|
From: | Francesco Faccio |
Subject: | Re: GSOC 17 - Octave - Reutilization of NNET on CNN Project |
Date: | Tue, 28 Mar 2017 18:57:39 +0200 |
On 22 March 2017 at 16:21, Rik <address@hidden> wrote:
> [...]
> Since Tensorflow exposes a C++ API it
> makes a whole lot of sense to me to use this approach rather than go
> through a longer path of Octave->Python->Tensorflow->Python->Octave. I thought the same but was told that TensorFlow C++ API is not only
quite unstable, it also only provides the computational part. The
interesting machine learning bits are only in Python.
Carnë
[Prev in Thread] | Current Thread | [Next in Thread] |