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[>
@kartikdutt18:matrix.org: With the 156 epochs, the validation accuracy is 0.91797 for the imagenette dataset
< kartikdutt18[m]>
Ahh, Thanks for the benchmark, I think that's a lot of epochs.
< kartikdutt18[m]>
> @kartikdutt18:matrix.org: I tried to check the training result, but I couldn't do that because PC has been freezing and doesn't work... So, I'll re-train after formatting it
< kartikdutt18[m]>
Thanks again.
< kartikdutt18[m]>
> kartikdutt18: About the weights, that's partially correct, but they are not initalized once you add them but if you call the ResetParameters() funtion in the ffn/rnn/gan class; that function is called automatically in the first forward pass, if not done before.
< kartikdutt18[m]>
Makes sense.
< kartikdutt18[m]>
@kimsangyeon-dgu:matrix.org: I think I have enough information to develop a PoC, Let's try that first.
< kartikdutt18[m]>
For the pretrained weights transfer.
< KimSangYeon-DGU[>
<kartikdutt18[m] "@kimsangyeon-dgu:matrix.org: I t"> Okay
< kartikdutt18[m]>
Thanks a lot. Makes sense.
favre49 has joined #mlpack
tomsun_ has quit [Remote host closed the connection]
< zoq>
chopper_inbound[: Thanks for the update, the initalization changes look good, one suggestion for the next update, maybe you can link to the PRs.
< chopper_inbound[>
zoq: Missed linking to PR this time. Will keep in mind next time. Thanks for reminding that :)
favre49 has quit [Ping timeout: 260 seconds]
favre49 has joined #mlpack
favre49 has quit [Ping timeout: 265 seconds]
favre49 has joined #mlpack
< rcurtin>
chopper_inbound[: thanks for the update, I enjoyed reading it. the image made me laugh :-D
< chopper_inbound[>
rcurtin: 😂 yeah, i mean how much more chaotic 2020 wants to be?
< rcurtin>
yeah, really :)
< jeffin143[m]>
@walragatver:matrix.org:
< jeffin143[m]>
Are you there ?
< walragatver[m]>
jeffin143 : yes I am here
< jeffin143[m]>
walragatver: did you try with fresh build dir
< jeffin143[m]>
Like creating a new build and then cmake and make and mlboard_test ?
favre49 has quit [Remote host closed the connection]
< walragatver[m]>
Yes jeffin143: an empty exist at the end
< walragatver[m]>
Directory
< walragatver[m]>
Even in fresh build
< walragatver[m]>
I think the correct command in Linux is rm -rf foldername
< walragatver[m]>
That would be the issue
< jeffin143[m]>
I am not sure if that is possible in c++
< jeffin143[m]>
Actually
< jeffin143[m]>
I am delete all file
< jeffin143[m]>
So the directory is empty
< jeffin143[m]>
So -rf is not need rmdir should work
< jeffin143[m]>
@walragatver:matrix.org: tagging tiu
ImQ009 has quit [Quit: Leaving]
< walragatver[m]>
jeffin143: Everything is getting deleted except the blank directory
< jeffin143[m]>
Ok I have a vm
< jeffin143[m]>
I will try to recreate the issue
< walragatver[m]>
From which library you are using rmdir from unistd.h?
< walragatver[m]>
jeffin143: Tagging you
tomsun_ has joined #mlpack
< jeffin143[m]>
Yes
< jeffin143[m]>
@walragatver:matrix.org:
tomsun has quit [Ping timeout: 264 seconds]
< walragatver[m]>
jeffin143: I tried to debug it. It's throwing errorno 39 directory not empty
< himanshu_pathak[>
<himanshu_pathak[ "Screenshot from 2020-06-24 01-54"> windows Buiild showing time 1d 17h I think it has gone mad :)
< jeffin143[m]>
> jeffin143: I tried to debug it. It's throwing errorno 39 directory not empty
< jeffin143[m]>
Not sure why
< jeffin143[m]>
> > <@himanshu_pathak:matrix.org> sent an image.
< jeffin143[m]>
> windows Buiild showing time 1d 17h I think it has gone mad :)
< jeffin143[m]>
Haha
< walragatver[m]>
jeffim143: I found the error it's because of Linux system.
< walragatver[m]>
There is a .fuse_hidden file which is present in the directory that's why deletion was not possible