News for hackers. Stuff that matters.
Re:Show HN: Juggernaut – Experimental Neural Network in Rust by liuliu on Wednesday July 26, 2017 @01:33PM (#14858265)
It doesn't matter. Most of the time, especially with Tensorflow, you will have a static computation graph somewhere. Nothing (well, implementation-defined) prevent you compile that into CoreML / Caffe / Caffe2 or just Tensorflow lean version to get deployed. PyTorch is a bit different because it supports dynamic graph.

There are no comments on this comment yet.