Integrate and optimize Core ML models for on-device inference in iOS apps.
npx skills add https://github.com/omarshahine/HomeClaw --skill coreml-omarshahine
Please help me install this Agent Skill. Skill: coreml Source: https://github.com/omarshahine/HomeClaw/tree/main/.agents/skills/coreml Command: npx skills add https://github.com/omarshahine/HomeClaw --skill coreml-omarshahine
This Skill enables developers to seamlessly integrate and optimize machine learning models directly within their iOS applications, allowing for powerful on-device AI inference without relying on cloud connectivity.
MLFeatureProvider.MLTensor for Swift-native tensor operations and MLState for stateful predictions in sequence models.Load the 'MyImageClassifier' model with all compute units enabled and make a prediction using a CVPixelBuffer.
High-intent search queries and answers about installing and using this skill.
On-device machine learning inference in iOS apps runs by loading compiled Core ML models (.mlmodelc) and passing input features to generate predictions without cloud connectivity. This Skill integrates models using auto-generated Swift classes or manual MLFeatureProvider for offline AI capabilities.
Configuring Core ML compute units involves selecting CPU, GPU, or Neural Engine resources to balance prediction speed and energy efficiency. This Skill optimizes performance profiling by allowing developers to target specific hardware units based on model requirements.
MLFeatureProvider supplies input and output data to Core ML models, while MLMultiArray handles multi-dimensional tensor data for predictions. This Skill utilizes both for manual model loading when auto-generated Swift classes are insufficient for complex inference tasks.
The Vision framework integrates with Core ML to process camera image streams like CVPixelBuffer for real-time object detection. This Skill combines Vision framework integration with Core ML model loading to identify objects instantly in iOS applications.
Core ML supports stateful predictions for sequence models using MLState alongside MLTensor for Swift-native tensor operations. This Skill utilizes these advanced features to maintain context across sequential inputs during on-device machine learning inference.
BorisserzLoad and run Core ML models on-device in Swift iOS apps.
ckorhonenOptimize CoreML models with quantization, palettization, and pruning.
mintuzIntegrate on-device AI models in iOS apps using Foundation Models and MLX Swift.
Roy-wonjiIntegrate Core ML models into iOS apps for on-device inference.