | n4nd0, yeah portugal is much easier to beat ;) | 20:38 |
n4nd0 | blackburn: haha it's fine | 20:38 |
@sonney2k | n4nd0, well have an array of SGMatrices then | 20:38 |
blackburn | portugal is easy to beat? lets see heh | 20:38 |
@sonney2k | blackburn, well Germans beat them ... | 20:39 |
n4nd0 | sonney2k: but the thing is that each SGMatrices are supposed to be of fixed num_rows and num_cols | 20:39 |
@sonney2k | but spain is tough | 20:39 |
blackburn | induction does not work here | 20:39 |
blackburn | :D | 20:39 |
n4nd0 | what I need doesn't have one of the dimensions fixed | 20:39 |
@sonney2k | n4nd0, ??? | 20:39 |
@sonney2k | what? | 20:39 |
@sonney2k | I thought you have several matrices of different shape? | 20:40 |
@sonney2k | how can they not be fixed? | 20:41 |
n4nd0 | sonney2k: sorry, I don't know what I wrote before | 20:48 |
n4nd0 | they were speaking to me and I lost the focus | 20:48 |
n4nd0 | sonney2k: so it is not several matrices of different shape | 20:48 |
n4nd0 | so each matrix represent a training example | 20:48 |
n4nd0 | all the training examples (all the matrices then) have the same number of features | 20:49 |
n4nd0 | => the number of columns for example is the same for all the matrices | 20:49 |
n4nd0 | BUT each of the features can be of different length | 20:49 |
n4nd0 | both within the same example and among different examples | 20:49 |
n4nd0 | => the number of rows (even for a matrix) is not fixed | 20:50 |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Ping timeout: 252 seconds] | 20:56 | |
@sonney2k | n4nd0 - but then it is ok - just use some array of matrices | 20:59 |
@sonney2k | the same way like string/sparse features do it | 20:59 |
@sonney2k | you cannot set them all at once though then | 21:00 |
blackburn | sonney2k: uh | 21:12 |
blackburn | fixed | 21:12 |
CIA-18 | shogun: Sergey Lisitsyn master * rc9b592d / src/shogun/features/SparseFeatures.cpp : Fixed get transposed in sparse features - http://git.io/NaIRVw | 21:13 |
-!- gsomix [~gsomix@95.67.148.119] has quit [Ping timeout: 250 seconds] | 21:19 | |
@sonney2k | blackburn, hurray | 21:29 |
@sonney2k | blackburn, looks like you are right | 21:33 |
@sonney2k | portugal looks pretty good | 21:33 |
-!- zxtx [~zv@216.239.55.154] has quit [Ping timeout: 264 seconds] | 21:33 | |
blackburn | yeah | 21:35 |
blackburn | very active and fast | 21:35 |
@sonney2k | I bet 0:0 | 21:35 |
blackburn | and christianny | 21:35 |
blackburn | :D | 21:35 |
blackburn | no penalty kicks please :) | 21:36 |
@sonney2k | I am too tired already now... | 21:36 |
shogun-buildbot | build #972 of python_static is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/python_static/builds/972 | 21:48 |
@sonney2k | now | 22:32 |
@sonney2k | f... | 22:32 |
blackburn | argh | 22:32 |
blackburn | ronaldo has broken aim | 22:32 |
blackburn | today | 22:32 |
@sonney2k | bias term needs a fix | 22:32 |
blackburn | may be he uses (w,x)+b and ball prefer (w,x)-b | 22:33 |
@sonney2k | from what I have seen spain is mostly harmless today | 22:34 |
blackburn | yeah it should be kind of luck | 22:34 |
@sonney2k | too bad that there was no early goal | 22:34 |
@sonney2k | these 0:0 games are :(( | 22:35 |
blackburn | way too much yellow | 22:35 |
blackburn | 8-9 already? | 22:35 |
@sonney2k | I wonder when the first red card will be given | 22:35 |
blackburn | probability is high already | 22:36 |
@sonney2k | portugal can change 2 more times right? | 22:36 |
blackburn | yes I think so | 22:37 |
@sonney2k | so maybe they have some plan... | 22:37 |
blackburn | to fix bias | 22:37 |
@sonney2k | hehe | 22:38 |
@sonney2k | I recommend valgrind ;-) | 22:39 |
blackburn | lets have some goal | 22:40 |
blackburn | I always laugh hearing ?????? yells | 22:40 |
blackburn | russian fans bought tickets in hope russia will go through :D | 22:41 |
@sonney2k | blackburn, some early goal please | 22:43 |
@sonney2k | otherwise I will fall asleep | 22:43 |
@sonney2k | the referee is pretty good though! | 22:45 |
blackburn | he spends so much time | 22:45 |
@sonney2k | ohh well penalties are pretty likely... | 22:48 |
blackburn | sonney2k: russian commentator said 'no sleep! penalties are near!' :D | 22:53 |
@sonney2k | blackburn, are you the commentator? | 22:53 |
blackburn | I am not, why? | 22:54 |
@sonney2k | because you said 'no sleep! penalties are near!' :D | 22:54 |
blackburn | whoops | 22:54 |
blackburn | that was dangerous | 22:54 |
@sonney2k | yes first dangerous thing | 22:54 |
@sonney2k | but portugal can still change 2 times... | 22:55 |
blackburn | custodio is going to appear | 22:55 |
@sonney2k | I think he will change 2 at once | 22:56 |
blackburn | good auROC | 22:57 |
blackburn | bad bias | 22:57 |
blackburn | :D | 22:57 |
