The workaround is to implement the missing grad method. If you'd like to do it, you can try the method described in this paper:
https://hal.inria.fr/inria-00072686/document Link to discussion on the Theano repo: https://github.com/Theano/Theano/issues/5440 On Wednesday, September 6, 2017 at 2:46:21 PM UTC-4, Shadekur Rahman wrote: > > Trying to use theano gradient when computation graph contains T.nlinalg.svd > > import theanoimport theano.tensor as T > > W = theano.shared(self.get_weights(5,5)) #numpy ndarray with size(5,5) > _,e,_ = T.nlinalg.svd(W) > cost = e[0] > res = theano.grad(cost, [W]) #gives an error > > > getting the following error: > > AttributeError: 'SVD' object has no attribute 'grad' > > > Does anyone know some workaround for this problem? > -- --- 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.
