IRC logs of #shogun for Sunday, 2012-07-29

--- Log opened Sun Jul 29 00:00:17 2012
-!- james_____ [~jaume@90.175.233.253] has quit [Ping timeout: 272 seconds]00:04
-!- walke434 [62e3926e@gateway/web/freenode/ip.98.227.146.110] has quit [Quit: Page closed]00:06
-!- james_____ [~jaume@90.175.233.253] has joined #shogun00:07
-!- james_____ [~jaume@90.175.233.253] has quit [Ping timeout: 246 seconds]00:49
-!- james_____ [~jaume@90.175.233.253] has joined #shogun00:50
-!- emrecelikten [~emre@213.153.216.140] has quit [Read error: Operation timed out]01:15
-!- james_____ [~jaume@90.175.233.253] has quit [Quit: Leaving]01:25
-!- needsch [~user@ip-176-198-229-75.unitymediagroup.de] has quit [Ping timeout: 272 seconds]01:55
-!- blackburn [~blackburn@109.226.92.17] has left #shogun []02:27
shogun-buildbotbuild #37 of nightly_none is complete: Success [build successful]  Build details are at http://www.shogun-toolbox.org/buildbot/builders/nightly_none/builds/3703:12
-!- gsomix [~gsomix@95.153.161.120] has joined #shogun06:52
-!- gsomix [~gsomix@95.153.161.120] has quit [Ping timeout: 252 seconds]07:52
-!- K0stIa [~kostia@147.32.98.152] has joined #shogun08:17
-!- K0stIa [~kostia@147.32.98.152] has left #shogun []08:21
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun08:46
-!- K0stIa [~kostia@147.32.98.152] has joined #shogun09:02
-!- pluskid [~pluskid@111.120.52.62] has joined #shogun09:13
-!- pluskid [~pluskid@111.120.52.62] has quit [Ping timeout: 252 seconds]09:53
-!- pluskid [~pluskid@li411-226.members.linode.com] has joined #shogun09:53
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Read error: Operation timed out]10:10
-!- emrecelikten [~emre@213.153.216.140] has joined #shogun10:12
-!- K0stIa [~kostia@147.32.98.152] has left #shogun []10:58
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun11:15
-!- K0stIa [~kostia@147.32.98.152] has joined #shogun11:16
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has joined #shogun12:26
-!- K0stIa [~kostia@147.32.98.152] has quit [Read error: Connection reset by peer]12:26
-!- pluskid [~pluskid@li411-226.members.linode.com] has quit [Ping timeout: 250 seconds]12:47
-!- pluskid [~pluskid@111.120.52.62] has joined #shogun13:08
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Ping timeout: 252 seconds]13:25
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has left #shogun []13:32
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun13:47
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Client Quit]13:47
-!- needsch [~user@ip-176-198-229-75.unitymediagroup.de] has joined #shogun14:13
-!- needsch [~user@ip-176-198-229-75.unitymediagroup.de] has quit [Read error: Connection reset by peer]14:22
-!- needsch [~user@ip-176-198-229-75.unitymediagroup.de] has joined #shogun14:22
-!- blackburn [~blackburn@109.226.92.17] has joined #shogun14:41
-!- blackburn [~blackburn@109.226.92.17] has quit [Quit: Leaving.]15:08
-!- gsomix [~gsomix@95.153.174.248] has joined #shogun15:34
-!- gsomix [~gsomix@95.153.174.248] has quit [Ping timeout: 272 seconds]15:40
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has joined #shogun15:48
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has left #shogun []15:48
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has joined #shogun15:48
K0stIa1HI, all! I'm using shogun in python. My shogun.Distribution doesn't have Gaussian, GMM... can anyone give my advice why is it so ?16:52
-!- pluskid [~pluskid@111.120.52.62] has quit [Quit: Leaving]17:03
-!- K0stIa [~kostia@alt2.hk.cvut.cz] has joined #shogun17:20
-!- K0stIa1 [~kostia@alt2.hk.cvut.cz] has quit [Read error: Connection reset by peer]17:20
