Transform ML models into native code with zero dependencies

Re:Transform ML models into native code with zero dependencies by nerfhammer on Tuesday March 05, 2019 @03:47AM (#19309142)

Now do it for tensorflow. Let's say I want to generate AI faces on a small ARM processor.

[ Parent | on HN ]

Re:Transform ML models into native code with zero dependencies by jononor on Tuesday March 05, 2019 @09:08AM (#19310561)

Tensorflow is working on tflite, which runs on small ARM processors (with runtime). And tfcompile is their compile-to-native approach (no runtime).

[ Parent | on HN ]