Re: Where is the D deep learning library?

[Ola Fosheim Grøstad via Digitalmars-d]

On Tuesday, 28 June 2016 at 17:17:47 UTC, Dejan Lekic wrote:
Thanks for reminding me why I stopped doing C++ programming...
When I saw that...

    using LeNet = loss_multiclass_log<
                                fc<10,
                                relu<fc<84,
                                relu<fc<120,
                                
max_pool<2,2,2,2,relu<con<16,5,5,1,1,
                                
max_pool<2,2,2,2,relu<con<6,5,5,1,1,
                                input<matrix<unsigned
                                   char>>>>>>>>>>>>>>;

... I got a headache...

You like this better?

alias LeNet = loss_multiclass_log!(
                                 fc!10,
                                 relu!(fc!84,
                                 relu!(fc!120,
                                 
max_pool!(2,2,2,2,relu!(con!(16,5,5,1,1,
                                 
max_pool!(2,2,2,2,relu!(con!(6,5,5,1,1,
                                 input!(matrix!(ubyte
                                 ) ) ) ) ) ) ) ) ) ) );