google/model_search

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

3238 stars · 548 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Model Search is a Google AutoML framework that implements neural architecture search algorithms at scale to find optimal DNN architectures for classification problems. It supports automated architecture search, model ensembling, and knowledge distillation with customizable search spaces.

Use cases

• automatically find the best neural network architecture for my classification dataset
• run AutoML architecture search on csv data
• compare many trained models with tensorboard
• search for the best ensemble of models
• distill models automatically
• define a custom search space of layer types for NAS

When to choose

• you need automated neural architecture search for classification tasks
• you want to compare many candidate architectures with minimal code
• you need built-in ensembling and model distillation
• you want a customizable search space defined via protobuf specs

When to avoid

• you need regression support, which is not currently implemented
• you want a maintained, actively developed AutoML tool
• you work outside TensorFlow-based workflows
• you need lightweight AutoML without running hundreds of training jobs

Facets

library · maturity maintenance

machine-learning deep-learning benchmarking machine-learning artificial-intelligence deep-learning python automl neural-architecture-search tensorflow model-ensembling knowledge-distillation hyperparameter-search linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google/model_search")