# keras-team/autokeras

**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/keras-team-autokeras).**

9,319 stars · 1,397 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/keras-team/autokeras
- Homepage: http://autokeras.com/
- awesome-repositories: https://awesome-repositories.com/repository/keras-team-autokeras.md

## Description

AutoKeras is an automated machine learning framework and Keras AutoML library designed to discover the most effective deep learning model structures for a given dataset. It functions as a tool for deep learning architecture search, eliminating manual hyperparameter tuning by automatically searching for and optimizing neural network architectures.

The framework provides capabilities for benchmarking and refining neural network designs to maximize performance. It includes a system for containerized machine learning deployment, allowing environments to be packaged into containers to ensure consistent execution across different operating systems.

The library covers a broad range of automation tasks, including deep learning model optimization and performance benchmarking. It manages the discovery of optimal layer configurations and hyperparameters within the Keras deep learning framework.

## Tags

### Artificial Intelligence & ML

- [Neural Architecture Search](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-architecture-search.md) — Automates the discovery and refinement of optimal neural network architectures for specific datasets. ([source](https://github.com/keras-team/autokeras/blob/master/RELEASE.md))
- [Deep Learning Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-architectures.md) — Identifies the most effective deep learning model structures to maximize results without manual tuning. ([source](https://github.com/keras-team/autokeras/blob/master/README.md))
- [Model Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/high-level-model-apis/model-synthesis.md) — Generates valid deep learning model code by mapping searched hyperparameters to Keras API components.
- [Structural Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/deep-learning-optimization/structural-optimization.md) — Refines neural network structures to maximize performance and accuracy for specific data.
- [Automated Architecture Search](https://awesome-repositories.com/f/artificial-intelligence-ml/model-architecture-selection/automated-architecture-search.md) — Automates the discovery of optimal layer configurations and hyperparameters within the Keras framework.
- [Bayesian Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-architecture-search/bayesian-optimization.md) — Uses Bayesian probabilistic models to predict and sample optimal neural network hyperparameters.
- [Model Performance Benchmarks](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-model-comparators/model-performance-benchmarks.md) — Trains and ranks multiple model candidates using standardized performance metrics and evaluation scripts. ([source](https://github.com/keras-team/autokeras/tree/master/benchmark))
- [Architecture Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-algorithms/reinforcement-learning-simulators/architecture-benchmarking.md) — Evaluates and compares different neural network architectures to determine the best performing design.

### Part of an Awesome List

- [Neural Architecture Search](https://awesome-repositories.com/f/awesome-lists/ai/neural-architecture-search.md) — Benchmarks and refines neural network designs to maximize performance without manual configuration.
- [Automated Machine Learning](https://awesome-repositories.com/f/awesome-lists/ai/automated-machine-learning.md) — AutoML library specifically for deep learning models.
- [AutoML](https://awesome-repositories.com/f/awesome-lists/ai/automl.md) — Accessible machine learning for all users.
- [Machine Learning Libraries](https://awesome-repositories.com/f/awesome-lists/ai/machine-learning-libraries.md) — AutoML for deep learning.
- [Automated Machine Learning](https://awesome-repositories.com/f/awesome-lists/devtools/automated-machine-learning.md) — Automated neural architecture search for Keras models.

### Scientific & Mathematical Computing

- [Iterative Feedback Loops](https://awesome-repositories.com/f/scientific-mathematical-computing/research-analysis-workflows/research-and-data-analysis-tools/research-and-analysis-tools/research-automation-tools/iterative-feedback-loops.md) — Employs an automated loop that repeatedly evaluates model performance to refine architecture candidates.

### Development Tools & Productivity

- [Dataset-Driven Search Spaces](https://awesome-repositories.com/f/development-tools-productivity/search-optimization/hyperparameter-search-algorithms/dataset-driven-search-spaces.md) — Determines initial hyperparameter search spaces and constraints based on input data dimensions and labels.

### DevOps & Infrastructure

- [Docker Container Deployments](https://awesome-repositories.com/f/devops-infrastructure/container-orchestration/container-runtimes/runtime-configuration-interfaces/docker-socket-orchestrators/docker-target-configurators/docker-container-deployments.md) — Packages the environment into Docker images for consistent execution across different operating systems. ([source](https://github.com/keras-team/autokeras/tree/master/docker))
- [Containerized Deployments](https://awesome-repositories.com/f/devops-infrastructure/containerized-deployments.md) — Packages machine learning environments into containers to ensure consistent execution across platforms.
- [Containerized Execution Environments](https://awesome-repositories.com/f/devops-infrastructure/containerized-execution-environments.md) — Provides isolated execution environments via containers to ensure reproducible training and deployment.