# google/model_search

Repository: https://github.com/google/model_search
Canonical: https://ross.abutalabs.com/products/model_search
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-07-30T21:36:15+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2052, "days_push": 764, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3238, forks 548 (observed 2026-08-28T04:07:50.421406+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking
- domain: machine-learning, artificial-intelligence, deep-learning
- platform: python
- tags: automl, neural-architecture-search, tensorflow, model-ensembling, knowledge-distillation, hyperparameter-search, linux, gpu

## Member repositories
- google/model_search (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.421406+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:24:33.013200+00:00, confidence not recorded.
  - readme: https://github.com/google/model_search (fetched 2026-08-28T04:07:50.421406+00:00, sha bcdd09774dcb)
- Data as of 2026-08-30T08:39:29.467469+00:00.