I built a neural network in keras. Everything goes fine when I use
tensorflow as backend. But when I use theano as backend, I always run into
this problem: MemoryError: ('Error allocating 3456 bytes of device memory
(CNMEM_STATUS_CUDA_ERROR).', "you might consider using 'theano.shared(...,
borrow=True)'")
. In fact the GPU has a 5.6G memory. Is there anyone knowing what is
going on?
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
