neural_factorization_machine icon indicating copy to clipboard operation
neural_factorization_machine copied to clipboard

how could I change layers to multi_layer

Open lagka opened this issue 7 years ago • 1 comments

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

lagka avatar Oct 29 '18 13:10 lagka

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

demien avatar Nov 26 '18 07:11 demien