@sonney2k | alright chocolate and stuff will keep me awake | 22:57 |
blackburn | stuff? | 22:57 |
@sonney2k | some sweet beer :D | 23:01 |
blackburn | :D | 23:01 |
blackburn | beer with chocolate? | 23:02 |
-!- zxtx [~zv@216.239.55.154] has joined #shogun | 23:02 | |
@sonney2k | seems like both teams aim for penalty kicks | 23:03 |
@sonney2k | oops | 23:04 |
blackburn | 12? 13? | 23:06 |
blackburn | all yellow | 23:06 |
blackburn | hmm | 23:07 |
blackburn | 9 | 23:07 |
blackburn | I thought more | 23:07 |
@sonney2k | how many via ronaldo? | 23:07 |
@sonney2k | 4? | 23:07 |
blackburn | hah | 23:07 |
blackburn | no idea | 23:07 |
blackburn | oops | 23:07 |
blackburn | hahha | 23:07 |
blackburn | pedro pedro | 23:07 |
@sonney2k | do they have rose shoes? | 23:08 |
@sonney2k | the spanish I mean | 23:08 |
blackburn | I didn't notice | 23:08 |
blackburn | ronaldo has | 23:08 |
blackburn | rose/white | 23:08 |
@sonney2k | rose/blue or? | 23:09 |
blackburn | isn't it very individual? | 23:09 |
@sonney2k | no idea | 23:09 |
blackburn | hah | 23:10 |
blackburn | spain is tough now | 23:10 |
@sonney2k | come on FFWD | 23:10 |
@sonney2k | yeah spains standard tactics works now | 23:11 |
@sonney2k | portugal is out of energie | 23:11 |
@sonney2k | energy regularizer does it's job | 23:11 |
blackburn | hah kerzhakoved | 23:11 |
blackburn | (new word came from russian player - means bad miss) :D | 23:12 |
@sonney2k | 1 more minute... | 23:13 |
blackburn | yeah almost done | 23:13 |
@sonney2k | awful game | 23:14 |
@sonney2k | hope tomorrow there will be one goal within the first 15 minutes | 23:14 |
@sonney2k | now it is time for penalty roulette | 23:14 |
blackburn | I almost got tree stuff done during this match | 23:14 |
@sonney2k | in that case there will be a 0:0 tomorrow too : | 23:16 |
@sonney2k | my bet is that ronaldo will shoot above the goal | 23:18 |
blackburn | haha | 23:19 |
blackburn | lets see | 23:19 |
blackburn | he could | 23:19 |
blackburn | haha | 23:20 |
blackburn | cool | 23:20 |
blackburn | fantastic | 23:20 |
@sonney2k | wow! | 23:20 |
@sonney2k | lets see if they can turn it around | 23:20 |
blackburn | symmetric | 23:21 |
@sonney2k | haha | 23:21 |
@sonney2k | 0:0 after penalties :D | 23:21 |
blackburn | argh | 23:22 |
blackburn | ahh | 23:22 |
blackburn | near | 23:22 |
blackburn | really near to save | 23:22 |
@sonney2k | some goals after all | 23:23 |
blackburn | pepe is kind of bull | 23:23 |
blackburn | I thought he would break net | 23:23 |
blackburn | symmetric still | 23:23 |
blackburn | identical goals identical saves | 23:23 |
blackburn | beauty | 23:24 |
@sonney2k | yes | 23:24 |
blackburn | pirlo-style | 23:25 |
blackburn | arghhhhhhhhhhh | 23:25 |
@sonney2k | too bad | 23:25 |
@sonney2k | that's it then | 23:26 |
blackburn | spain probably | 23:26 |
@sonney2k | yeah | 23:26 |
-!- zxtx [~zv@216.239.55.154] has quit [Ping timeout: 245 seconds] | 23:26 | |
blackburn | spain | 23:26 |
@sonney2k | lucky | 23:26 |
@sonney2k | could have been the other way round aswell | 23:27 |
blackburn | bad bar miss | 23:27 |
blackburn | okay lets see germany-spain on sunday :D | 23:28 |
@sonney2k | nahh I don't want to see that ;) | 23:29 |
blackburn | would you like to see italy in finals? | 23:33 |
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 23:38 | |
n4nd0 | blackburn: :) | 23:39 |
blackburn | heh | 23:39 |
@sonney2k | n4nd0, lucky you :D | 23:40 |
@sonney2k | blackburn, surely *not* | 23:40 |
n4nd0 | sonney2k: c'mon ... we deserved it in the extra time! | 23:40 |
@sonney2k | n4nd0, nope | 23:41 |
n4nd0 | O_O | 23:41 |
-!- zxtx [~zv@216.239.55.154] has joined #shogun | 23:41 | |
n4nd0 | haha I see in the logs you have been talking about the match | 23:41 |
@sonney2k | spain was not superior this time | 23:41 |
n4nd0 | not until the extra time | 23:42 |
@sonney2k | but I don't expect germany to win against italy (or spain for that matter) | 23:42 |
@sonney2k | n4nd0, yes | 23:42 |
n4nd0 | I think that Germany can do it | 23:42 |
@sonney2k | but still just 1 chance | 23:42 |
@sonney2k | italy played pretty rough last time | 23:43 |
@sonney2k | wasn't it in semi-finals too? | 23:43 |
n4nd0 | wow and what about Ramos' penalty? | 23:43 |
n4nd0 | I couldn't believe that | 23:43 |
n4nd0 | I am Real Madrid supporter and suffered the one against Bayern ... | 23:43 |
@sonney2k | wiking promised to send a PR thursday night | 23:44 |
@sonney2k | so someone around/after the game :D | 23:44 |
@sonney2k | alright | 23:44 |
@sonney2k | time to sleep | 23:45 |
n4nd0 | sonney2k: good night! | 23:45 |
-!- zxtx [~zv@216.239.55.154] has quit [Ping timeout: 244 seconds] | 23:48 | |
--- Log closed Thu Jun 28 00:00:17 2012 |
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!