With the release of iOS 11, several popular machine learning frameworks became compatible with it on the model level. You can build and train your models with these frameworks, then export them in a framework-specific format and convert them to the CoreML format for future integration with your app. Such models have fixed parameters and can be used only for inference. As Xcode generates a separate Swift class for each of those models, there is no way to replace or update them in the runtime. The main usage area for such models are different pattern-recognizing applications, like count your calories by taking a photo. At the time of writing this book (iOS 11 Beta), CoreML is compatible with the following libraries and models:
- Caffe 1.0: Neural networks
- Keras 1.2.2: Neural networks
- libSVM 3.22: SVM
- scikit-learn 0.18.1: Tree ensembles, generalized linear...
