Thank you for help! )) 2016-08-16 23:08 GMT+03:00 Frédéric Bastien <[email protected]>:
> Use smaller batch-size and smaller layer size or upgrade hardware. > > On Tue, Aug 16, 2016 at 3:47 PM, Станислав Кусков < > [email protected]> wrote: > >> PS. >> CPU i7 6500 (4 cores), GPU (GTX950m 2 GB), RAM 6 GB >> >> вторник, 16 августа 2016 г., 22:36:03 UTC+3 пользователь Robb Brown >> написал: >>> >>> Convolutional networks can be used to efficiently work with large >>> images. We typically work with volumes that are 200x200x200 or so. >>> >>> Another approach would be to use a fully connected network with lower >>> capacity. That will often work better anyway because it will avoid some >>> over fitting. >>> >> -- >> >> --- >> 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. >> > > -- > > --- > You received this message because you are subscribed to a topic in the > Google Groups "theano-users" group. > To unsubscribe from this topic, visit https://groups.google.com/d/ > topic/theano-users/DVitC6luilw/unsubscribe. > To unsubscribe from this group and all its topics, send an email to > [email protected]. > For more options, visit https://groups.google.com/d/optout. > -- С уважением, Станислав Кусков -- --- 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.
