Soumith Chintala

lua-torch hasn't updated it's packages since July 2017: https://github.com/torch/distro/commits/master I'm not sure what changed.

@winglian I suggest you put a targeted speedup, on what qualifies for "optimized". Who knows, maybe `torch.compile` used the right way can generate your definition of "optimized" :) and someone...

Did you read the error at all? What does it say? On Sunday, June 21, 2015, Linchao Zhu [email protected] wrote: > Hey, thank you for you quick reply! I tried...

Vggd is probably not going to fit in k20 On Sunday, June 21, 2015, soumith [email protected] wrote: > Did you read the error at all? What does it say? >...

Hi, could you try to reduce the batch size, using the commandline option: -batchSize 32 or even reduce it to: -batchSize 16 See if that helps. On Sun, Jun 21,...

hey @zhongwen , this is because when we synchronize the weights across GPUs, we provide dedicated buffers on GPU-1 for all weights to accumulate into (so that the weight transfer...

hey @zhongwen , You also have to take into account on GPU0, the Linear layers. They are only running on GPU0 and not running on GPU1. The DataParallel is only...

@felixsmueller i do not divide by the std-deviation because that's what the google network seemed to do in training. Usually for all my trained networks, I normalize to 0-mean and...

hi eren, there seems to be a change in either the spacing or tabs. When I look at the diff in the "Files changed" tab above, there are many lines...

the matlab C lib is probably not thread-safe or reentrant, you'll have to check that.