--- title: "autokeras vs metric-learn" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keras-team-autokeras-vs-scikit-learn-contrib-metric-learn" tools: ["keras-team-autokeras", "scikit-learn-contrib-metric-learn"] --- # autokeras vs metric-learn *GraphCanon updated Aug 4, 2026* ## Verdict Pick autokeras if autoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+; pick metric-learn if metric-learn is a Python library for metric learning that offers a range of algorithms compatible with scikit-learn's API and supports various methods like LMNN, ITML, LFDA among others. [autokeras](http://autokeras.com/) reports 9.3k GitHub stars, 1.4k forks, and 161 open issues, last pushed Nov 25, 2025. [metric-learn](http://contrib.scikit-learn.org/metric-learn/) has 1.4k stars, 231 forks, and 51 open issues, last pushed Mar 19, 2026. Figures are from public GitHub metadata via [autokeras's repository](https://github.com/keras-team/autokeras) and [metric-learn's repository](https://github.com/scikit-learn-contrib/metric-learn). | | [autokeras](/tools/keras-team-autokeras.md) | [metric-learn](/tools/scikit-learn-contrib-metric-learn.md) | | --- | --- | --- | | Tagline | AutoML library for deep learning | Metric learning algorithms in Python | | Stars | 9,328 | 1,438 | | Forks | 1,393 | 231 | | Open issues | 161 | 51 | | Language | Python | Python | | Adopt for | AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. | Metric-learn is a Python library for metric learning that offers a range of algorithms compatible with scikit-learn's API and supports various methods like LMNN, ITML, LFDA among others. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Developer Tools, Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [autokeras](/tools/keras-team-autokeras.md) | [metric-learn](/tools/scikit-learn-contrib-metric-learn.md) | | --- | --- | --- | | Days since push | 251d | 136d | | Open issues (now) | 161 | 51 | | Full report | [trust report](/tools/keras-team-autokeras/trust.md) | [trust report](/tools/scikit-learn-contrib-metric-learn/trust.md) | ## Shared compatibility - **Python**: [autokeras](/tools/keras-team-autokeras.md) - Python runtime; [metric-learn](/tools/scikit-learn-contrib-metric-learn.md) - Python runtime ## Decision facts: autokeras - **Adopt for:** AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. ## Decision facts: metric-learn - **Requirements:** The application requires Python version 3.6 or higher and specific dependencies such as numpy, scipy, and scikit-learn. - **Adopt for:** Metric-learn is a Python library for metric learning that offers a range of algorithms compatible with scikit-learn's API and supports various methods like LMNN, ITML, LFDA among others. ## Choose when ### Choose autokeras if… - License: autokeras is Apache-2.0, metric-learn is MIT. - Tags unique to autokeras: autodl, automl, deep-learning, keras. - Also covers Developer Tools. - When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### Choose metric-learn if… - License: metric-learn is MIT, autokeras is Apache-2.0. - Requirements: The application requires Python version 3.6 or higher and specific dependencies such as numpy, scipy, and scikit-learn.. - Tags unique to metric-learn: metric-learning, python, scikit-learn. - When you need to use specific metric learning techniques such as Large Margin Nearest Neighbor (LMNN) or Neighborhood Components Analysis (NCA), which are implemented efficiently in Python. ## When NOT to use autokeras - When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. - If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ## When NOT to use metric-learn - If your development environment does not already use Python, as metric-learn is specific to this language and its ecosystem. - For applications that require real-time performance critical operations, since the library may rely on computationally intensive algorithms that could affect latency in real-time systems. ## Common questions ### What is the difference between autokeras and metric-learn? autokeras: AutoML library for deep learning. metric-learn: Metric learning algorithms in Python. See the comparison table for live GitHub stats and shared categories. ### When should I choose autokeras over metric-learn? Choose autokeras over metric-learn when License: autokeras is Apache-2.0, metric-learn is MIT; Tags unique to autokeras: autodl, automl, deep-learning, keras; Also covers Developer Tools; When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### When should I choose metric-learn over autokeras? Choose metric-learn over autokeras when License: metric-learn is MIT, autokeras is Apache-2.0; Requirements: The application requires Python version 3.6 or higher and specific dependencies such as numpy, scipy, and scikit-learn.; Tags unique to metric-learn: metric-learning, python, scikit-learn; When you need to use specific metric learning techniques such as Large Margin Nearest Neighbor (LMNN) or Neighborhood Components Analysis (NCA), which are implemented efficiently in Python. ### When should I avoid autokeras? When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ### When should I avoid metric-learn? If your development environment does not already use Python, as metric-learn is specific to this language and its ecosystem. For applications that require real-time performance critical operations, since the library may rely on computationally intensive algorithms that could affect latency in real-time systems. ### Is autokeras or metric-learn more popular on GitHub? autokeras has more GitHub stars (9,328 vs 1,438). Stars measure visibility, not whether either tool fits your constraints. ### Are autokeras and metric-learn open source? Yes - both are open-source projects on GitHub (autokeras: Apache-2.0, metric-learn: MIT). ### Where can I find alternatives to autokeras or metric-learn? GraphCanon lists graph-backed alternatives at [autokeras alternatives](/tools/keras-team-autokeras/alternatives) and [metric-learn alternatives](/tools/scikit-learn-contrib-metric-learn/alternatives) ([autokeras markdown twin](/tools/keras-team-autokeras/alternatives.md), [metric-learn markdown twin](/tools/scikit-learn-contrib-metric-learn/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/keras-team-autokeras-vs-scikit-learn-contrib-metric-learn.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, autokeras or metric-learn? autokeras: Slowing. metric-learn: Slowing. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for autokeras and metric-learn? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [autokeras trust report](/tools/keras-team-autokeras/trust); [metric-learn trust report](/tools/scikit-learn-contrib-metric-learn/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=keras-team-autokeras`](/api/graphcanon/graph?tool=keras-team-autokeras) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_