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 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.
