keras-team/autokeras

Health v2 · maintenance only

Adoption not part of the score

9326 stars · 1389 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

AutoKeras is an AutoML library for deep learning built on Keras, developed by DATA Lab at Texas A&M University. It automates model architecture search and training for tasks like image, text, and tabular classification and regression with a simple high-level API.

Use cases

• automatically train an image classifier without designing a CNN
• perform neural architecture search for my dataset
• build a tabular data regression model with AutoML
• find the best deep learning model without manual tuning
• classify text with automated model selection
• quickly prototype deep learning models with minimal code

When to choose

• you want automated model selection and hyperparameter tuning on top of Keras/TensorFlow
• you lack deep learning expertise but need decent models fast
• you want a simple fit/predict API for common ML tasks

When to avoid

• you need full manual control over architecture and training details
• you work outside TensorFlow/Keras ecosystems with strict constraints
• you need cutting-edge state-of-the-art performance rather than automated convenience

Facets

library · maturity active

machine-learning deep-learning llm-training machine-learning deep-learning data-science python cross-platform automl neural-architecture-search keras tensorflow hyperparameter-tuning autodl

Member repositories

For agents

markdown · JSON · MCP: product_card(name="keras-team/autokeras")