Apple has updated Core ML Tools to version 0.7. Included is a new TensorFlow converter that lets developers train machine learning models in Google’s TensorFlow and deploy them with Apple’s Core ML
From the Google Developers Blog:
Today, in collaboration with Apple, we are happy to announce support for Core ML! With this announcement, iOS developers can leverage the strengths of Core ML for deploying TensorFlow models. In addition, TensorFlow Lite will continue to support cross-platform deployment, including iOS, through the TensorFlow Lite format (.tflite) as described in the original announcement.
Core ML Tools 0.7 also includes support for custom layers, so you can quickly create, test, and deploy new layers using Core ML on iOS 11.2 or later.
Floating Point 16 (FP16) is included for neural networks as well, which should reduce model sizes by half.