ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at
HarshVardhanKuma has joined #mlpack
< HarshVardhanKuma> I'm using CLI bindings. However, the training file option in examples demonstrates the use of CSV files. Is there any way to provide some form of a binary object? Also, what kind of binary object that would be and how to create it?
< HarshVardhanKuma> binary object as a training file..
< HarshVardhanKuma> One other thing, I could not find SVM implementation with custom kernels? The linearSVM class does not provide with an option for selecting kernels like RBF etc?
ImQ009 has joined #mlpack
HarshVardhanKuma has quit [Ping timeout: 245 seconds]
M94KAAC193 has quit [Ping timeout: 245 seconds]
_slack_mlpack_31 has quit [Ping timeout: 245 seconds]
Cadair has quit [Ping timeout: 245 seconds]
_slack_mlpack_31 has joined #mlpack
M94KAAC193 has joined #mlpack
AbhishekMishra[m has quit [Ping timeout: 250 seconds]
HrithikNambiar[m has quit [Ping timeout: 250 seconds]
M94KAAC19T has quit [Ping timeout: 250 seconds]
HarshVardhanKuma has joined #mlpack
Cadair has joined #mlpack
HrithikNambiar[m has joined #mlpack
M94KAAC19T has joined #mlpack
AbhishekMishra[m has joined #mlpack
< shrit[m]> What do you mean by binary training file? are you refering to the model? or the dataset
< shrit[m]> I have never seen a binary dataset file, but you can have a binary model
< rcurtin[m]> HarshVardhanKumar (Harsh Kumar): you can use HDF5 or Armadillo binary formats; see the documentation for the accepted formats here:
< rcurtin[m]> HarshVardhanKumar (Harsh Kumar): for your question about SVM, we have linear SVM implemented but not kernel SVM
ServerStatsDisco has joined #mlpack
MatrixTravelerb4 has joined #mlpack
rcurtin has joined #mlpack
ImQ009 has quit [Quit: Leaving]
< rcurtin[m]> ok, I purged all the freenode spam from my logs... now I'm rebuilding the site, and hopefully it should be gone
< rcurtin[m]> I tried to set up the IRC bridge to the other IRC server, but our channel is too big... so far that bridge is only operating for matrix channels with less than 100 users :)
< shrit[m]> great
< rcurtin[m]> ok, the IRC logs are clean now:
< rcurtin[m]> NippunSharma (Nippun Sharma): I saw you were asking about how to build the website... I'll answer shortly to fix that... the "short" story is that you can run `_src/scripts/` but it may take a long time since it builds all versions :)
zoq_ has joined #mlpack