I have a network with multiple BiLSTMs and attention layers. I sorted the training data in mini-batches of varying lengths of inputs, however containing the same number of training examples. When I train the network from mini-batch sequenced from larger lengths to smaller ones, every thing works fine, but when I shuffle the mini batches for training I get the "pygpu.gpuarray.GpuArrayException: out of memory" error at arbitrary point of training. Has anyone else experienced this, if so I would very much like to know the remedy. We have GeForce GTX 1080 Ti GPUs with 11172MiB of memory.
thanks Narendra -- ******************************************************************************* This e-mail and any of its attachments may contain Interactions Corporation proprietary information, which is privileged, confidential, or subject to copyright belonging to the Interactions Corporation. This e-mail is intended solely for the use of the individual or entity to which it is addressed. If you are not the intended recipient of this e-mail, you are hereby notified that any dissemination, distribution, copying, or action taken in relation to the contents of and attachments to this e-mail is strictly prohibited and may be unlawful. If you have received this e-mail in error, please notify the sender immediately and permanently delete the original and any copy of this e-mail and any printout. Thank You. ******************************************************************************* -- --- 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.
