Soumith Chintala

Yes that seems the right way to go. On Saturday, June 13, 2015, Andrej [email protected] wrote: > I was just thinking about this as well. @soumith > https://github.com/soumith is the...

@karpathy The only thing that I would be super careful about, especially with recurrent nets, is the weight-sharing. Whenever you typecast it, the weight-sharing will be untied, and you might...

One way to make sure everything is okay, is to add simple assertions for checking weight sharing. That way, if someone is on an older torch, they can see the...

also update cunn lib

you could install torch with plain lua, (not luajit) and you wont run into such memory issues. luajit has a heap limit of 2GB in lua-land. To install plain lua:...

@SaMnCo it might be related to: https://github.com/torch/torch7/pull/476 on a PC, save the checkpoint as 'ascii', and then load it on ARMv7. -- on your laptop / desktop checkpoint = torch.load(filename)...

@SaMnCo 3GB, hmmm that's plausible but irritating. What are you running this on? I can replicate it tomorrow on my NVIDIA TK1 or TX1.

@SaMnCo @kinoc here's the fix, I just tested it on my TX1. No need of ascii model anymore. ``` bash git clone https://github.com/mvitez/torch7.git mvittorch7 cd mvittorch7 luarocks make rocks/torch-scm-1.rockspec ```...

which hardware are you running this on? and what cudnn vrersion? maybe theres an issue there. this rrror message is straight from the cudnn lib

if you have cudnn 4.0 then you need the cudnn.torch r4 bindings. git clone https://github.com/soumith/cudnn.torch -b R4 cd cudnn.torch luarocks make Things should work after that On Sunday, December 6,...