hexiangnan/neural_factorization_machine

how could I change layers to multi_layer

lagka opened this issue · 1 comments

lagka commented

I change the parameter layers from [64] to [64,128,256,128,64],and I meet the error "InvalidArgumentError (see above for traceback): slice index 4 of dimension 0 out of bounds."
How could I fix it

I think you need to extend the keep_prob. The size should be (1 + #deep layer). 1 + 5 as your case.