What command for the lasagne implementation was passed for the MNIST experiment in the paper? In particular, what option modifies the fully connected layer to have 450 neurons?
To run MNIST, it appears one needs simplemodel since that makes use of a widths parameter. Unfortunately, that code is not included in this repo. Could some one add it?
What command for the lasagne implementation was passed for the MNIST experiment in the paper? In particular, what option modifies the fully connected layer to have 450 neurons?