# autonomio/talos

Hyperparameter Experiments with TensorFlow and Keras

Repository: https://github.com/autonomio/talos
Canonical: https://ross.abutalabs.com/products/autonomio-talos
Homepage: https://autonom.io
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, keras, keras-tensorflow, hyperparameter-optimization, artificial-intelligence, tensorflow
Last push: 2024-04-22T10:30:49+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3043, "days_push": 863, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1636, forks 266 (observed 2026-08-28T04:05:14.655668+00:00)

## What it is
Talos is a Python library for automating hyperparameter experiments and model evaluation with TensorFlow (tf.keras), Keras, and PyTorch models. It wraps existing model code without new syntax, offering grid search, random search variants, and probabilistic optimizers.

## Use cases
- tune hyperparameters for a keras model
- run grid search over tensorflow model parameters
- automate deep learning hyperparameter experiments
- evaluate model generalization across parameter sets
- optimize neural network hyperparameters without learning new syntax

## When to choose
- you use tf.keras, Keras, or PyTorch and want minimal-overhead hyperparameter tuning
- you want grid, random, or probabilistic search with experiment analytics
- you need a simple optimize-to-predict pipeline in one line

## When to avoid
- you need cutting-edge optimizers like Optuna or Ray Tune integrations
- your project is not Python or not deep-learning based
- you need actively developed features beyond maintenance

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking
- domain: deep-learning, machine-learning, data-science
- platform: python
- tags: hyperparameter-optimization, keras, tensorflow, grid-search, random-search, model-evaluation

## Member repositories
- autonomio/talos (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:14.655668+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 2026-08-30T03:46:57.776608+00:00, confidence not recorded.
  - readme: https://github.com/autonomio/talos (fetched 2026-08-28T04:05:14.655668+00:00, sha 3623bc04aa17)
  - registry_pypi: https://pypi.org/pypi/talos/json (fetched 2026-08-29T11:19:58.662360+00:00, sha 164f527d4a05)
- Data as of 2026-08-30T08:39:29.467469+00:00.