Bug#1039466: ITP: frugally-deep -- use Keras models in C++

[Andrius Merkys <merkys@debian.org>]

Package: wnpp
Owner: Andrius Merkys <merkys@debian.org>
Severity: wishlist

* Package name    : frugally-deep
  Version         : 0.15.20
  Upstream Author : Tobias Hermann
* URL             : https://github.com/Dobiasd/frugally-deep
* License         : Expat
  Programming Lang: C++
  Description     : use Keras models in C++

frugally-deep is a small header-only library written in modern and pure 
C++. It supports inference for sequential models and computational 
graphs with a more complex topology, created with the functional API. It 
re-implements a small subset of TensorFlow, i.e., the operations needed 
to support prediction. frugally-deep results in a much smaller binary 
size than linking against TensorFlow. It avoids temporarily allocating 
additional RAM during convolutions (by not materializing the im2col 
input matrix).

The package is required to update voronota.

Remark: This package is to be maintained with The Debichem Group at
   https://salsa.debian.org/debichem-team/frugally-deep