wanghechong

multi-GPU

2

i want to use multi-GPU to train my model, but it report error like"torch/install/share/lua/5.1/cunn/DataParallelTable.lua:348: attempt to call method 'type' (a nil value)" i do not know why, but the cunn...

i come across a problem when i trian the model, when i have trained the model 90 minutes， the GPU suddenly report the error about out of memory, it shoule...

i read you code carefully, but i do not vary understand like 'decoder_clones = clone_many_times(decoder, opt.max_sent_l_targ) ' , why we need to copy opt.max_sent_l_targ times, and we share the parameters...