verne.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
< zoq>
ironstark: Sure, no problem.
Alvis_ has quit [Ping timeout: 246 seconds]
aashay has quit [Quit: Connection closed for inactivity]
< vivekp>
zoq, rcurtin: After changing adaMax parameter to a template parameter, I'm facing some issues with logistic regression tests
< vivekp>
although simple tests work fine (found out after commenting out logistic regression tests)
diehumblex has quit [Quit: Connection closed for inactivity]
mikeling has joined #mlpack
< zoq>
vivekp: hm, I'll have to take a closer look at the issue. I guess it would work if you define an alias but I thought I tested it without using an alias ...
< zoq>
vivekp: I'll do that tomorrow
< ironstark>
zoq: I have made the suggested changes. Please take a look whenever you find time :)
< sumedhghaisas>
zoq: Hey marcus
< sumedhghaisas>
got some time?
< sumedhghaisas>
I will try to submit my proposal tomorrow by the end of the day ... hopefully
< sumedhghaisas>
Finally got around a proposal involving Batch Norm, Layer Merging and NTMs
< sumedhghaisas>
Fitting pretty well in the timeline
< sumedhghaisas>
On a completely different note... wanted to talk to you about the idea I had about using gradient better while optimizing
richukuttan has joined #mlpack
< richukuttan>
zoq: have a few doublts, listed in the comments. Please look it over when you have the time.
richukuttan has quit [Client Quit]
sumedhghaisas has quit [Ping timeout: 260 seconds]
naxalpha has joined #mlpack
vinayakvivek has joined #mlpack
bharath_ has joined #mlpack
Trion has joined #mlpack
bharath_ has quit [Remote host closed the connection]
bharath_ has joined #mlpack
bharath_ has quit [Ping timeout: 246 seconds]
bharath_ has joined #mlpack
bharath_ has quit [Remote host closed the connection]
HoloIRCUser5 has quit [Read error: Connection reset by peer]
HoloIRCUser has joined #mlpack
bharath_ has quit [Remote host closed the connection]
bharath_ has joined #mlpack
bharath_ has quit [Ping timeout: 240 seconds]
vss has quit [Quit: Page closed]
usama has joined #mlpack
mikeling has quit [Quit: Connection closed for inactivity]
ludonix has joined #mlpack
ludonix has quit [Client Quit]
naxalpha has quit [Ping timeout: 260 seconds]
Alvis_ has quit [Ping timeout: 246 seconds]
Alvis_ has joined #mlpack
aashay has joined #mlpack
HoloIRCUser has quit [Ping timeout: 260 seconds]
Alvis_ has quit [Ping timeout: 246 seconds]
chvsp has joined #mlpack
ironstark has quit [Ping timeout: 240 seconds]
ironstark has joined #mlpack
usama has quit [Quit: Page closed]
Trion has quit [Quit: Have to go, see ya!]
naxalpha has joined #mlpack
< naxalpha>
Hi, Kindly review my proposal and provide me feedback!
mikeling has joined #mlpack
naxalpha has quit []
pawan_sasanka has joined #mlpack
pawan_sasanka_ has joined #mlpack
pawan_sasanka has quit [Ping timeout: 260 seconds]
pawan_sasanka_ is now known as pawan_sasanka
pawan_sasanka has left #mlpack []
ludonix has joined #mlpack
thyrix has joined #mlpack
nish21 has joined #mlpack
thyrix has quit [Quit: Page closed]
nish21 has quit [Ping timeout: 260 seconds]
ironstark has quit [Quit: Leaving]
ironstark has joined #mlpack
nish21 has joined #mlpack
Guest6280 has quit [Quit: Guest6280]
yannis has joined #mlpack
yannis is now known as Guest6280
kris has joined #mlpack
nish21 has quit [Ping timeout: 260 seconds]
ludonix has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
mikeling has quit [Quit: Connection closed for inactivity]
ironstark has quit [Ping timeout: 240 seconds]
kris has quit [Ping timeout: 246 seconds]
ironstark has joined #mlpack
kris has joined #mlpack
nu11p7r has quit [Ping timeout: 240 seconds]
Guest6280 has quit [Quit: Guest6280]
yannis has joined #mlpack
yannis is now known as Guest6280
naxalpha has joined #mlpack
sumedhghaisas has joined #mlpack
sahilc has joined #mlpack
Alvis has joined #mlpack
chvsp has quit [Ping timeout: 260 seconds]
vss has joined #mlpack
sumedhghaisas has quit [Remote host closed the connection]
ironstark has quit [Quit: Leaving]
diehumblex has joined #mlpack
sahilc has quit [Ping timeout: 260 seconds]
< cult->
/usr/include/boost/serialization/access.hpp:118:9: error: ‘class mlpack::tree::HoeffdingTree<>’ has no member named ‘serialize’
< cult->
it has Serialize but not serialize.. what can i do?
< rcurtin>
ah, use data::Save() to save the model
< rcurtin>
or 'data::CreateNVP()' if you want to serialize to an existing boost::archive object
< rcurtin>
so either
< rcurtin>
data::Save(model, "model name", "filename.bin" /* or whatever format */);
< rcurtin>
or
< rcurtin>
ar & data::CreateNVP(model, "model name");
< rcurtin>
where 'model' is your HoeffdingTree<> object
Alvis has quit [Ping timeout: 246 seconds]
< cult->
i need vector of chars because im saving this to database instead of disk..
< cult->
createnvp would workj?
< cult->
ok got it
sumedhghaisas has joined #mlpack
< sumedhghaisas>
zoq: Hey Marcus
vss has quit [Quit: Page closed]
amiller27 has joined #mlpack
vss has joined #mlpack
ironstark has joined #mlpack
< ironstark>
I had a few questions regarding the current way of projecting the visualizations generated in mlpack.org/benchmark-old
< ironstark>
Are those benchmarks tests run periodically and then the graphs generated or are those graphs static?
Alvis has joined #mlpack
zoq_ has joined #mlpack
zoq has quit [Ping timeout: 246 seconds]
vss has quit [Ping timeout: 260 seconds]
naxalpha has quit [Ping timeout: 260 seconds]
amiller27 has left #mlpack []
naxalpha has joined #mlpack
naxalpha has quit [Client Quit]
< ironstark>
zoq_ : I have updated the PR(#33) (Annoy Implementation). The error crept up because my dataset folder was outdated and the iris_train file in it had no labels
< ironstark>
Please Review whenever you find time
< kris>
If the ffn is output layer type is NLL then how do we ensure that the out put given to the nll layer are log probabilities.
< kris>
I didn't see that in the code
< kris>
unless at second last layer we use log soft max layer
shikhar has joined #mlpack
shikhar has quit [Quit: Page closed]
kris has quit [Quit: Leaving.]
govg has quit [Ping timeout: 258 seconds]
AndroUser2 has joined #mlpack
< zoq_>
kris: The negative log likelihood layer expectes that the input contains log-probabilities for each class. Obtaining log-probabilities is easily achieved by adding a LogSoftMax layer before the last layer.
< zoq_>
sumedhghaisa: Hello, feel free to ask anything; once I have a chance I get back to you.
< zoq_>
ironstark: The old benchmarks view is deprecated and has not been updated since we switched to the javascript interface.
zoq_ is now known as zoq
diehumblex has quit [Quit: Connection closed for inactivity]
vinayakvivek has quit [Quit: Connection closed for inactivity]