# apple/coremltools

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/apple-coremltools).**

5,333 stars · 806 forks · Python · BSD-3-Clause

## Links

- GitHub: https://github.com/apple/coremltools
- Homepage: https://coremltools.readme.io
- awesome-repositories: https://awesome-repositories.com/repository/apple-coremltools.md

## Topics

`coreml` `coremltools` `machine-learning` `model-conversion` `model-converter` `pytorch` `tensorflow`

## Description

coremltools is a conversion toolkit and translator designed to transform machine learning models from various frameworks into the Core ML format for execution on Apple hardware. It provides a suite of tools for migrating weights and architectures from external libraries into a deployable model format.

The project includes an optimization tool and a programmatic interface for editing model graphs and modifying metadata to improve performance on target hardware. It also features a validation suite used to check model specifications and operation compatibility to ensure correct execution within the runtime.

The toolkit covers a broad range of deployment capabilities, including model graph editing, metadata configuration, and compatibility verification against formal format specifications.

## Tags

### Artificial Intelligence & ML

- [Cross-Framework Model Conversion](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-framework-model-conversion.md) — Transforms machine learning models from various external frameworks into the Core ML format for Apple hardware.
- [Graph Model Transformations](https://awesome-repositories.com/f/artificial-intelligence-ml/graph-model-transformations.md) — Represents machine learning models as computational graphs to enable structural transformations and optimization.
- [Hardware-Specific Model Optimizations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/machine-learning-optimization/ml-performance-profilers/hardware-specific-model-optimizations.md) — Optimizes model graphs and metadata specifically to leverage Apple hardware accelerators and neural engines.
- [Model Graph Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-graph-optimizers.md) — Provides a programmatic interface to simplify and optimize model graphs for improved inference performance.
- [Model Conversion Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-inference-engines/model-conversion-toolkits.md) — Provides a comprehensive toolkit for converting model checkpoints into lightweight libraries for specific hardware runtimes.
- [High-Level Model APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/high-level-model-apis.md) — Provides high-level APIs for the incremental programmatic construction of neural network architectures.
- [Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/deep-learning-optimization/model-deployment.md) — Prepares and validates optimized models for production execution on target hardware.
- [Model Validation Schemas](https://awesome-repositories.com/f/artificial-intelligence-ml/model-validation-schemas.md) — Verifies model correctness by enforcing schema constraints on inputs and operations for the target runtime.

### DevOps & Infrastructure

- [Model Conversion](https://awesome-repositories.com/f/devops-infrastructure/model-conversion.md) — Transforms trained models from various frameworks into optimized formats for target hardware deployment. ([source](https://coremltools.readme.io/llms.txt#coremltools-documentation))

### Software Engineering & Architecture

- [ML Operator Translations](https://awesome-repositories.com/f/software-engineering-architecture/architectural-design-patterns/design-patterns/functional-design-patterns/pure-functional-logic-implementations/ml-operator-translations.md) — Provides translation of individual mathematical operators between different machine learning frameworks.

### Development Tools & Productivity

- [Model-to-Runtime Compatibility Verifications](https://awesome-repositories.com/f/development-tools-productivity/compatibility-verification/model-to-runtime-compatibility-verifications.md) — Identifies unsupported operations to verify model compatibility with specific versions of the inference engine. ([source](https://coremltools.readme.io/llms.txt#coremltools-documentation))
- [Model Compatibility Suites](https://awesome-repositories.com/f/development-tools-productivity/compilers-toolchains/compilers/validation-suites/model-compatibility-suites.md) — Ships a validation suite to check model specifications and operation compatibility for correct runtime execution.
- [Deployment Specification Validators](https://awesome-repositories.com/f/development-tools-productivity/configuration-file-validators/schema-validators/deployment-specification-validators.md) — Checks model specifications against formal schemas and runtime requirements before deployment. ([source](https://apple.github.io/coremltools))

### Programming Languages & Runtimes

- [Intermediate Representation Translation](https://awesome-repositories.com/f/programming-languages-runtimes/intermediate-representation-translation.md) — Translates tensors and operators into a standardized internal format to decouple source frameworks from target conversion.