how could I change layers to multi_layer

hexiangnan / neural_factorization_machine

TenforFlow Implementation of Neural Factorization Machine

466 stars 186 forks source link

how could I change layers to multi_layer #5

Open lagka opened 5 years ago

lagka commented 5 years ago

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

demien commented 5 years ago

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