I found the problem is actually caused by softmax which are not parallelized, but clearly each sample in a mini-batch can be parallelized.
Does anyone know how to solve this? -- --- 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.
