[mlpack-git] [mlpack] [Proposal]Add a function to visualize the results of sparse_autoencoder (#452)

[stereomatchingkiss]

When I start to implement it, I find out make it as a global function maybe a better choice, because other families of autoencoders can use the same logic to visualize the training results.
   
    //api of SparseAutoencoder, get the w1 of sa
    const arma::mat w1() const; 

    //global api,generate the maximalInput
    MaximalInput(sa.w1().t(), maximalInput);


---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/452#issuecomment-150719108
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151023/3253e275/attachment.html>