ok, and if i wont pass just 3d tensor make the batch_size to 1? thank you בתאריך יום שלישי, 7 בפברואר 2017 בשעה 23:46:28 UTC+2, מאת nouiz: > > sgnconv don't work in the new gpu back-end, but you can use conv2d instead > and it should fix your problem for now. > > On Tue, Feb 7, 2017 at 4:14 AM xxx <[email protected] <javascript:>> wrote: > >> >> >> hi >> i install theano 9.1b ,cuda 8 , cudnn 5.1 >> this is my import in the code >> >> >> >> import theano >> import theano.tensor as T >> from theano.tensor.nnet import conv2d >> from theano.tensor.signal import conv as sgnconv >> from theano.tensor.signal import pool >> >> >> i got this error >> >> >>> AssertionError: >>> ConvOp does not work with the gpuarray backend. >>> >>> Use the new convolution interface to have GPU convolution working: >>> theano.tensor.nnet.conv2d() >>> >> what i need to convert for the new backend? >> thank >> >> -- >> >> --- >> 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] <javascript:>. >> 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.
