Soumith Chintala

i dont have matlab anymore to help.

you could also load hdf5 files in matlab: https://github.com/deepmind/torch-hdf5

it is because matlab is column-major in storing matrices, torch is row-major. on another note, this repo is mostly abandoned and not maintained. If you want better maintained interfaces to...

yes. On Wed, May 20, 2015 at 3:49 AM, Uri Cohen [email protected] wrote: > I see how this applies to 2d matrices being transposed, but does this also > mean...

might be relevant, though not exactly what you're looking for: https://github.com/soumith/torch-signal/blob/master/init.lua

cant remember where I messaged you, but the four commits authored by me here: https://github.com/torch/luajit-rocks/commits/master/luarocks

hey @jmsellier that command you quoted does not appear anywhere on our website. We never recommend "sudo" when installing torch at the moment. I suggest you clean up the installation...

@jmsellier I think you are running this in a virtual machine. Can you use this command for install: TORCH_LUA_VERSION=LUAJIT20 ./install.sh

i'll try to get this resolved in the torch repo in the next week.

You can call :float() on you gpu-model and it changes into a cpu model. On Saturday, June 13, 2015, John Wiseman [email protected] wrote: > Is the restriction that a model...