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/
govg has quit [Ping timeout: 246 seconds]
govg has joined #mlpack
kris1 has quit [Quit: kris1]
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 252 seconds]
kris___ has quit [Quit: Connection closed for inactivity]
kris1 has joined #mlpack
govg has joined #mlpack
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
vivekp has quit [Ping timeout: 246 seconds]
vivekp has joined #mlpack
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 255 seconds]
kris1_ is now known as kris1
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris___ has joined #mlpack
< kris___>
lozhnikov:
< kris___>
I was able to get the training working but the accuracies are pretty low.
< kris___>
around 14% on 1000 images using 500 random samples
< lozhnikov>
kris___: looks like there is an error somewhere
< kris___>
Did you look at the updated gist.
< lozhnikov>
I looked through that quickly, but I didn't find errors
< kris___>
Okay should i test with convolutional generated features.
< lozhnikov>
hmm.. I thought you did that and got 14% accuracy
< lozhnikov>
I didn't look through the test in detail
< kris___>
Now for training and testing both i am using the random samples.
< kris___>
Sure, no problem. I might not be available in the evening most probably.
< kris___>
But if you suggest any changes i can do them in the night.
< lozhnikov>
kris___: I think the best approach is to implement exactly the same test as in the paper
< kris___>
Hmmm... okay. Sure i would try that.
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 240 seconds]
kris1_ is now known as kris1
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris1 has quit [Read error: Connection reset by peer]
kris1 has joined #mlpack
kris1_ has joined #mlpack
kris1 has quit [Ping timeout: 252 seconds]
kris1_ is now known as kris1
kris1 has quit [Read error: Connection reset by peer]
kris1 has joined #mlpack
kris1 has quit [Read error: Connection reset by peer]
kris1 has joined #mlpack
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
kris1 has quit [Quit: kris1]
kris___ has quit [Quit: Connection closed for inactivity]