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun18:25
-!- gsomix [~gsomix@95.153.172.248] has joined #shogun19:02
-!- gsomix [~gsomix@95.153.172.248] has quit [Quit: Ex-Chat]19:07
-!- blackburn [~blackburn@109.226.92.17] has joined #shogun19:31
-!- gsomix [~gsomix@95.153.172.248] has joined #shogun19:35
gsomixsonney2k, around? ?)19:37
-!- gsomix [~gsomix@95.153.172.248] has quit [Quit: Ex-Chat]19:59
n4nd0blackburn: hey! how are you doing?20:10
blackburnn4nd0: hey pretty fine20:13
blackburnwhat about you?20:13
n4nd0blackburn: I am fine too20:13
n4nd0blackburn: I start to feel happy with the hmsvm :)20:13
blackburnheh20:13
blackburndid you test it already?20:14
n4nd0I am getting the same results for small examples20:14
n4nd0up to 10 training examples right now20:14
n4nd0and after lot of errors fixed, the results are the same20:14
n4nd0blackburn: I want to try now with larger datasets20:14
n4nd0it could be really good if I could use the .mat files that can be generated with the hmsvm toolbox20:15
blackburnn4nd0: btw I have bad understanding what can be HM outputted?20:15
blackburnn4nd0: what are you using for tests?20:15
n4nd0blackburn: what do you mean with HM outputted?20:15
n4nd0blackburn: just manually generated toy data20:16
blackburnfor example if I have images20:16
blackburnwhat can be HMs?20:16
n4nd0mmm do you mean what problem can be modelled with an hmm?20:16
blackburnin case of bioinf stuff it goes to 4 state model like ACTG20:16
n4nd0problems*20:16
blackburnyeah20:16
blackburnbut what are other examples?20:16
n4nd0I haven't used HMMs in computer vision20:17
n4nd0so I cannot tell you about what it could be in an image20:17
n4nd0I have googled it right now20:18
n4nd0it seems that it is used in gesture recognition20:18
n4nd0my guess:20:18
n4nd0the hidden states are the gestures themselves20:18
n4nd0the observation may be features extracted from images20:19
blackburnhmm that sounds interesting :)20:19
n4nd0blackburn: anyway, do you know if I can load from python *any* .mat file?20:19
blackburnn4nd0: sure you can20:19
blackburnscipy.io.loadmat20:19
n4nd0when I tried to load the ones generated by the hmsvm toolbox20:20
n4nd0I got some errors, but I was probably doing somethiing wrong20:20
blackburnerrors like?20:20
n4nd0mmm let me check20:20
n4nd0it was a couple of weeks ago when I tried this20:20
n4nd0I don't even have that code more20:21
n4nd0it was something very simple, 5-10 lines loading a module and trying to load the .mat file20:21
n4nd0importing a module, better20:21
blackburnI use .mat loading in my tester scripts and it works nice20:22
n4nd0is any of those in the repo?20:22
n4nd0using this from tools.load import LoadMatrix it didn't work out well20:22
blackburnn4nd0: use scipy.io.loadmat20:25
blackburnn4nd0: it returns dictionary matlab_name -> value20:28
n4nd0blackburn: nice!20:29
n4nd0I could get it to work20:29
n4nd0thank you very much :)20:29
n4nd0ok, I am going to take a break now to have dinner and see the games20:30
n4nd0see you later!20:30
blackburnn4nd0: :) see you20:30
-!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving]20:30
-!- gsomix [~gsomix@95.153.169.184] has joined #shogun21:17
-!- gsomix [~gsomix@95.153.169.184] has quit [Ping timeout: 250 seconds]21:48
-!- emrecelikten [~emre@213.153.216.140] has quit [Ping timeout: 246 seconds]22:13
-!- emrecelikten [~emre@176.40.234.211] has joined #shogun22:14
-!- K0stIa [~kostia@alt2.hk.cvut.cz] has quit [Ping timeout: 272 seconds]22:33
--- Log closed Mon Jul 30 00:00:17 2012

Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!