News for hackers. Stuff that matters.

A comment on Running your models in production with TensorFlow Serving.

Re:Running your models in production with TensorFlow Serving by swah on Wednesday February 17, 2016 @04:58AM (#11116695)
Off-topic: I always open C++ projects from Google - they are always so tidy and clean. It just feels like a work of craftmanship, if that actually exists in software: https://github.com/tensorflow/serving/tree/master/tensorflow...

OTOH, I have a strong prejudice against Javascript on the backend... And its not due to it being dynamic - the same doesn't happen with Python codebases. It is completely irrational.

[ Parent | on HN ]
Re:Running your models in production with TensorFlow Serving by pjmlp on Wednesday February 17, 2016 @05:26AM (#11116828)
I don't share the same opinion from the NDK code.

Plain C with C++ compiler, with a pseudo Hungarian notation.

[ Parent | on HN ]