Mastering Computer Vision with TensorFlow 2.x

Core ML

Core ML is Apple's machine learning framework, which integrates neural network models from various sources such as TensorFlow, converts them if necessary, and then optimizes the GPU/CPU performance for on-device training and inference, all while minimizing app size and power usage. Core ML 3, which was introduced in WWDC 2019, updates the neural network model for specific user data on the device, thus eliminating device-to-cloud interaction and maximizing user privacy. For more information, visit https://developer.apple.com/machine-learning/core-ml. Core ML itself builds on top of low-level primitives such as Accelerate and BNNS, as well as Metal Performance Shaders. All of the Core ML models have an .mlmodel extension.

The core part ...