# maxpumperla/hyperas

Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization

Repository: https://github.com/maxpumperla/hyperas
Canonical: https://ross.abutalabs.com/products/hyperas
Homepage: http://maxpumperla.com/hyperas/
Language: Python
License: MIT
License Family: permissive
Topics: hyperopt, keras, hyperparameter-optimization
Last push: 2023-01-05T06:02:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3848, "days_push": 1336, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2173, forks 315 (observed 2026-08-28T04:06:21.954789+00:00)

## What it is
Hyperas is a Python library that wraps Hyperopt to provide convenient hyperparameter optimization for Keras models. Users annotate model parameters with a simple template syntax instead of learning Hyperopt's API.

## Use cases
- tune dropout rates in a Keras neural network
- find optimal hyperparameters for a deep learning model
- run hyperopt without learning its syntax
- optimize keras model accuracy automatically
- sweep hyperparameter ranges for neural network training
- automate model tuning experiments

## When to choose
- you use Keras and want simple hyperparameter tuning with minimal boilerplate
- you want Hyperopt's TPE search without learning its API
- you are prototyping models and need quick parameter sweeps

## When to avoid
- you use PyTorch, TensorFlow 2.x/Keras 3, or other frameworks instead of classic Keras
- you need actively maintained tooling with modern framework support
- you need distributed or large-scale hyperparameter search (consider Optuna or Ray Tune)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, developer-tools
- domain: machine-learning, deep-learning, developer-tools
- platform: python
- tags: hyperparameter-optimization, hyperopt, keras, deep-learning, model-tuning

## Member repositories
- maxpumperla/hyperas (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.954789+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 2026-08-30T02:49:02.662984+00:00, confidence not recorded.
  - readme: https://github.com/maxpumperla/hyperas (fetched 2026-08-28T04:06:21.954789+00:00, sha b296eefd3710)
  - homepage: http://maxpumperla.com/hyperas/ (fetched 2026-08-29T10:29:12.499656+00:00, sha 07a53d95bf49)
  - registry_pypi: https://pypi.org/pypi/hyperas/json (fetched 2026-08-29T10:29:12.508646+00:00, sha eb65edc48184)
- Data as of 2026-08-30T08:39:29.467469+00:00.