News for hackers. Stuff that matters.
Re:How HBO’s Silicon Valley Built “Not Hotdog” with TensorFl... by tebica on Monday June 26, 2017 @09:22AM (#14636562)
Love the post! This explains how mobile TensorFlow can be a actually used on daily life.
Re:How HBO’s Silicon Valley Built “Not Hotdog” with TensorFl... by timanglade on Monday June 26, 2017 @09:32AM (#14636633)
One of my primary motivators behind building this blogpost was to show how exactly one can use TensorFlow to ship a production mobile application. There’s certainly a lot of material out there, but a lot of it is either light on details, or only fit for prototypes/demos. There was quite a bit of work involved in making TensorFlow work well on a variety of devices, and I’m proud we managed to get it down to just 50MB or so of RAM usage (network included), and a very low crash rate. Hopefully things like CoreML on iOS and TensorFlow Lite on Android will make things even easier for developers in the future!
Re:How HBO’s Silicon Valley Built “Not Hotdog” with TensorFl... by metakermit on Monday June 26, 2017 @11:09AM (#14637384)
yeah, that's my main pain with the TF docs – great if you just want to try one of the MNIST tutorial variations, but there's a lot more you need to figure out when you get beyond of these "hello world" examples…
Re:How HBO’s Silicon Valley Built “Not Hotdog” with TensorFl... by timanglade on Monday June 26, 2017 @11:12AM (#14637410)
Yup and in fairness maybe that’s something the community (myself included) should really step in and improve — but it’s not always clear how the leadership of the project would like these things to improve, and I often get the feeling they have their own production fixes & practices internally that they’re not (yet) sharing with the public… I could be wrong though.