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 http://www.mlpack.org/irc/
KimSangYeon-DGU has quit [Ping timeout: 256 seconds]
pd09041999 has quit [Ping timeout: 255 seconds]
jeffin143 has joined #mlpack
pd09041999 has joined #mlpack
pd09041999 has quit [Max SendQ exceeded]
< jeffin143>
Zoq : about the discussion we had that day* on reshape layer, the subview layer can flatten the layer so we have that support in our framework*
jeffin143 has quit [Read error: Connection reset by peer]
jeffin143 has joined #mlpack
jeffin143 has quit [Read error: Connection reset by peer]
< zoq>
jeffin143: Ahh you are right.
jeffin143 has joined #mlpack
< jeffin143>
Zoq : then may be we could just opt in for a layer which could do something like - if 100*50 is there, it could reshape it to 10*500
Loki_ has joined #mlpack
< Loki_>
Hi mulx10 what is your project idea for gsoc.
Loki_ has quit [Client Quit]
< zoq>
jeffin143: Not sure we need an extra layer for that, since the operation is so simple someone could arma reshape or memptr. I think the reshape layer is a good idea.
< jeffin143>
Zoq: Sorry but , couldn't get you :)
< zoq>
jeffin143: I don't think we need and extra layer to flatten the output, but we could implement a layer that does reshaping.
< jeffin143>
Yup : that was what i was saying * , just one reshape layer would work , since flatten could be done using subview layer .
< zoq>
jeffin143: okay, would be nice that have that
< jeffin143>
Umm would start working on it , once i m done with my exams :)
vivekp has quit [Ping timeout: 258 seconds]
jeffin143 has quit [Read error: Connection reset by peer]
jeffin143 has joined #mlpack
jeffin143 has quit [Client Quit]
< zoq>
jeffin143: Sounds good, best of luck with your exams.