x = T.tensor3() xshape = T.shape(x) for i in T.arange(xshape[0]): print i f = theano.function([x],[])
It seems that I can not using T.arange(xshape[0]). But xshape[0] should be an integer right? Do you know some other ways to get the shape of a tensor and immediately use it inside a Theano function? Thanks! -- --- 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.
