Core ML API
Use the Core ML API directly to support custom workflows and advanced use cases.
Overview
In most cases, you interact only with your model's dynamically generated interface, which is created by Xcode automatically when you add a model to your Xcode project. You can use Core ML APIs directly in cases where you need to support custom workflows or advanced use cases. As an example, if you need to make predictions while asynchronously collecting input data into a custom structure, you can adopt the MLFeatureProvider protocol.
To use the Core ML APIs directly:
-
Adopt the
MLFeatureProviderprotocol in a class or structure in your app. -
Use
MLModelmethods with yourMLFeatureProvider.
Topics
Machine Learning Model
An encapsulation of all the details of your machine learning model.
Downloading and Compiling a Model on the User's Device
Distribute Core ML models to the user's device after the app is installed.
Making Predictions with a Sequence of Inputs
Integrate a recurrent neural network model to process sequences of inputs.
Model Features
A feature's value and its type bundled as a read-only instance.
An interface that represents a collection of values for either a model's input or its output.
A convenience wrapper for the given dictionary of data.
An interface that represents a collection of feature providers.
A convenience wrapper for batches of feature providers.
Model Updates
A task that updates a model with additional training data.
Personalizing a Model with On-Device Updates
Modify an updatable Core ML model by running an update task with labeled data.
Customization
Integrate custom neural network layers into your Core ML app.
Make your own custom layer for Core ML models.
An interface that defines the behavior of a custom layer in your neural network model.
An interface that defines the behavior of a custom model.
Errors
The categories of model-specific errors.
The domain for Core ML errors.
扫一扫
327
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
