suriyadeepan / practical_seq2seq

A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
http://suriyadeepan.github.io/2016-12-31-practical-seq2seq/
GNU General Public License v3.0
569 stars 270 forks source link

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[4096] #23

Closed kenyeung128 closed 7 years ago

kenyeung128 commented 7 years ago

Hi,

When i run the twitter code, looks like ran out of memory, anyway to get it running? I am running it on aws p2 x 8 Thanks.

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[4096]

kenyeung128 commented 7 years ago

i get it resolved, it's because of another process using too much memory for training