coreml-validate

Community

Ensure CoreML model accuracy with numerical parity validation.

Authormattmireles
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of validating CoreML models' numerical accuracy against PyTorch reference models, ensuring the model outputs are consistent and reliable.

Core Features & Use Cases

  • Numerical Parity Validation: Compares CoreML model outputs against PyTorch reference model outputs, providing detailed correlation and error analysis.
  • Multi-Precision Comparison: Allows comparison of both FP16 and FP32 precision outputs for accuracy assessment.
  • Pipeline Comparison: Validates full inference pipelines, isolating and identifying any discrepancies at each stage.

Quick Start

Trigger the 'coreml-validate' skill with the specific model file and reference pipeline, e.g., 'coreml-validate path/to/model.mlpackage path/to/reference'

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: coreml-validate
Download link: https://github.com/mattmireles/kokoro-coreml/archive/main.zip#coreml-validate

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.